Merge 'Fix hang in multishard_writer' from Asias

"
This series fix hang in multishard_writer when error happens. It contains
- multishard_writer: Abort the queue attached to consumers when producer fails
- repair: Fix hang when the writer is dead

Fixes #6241
Refs: #6248
"

* asias-stream_fix_multishard_writer_hang:
  repair: Fix hang when the writer is dead
  mutation_writer_test: Add test_multishard_writer_producer_aborts
  multishard_writer: Abort the queue attached to consumers when producer fails

(cherry picked from commit 8925e00e96)

.dockerignore

@@ -1,4 +1,3 @@
 .git
 build
 seastar/build
-testlog

.gitattributes

@@ -1,3 +1,2 @@
 *.cc diff=cpp
 *.hh diff=cpp
-*.svg binary

.github/CODEOWNERS

@@ -1,101 +0,0 @@
-# AUTH
-auth/* @elcallio @vladzcloudius
-
-# CACHE
-row_cache* @tgrabiec
-*mutation* @tgrabiec
-test/boost/mvcc* @tgrabiec
-
-# CDC
-cdc/* @kbr- @elcallio @piodul @jul-stas
-test/cql/cdc_* @kbr- @elcallio @piodul @jul-stas
-test/boost/cdc_* @kbr- @elcallio @piodul @jul-stas
-
-# COMMITLOG / BATCHLOG
-db/commitlog/* @elcallio
-db/batch* @elcallio
-
-# COORDINATOR
-service/storage_proxy* @gleb-cloudius
-
-# COMPACTION
-compaction/* @raphaelsc @nyh
-
-# CQL TRANSPORT LAYER
-transport/*
-
-# CQL QUERY LANGUAGE
-cql3/* @tgrabiec @psarna @cvybhu
-
-# COUNTERS
-counters* @jul-stas
-tests/counter_test* @jul-stas
-
-# DOCS
-docs/* @annastuchlik @tzach
-docs/alternator @annastuchlik @tzach @nyh @psarna
-
-# GOSSIP
-gms/* @tgrabiec @asias
-
-# DOCKER
-dist/docker/*
-
-# LSA
-utils/logalloc* @tgrabiec
-
-# MATERIALIZED VIEWS
-db/view/* @nyh @psarna
-cql3/statements/*view* @nyh @psarna
-test/boost/view_* @nyh @psarna
-
-# PACKAGING
-dist/* @syuu1228
-
-# REPAIR
-repair/* @tgrabiec @asias @nyh
-
-# SCHEMA MANAGEMENT
-db/schema_tables* @tgrabiec @nyh
-db/legacy_schema_migrator* @tgrabiec @nyh
-service/migration* @tgrabiec @nyh
-schema* @tgrabiec @nyh
-
-# SECONDARY INDEXES
-db/index/* @nyh @psarna
-cql3/statements/*index* @nyh @psarna
-test/boost/*index* @nyh @psarna
-
-# SSTABLES
-sstables/* @tgrabiec @raphaelsc @nyh
-
-# STREAMING
-streaming/* @tgrabiec @asias
-service/storage_service.* @tgrabiec @asias
-
-# ALTERNATOR
-alternator/* @nyh @psarna
-test/alternator/* @nyh @psarna
-
-# HINTED HANDOFF
-db/hints/* @piodul @vladzcloudius
-
-# REDIS
-redis/* @nyh @syuu1228
-test/redis/* @nyh @syuu1228
-
-# READERS
-reader_* @denesb
-querier* @denesb
-test/boost/mutation_reader_test.cc @denesb
-test/boost/querier_cache_test.cc @denesb
-
-# PYTEST-BASED CQL TESTS
-test/cql-pytest/* @nyh
-
-# RAFT
-raft/* @kbr- @gleb-cloudius @kostja
-test/raft/* @kbr- @gleb-cloudius @kostja
-
-# HEAT-WEIGHTED LOAD BALANCING
-db/heat_load_balance.* @nyh @gleb-cloudius

.github/workflows/docs-pages.yaml

@@ -1,35 +0,0 @@
-name: "Docs / Publish"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-on:
-  push:
-    branches:
-      - master
-    paths:
-      - "docs/**"
-  workflow_dispatch:
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v3
-        with:
-          python-version: 3.7
-      - name: Set up env
-        run: make -C docs setupenv
-      - name: Build docs
-        run: make -C docs multiversion
-      - name: Build redirects
-        run: make -C docs redirects
-      - name: Deploy docs to GitHub Pages
-        run: ./docs/_utils/deploy.sh
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pr.yaml

@@ -1,28 +0,0 @@
-name: "Docs / Build PR"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-on:
-  pull_request:
-    branches:
-      - master
-    paths:
-      - "docs/**"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v3
-        with:
-          python-version: 3.7
-      - name: Set up env
-        run: make -C docs setupenv
-      - name: Build docs
-        run: make -C docs test

.gitignore

@@ -22,14 +22,3 @@ resources
 .pytest_cache
 /expressions.tokens
 tags
-!db/tags/
-testlog
-test/*/*.reject
-.vscode
-docs/_build
-docs/poetry.lock
-compile_commands.json
-.ccls-cache/
-.mypy_cache
-.envrc
-rust/Cargo.lock

.gitmodules

@@ -1,23 +1,17 @@
 [submodule "seastar"]
 	path = seastar
-	url = ../seastar
+	url = ../scylla-seastar
 	ignore = dirty
 [submodule "swagger-ui"]
 	path = swagger-ui
 	url = ../scylla-swagger-ui
 	ignore = dirty
+[submodule "xxHash"]
+	path = xxHash
+	url = ../xxHash
 [submodule "libdeflate"]
 	path = libdeflate
 	url = ../libdeflate
-[submodule "abseil"]
-	path = abseil
-	url = ../abseil-cpp
-[submodule "scylla-jmx"]
-	path = tools/jmx
-	url = ../scylla-jmx
-[submodule "scylla-tools"]
-	path = tools/java
-	url = ../scylla-tools-java
-[submodule "scylla-python3"]
-	path = tools/python3
-	url = ../scylla-python3
+[submodule "zstd"]
+	path = zstd
+	url = ../zstd

.mailmap

@@ -1,3 +0,0 @@
-Avi Kivity <avi@scylladb.com> Avi Kivity' via ScyllaDB development <scylladb-dev@googlegroups.com>
-Raphael S. Carvalho <raphaelsc@scylladb.com> Raphael S. Carvalho' via ScyllaDB development <scylladb-dev@googlegroups.com>
-Pavel Emelyanov <xemul@scylladb.com> Pavel Emelyanov' via ScyllaDB development <scylladb-dev@googlegroups.com>

CMakeLists.txt

@@ -1,804 +1,142 @@
-cmake_minimum_required(VERSION 3.18)
+##
+## For best results, first compile the project using the Ninja build-system.
+##
 
+cmake_minimum_required(VERSION 3.7)
 project(scylla)
 
-if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
-  message(STATUS "Setting build type to 'Release' as none was specified.")
-  set(CMAKE_BUILD_TYPE "Release" CACHE
-      STRING "Choose the type of build." FORCE)
-  # Set the possible values of build type for cmake-gui
-  set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
-    "Debug" "Release" "Dev" "Sanitize")
+if (NOT DEFINED FOR_IDE AND NOT DEFINED ENV{FOR_IDE} AND NOT DEFINED ENV{CLION_IDE})
+    message(FATAL_ERROR "This CMakeLists.txt file is only valid for use in IDEs, please define FOR_IDE to acknowledge this.")
 endif()
 
-if(CMAKE_BUILD_TYPE)
-    string(TOLOWER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
-else()
-    set(BUILD_TYPE "release")
-endif()
+# Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
+set(SEASTAR_INCLUDE_DIRS "seastar")
 
-function(default_target_arch arch)
-    set(x86_instruction_sets i386 i686 x86_64)
-    if(CMAKE_SYSTEM_PROCESSOR IN_LIST x86_instruction_sets)
-        set(${arch} "westmere" PARENT_SCOPE)
-    elseif(CMAKE_SYSTEM_PROCESSOR EQUAL "aarch64")
-        set(${arch} "armv8-a+crc+crypto" PARENT_SCOPE)
+# These paths are always available, since they're included in the repository. Additional DPDK headers are placed while
+# Seastar is built, and are captured in `SEASTAR_INCLUDE_DIRS` through parsing the Seastar pkg-config file (below).
+set(SEASTAR_DPDK_INCLUDE_DIRS
+        seastar/dpdk/lib/librte_eal/common/include
+        seastar/dpdk/lib/librte_eal/common/include/generic
+        seastar/dpdk/lib/librte_eal/common/include/x86
+        seastar/dpdk/lib/librte_ether)
+
+find_package(PkgConfig REQUIRED)
+
+set(ENV{PKG_CONFIG_PATH} "${CMAKE_SOURCE_DIR}/seastar/build/release:$ENV{PKG_CONFIG_PATH}")
+pkg_check_modules(SEASTAR seastar)
+
+find_package(Boost COMPONENTS filesystem program_options system thread)
+
+##
+## Populate the names of all source and header files in the indicated paths in a designated variable.
+##
+## When RECURSIVE is specified, directories are traversed recursively.
+##
+## Use: scan_scylla_source_directories(VAR my_result_var [RECURSIVE] PATHS [path1 path2 ...])
+##
+function (scan_scylla_source_directories)
+    set(options RECURSIVE)
+    set(oneValueArgs VAR)
+    set(multiValueArgs PATHS)
+    cmake_parse_arguments(args "${options}" "${oneValueArgs}" "${multiValueArgs}" "${ARGN}")
+
+    set(globs "")
+
+    foreach (dir ${args_PATHS})
+        list(APPEND globs "${dir}/*.cc" "${dir}/*.hh")
+    endforeach()
+
+    if (args_RECURSIVE)
+        set(glob_kind GLOB_RECURSE)
     else()
-        set(${arch} "" PARENT_SCOPE)
+        set(glob_kind GLOB)
     endif()
-endfunction()
-default_target_arch(target_arch)
-if(target_arch)
-    set(target_arch_flag "-march=${target_arch}")
-endif()
 
-set(cxx_coro_flag)
-if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
-    set(cxx_coro_flag -fcoroutines)
-endif()
+    file(${glob_kind} var
+            ${globs})
 
-# Configure Seastar compile options to align with Scylla
-set(Seastar_CXX_FLAGS ${cxx_coro_flag} ${target_arch_flag} CACHE INTERNAL "" FORCE)
-set(Seastar_CXX_DIALECT gnu++20 CACHE INTERNAL "" FORCE)
-
-add_subdirectory(seastar)
-add_subdirectory(abseil)
-# Exclude absl::strerror from the default "all" target since it's not
-# used in Scylla build and, moreover, makes use of deprecated glibc APIs,
-# such as sys_nerr, which are not exposed from "stdio.h" since glibc 2.32,
-# which happens to be the case for recent Fedora distribution versions.
-#
-# Need to use the internal "absl_strerror" target name instead of namespaced
-# variant because `set_target_properties` does not understand the latter form,
-# unfortunately.
-set_target_properties(absl_strerror PROPERTIES EXCLUDE_FROM_ALL TRUE)
-
-# System libraries dependencies
-find_package(Boost COMPONENTS filesystem program_options system thread regex REQUIRED)
-find_package(Lua REQUIRED)
-find_package(ZLIB REQUIRED)
-find_package(ICU COMPONENTS uc REQUIRED)
-
-set(scylla_build_dir "${CMAKE_BINARY_DIR}/build/${BUILD_TYPE}")
-set(scylla_gen_build_dir "${scylla_build_dir}/gen")
-file(MAKE_DIRECTORY "${scylla_build_dir}" "${scylla_gen_build_dir}")
-
-# Place libraries, executables and archives in ${buildroot}/build/${mode}/
-foreach(mode RUNTIME LIBRARY ARCHIVE)
-    set(CMAKE_${mode}_OUTPUT_DIRECTORY "${scylla_build_dir}")
-endforeach()
-
-# Generate C++ source files from thrift definitions
-function(scylla_generate_thrift)
-    set(one_value_args TARGET VAR IN_FILE OUT_DIR SERVICE)
-    cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
-
-    get_filename_component(in_file_name ${args_IN_FILE} NAME_WE)
-
-    set(aux_out_file_name ${args_OUT_DIR}/${in_file_name})
-    set(outputs
-        ${aux_out_file_name}_types.cpp
-        ${aux_out_file_name}_types.h
-        ${aux_out_file_name}_constants.cpp
-        ${aux_out_file_name}_constants.h
-        ${args_OUT_DIR}/${args_SERVICE}.cpp
-        ${args_OUT_DIR}/${args_SERVICE}.h)
-
-    add_custom_command(
-        DEPENDS
-            ${args_IN_FILE}
-            thrift
-        OUTPUT ${outputs}
-        COMMAND ${CMAKE_COMMAND} -E make_directory ${args_OUT_DIR}
-        COMMAND thrift -gen cpp:cob_style,no_skeleton -out "${args_OUT_DIR}" "${args_IN_FILE}")
-
-    add_custom_target(${args_TARGET}
-        DEPENDS ${outputs})
-
-    set(${args_VAR} ${outputs} PARENT_SCOPE)
+    set(${args_VAR} ${var} PARENT_SCOPE)
 endfunction()
 
-scylla_generate_thrift(
-    TARGET scylla_thrift_gen_cassandra
-    VAR scylla_thrift_gen_cassandra_files
-    IN_FILE "${CMAKE_SOURCE_DIR}/interface/cassandra.thrift"
-    OUT_DIR ${scylla_gen_build_dir}
-    SERVICE Cassandra)
+## Although Seastar is an external project, it is common enough to explore the sources while doing
+## Scylla development that we'll treat the Seastar sources as part of this project for easier navigation.
+scan_scylla_source_directories(
+        VAR SEASTAR_SOURCE_FILES
+        RECURSIVE
 
-# Parse antlr3 grammar files and generate C++ sources
-function(scylla_generate_antlr3)
-    set(one_value_args TARGET VAR IN_FILE OUT_DIR)
-    cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
+        PATHS
+          seastar/core
+          seastar/http
+          seastar/json
+          seastar/net
+          seastar/rpc
+          seastar/tests
+          seastar/util)
 
-    get_filename_component(in_file_pure_name ${args_IN_FILE} NAME)
-    get_filename_component(stem ${in_file_pure_name} NAME_WE)
+scan_scylla_source_directories(
+        VAR SCYLLA_ROOT_SOURCE_FILES
+        PATHS .)
 
-    set(outputs
-        "${args_OUT_DIR}/${stem}Lexer.hpp"
-        "${args_OUT_DIR}/${stem}Lexer.cpp"
-        "${args_OUT_DIR}/${stem}Parser.hpp"
-        "${args_OUT_DIR}/${stem}Parser.cpp")
+scan_scylla_source_directories(
+        VAR SCYLLA_SUB_SOURCE_FILES
+        RECURSIVE
 
-    add_custom_command(
-        DEPENDS
-            ${args_IN_FILE}
-        OUTPUT ${outputs}
-        # Remove #ifdef'ed code from the grammar source code
-        COMMAND sed -e "/^#if 0/,/^#endif/d" "${args_IN_FILE}" > "${args_OUT_DIR}/${in_file_pure_name}"
-        COMMAND antlr3 "${args_OUT_DIR}/${in_file_pure_name}"
-        # We replace many local `ExceptionBaseType* ex` variables with a single function-scope one.
-        # Because we add such a variable to every function, and because `ExceptionBaseType` is not a global
-        # name, we also add a global typedef to avoid compilation errors.
-        COMMAND sed -i -e "/^.*On :.*$/d" "${args_OUT_DIR}/${stem}Lexer.hpp"
-        COMMAND sed -i -e "/^.*On :.*$/d" "${args_OUT_DIR}/${stem}Lexer.cpp"
-        COMMAND sed -i -e "/^.*On :.*$/d" "${args_OUT_DIR}/${stem}Parser.hpp"
-        COMMAND sed -i
-            -e "s/^\\( *\\)\\(ImplTraits::CommonTokenType\\* [a-zA-Z0-9_]* = NULL;\\)$/\\1const \\2/"
-            -e "/^.*On :.*$/d"
-            -e "1i using ExceptionBaseType = int;"
-            -e "s/^{/{ ExceptionBaseType\\* ex = nullptr;/; s/ExceptionBaseType\\* ex = new/ex = new/; s/exceptions::syntax_exception e/exceptions::syntax_exception\\& e/"
-            "${args_OUT_DIR}/${stem}Parser.cpp"
-        VERBATIM)
+        PATHS
+          api
+          auth
+          cql3
+          db
+          dht
+          exceptions
+          gms
+          index
+          io
+          locator
+          message
+          repair
+          service
+          sstables
+          streaming
+          tests
+          thrift
+          tracing
+          transport
+          utils)
 
-    add_custom_target(${args_TARGET}
-        DEPENDS ${outputs})
+scan_scylla_source_directories(
+        VAR SCYLLA_GEN_SOURCE_FILES
+        RECURSIVE
+        PATHS build/release/gen)
 
-    set(${args_VAR} ${outputs} PARENT_SCOPE)
-endfunction()
-
-set(antlr3_grammar_files
-    cql3/Cql.g
-    alternator/expressions.g)
-
-set(antlr3_gen_files)
-
-foreach(f ${antlr3_grammar_files})
-    get_filename_component(grammar_file_name "${f}" NAME_WE)
-    get_filename_component(f_dir "${f}" DIRECTORY)
-    scylla_generate_antlr3(
-        TARGET scylla_antlr3_gen_${grammar_file_name}
-        VAR scylla_antlr3_gen_${grammar_file_name}_files
-        IN_FILE "${CMAKE_SOURCE_DIR}/${f}"
-        OUT_DIR ${scylla_gen_build_dir}/${f_dir})
-    list(APPEND antlr3_gen_files "${scylla_antlr3_gen_${grammar_file_name}_files}")
-endforeach()
-
-# Generate C++ sources from ragel grammar files
-seastar_generate_ragel(
-    TARGET scylla_ragel_gen_protocol_parser
-    VAR scylla_ragel_gen_protocol_parser_file
-    IN_FILE "${CMAKE_SOURCE_DIR}/redis/protocol_parser.rl"
-    OUT_FILE ${scylla_gen_build_dir}/redis/protocol_parser.hh)
-
-# Generate C++ sources from Swagger definitions
-set(swagger_files
-    api/api-doc/cache_service.json
-    api/api-doc/collectd.json
-    api/api-doc/column_family.json
-    api/api-doc/commitlog.json
-    api/api-doc/compaction_manager.json
-    api/api-doc/config.json
-    api/api-doc/endpoint_snitch_info.json
-    api/api-doc/error_injection.json
-    api/api-doc/failure_detector.json
-    api/api-doc/gossiper.json
-    api/api-doc/hinted_handoff.json
-    api/api-doc/lsa.json
-    api/api-doc/messaging_service.json
-    api/api-doc/storage_proxy.json
-    api/api-doc/storage_service.json
-    api/api-doc/stream_manager.json
-    api/api-doc/system.json
-    api/api-doc/task_manager.json
-    api/api-doc/task_manager_test.json
-    api/api-doc/utils.json)
-
-set(swagger_gen_files)
-
-foreach(f ${swagger_files})
-    get_filename_component(fname "${f}" NAME_WE)
-    get_filename_component(dir "${f}" DIRECTORY)
-    seastar_generate_swagger(
-        TARGET scylla_swagger_gen_${fname}
-        VAR scylla_swagger_gen_${fname}_files
-        IN_FILE "${CMAKE_SOURCE_DIR}/${f}"
-        OUT_DIR "${scylla_gen_build_dir}/${dir}")
-    list(APPEND swagger_gen_files "${scylla_swagger_gen_${fname}_files}")
-endforeach()
-
-# Create C++ bindings for IDL serializers
-function(scylla_generate_idl_serializer)
-    set(one_value_args TARGET VAR IN_FILE OUT_FILE)
-    cmake_parse_arguments(args "" "${one_value_args}" "" ${ARGN})
-    get_filename_component(out_dir ${args_OUT_FILE} DIRECTORY)
-    set(idl_compiler "${CMAKE_SOURCE_DIR}/idl-compiler.py")
-
-    find_package(Python3 COMPONENTS Interpreter)
-
-    add_custom_command(
-        DEPENDS
-            ${args_IN_FILE}
-            ${idl_compiler}
-        OUTPUT ${args_OUT_FILE}
-        COMMAND ${CMAKE_COMMAND} -E make_directory ${out_dir}
-        COMMAND Python3::Interpreter ${idl_compiler} --ns ser -f ${args_IN_FILE} -o ${args_OUT_FILE})
-
-    add_custom_target(${args_TARGET}
-        DEPENDS ${args_OUT_FILE})
-
-    set(${args_VAR} ${args_OUT_FILE} PARENT_SCOPE)
-endfunction()
-
-set(idl_serializers
-    idl/cache_temperature.idl.hh
-    idl/commitlog.idl.hh
-    idl/consistency_level.idl.hh
-    idl/frozen_mutation.idl.hh
-    idl/frozen_schema.idl.hh
-    idl/gossip_digest.idl.hh
-    idl/hinted_handoff.idl.hh
-    idl/idl_test.idl.hh
-    idl/keys.idl.hh
-    idl/messaging_service.idl.hh
-    idl/mutation.idl.hh
-    idl/paging_state.idl.hh
-    idl/partition_checksum.idl.hh
-    idl/paxos.idl.hh
-    idl/query.idl.hh
-    idl/raft.idl.hh
-    idl/range.idl.hh
-    idl/read_command.idl.hh
-    idl/reconcilable_result.idl.hh
-    idl/replay_position.idl.hh
-    idl/result.idl.hh
-    idl/ring_position.idl.hh
-    idl/streaming.idl.hh
-    idl/token.idl.hh
-    idl/tracing.idl.hh
-    idl/truncation_record.idl.hh
-    idl/uuid.idl.hh
-    idl/view.idl.hh)
-
-set(idl_gen_files)
-
-foreach(f ${idl_serializers})
-    get_filename_component(idl_name "${f}" NAME)
-    get_filename_component(idl_target "${idl_name}" NAME_WE)
-    get_filename_component(idl_dir "${f}" DIRECTORY)
-    string(REPLACE ".idl.hh" ".dist.hh" idl_out_hdr_name "${idl_name}")
-    scylla_generate_idl_serializer(
-        TARGET scylla_idl_gen_${idl_target}
-        VAR scylla_idl_gen_${idl_target}_files
-        IN_FILE "${CMAKE_SOURCE_DIR}/${f}"
-        OUT_FILE ${scylla_gen_build_dir}/${idl_dir}/${idl_out_hdr_name})
-    list(APPEND idl_gen_files "${scylla_idl_gen_${idl_target}_files}")
-endforeach()
-
-set(scylla_sources
-    absl-flat_hash_map.cc
-    alternator/auth.cc
-    alternator/conditions.cc
-    alternator/controller.cc
-    alternator/executor.cc
-    alternator/expressions.cc
-    alternator/serialization.cc
-    alternator/server.cc
-    alternator/stats.cc
-    alternator/streams.cc
-    api/api.cc
-    api/cache_service.cc
-    api/collectd.cc
-    api/column_family.cc
-    api/commitlog.cc
-    api/compaction_manager.cc
-    api/config.cc
-    api/endpoint_snitch.cc
-    api/error_injection.cc
-    api/failure_detector.cc
-    api/gossiper.cc
-    api/hinted_handoff.cc
-    api/lsa.cc
-    api/messaging_service.cc
-    api/storage_proxy.cc
-    api/storage_service.cc
-    api/stream_manager.cc
-    api/system.cc
-    api/task_manager.cc
-    api/task_manager_test.cc
-    atomic_cell.cc
-    auth/allow_all_authenticator.cc
-    auth/allow_all_authorizer.cc
-    auth/authenticated_user.cc
-    auth/authentication_options.cc
-    auth/authenticator.cc
-    auth/common.cc
-    auth/default_authorizer.cc
-    auth/password_authenticator.cc
-    auth/passwords.cc
-    auth/permission.cc
-    auth/permissions_cache.cc
-    auth/resource.cc
-    auth/role_or_anonymous.cc
-    auth/roles-metadata.cc
-    auth/sasl_challenge.cc
-    auth/service.cc
-    auth/standard_role_manager.cc
-    auth/transitional.cc
-    bytes.cc
-    caching_options.cc
-    canonical_mutation.cc
-    cdc/cdc_partitioner.cc
-    cdc/generation.cc
-    cdc/log.cc
-    cdc/metadata.cc
-    cdc/split.cc
-    clocks-impl.cc
-    collection_mutation.cc
-    compaction/compaction.cc
-    compaction/compaction_manager.cc
-    compaction/compaction_strategy.cc
-    compaction/leveled_compaction_strategy.cc
-    compaction/size_tiered_compaction_strategy.cc
-    compaction/time_window_compaction_strategy.cc
-    compress.cc
-    converting_mutation_partition_applier.cc
-    counters.cc
-    cql3/abstract_marker.cc
-    cql3/attributes.cc
-    cql3/cf_name.cc
-    cql3/column_condition.cc
-    cql3/column_identifier.cc
-    cql3/column_specification.cc
-    cql3/constants.cc
-    cql3/cql3_type.cc
-    cql3/expr/expression.cc
-    cql3/expr/prepare_expr.cc
-    cql3/expr/restrictions.cc
-    cql3/functions/aggregate_fcts.cc
-    cql3/functions/castas_fcts.cc
-    cql3/functions/error_injection_fcts.cc
-    cql3/functions/functions.cc
-    cql3/functions/user_function.cc
-    cql3/index_name.cc
-    cql3/keyspace_element_name.cc
-    cql3/lists.cc
-    cql3/maps.cc
-    cql3/operation.cc
-    cql3/prepare_context.cc
-    cql3/query_options.cc
-    cql3/query_processor.cc
-    cql3/restrictions/statement_restrictions.cc
-    cql3/result_set.cc
-    cql3/role_name.cc
-    cql3/selection/abstract_function_selector.cc
-    cql3/selection/selectable.cc
-    cql3/selection/selection.cc
-    cql3/selection/selector.cc
-    cql3/selection/selector_factories.cc
-    cql3/selection/simple_selector.cc
-    cql3/sets.cc
-    cql3/statements/alter_keyspace_statement.cc
-    cql3/statements/alter_service_level_statement.cc
-    cql3/statements/alter_table_statement.cc
-    cql3/statements/alter_type_statement.cc
-    cql3/statements/alter_view_statement.cc
-    cql3/statements/attach_service_level_statement.cc
-    cql3/statements/authentication_statement.cc
-    cql3/statements/authorization_statement.cc
-    cql3/statements/batch_statement.cc
-    cql3/statements/cas_request.cc
-    cql3/statements/cf_prop_defs.cc
-    cql3/statements/cf_statement.cc
-    cql3/statements/create_aggregate_statement.cc
-    cql3/statements/create_function_statement.cc
-    cql3/statements/create_index_statement.cc
-    cql3/statements/create_keyspace_statement.cc
-    cql3/statements/create_service_level_statement.cc
-    cql3/statements/create_table_statement.cc
-    cql3/statements/create_type_statement.cc
-    cql3/statements/create_view_statement.cc
-    cql3/statements/delete_statement.cc
-    cql3/statements/detach_service_level_statement.cc
-    cql3/statements/drop_aggregate_statement.cc
-    cql3/statements/drop_function_statement.cc
-    cql3/statements/drop_index_statement.cc
-    cql3/statements/drop_keyspace_statement.cc
-    cql3/statements/drop_service_level_statement.cc
-    cql3/statements/drop_table_statement.cc
-    cql3/statements/drop_type_statement.cc
-    cql3/statements/drop_view_statement.cc
-    cql3/statements/function_statement.cc
-    cql3/statements/grant_statement.cc
-    cql3/statements/index_prop_defs.cc
-    cql3/statements/index_target.cc
-    cql3/statements/ks_prop_defs.cc
-    cql3/statements/list_permissions_statement.cc
-    cql3/statements/list_service_level_attachments_statement.cc
-    cql3/statements/list_service_level_statement.cc
-    cql3/statements/list_users_statement.cc
-    cql3/statements/modification_statement.cc
-    cql3/statements/permission_altering_statement.cc
-    cql3/statements/property_definitions.cc
-    cql3/statements/raw/parsed_statement.cc
-    cql3/statements/revoke_statement.cc
-    cql3/statements/role-management-statements.cc
-    cql3/statements/schema_altering_statement.cc
-    cql3/statements/select_statement.cc
-    cql3/statements/service_level_statement.cc
-    cql3/statements/sl_prop_defs.cc
-    cql3/statements/truncate_statement.cc
-    cql3/statements/update_statement.cc
-    cql3/statements/strongly_consistent_modification_statement.cc
-    cql3/statements/strongly_consistent_select_statement.cc
-    cql3/statements/use_statement.cc
-    cql3/type_json.cc
-    cql3/untyped_result_set.cc
-    cql3/update_parameters.cc
-    cql3/user_types.cc
-    cql3/util.cc
-    cql3/ut_name.cc
-    cql3/values.cc
-    data_dictionary/data_dictionary.cc
-    db/batchlog_manager.cc
-    db/commitlog/commitlog.cc
-    db/commitlog/commitlog_entry.cc
-    db/commitlog/commitlog_replayer.cc
-    db/config.cc
-    db/consistency_level.cc
-    db/cql_type_parser.cc
-    db/data_listeners.cc
-    db/extensions.cc
-    db/heat_load_balance.cc
-    db/hints/host_filter.cc
-    db/hints/manager.cc
-    db/hints/resource_manager.cc
-    db/hints/sync_point.cc
-    db/large_data_handler.cc
-    db/legacy_schema_migrator.cc
-    db/marshal/type_parser.cc
-    db/rate_limiter.cc
-    db/schema_tables.cc
-    db/size_estimates_virtual_reader.cc
-    db/snapshot-ctl.cc
-    db/sstables-format-selector.cc
-    db/system_distributed_keyspace.cc
-    db/system_keyspace.cc
-    db/view/row_locking.cc
-    db/view/view.cc
-    db/view/view_update_generator.cc
-    db/virtual_table.cc
-    dht/boot_strapper.cc
-    dht/i_partitioner.cc
-    dht/murmur3_partitioner.cc
-    dht/range_streamer.cc
-    dht/token.cc
-    replica/distributed_loader.cc
-    duration.cc
-    exceptions/exceptions.cc
-    readers/mutation_readers.cc
-    frozen_mutation.cc
-    frozen_schema.cc
-    generic_server.cc
-    gms/application_state.cc
-    gms/endpoint_state.cc
-    gms/failure_detector.cc
-    gms/feature_service.cc
-    gms/gossip_digest_ack2.cc
-    gms/gossip_digest_ack.cc
-    gms/gossip_digest_syn.cc
-    gms/gossiper.cc
-    gms/inet_address.cc
-    gms/versioned_value.cc
-    gms/version_generator.cc
-    hashers.cc
-    index/secondary_index.cc
-    index/secondary_index_manager.cc
-    init.cc
-    keys.cc
-    utils/lister.cc
-    locator/abstract_replication_strategy.cc
-    locator/azure_snitch.cc
-    locator/ec2_multi_region_snitch.cc
-    locator/ec2_snitch.cc
-    locator/everywhere_replication_strategy.cc
-    locator/gce_snitch.cc
-    locator/gossiping_property_file_snitch.cc
-    locator/local_strategy.cc
-    locator/network_topology_strategy.cc
-    locator/production_snitch_base.cc
-    locator/rack_inferring_snitch.cc
-    locator/simple_snitch.cc
-    locator/simple_strategy.cc
-    locator/snitch_base.cc
-    locator/token_metadata.cc
-    lang/lua.cc
-    main.cc
-    replica/memtable.cc
-    message/messaging_service.cc
-    multishard_mutation_query.cc
-    mutation.cc
-    mutation_fragment.cc
-    mutation_partition.cc
-    mutation_partition_serializer.cc
-    mutation_partition_view.cc
-    mutation_query.cc
-    readers/mutation_reader.cc
-    mutation_writer/feed_writers.cc
-    mutation_writer/multishard_writer.cc
-    mutation_writer/partition_based_splitting_writer.cc
-    mutation_writer/shard_based_splitting_writer.cc
-    mutation_writer/timestamp_based_splitting_writer.cc
-    partition_slice_builder.cc
-    partition_version.cc
-    querier.cc
-    query.cc
-    query_ranges_to_vnodes.cc
-    query-result-set.cc
-    raft/fsm.cc
-    raft/log.cc
-    raft/raft.cc
-    raft/server.cc
-    raft/tracker.cc
-    service/broadcast_tables/experimental/lang.cc
-    range_tombstone.cc
-    range_tombstone_list.cc
-    tombstone_gc_options.cc
-    tombstone_gc.cc
-    reader_concurrency_semaphore.cc
-    redis/abstract_command.cc
-    redis/command_factory.cc
-    redis/commands.cc
-    redis/keyspace_utils.cc
-    redis/lolwut.cc
-    redis/mutation_utils.cc
-    redis/options.cc
-    redis/query_processor.cc
-    redis/query_utils.cc
-    redis/server.cc
-    redis/service.cc
-    redis/stats.cc
-    release.cc
-    repair/repair.cc
-    repair/row_level.cc
-    replica/database.cc
-    replica/table.cc
-    row_cache.cc
-    schema.cc
-    schema_mutations.cc
-    schema_registry.cc
-    serializer.cc
-    service/client_state.cc
-    service/forward_service.cc
-    service/migration_manager.cc
-    service/misc_services.cc
-    service/pager/paging_state.cc
-    service/pager/query_pagers.cc
-    service/paxos/paxos_state.cc
-    service/paxos/prepare_response.cc
-    service/paxos/prepare_summary.cc
-    service/paxos/proposal.cc
-    service/priority_manager.cc
-    service/qos/qos_common.cc
-    service/qos/service_level_controller.cc
-    service/qos/standard_service_level_distributed_data_accessor.cc
-    service/raft/raft_group_registry.cc
-    service/raft/raft_rpc.cc
-    service/raft/raft_sys_table_storage.cc
-    service/raft/group0_state_machine.cc
-    service/storage_proxy.cc
-    service/storage_service.cc
-    sstables/compress.cc
-    sstables/integrity_checked_file_impl.cc
-    sstables/kl/reader.cc
-    sstables/metadata_collector.cc
-    sstables/m_format_read_helpers.cc
-    sstables/mx/reader.cc
-    sstables/mx/writer.cc
-    sstables/prepended_input_stream.cc
-    sstables/random_access_reader.cc
-    sstables/sstable_directory.cc
-    sstables/sstable_mutation_reader.cc
-    sstables/sstables.cc
-    sstables/sstable_set.cc
-    sstables/sstables_manager.cc
-    sstables/sstable_version.cc
-    sstables/writer.cc
-    streaming/consumer.cc
-    streaming/progress_info.cc
-    streaming/session_info.cc
-    streaming/stream_coordinator.cc
-    streaming/stream_manager.cc
-    streaming/stream_plan.cc
-    streaming/stream_reason.cc
-    streaming/stream_receive_task.cc
-    streaming/stream_request.cc
-    streaming/stream_result_future.cc
-    streaming/stream_session.cc
-    streaming/stream_session_state.cc
-    streaming/stream_summary.cc
-    streaming/stream_task.cc
-    streaming/stream_transfer_task.cc
-    table_helper.cc
-    tasks/task_manager.cc
-    thrift/controller.cc
-    thrift/handler.cc
-    thrift/server.cc
-    thrift/thrift_validation.cc
-    timeout_config.cc
-    tools/scylla-sstable-index.cc
-    tools/scylla-types.cc
-    tracing/traced_file.cc
-    tracing/trace_keyspace_helper.cc
-    tracing/trace_state.cc
-    tracing/tracing_backend_registry.cc
-    tracing/tracing.cc
-    transport/controller.cc
-    transport/cql_protocol_extension.cc
-    transport/event.cc
-    transport/event_notifier.cc
-    transport/messages/result_message.cc
-    transport/server.cc
-    types.cc
-    unimplemented.cc
-    utils/arch/powerpc/crc32-vpmsum/crc32_wrapper.cc
-    utils/array-search.cc
-    utils/ascii.cc
-    utils/base64.cc
-    utils/big_decimal.cc
-    utils/bloom_calculations.cc
-    utils/bloom_filter.cc
-    utils/buffer_input_stream.cc
-    utils/build_id.cc
-    utils/config_file.cc
-    utils/directories.cc
-    utils/disk-error-handler.cc
-    utils/dynamic_bitset.cc
-    utils/error_injection.cc
-    utils/exceptions.cc
-    utils/file_lock.cc
-    utils/generation-number.cc
-    utils/gz/crc_combine.cc
-    utils/gz/gen_crc_combine_table.cc
-    utils/human_readable.cc
-    utils/i_filter.cc
-    utils/large_bitset.cc
-    utils/like_matcher.cc
-    utils/limiting_data_source.cc
-    utils/logalloc.cc
-    utils/managed_bytes.cc
-    utils/multiprecision_int.cc
-    utils/murmur_hash.cc
-    utils/rate_limiter.cc
-    utils/rjson.cc
-    utils/runtime.cc
-    utils/updateable_value.cc
-    utils/utf8.cc
-    utils/uuid.cc
-    utils/UUID_gen.cc
-    validation.cc
-    vint-serialization.cc
-    zstd.cc)
-
-set(scylla_gen_sources
-    "${scylla_thrift_gen_cassandra_files}"
-    "${scylla_ragel_gen_protocol_parser_file}"
-    "${swagger_gen_files}"
-    "${idl_gen_files}"
-    "${antlr3_gen_files}")
+set(SCYLLA_SOURCE_FILES
+        ${SCYLLA_ROOT_SOURCE_FILES}
+        ${SCYLLA_GEN_SOURCE_FILES}
+        ${SCYLLA_SUB_SOURCE_FILES})
 
 add_executable(scylla
-    ${scylla_sources}
-    ${scylla_gen_sources})
+        ${SEASTAR_SOURCE_FILES}
+        ${SCYLLA_SOURCE_FILES})
 
-target_link_libraries(scylla PRIVATE
-    seastar
-    # Boost dependencies
-    Boost::filesystem
-    Boost::program_options
-    Boost::system
-    Boost::thread
-    Boost::regex
-    Boost::headers
-    # Abseil libs
-    absl::hashtablez_sampler
-    absl::raw_hash_set
-    absl::synchronization
-    absl::graphcycles_internal
-    absl::stacktrace
-    absl::symbolize
-    absl::debugging_internal
-    absl::demangle_internal
-    absl::time
-    absl::time_zone
-    absl::int128
-    absl::city
-    absl::hash
-    absl::malloc_internal
-    absl::spinlock_wait
-    absl::base
-    absl::dynamic_annotations
-    absl::raw_logging_internal
-    absl::exponential_biased
-    absl::throw_delegate
-    # System libs
-    ZLIB::ZLIB
-    ICU::uc
-    systemd
-    zstd
-    snappy
-    ${LUA_LIBRARIES}
-    thrift
-    crypt)
+# Note that since CLion does not undestand GCC6 concepts, we always disable them (even if users configure otherwise).
+# CLion seems to have trouble with `-U` (macro undefinition), so we do it this way instead.
+list(REMOVE_ITEM SEASTAR_CFLAGS "-DHAVE_GCC6_CONCEPTS")
 
-target_link_libraries(scylla PRIVATE
-    -Wl,--build-id=sha1 # Force SHA1 build-id generation
-    # TODO: Use lld linker if it's available, otherwise gold, else bfd
-    -fuse-ld=lld)
-# TODO: patch dynamic linker to match configure.py behavior
+# If the Seastar pkg-config information is available, append to the default flags.
+#
+# For ease of browsing the source code, we always pretend that DPDK is enabled.
+target_compile_options(scylla PUBLIC
+        -std=gnu++1z
+        -DHAVE_DPDK
+        -DHAVE_HWLOC
+        "${SEASTAR_CFLAGS}")
 
-target_compile_options(scylla PRIVATE
-    -std=gnu++20
-    ${cxx_coro_flag}
-    ${target_arch_flag})
-# Hacks needed to expose internal APIs for xxhash dependencies
-target_compile_definitions(scylla PRIVATE XXH_PRIVATE_API HAVE_LZ4_COMPRESS_DEFAULT)
-
-target_include_directories(scylla PRIVATE
-    "${CMAKE_CURRENT_SOURCE_DIR}"
-    libdeflate
-    abseil
-    "${scylla_gen_build_dir}")
-
-###
-### Create crc_combine_table helper executable.
-### Use it to generate crc_combine_table.cc to be used in scylla at build time.
-###
-add_executable(crc_combine_table utils/gz/gen_crc_combine_table.cc)
-target_link_libraries(crc_combine_table PRIVATE seastar)
-target_include_directories(crc_combine_table PRIVATE "${CMAKE_CURRENT_SOURCE_DIR}")
-target_compile_options(crc_combine_table PRIVATE
-    -std=gnu++20
-    ${cxx_coro_flag}
-    ${target_arch_flag})
-add_dependencies(scylla crc_combine_table)
-
-# Generate an additional source file at build time that is needed for Scylla compilation
-add_custom_command(OUTPUT "${scylla_gen_build_dir}/utils/gz/crc_combine_table.cc"
-    COMMAND $<TARGET_FILE:crc_combine_table> > "${scylla_gen_build_dir}/utils/gz/crc_combine_table.cc"
-    DEPENDS crc_combine_table)
-target_sources(scylla PRIVATE "${scylla_gen_build_dir}/utils/gz/crc_combine_table.cc")
-
-###
-### Generate version file and supply appropriate compile definitions for release.cc
-###
-execute_process(COMMAND ${CMAKE_SOURCE_DIR}/SCYLLA-VERSION-GEN --output-dir "${CMAKE_BINARY_DIR}/gen" RESULT_VARIABLE scylla_version_gen_res)
-if(scylla_version_gen_res)
-    message(SEND_ERROR "Version file generation failed. Return code: ${scylla_version_gen_res}")
-endif()
-
-file(READ "${CMAKE_BINARY_DIR}/gen/SCYLLA-VERSION-FILE" scylla_version)
-string(STRIP "${scylla_version}" scylla_version)
-
-file(READ "${CMAKE_BINARY_DIR}/gen/SCYLLA-RELEASE-FILE" scylla_release)
-string(STRIP "${scylla_release}" scylla_release)
-
-get_property(release_cdefs SOURCE "${CMAKE_SOURCE_DIR}/release.cc" PROPERTY COMPILE_DEFINITIONS)
-list(APPEND release_cdefs "SCYLLA_VERSION=\"${scylla_version}\"" "SCYLLA_RELEASE=\"${scylla_release}\"")
-set_source_files_properties("${CMAKE_SOURCE_DIR}/release.cc" PROPERTIES COMPILE_DEFINITIONS "${release_cdefs}")
-
-###
-### Custom command for building libdeflate. Link the library to scylla.
-###
-set(libdeflate_lib "${scylla_build_dir}/libdeflate/libdeflate.a")
-add_custom_command(OUTPUT "${libdeflate_lib}"
-    COMMAND make -C "${CMAKE_SOURCE_DIR}/libdeflate"
-        BUILD_DIR=../build/${BUILD_TYPE}/libdeflate/
-        CC=${CMAKE_C_COMPILER}
-        "CFLAGS=${target_arch_flag}"
-        ../build/${BUILD_TYPE}/libdeflate//libdeflate.a) # Two backslashes are important!
-# Hack to force generating custom command to produce libdeflate.a
-add_custom_target(libdeflate DEPENDS "${libdeflate_lib}")
-target_link_libraries(scylla PRIVATE "${libdeflate_lib}")
-
-# TODO: create cmake/ directory and move utilities (generate functions etc) there
-# TODO: Build tests if BUILD_TESTING=on (using CTest module)
+# The order matters here: prefer the "static" DPDK directories to any dynamic paths from pkg-config. Some files are only
+# available dynamically, though.
+target_include_directories(scylla PUBLIC
+        .
+        ${SEASTAR_DPDK_INCLUDE_DIRS}
+        ${SEASTAR_INCLUDE_DIRS}
+        ${Boost_INCLUDE_DIRS}
+        xxhash
+        libdeflate
+        build/release/gen)

CONTRIBUTING.md

@@ -1,22 +1,11 @@
-# Contributing to Scylla
+# Asking questions or requesting help
 
-## Asking questions or requesting help
+Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
 
-Use the [Scylla Users mailing list](https://groups.google.com/g/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+# Reporting an issue
 
-Join the [Scylla Developers mailing list](https://groups.google.com/g/scylladb-dev) for deeper technical discussions and to discuss your ideas for contributions.
+Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to report issues.  Fill in as much information as you can in the issue template, especially for performance problems.
 
-## Reporting an issue
+# Contributing Code to Scylla
 
-Please use the [issue tracker](https://github.com/scylladb/scylla/issues/) to report issues or to suggest features. Fill in as much information as you can in the issue template, especially for performance problems.
-
-## Contributing code to Scylla
-
-Before you can contribute code to Scylla for the first time, you should sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send the signed form cla@scylladb.com. You can then submit your changes as patches to the to the [scylladb-dev mailing list](https://groups.google.com/forum/#!forum/scylladb-dev) or as a pull request to the [Scylla project on github](https://github.com/scylladb/scylla).
-If you need help formatting or sending patches, [check out these instructions](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches).
-
-The Scylla C++ source code uses the [Seastar coding style](https://github.com/scylladb/seastar/blob/master/coding-style.md) so please adhere to that in your patches. Note that Scylla code is written with `using namespace seastar`, so should not explicitly add the `seastar::` prefix to Seastar symbols. You will usually not need to add `using namespace seastar` to new source files, because most Scylla header files have `#include "seastarx.hh"`, which does this.
-
-Header files in Scylla must be self-contained, i.e., each can be included without having to include specific other headers first. To verify that your change did not break this property, run `ninja dev-headers`. If you added or removed header files, you must `touch configure.py` first - this will cause `configure.py` to be automatically re-run to generate a fresh list of header files.
-
-For more criteria on what reviewers consider good code, see the [review checklist](https://github.com/scylladb/scylla/blob/master/docs/dev/review-checklist.md).
+To contribute code to Scylla, you need to sign the [Contributor License Agreement](http://www.scylladb.com/opensource/cla/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.

HACKING.md

@@ -18,35 +18,23 @@ $ git submodule update --init --recursive
 
 ### Dependencies
 
-Scylla is fairly fussy about its build environment, requiring a very recent
-version of the C++20 compiler and numerous tools and libraries to build.
+Scylla depends on the system package manager for its development dependencies.
 
-Run `./install-dependencies.sh` (as root) to use your Linux distributions's
-package manager to install the appropriate packages on your build machine.
-However, this will only work on very recent distributions. For example,
-currently Fedora users must upgrade to Fedora 32 otherwise the C++ compiler
-will be too old, and not support the new C++20 standard that Scylla uses.
+Running `./install-dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
 
-Alternatively, to avoid having to upgrade your build machine or install
-various packages on it, we provide another option - the **frozen toolchain**.
-This is a script, `./tools/toolchain/dbuild`, that can execute build or run
-commands inside a Docker image that contains exactly the right build tools and
-libraries. The `dbuild` technique is useful for beginners, but is also the way
-in which ScyllaDB produces official releases, so it is highly recommended.
+On Ubuntu and Debian based Linux distributions, some packages
+required to build Scylla are missing in the official upstream:
 
-To use `dbuild`, you simply prefix any build or run command with it. Building
-and running Scylla becomes as easy as:
+- libthrift-dev and libthrift
+- antlr3-c++-dev
 
-```bash
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
-$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
-```
+Try running ```sudo ./scripts/scylla_current_repo``` to add Scylla upstream,
+and get the missing packages from it.
 
 ### Build system
 
 **Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
-thread, and up to 3 GB per native thread while linking. GCC >= 10 is
+thread, and up to 3 GB per native thread while linking. GCC >= 8.1.1. is
 required.
 
 Scylla is built with [Ninja](https://ninja-build.org/), a low-level rule-based system. A Python script, `configure.py`, generates a Ninja file (`build.ninja`) based on configuration options.
@@ -153,7 +141,7 @@ In v3:
 "Tests: unit ({mode}), dtest ({smp})"
 ```
 
-The usual is "Tests: unit (dev)", although running debug tests is encouraged.
+The usual is "Tests: unit (release)", although running debug tests is encouraged.
 
 5. When answering review comments, prefer inline quotes as they make it easier to track the conversation across multiple e-mails.
 
@@ -172,8 +160,12 @@ and you will get output like this:
 ```
 CQL QUERY LANGUAGE
   Tomasz Grabiec <tgrabiec@scylladb.com>   [maintainer]
+  Pekka Enberg <penberg@scylladb.com>      [maintainer]
 MATERIALIZED VIEWS
+  Pekka Enberg <penberg@scylladb.com>      [maintainer]
+  Duarte Nunes <duarte@scylladb.com>       [maintainer]
   Nadav Har'El <nyh@scylladb.com>          [reviewer]
+  Duarte Nunes <duarte@scylladb.com>       [reviewer]
 ```
 
 ### Running Scylla
@@ -362,61 +354,7 @@ $ git remote update
 $ git checkout -t local/my_local_seastar_branch
 ```
 
-### Generating code coverage report
-
-Install dependencies:
-
-    $ dnf install llvm # for llvm-profdata and llvm-cov
-    $ dnf install lcov # for genhtml
-
-Instruct `configure.py` to generate build files for `coverage` mode:
-
-    $ ./configure.py --mode=coverage
-
-Build the tests you want to run, then run them via `test.py` (important!):
-
-    $ ./test.py --mode=coverage [...]
-
-Alternatively, you can run individual tests via `./scripts/coverage.py --run`.
-
-Open the link printed at the end. Be horrified. Go and write more tests.
-
-For more details see `./scripts/coverage.py --help`.
-
-### Resolving stack backtraces
-
-Scylla may print stack backtraces to the log for several reasons.
-For example:
-- When aborting (e.g. due to assertion failure, internal error, or segfault)
-- When detecting seastar reactor stalls (where a seastar task runs for a long time without yielding the cpu to other tasks on that shard)
-
-The backtraces contain code pointers so they are not very helpful without resolving into code locations.
-To resolve the backtraces, one needs the scylla relocatable package that contains the scylla binary (with debug information),
-as well as the dynamic libraries it is linked against.
-
-Builds from our automated build system are uploaded to the cloud
-and can be searched on http://backtrace.scylladb.com/
-
-Make sure you have the scylla server exact `build-id` to locate
-its respective relocatable package, required for decoding backtraces it prints.
-
-The build-id is printed to the system log when scylla starts.
-It can also be found by executing `scylla --build-id`, or
-by using the `file` utility, for example:
-```
-$ scylla --build-id
-4cba12e6eb290a406bfa4930918db23941fd4be3
-
-$ file scylla
-scylla: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked, interpreter /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////lib64/ld-linux-x86-64.so.2, for GNU/Linux 3.2.0, BuildID[sha1]=4cba12e6eb290a406bfa4930918db23941fd4be3, with debug_info, not stripped, too many notes (256)
-```
-
-To find the build-id of a coredump, use the `eu-unstrip` utility as follows:
-```
-$ eu-unstrip -n --core <coredump> | awk '/scylla$/ { s=$2; sub(/@.*$/, "", s); print s; exit(0); }'
-4cba12e6eb290a406bfa4930918db23941fd4be3
-```
-
 ### Core dump debugging
 
-See [debugging.md](docs/dev/debugging.md).
+Slides:
+2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

MAINTAINERS

@@ -0,0 +1,131 @@
+M: Maintainer with commit access
+R: Reviewer with subsystem expertise
+F: Filename, directory, or pattern for the subsystem
+
+---
+
+AUTH
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Calle Wilund <calle@scylladb.com>
+R: Vlad Zolotarov <vladz@scylladb.com>
+R: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
+F: auth/*
+
+CACHE
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Paweł Dziepak <pdziepak@scylladb.com>
+R: Piotr Jastrzebski <piotr@scylladb.com>
+F: row_cache*
+F: *mutation*
+F: tests/mvcc*
+
+COMMITLOG / BATCHLOGa
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Calle Wilund <calle@scylladb.com>
+F: db/commitlog/*
+F: db/batch*
+
+COORDINATOR
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Gleb Natapov <gleb@scylladb.com>
+F: service/storage_proxy*
+
+COMPACTION
+R: Raphael S. Carvalho <raphaelsc@scylladb.com>
+R: Glauber Costa <glauber@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+F: sstables/compaction*
+
+CQL TRANSPORT LAYER
+M: Pekka Enberg <penberg@scylladb.com>
+F: transport/*
+
+CQL QUERY LANGUAGE
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Pekka Enberg <penberg@scylladb.com>
+F: cql3/*
+
+COUNTERS
+M: Paweł Dziepak <pdziepak@scylladb.com>
+F: counters*
+F: tests/counter_test*
+
+GOSSIP
+M: Duarte Nunes <duarte@scylladb.com>
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+R: Asias He <asias@scylladb.com>
+F: gms/*
+
+DOCKER
+M: Pekka Enberg <penberg@scylladb.com>
+F: dist/docker/*
+
+LSA
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Paweł Dziepak <pdziepak@scylladb.com>
+F: utils/logalloc*
+
+MATERIALIZED VIEWS
+M: Duarte Nunes <duarte@scylladb.com>
+M: Pekka Enberg <penberg@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+R: Duarte Nunes <duarte@scylladb.com>
+F: db/view/*
+F: cql3/statements/*view*
+
+PACKAGING
+R: Takuya ASADA <syuu@scylladb.com>
+F: dist/*
+
+REPAIR
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Asias He <asias@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+F: repair/*
+
+SCHEMA MANAGEMENT
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+M: Pekka Enberg <penberg@scylladb.com>
+F: db/schema_tables*
+F: db/legacy_schema_migrator*
+F: service/migration*
+F: schema*
+
+SECONDARY INDEXES
+M: Pekka Enberg <penberg@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+R: Pekka Enberg <penberg@scylladb.com>
+F: db/index/*
+F: cql3/statements/*index*
+
+SSTABLES
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Raphael S. Carvalho <raphaelsc@scylladb.com>
+R: Glauber Costa <glauber@scylladb.com>
+R: Nadav Har'El <nyh@scylladb.com>
+F: sstables/*
+
+STREAMING
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+R: Asias He <asias@scylladb.com>
+F: streaming/*
+F: service/storage_service.*
+
+THRIFT TRANSPORT LAYER
+M: Duarte Nunes <duarte@scylladb.com>
+F: thrift/*
+
+THE REST
+M: Avi Kivity <avi@scylladb.com>
+M: Paweł Dziepak <pdziepak@scylladb.com>
+M: Duarte Nunes <duarte@scylladb.com>
+M: Tomasz Grabiec <tgrabiec@scylladb.com>
+F: *

NOTICE.txt

@@ -1,11 +1,5 @@
 This project includes code developed by the Apache Software Foundation (http://www.apache.org/),
 especially Apache Cassandra.
 
-It includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
+It also includes files from https://github.com/antonblanchard/crc32-vpmsum (author Anton Blanchard <anton@au.ibm.com>, IBM).
 These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.
-
-It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)
-
-It includes modified tests from https://github.com/etcd-io/etcd.git (owned by The etcd Authors)
-
-It includes files from https://github.com/bytecodealliance/wasmtime-cpp (owned by Bytecode Alliance), licensed with Apache License 2.0.

README.md

@@ -1,110 +1,103 @@
 # Scylla
 
-[![Slack](https://img.shields.io/badge/slack-scylla-brightgreen.svg?logo=slack)](http://slack.scylladb.com)
-[![Twitter](https://img.shields.io/twitter/follow/ScyllaDB.svg?style=social&label=Follow)](https://twitter.com/intent/follow?screen_name=ScyllaDB)
+## Quick-start
 
-## What is Scylla?
-
-Scylla is the real-time big data database that is API-compatible with Apache Cassandra and Amazon DynamoDB.
-Scylla embraces a shared-nothing approach that increases throughput and storage capacity to realize order-of-magnitude performance improvements and reduce hardware costs.
-
-For more information, please see the [ScyllaDB web site].
-
-[ScyllaDB web site]: https://www.scylladb.com
-
-## Build Prerequisites
-
-Scylla is fairly fussy about its build environment, requiring very recent
-versions of the C++20 compiler and of many libraries to build. The document
-[HACKING.md](HACKING.md) includes detailed information on building and
-developing Scylla, but to get Scylla building quickly on (almost) any build
-machine, Scylla offers a [frozen toolchain](tools/toolchain/README.md),
-This is a pre-configured Docker image which includes recent versions of all
-the required compilers, libraries and build tools. Using the frozen toolchain
-allows you to avoid changing anything in your build machine to meet Scylla's
-requirements - you just need to meet the frozen toolchain's prerequisites
-(mostly, Docker or Podman being available).
-
-## Building Scylla
-
-Building Scylla with the frozen toolchain `dbuild` is as easy as:
+To get the build going quickly, Scylla offers a [frozen toolchain](tools/toolchain/README.md)
+which would build and run Scylla using a pre-configured Docker image.
+Using the frozen toolchain will also isolate all of the installed
+dependencies in a Docker container.
+Assuming you have met the toolchain prerequisites, which is running
+Docker in user mode, building and running is as easy as:
 
 ```bash
-$ git submodule update --init --force --recursive
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
-```
+$ ./tools/toolchain/dbuild ./configure.py
+$ ./tools/toolchain/dbuild ninja build/release/scylla
+$ ./tools/toolchain/dbuild ./build/release/scylla --developer-mode 1
+ ```
 
-For further information, please see:
+Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
 
-* [Developer documentation] for more information on building Scylla.
-* [Build documentation] on how to build Scylla binaries, tests, and packages.
-* [Docker image build documentation] for information on how to build Docker images.
-
-[developer documentation]: HACKING.md
-[build documentation]: docs/dev/building.md
-[docker image build documentation]: dist/docker/debian/README.md
+**Note**: GCC >= 8.1.1 is required to compile Scylla.
 
 ## Running Scylla
 
-To start Scylla server, run:
+* Run Scylla
+```
+./build/release/scylla
 
-```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --workdir tmp --smp 1 --developer-mode 1
 ```
 
-This will start a Scylla node with one CPU core allocated to it and data files stored in the `tmp` directory.
-The `--developer-mode` is needed to disable the various checks Scylla performs at startup to ensure the machine is configured for maximum performance (not relevant on development workstations).
-Please note that you need to run Scylla with `dbuild` if you built it with the frozen toolchain.
+* run Scylla with one CPU and ./tmp as data directory
 
-For more run options, run:
-
-```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --help
+```
+./build/release/scylla --datadir tmp --commitlog-directory tmp --smp 1
 ```
 
-## Testing
-
-See [test.py manual](docs/dev/testing.md).
+* For more run options:
+```
+./build/release/scylla --help
+```
 
 ## Scylla APIs and compatibility
 By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
-Thrift. There is also support for the API of Amazon DynamoDB™,
-which needs to be enabled and configured in order to be used. For more
-information on how to enable the DynamoDB™ API in Scylla,
-and the current compatibility of this feature as well as Scylla-specific extensions, see
+Thrift. There is also experimental support for the API of Amazon DynamoDB,
+but being experimental it needs to be explicitly enabled to be used. For more
+information on how to enable the experimental DynamoDB compatibility in Scylla,
+and the current limitations of this feature, see
 [Alternator](docs/alternator/alternator.md) and
 [Getting started with Alternator](docs/alternator/getting-started.md).
 
 ## Documentation
 
-Documentation can be found [here](docs/dev/README.md).
+Documentation can be found in [./docs](./docs) and on the
+[wiki](https://github.com/scylladb/scylla/wiki). There is currently no clear
+definition of what goes where, so when looking for something be sure to check
+both.
 Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
 User documentation can be found [here](https://docs.scylladb.com/).
 
-## Training 
+## Building Fedora RPM
 
-Training material and online courses can be found at [Scylla University](https://university.scylladb.com/). 
-The courses are free, self-paced and include hands-on examples. They cover a variety of topics including Scylla data modeling, 
-administration, architecture, basic NoSQL concepts, using drivers for application development, Scylla setup, failover, compactions, 
-multi-datacenters and how Scylla integrates with third-party applications.
+As a pre-requisite, you need to install [Mock](https://fedoraproject.org/wiki/Mock) on your machine:
+
+```
+# Install mock:
+sudo yum install mock
+
+# Add user to the "mock" group:
+usermod -a -G mock $USER && newgrp mock
+```
+
+Then, to build an RPM, run:
+
+```
+./dist/redhat/build_rpm.sh
+```
+
+The built RPM is stored in ``/var/lib/mock/<configuration>/result`` directory.
+For example, on Fedora 21 mock reports the following:
+
+```
+INFO: Done(scylla-server-0.00-1.fc21.src.rpm) Config(default) 20 minutes 7 seconds
+INFO: Results and/or logs in: /var/lib/mock/fedora-21-x86_64/result
+```
+
+## Building Fedora-based Docker image
+
+Build a Docker image with:
+
+```
+cd dist/docker
+docker build -t <image-name> .
+```
+
+Run the image with:
+
+```
+docker run -p $(hostname -i):9042:9042 -i -t <image name>
+```
 
 ## Contributing to Scylla
 
-If you want to report a bug or submit a pull request or a patch, please read the [contribution guidelines].
-
-If you are a developer working on Scylla, please read the [developer guidelines].
-
-[contribution guidelines]: CONTRIBUTING.md
-[developer guidelines]: HACKING.md
-
-## Contact
-
-* The [users mailing list] and [Slack channel] are for users to discuss configuration, management, and operations of the ScyllaDB open source.
-* The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
-
-[Users mailing list]: https://groups.google.com/forum/#!forum/scylladb-users
-
-[Slack channel]: http://slack.scylladb.com/
-
-[Developers mailing list]: https://groups.google.com/forum/#!forum/scylladb-dev
+[Hacking howto](HACKING.md)
+[Guidelines for contributing](CONTRIBUTING.md)

SCYLLA-VERSION-GEN

@@ -1,109 +1,26 @@
 #!/bin/sh
 
-USAGE=$(cat <<-END
-Usage: $(basename "$0") [-h|--help] [-o|--output-dir PATH] [--date-stamp DATE] -- generate Scylla version and build information files.
-
-Options:
-  -h|--help show this help message.
-  -o|--output-dir PATH specify destination path at which the version files are to be created.
-  -d|--date-stamp DATE manually set date for release parameter
-
-By default, the script will attempt to parse 'version' file
-in the current directory, which should contain a string of
-'\$version-\$release' form.
-
-Otherwise, it will call 'git log' on the source tree (the
-directory, which contains the script) to obtain current
-commit hash and use it for building the version and release
-strings.
-
-The script assumes that it's called from the Scylla source
-tree.
-
-The files created are:
-  SCYLLA-VERSION-FILE
-  SCYLLA-RELEASE-FILE
-  SCYLLA-PRODUCT-FILE
-
-By default, these files are created in the 'build'
-subdirectory under the directory containing the script.
-The destination directory can be overriden by
-using '-o PATH' option.
-END
-)
-
-DATE=""
-
-while [[ $# -gt 0 ]]; do
-	opt="$1"
-	case $opt in
-		-h|--help)
-			echo "$USAGE"
-			exit 0
-			;;
-		-o|--output-dir)
-			OUTPUT_DIR="$2"
-			shift
-			shift
-			;;
-		--date-stamp)
-			DATE="$2"
-			shift
-			shift
-			;;
-		*)
-			echo "Unexpected argument found: $1"
-			echo
-			echo "$USAGE"
-			exit 1
-			;;
-	esac
-done
-
-SCRIPT_DIR="$(dirname "$0")"
-
-if [ -z "$OUTPUT_DIR" ]; then
-	OUTPUT_DIR="$SCRIPT_DIR/build"
-fi
-
-if [ -z "$DATE" ]; then
-  DATE=$(date --utc +%Y%m%d)
-fi
-
-# Default scylla product/version tags
 PRODUCT=scylla
-VERSION=5.2.0-dev
+VERSION=3.2.5
 
 if test -f version
 then
 	SCYLLA_VERSION=$(cat version | awk -F'-' '{print $1}')
 	SCYLLA_RELEASE=$(cat version | awk -F'-' '{print $2}')
 else
+	DATE=$(date +%Y%m%d)
+	GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
 	SCYLLA_VERSION=$VERSION
-	if [ -z "$SCYLLA_RELEASE" ]; then
-		DATE=$(date --utc +%Y%m%d)
-		GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1 --abbrev=12)
-		# For custom package builds, replace "0" with "counter.your_name",
-		# where counter starts at 1 and increments for successive versions.
-		# This ensures that the package manager will select your custom
-		# package over the standard release.
-		SCYLLA_BUILD=0
-		SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
-	elif [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-		echo "setting SCYLLA_RELEASE only makes sense in clean builds" 1>&2
-		exit 1
-	fi
-fi
-
-if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" |cut -d . -f 3)
-	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
-		exit 0
-	fi
+	# For custom package builds, replace "0" with "counter.your_name",
+	# where counter starts at 1 and increments for successive versions.
+	# This ensures that the package manager will select your custom
+	# package over the standard release.
+	SCYLLA_BUILD=0
+	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi
 
 echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
-mkdir -p "$OUTPUT_DIR"
-echo "$SCYLLA_VERSION" > "$OUTPUT_DIR/SCYLLA-VERSION-FILE"
-echo "$SCYLLA_RELEASE" > "$OUTPUT_DIR/SCYLLA-RELEASE-FILE"
-echo "$PRODUCT" > "$OUTPUT_DIR/SCYLLA-PRODUCT-FILE"
+mkdir -p build
+echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
+echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE
+echo "$PRODUCT" > build/SCYLLA-PRODUCT-FILE

absl-flat_hash_map.cc

@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include "absl-flat_hash_map.hh"
-
-size_t sstring_hash::operator()(std::string_view v) const noexcept {
-    return absl::Hash<std::string_view>{}(v);
-}

absl-flat_hash_map.hh

@@ -1,34 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include <absl/container/flat_hash_map.h>
-#include <seastar/core/sstring.hh>
-
-using namespace seastar;
-
-struct sstring_hash {
-    using is_transparent = void;
-    size_t operator()(std::string_view v) const noexcept;
-};
-
-struct sstring_eq {
-    using is_transparent = void;
-    bool operator()(std::string_view a, std::string_view b) const noexcept {
-        return a == b;
-    }
-};
-
-template <typename K, typename V, typename... Ts>
-struct flat_hash_map : public absl::flat_hash_map<K, V, Ts...> {
-};
-
-template <typename V>
-struct flat_hash_map<sstring, V>
-    : public absl::flat_hash_map<sstring, V, sstring_hash, sstring_eq> {};

alternator-test/conftest.py

@@ -0,0 +1,179 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# This file contains "test fixtures", a pytest concept described in
+# https://docs.pytest.org/en/latest/fixture.html.
+# A "fixture" is some sort of setup which an invididual test requires to run.
+# The fixture has setup code and teardown code, and if multiple tests
+# require the same fixture, it can be set up only once - while still allowing
+# the user to run individual tests and automatically set up the fixtures they need.
+
+import pytest
+import boto3
+from util import create_test_table
+
+# Test that the Boto libraries are new enough. These tests want to test a
+# large variety of DynamoDB API features, and to do this we need a new-enough
+# version of the the Boto libraries (boto3 and botocore) so that they can
+# access all these API features.
+# In particular, the BillingMode feature was added in botocore 1.12.54.
+import botocore
+import sys
+from distutils.version import LooseVersion
+if (LooseVersion(botocore.__version__) < LooseVersion('1.12.54')):
+    pytest.exit("Your Boto library is too old. Please upgrade it,\ne.g. using:\n    sudo pip{} install --upgrade boto3".format(sys.version_info[0]))
+
+# By default, tests run against a local Scylla installation on localhost:8080/.
+# The "--aws" option can be used to run against Amazon DynamoDB in the us-east-1
+# region.
+def pytest_addoption(parser):
+    parser.addoption("--aws", action="store_true",
+        help="run against AWS instead of a local Scylla installation")
+    parser.addoption("--https", action="store_true",
+        help="communicate via HTTPS protocol on port 8043 instead of HTTP when"
+            " running against a local Scylla installation")
+
+# "dynamodb" fixture: set up client object for communicating with the DynamoDB
+# API. Currently this chooses either Amazon's DynamoDB in the default region
+# or a local Alternator installation on http://localhost:8080 - depending on the
+# existence of the "--aws" option. In the future we should provide options
+# for choosing other Amazon regions or local installations.
+# We use scope="session" so that all tests will reuse the same client object.
+@pytest.fixture(scope="session")
+def dynamodb(request):
+    if request.config.getoption('aws'):
+        return boto3.resource('dynamodb')
+    else:
+        # Even though we connect to the local installation, Boto3 still
+        # requires us to specify dummy region and credential parameters,
+        # otherwise the user is forced to properly configure ~/.aws even
+        # for local runs.
+        local_url = 'https://localhost:8043' if request.config.getoption('https') else 'http://localhost:8000'
+        # Disable verifying in order to be able to use self-signed TLS certificates
+        verify = not request.config.getoption('https')
+        # Silencing the 'Unverified HTTPS request warning'
+        if request.config.getoption('https'):
+            import urllib3
+            urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+        return boto3.resource('dynamodb', endpoint_url=local_url, verify=verify,
+            region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass')
+
+# "test_table" fixture: Create and return a temporary table to be used in tests
+# that need a table to work on. The table is automatically deleted at the end.
+# We use scope="session" so that all tests will reuse the same client object.
+# This "test_table" creates a table which has a specific key schema: both a
+# partition key and a sort key, and both are strings. Other fixtures (below)
+# can be used to create different types of tables.
+#
+# TODO: Although we are careful about deleting temporary tables when the
+# fixture is torn down, in some cases (e.g., interrupted tests) we can be left
+# with some tables not deleted, and they will never be deleted. Because all
+# our temporary tables have the same test_table_prefix, we can actually find
+# and remove these old tables with this prefix. We can have a fixture, which
+# test_table will require, which on teardown will delete all remaining tables
+# (possibly from an older run). Because the table's name includes the current
+# time, we can also remove just tables older than a particular age. Such
+# mechanism will allow running tests in parallel, without the risk of deleting
+# a parallel run's temporary tables.
+@pytest.fixture(scope="session")
+def test_table(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ])
+    yield table
+    # We get back here when this fixture is torn down. We ask Dynamo to delete
+    # this table, but not wait for the deletion to complete. The next time
+    # we create a test_table fixture, we'll choose a different table name
+    # anyway.
+    table.delete()
+
+# The following fixtures test_table_* are similar to test_table but create
+# tables with different key schemas.
+@pytest.fixture(scope="session")
+def test_table_s(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ])
+    yield table
+    table.delete()
+@pytest.fixture(scope="session")
+def test_table_b(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'B' } ])
+    yield table
+    table.delete()
+@pytest.fixture(scope="session")
+def test_table_sb(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'B' } ])
+    yield table
+    table.delete()
+@pytest.fixture(scope="session")
+def test_table_sn(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'N' } ])
+    yield table
+    table.delete()
+
+# "filled_test_table" fixture:  Create a temporary table to be used in tests
+# that involve reading data - GetItem, Scan, etc. The table is filled with
+# 328 items - each consisting of a partition key, clustering key and two
+# string attributes. 164 of the items are in a single partition (with the
+# partition key 'long') and the 164 other items are each in a separate
+# partition. Finally, a 329th item is added with different attributes.
+# This table is supposed to be read from, not updated nor overwritten.
+# This fixture returns both a table object and the description of all items
+# inserted into it.
+@pytest.fixture(scope="session")
+def filled_test_table(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ])
+    count = 164
+    items = [{
+        'p': str(i),
+        'c': str(i),
+        'attribute': "x" * 7,
+        'another': "y" * 16
+    } for i in range(count)]
+    items = items + [{
+        'p': 'long',
+        'c': str(i),
+        'attribute': "x" * (1 + i % 7),
+        'another': "y" * (1 + i % 16)
+    } for i in range(count)]
+    items.append({'p': 'hello', 'c': 'world', 'str': 'and now for something completely different'})
+
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+
+    yield table, items
+    table.delete()

alternator-test/test_authorization.py

@@ -0,0 +1,74 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for authorization
+
+import pytest
+import botocore
+from botocore.exceptions import ClientError
+import boto3
+import requests
+
+# Test that trying to perform an operation signed with a wrong key
+# will not succeed
+def test_wrong_key_access(request, dynamodb):
+    print("Please make sure authorization is enforced in your Scylla installation: alternator_enforce_authorization: true")
+    url = dynamodb.meta.client._endpoint.host
+    with pytest.raises(ClientError, match='UnrecognizedClientException'):
+        if url.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url, aws_access_key_id='wrong_id', aws_secret_access_key='').describe_endpoints()
+        else:
+            verify = not url.startswith('https')
+            boto3.client('dynamodb',endpoint_url=url, region_name='us-east-1', aws_access_key_id='whatever', aws_secret_access_key='', verify=verify).describe_endpoints()
+
+# A similar test, but this time the user is expected to exist in the database (for local tests)
+def test_wrong_password(request, dynamodb):
+    print("Please make sure authorization is enforced in your Scylla installation: alternator_enforce_authorization: true")
+    url = dynamodb.meta.client._endpoint.host
+    with pytest.raises(ClientError, match='UnrecognizedClientException'):
+        if url.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url, aws_access_key_id='alternator', aws_secret_access_key='wrong_key').describe_endpoints()
+        else:
+            verify = not url.startswith('https')
+            boto3.client('dynamodb',endpoint_url=url, region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='wrong_key', verify=verify).describe_endpoints()
+
+# A test ensuring that expired signatures are not accepted
+def test_expired_signature(dynamodb, test_table):
+    url = dynamodb.meta.client._endpoint.host
+    print(url)
+    headers = {'Content-Type': 'application/x-amz-json-1.0',
+               'X-Amz-Date': '20170101T010101Z',
+               'X-Amz-Target': 'DynamoDB_20120810.DescribeEndpoints',
+               'Authorization': 'AWS4-HMAC-SHA256 Credential=alternator/2/3/4/aws4_request SignedHeaders=x-amz-date;host Signature=123'
+    }
+    response = requests.post(url, headers=headers)
+    assert not response.ok
+    assert "InvalidSignatureException" in response.text and "Signature expired" in response.text
+
+# A test ensuring that signatures that exceed current time too much are not accepted.
+# Watch out - this test is valid only for around next 1000 years, it needs to be updated later.
+def test_signature_too_futuristic(dynamodb, test_table):
+    url = dynamodb.meta.client._endpoint.host
+    print(url)
+    headers = {'Content-Type': 'application/x-amz-json-1.0',
+               'X-Amz-Date': '30200101T010101Z',
+               'X-Amz-Target': 'DynamoDB_20120810.DescribeEndpoints',
+               'Authorization': 'AWS4-HMAC-SHA256 Credential=alternator/2/3/4/aws4_request SignedHeaders=x-amz-date;host Signature=123'
+    }
+    response = requests.post(url, headers=headers)
+    assert not response.ok
+    assert "InvalidSignatureException" in response.text and "Signature not yet current" in response.text

alternator-test/test_batch.py

@@ -0,0 +1,253 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for batch operations - BatchWriteItem, BatchReadItem.
+# Note that various other tests in other files also use these operations,
+# so they are actually tested by other tests as well.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string, full_scan, full_query, multiset
+
+# Test ensuring that items inserted by a batched statement can be properly extracted
+# via GetItem. Schema has both hash and sort keys.
+def test_basic_batch_write_item(test_table):
+    count = 7
+
+    with test_table.batch_writer() as batch:
+        for i in range(count):
+            batch.put_item(Item={
+                'p': "batch{}".format(i),
+                'c': "batch_ck{}".format(i),
+                'attribute': str(i),
+                'another': 'xyz'
+            })
+
+    for i in range(count):
+        item = test_table.get_item(Key={'p': "batch{}".format(i), 'c': "batch_ck{}".format(i)}, ConsistentRead=True)['Item']
+        assert item['p'] == "batch{}".format(i)
+        assert item['c'] == "batch_ck{}".format(i)
+        assert item['attribute'] == str(i)
+        assert item['another'] == 'xyz' 
+
+# Test batch write to a table with only a hash key
+def test_batch_write_hash_only(test_table_s):
+    items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for item in items:
+        assert test_table_s.get_item(Key={'p': item['p']}, ConsistentRead=True)['Item'] == item
+
+# Test batch delete operation (DeleteRequest): We create a bunch of items, and
+# then delete them all.
+def test_batch_write_delete(test_table_s):
+    items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for item in items:
+        assert test_table_s.get_item(Key={'p': item['p']}, ConsistentRead=True)['Item'] == item
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.delete_item(Key={'p': item['p']})
+    # Verify that all items are now missing:
+    for item in items:
+        assert not 'Item' in test_table_s.get_item(Key={'p': item['p']}, ConsistentRead=True)
+
+# Test the same batch including both writes and delete. Should be fine.
+def test_batch_write_and_delete(test_table_s):
+    p1 = random_string()
+    p2 = random_string()
+    test_table_s.put_item(Item={'p': p1})
+    assert 'Item' in test_table_s.get_item(Key={'p': p1}, ConsistentRead=True)
+    assert not 'Item' in test_table_s.get_item(Key={'p': p2}, ConsistentRead=True)
+    with test_table_s.batch_writer() as batch:
+        batch.put_item({'p': p2})
+        batch.delete_item(Key={'p': p1})
+    assert not 'Item' in test_table_s.get_item(Key={'p': p1}, ConsistentRead=True)
+    assert 'Item' in test_table_s.get_item(Key={'p': p2}, ConsistentRead=True)
+
+# It is forbidden to update the same key twice in the same batch.
+# DynamoDB says "Provided list of item keys contains duplicates".
+def test_batch_write_duplicate_write(test_table_s, test_table):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table_s.batch_writer() as batch:
+            batch.put_item({'p': p})
+            batch.put_item({'p': p})
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table.batch_writer() as batch:
+            batch.put_item({'p': p, 'c': c})
+            batch.put_item({'p': p, 'c': c})
+    # But it is fine to touch items with one component the same, but the other not.
+    other = random_string()
+    with test_table.batch_writer() as batch:
+        batch.put_item({'p': p, 'c': c})
+        batch.put_item({'p': p, 'c': other})
+        batch.put_item({'p': other, 'c': c})
+
+def test_batch_write_duplicate_delete(test_table_s, test_table):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table_s.batch_writer() as batch:
+            batch.delete_item(Key={'p': p})
+            batch.delete_item(Key={'p': p})
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table.batch_writer() as batch:
+            batch.delete_item(Key={'p': p, 'c': c})
+            batch.delete_item(Key={'p': p, 'c': c})
+    # But it is fine to touch items with one component the same, but the other not.
+    other = random_string()
+    with test_table.batch_writer() as batch:
+        batch.delete_item(Key={'p': p, 'c': c})
+        batch.delete_item(Key={'p': p, 'c': other})
+        batch.delete_item(Key={'p': other, 'c': c})
+
+def test_batch_write_duplicate_write_and_delete(test_table_s, test_table):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table_s.batch_writer() as batch:
+            batch.delete_item(Key={'p': p})
+            batch.put_item({'p': p})
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*duplicates'):
+        with test_table.batch_writer() as batch:
+            batch.delete_item(Key={'p': p, 'c': c})
+            batch.put_item({'p': p, 'c': c})
+    # But it is fine to touch items with one component the same, but the other not.
+    other = random_string()
+    with test_table.batch_writer() as batch:
+        batch.delete_item(Key={'p': p, 'c': c})
+        batch.put_item({'p': p, 'c': other})
+        batch.put_item({'p': other, 'c': c})
+
+# Test that BatchWriteItem's PutRequest completely replaces an existing item.
+# It shouldn't merge it with a previously existing value. See also the same
+# test for PutItem - test_put_item_replace().
+def test_batch_put_item_replace(test_table_s, test_table):
+    p = random_string()
+    with test_table_s.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'a': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hi'}
+    with test_table_s.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'b': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
+    c = random_string()
+    with test_table.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'c': c, 'a': 'hi'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 'hi'}
+    with test_table.batch_writer() as batch:
+        batch.put_item(Item={'p': p, 'c': c, 'b': 'hello'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'b': 'hello'}
+
+# Test that if one of the batch's operations is invalid, because a key
+# column is missing or has the wrong type, the entire batch is rejected
+# before any write is done.
+def test_batch_write_invalid_operation(test_table_s):
+    # test key attribute with wrong type:
+    p1 = random_string()
+    p2 = random_string()
+    items = [{'p': p1}, {'p': 3}, {'p': p2}]
+    with pytest.raises(ClientError, match='ValidationException'):
+        with test_table_s.batch_writer() as batch:
+            for item in items:
+                batch.put_item(item)
+    for p in [p1, p2]:
+        assert not 'item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+    # test missing key attribute:
+    p1 = random_string()
+    p2 = random_string()
+    items = [{'p': p1}, {'x': 'whatever'}, {'p': p2}]
+    with pytest.raises(ClientError, match='ValidationException'):
+        with test_table_s.batch_writer() as batch:
+            for item in items:
+                batch.put_item(item)
+    for p in [p1, p2]:
+        assert not 'item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+
+# Basic test for BatchGetItem, reading several entire items.
+# Schema has both hash and sort keys.
+def test_batch_get_item(test_table):
+    items = [{'p': random_string(), 'c': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p', 'c')} for x in items]
+    # We use the low-level batch_get_item API for lack of a more convenient
+    # API. At least it spares us the need to encode the key's types...
+    reply = test_table.meta.client.batch_get_item(RequestItems = {test_table.name: {'Keys': keys, 'ConsistentRead': True}})
+    print(reply)
+    got_items = reply['Responses'][test_table.name]
+    assert multiset(got_items) == multiset(items)
+
+# Same, with schema has just hash key.
+def test_batch_get_item_hash(test_table_s):
+    items = [{'p': random_string(), 'val': random_string()} for i in range(10)]
+    with test_table_s.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p')} for x in items]
+    reply = test_table_s.meta.client.batch_get_item(RequestItems = {test_table_s.name: {'Keys': keys, 'ConsistentRead': True}})
+    got_items = reply['Responses'][test_table_s.name]
+    assert multiset(got_items) == multiset(items)
+
+# Test what do we get if we try to read two *missing* values in addition to
+# an existing one. It turns out the missing items are simply not returned,
+# with no sign they are missing.
+def test_batch_get_item_missing(test_table_s):
+    p = random_string();
+    test_table_s.put_item(Item={'p': p})
+    reply = test_table_s.meta.client.batch_get_item(RequestItems = {test_table_s.name: {'Keys': [{'p': random_string()}, {'p': random_string()}, {'p': p}], 'ConsistentRead': True}})
+    got_items = reply['Responses'][test_table_s.name]
+    assert got_items == [{'p' : p}]
+
+# If all the keys requested from a particular table are missing, we still
+# get a response array for that table - it's just empty.
+def test_batch_get_item_completely_missing(test_table_s):
+    reply = test_table_s.meta.client.batch_get_item(RequestItems = {test_table_s.name: {'Keys': [{'p': random_string()}], 'ConsistentRead': True}})
+    got_items = reply['Responses'][test_table_s.name]
+    assert got_items == []
+
+# Test GetItem with AttributesToGet
+def test_batch_get_item_attributes_to_get(test_table):
+    items = [{'p': random_string(), 'c': random_string(), 'val1': random_string(), 'val2': random_string()} for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p', 'c')} for x in items]
+    for wanted in [['p'], ['p', 'c'], ['val1'], ['p', 'val2']]:
+        reply = test_table.meta.client.batch_get_item(RequestItems = {test_table.name: {'Keys': keys, 'AttributesToGet': wanted, 'ConsistentRead': True}})
+        got_items = reply['Responses'][test_table.name]
+        expected_items = [{k: item[k] for k in wanted if k in item} for item in items]
+        assert multiset(got_items) == multiset(expected_items)
+
+# Test GetItem with ProjectionExpression (just a simple one, with
+# top-level attributes)
+def test_batch_get_item_projection_expression(test_table):
+    items = [{'p': random_string(), 'c': random_string(), 'val1': random_string(), 'val2': random_string()} for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    keys = [{k: x[k] for k in ('p', 'c')} for x in items]
+    for wanted in [['p'], ['p', 'c'], ['val1'], ['p', 'val2']]:
+        reply = test_table.meta.client.batch_get_item(RequestItems = {test_table.name: {'Keys': keys, 'ProjectionExpression': ",".join(wanted), 'ConsistentRead': True}})
+        got_items = reply['Responses'][test_table.name]
+        expected_items = [{k: item[k] for k in wanted if k in item} for item in items]
+        assert multiset(got_items) == multiset(expected_items)

alternator-test/test_condition_expression.py

@@ -0,0 +1,40 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the ConditionExpression parameter
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string
+
+# Test that ConditionExpression works as expected
+@pytest.mark.xfail(reason="ConditionExpression not yet implemented")
+def test_update_condition_expression(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1',
+        ExpressionAttributeValues={':val1': 4})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1',
+        ConditionExpression='b = :oldval',
+        ExpressionAttributeValues={':val1': 6, ':oldval': 4})
+    with pytest.raises(ClientError, match='ConditionalCheckFailedException.*'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1',
+            ConditionExpression='b = :oldval',
+            ExpressionAttributeValues={':val1': 8, ':oldval': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 6}

alternator-test/test_describe_endpoints.py

@@ -0,0 +1,49 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Test for the DescribeEndpoints operation
+
+import boto3
+
+# Test that the DescribeEndpoints operation works as expected: that it
+# returns one endpoint (it may return more, but it never does this in
+# Amazon), and this endpoint can be used to make more requests.
+def test_describe_endpoints(request, dynamodb):
+    endpoints = dynamodb.meta.client.describe_endpoints()['Endpoints']
+    # It is not strictly necessary that only a single endpoint be returned,
+    # but this is what Amazon DynamoDB does today (and so does Alternator).
+    assert len(endpoints) == 1
+    for endpoint in endpoints:
+        assert 'CachePeriodInMinutes' in endpoint.keys()
+        address = endpoint['Address']
+        # Check that the address is a valid endpoint by checking that we can
+        # send it another describe_endpoints() request ;-) Note that the
+        # address does not include the "http://" or "https://" prefix, and
+        # we need to choose one manually.
+        prefix = "https://" if request.config.getoption('https') else "http://"
+        verify = not request.config.getoption('https')
+        url = prefix + address
+        if address.endswith('.amazonaws.com'):
+            boto3.client('dynamodb',endpoint_url=url, verify=verify).describe_endpoints()
+        else:
+            # Even though we connect to the local installation, Boto3 still
+            # requires us to specify dummy region and credential parameters,
+            # otherwise the user is forced to properly configure ~/.aws even
+            # for local runs.
+            boto3.client('dynamodb',endpoint_url=url, region_name='us-east-1', aws_access_key_id='alternator', aws_secret_access_key='secret_pass', verify=verify).describe_endpoints()
+        # Nothing to check here - if the above call failed with an exception,
+        # the test would fail.

alternator-test/test_describe_table.py

@@ -1,6 +1,19 @@
-# Copyright 2019-present ScyllaDB
+# Copyright 2019 ScyllaDB
 #
-# SPDX-License-Identifier: AGPL-3.0-or-later
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 
 # Tests for the DescribeTable operation.
 # Some attributes used only by a specific major feature will be tested
@@ -28,6 +41,7 @@ def test_describe_table_basic(test_table):
 
 # Test that DescribeTable correctly returns the table's schema, in
 # AttributeDefinitions and KeySchema attributes
+@pytest.mark.xfail(reason="DescribeTable does not yet return schema")
 def test_describe_table_schema(test_table):
     got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
     expected = { # Copied from test_table()'s fixture
@@ -94,9 +108,9 @@ def test_describe_table_size(test_table):
 # Test the ProvisionedThroughput attribute returned by DescribeTable.
 # This is a very partial test: Our test table is configured without
 # provisioned throughput, so obviously it will not have interesting settings
-# for it. But DynamoDB documents that zeros be returned for WriteCapacityUnits
-# and ReadCapacityUnits, and does this in practice as well - and some
-# applications assume these numbers are always there (even if 0).
+# for it. DynamoDB returns zeros for some of the attributes, even though
+# the documentation suggests missing values should have been fine too.
+@pytest.mark.xfail(reason="DescribeTable does not return provisioned throughput")
 def test_describe_table_provisioned_throughput(test_table):
     got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
     assert got['ProvisionedThroughput']['NumberOfDecreasesToday'] == 0
@@ -128,16 +142,19 @@ def test_describe_table_stream_specification(test_table):
 # includes which zone it is on, which account, and of course the table's
 # name. The ARN format is described in
 # https://docs.aws.amazon.com/general/latest/gr/aws-arns-and-namespaces.html#genref-arns
+@pytest.mark.xfail(reason="DescribeTable does not return ARN")
 def test_describe_table_arn(test_table):
     got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
     assert 'TableArn' in got and got['TableArn'].startswith('arn:')
 
 # Test that the table has a TableId.
-# DynamoDB documentation states that this id must look like a UUID.
+# TODO: Figure out what is this TableId supposed to be, it is just a
+# unique id that is created with the table and never changes? Or anything
+# else?
+@pytest.mark.xfail(reason="DescribeTable does not return TableId")
 def test_describe_table_id(test_table):
     got = test_table.meta.client.describe_table(TableName=test_table.name)['Table']
     assert 'TableId' in got
-    assert re.fullmatch('[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}', got['TableId'])
 
 # DescribeTable error path: trying to describe a non-existent table should
 # result in a ResourceNotFoundException.

alternator-test/test_expected.py

@@ -1,6 +1,19 @@
-# Copyright 2019-present ScyllaDB
+# Copyright 2019 ScyllaDB
 #
-# SPDX-License-Identifier: AGPL-3.0-or-later
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 
 # Tests for the "Expected" parameter used to make certain operations (PutItem,
 # UpdateItem and DeleteItem) conditional on the existing attribute values.
@@ -73,6 +86,7 @@ def test_update_expected_1_eq_true(test_table_s):
 # Check that set equality is checked correctly. Unlike string equality (for
 # example), it cannot be done with just naive string comparison of the JSON
 # representation, and we need to allow for any order.
+@pytest.mark.xfail(reason="bug in EQ test of sets")
 def test_update_expected_1_eq_set(test_table_s):
     p = random_string()
     # Because boto3 sorts the set values we give it, in order to generate a
@@ -157,6 +171,7 @@ def test_update_expected_1_ne_false(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "LE":
+@pytest.mark.xfail(reason="ComparisonOperator=LE in Expected not yet implemented")
 def test_update_expected_1_le(test_table_s):
     p = random_string()
     # LE should work for string, number, and binary type
@@ -224,30 +239,6 @@ def test_update_expected_1_le(test_table_s):
                             'AttributeValueList': [2, 3]}}
         )
 
-# Comparison operators like le work only on numbers, strings or bytes.
-# As noted in issue #8043, if any other type is included in *the query*,
-# the result should be a ValidationException, but if the wrong type appears
-# in the item, not the query, the result is a failed condition.
-def test_update_expected_1_le_validation(test_table_s):
-    p = random_string()
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
-                          'b': {'Value': [1,2], 'Action': 'PUT'}})
-    # Bad type (a list) in the query. Result is ValidationException.
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'a': {'ComparisonOperator': 'LE',
-                            'AttributeValueList': [[1,2,3]]}}
-        )
-    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'b': {'ComparisonOperator': 'LE',
-                            'AttributeValueList': [3]}}
-        )
-    assert not 'z' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']
-
 # Tests for Expected with ComparisonOperator = "LT":
 def test_update_expected_1_lt(test_table_s):
     p = random_string()
@@ -317,6 +308,7 @@ def test_update_expected_1_lt(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "GE":
+@pytest.mark.xfail(reason="ComparisonOperator=GE in Expected not yet implemented")
 def test_update_expected_1_ge(test_table_s):
     p = random_string()
     # GE should work for string, number, and binary type
@@ -533,16 +525,8 @@ def test_update_expected_1_null(test_table_s):
             Expected={'a': {'ComparisonOperator': 'NULL', 'AttributeValueList': [2]}}
         )
 
-# When ComparisonOperator = "NULL", AttributeValueList should be empty if it
-# exists, but as this test verifies, it may also be missing completely.
-def test_update_expected_1_null_missing_list(test_table_s):
-    p = random_string()
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 2, 'Action': 'PUT'}},
-        Expected={'a': {'ComparisonOperator': 'NULL'}})
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
-
 # Tests for Expected with ComparisonOperator = "CONTAINS":
+@pytest.mark.xfail(reason="ComparisonOperator=CONTAINS in Expected not yet implemented")
 def test_update_expected_1_contains(test_table_s):
     # true cases. CONTAINS can be used for two unrelated things: check substrings
     # (in string or binary) and membership (in set or list).
@@ -618,10 +602,6 @@ def test_update_expected_1_contains(test_table_s):
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'CONTAINS', 'AttributeValueList': []}}
         )
-    # Strangely, while ConditionExpression's contains() allows the argument
-    # to be of any type and checks if the attribute is perhaps a list
-    # containing that item, Expected's "CONTAINS" is more limited, and
-    # refuses a list as the argument (to be searched in a list of lists)
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
@@ -629,6 +609,7 @@ def test_update_expected_1_contains(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "NOT_CONTAINS":
+@pytest.mark.xfail(reason="ComparisonOperator=NOT_CONTAINS in Expected not yet implemented")
 def test_update_expected_1_not_contains(test_table_s):
     # true cases. NOT_CONTAINS can be used for two unrelated things: check substrings
     # (in string or binary) and membership (in set or list).
@@ -708,10 +689,6 @@ def test_update_expected_1_not_contains(test_table_s):
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'NOT_CONTAINS', 'AttributeValueList': []}}
         )
-    # Strangely, while ConditionExpression's contains() allows the argument
-    # to be of any type and checks if the attribute is perhaps a list
-    # containing that item, Expected's "CONTAINS" is more limited, and
-    # refuses a list as the argument (to be searched in a list of lists)
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
@@ -722,21 +699,14 @@ def test_update_expected_1_not_contains(test_table_s):
 def test_update_expected_1_begins_with_true(test_table_s):
     p = random_string()
     test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'},
-                          'd': {'Value': bytearray('hi there', 'utf-8'), 'Action': 'PUT'}})
+        AttributeUpdates={'a': {'Value': 'hello', 'Action': 'PUT'}})
     # Case where expected and update are on different attribute:
     test_table_s.update_item(Key={'p': p},
         AttributeUpdates={'b': {'Value': 3, 'Action': 'PUT'}},
         Expected={'a': {'ComparisonOperator': 'BEGINS_WITH',
                         'AttributeValueList': ['hell']}}
     )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 3
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'b': {'Value': 4, 'Action': 'PUT'}},
-        Expected={'d': {'ComparisonOperator': 'BEGINS_WITH',
-                        'AttributeValueList': [bytearray('hi', 'utf-8')]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 4
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 3}
     # For BEGINS_WITH, AttributeValueList must have a single element
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
@@ -828,13 +798,13 @@ def test_update_expected_1_in(test_table_s):
         )
 
 # Tests for Expected with ComparisonOperator = "BETWEEN":
+@pytest.mark.xfail(reason="ComparisonOperator=BETWEEN in Expected not yet implemented")
 def test_update_expected_1_between(test_table_s):
     p = random_string()
     test_table_s.update_item(Key={'p': p},
         AttributeUpdates={'a': {'Value': 2, 'Action': 'PUT'},
                           'b': {'Value': 'cat', 'Action': 'PUT'},
-                          'c': {'Value': bytearray('cat', 'utf-8'), 'Action': 'PUT'},
-                          'd': {'Value': set([2, 4, 7]), 'Action': 'PUT'}})
+                          'c': {'Value': bytearray('cat', 'utf-8'), 'Action': 'PUT'}})
     # true cases:
     test_table_s.update_item(Key={'p': p},
         AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
@@ -872,10 +842,6 @@ def test_update_expected_1_between(test_table_s):
             AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': ['cat', 'dog']}}
         )
-    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-            Expected={'q': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [0, 100]}})
     assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 6
     # The given AttributeValueList array must contain exactly two items of the
     # same type, and in the right order. Any other input is considered a validation
@@ -892,46 +858,10 @@ def test_update_expected_1_between(test_table_s):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [4, 3]}})
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-            Expected={'b': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': ['dog', 'aardvark']}})
     with pytest.raises(ClientError, match='ValidationException'):
         test_table_s.update_item(Key={'p': p},
             AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
             Expected={'a': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [4, 'dog']}})
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-            Expected={'d': {'ComparisonOperator': 'BETWEEN', 'AttributeValueList': [set([1]), set([2])]}})
-
-# BETWEEN work only on numbers, strings or bytes. As noted in issue #8043,
-# if any other type is included in *the query*, the result should be a
-# ValidationException, but if the wrong type appears in the item, not the
-# query, the result is a failed condition.
-# BETWEEN should also generate ValidationException if the two ends of the
-# range are not of the same type or not in the correct order, but this
-# already is tested in the test above (test_update_expected_1_between).
-def test_update_expected_1_between_validation(test_table_s):
-    p = random_string()
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'a': {'Value': 1, 'Action': 'PUT'},
-                          'b': {'Value': [1,2], 'Action': 'PUT'}})
-    # Bad type (a list) in the query. Result is ValidationException.
-    with pytest.raises(ClientError, match='ValidationException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'a': {'ComparisonOperator': 'BETWEEN',
-                            'AttributeValueList': [[1,2,3], [2,3,4]]}}
-        )
-    with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 17, 'Action': 'PUT'}},
-            Expected={'b': {'ComparisonOperator': 'BETWEEN',
-                            'AttributeValueList': [1,2]}}
-        )
-    assert not 'z' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']
-
 
 ##############################################################################
 # Instead of ComparisonOperator and AttributeValueList, one can specify either
@@ -1108,19 +1038,6 @@ def test_update_expected_empty(test_table_s):
             AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
             Expected={}, ConditionalOperator='AND')
 
-# Specifying ConditionalOperator is forbidden if the "Expected" Attribute
-# is missing:
-def test_conditional_operator_expected_missing(test_table_s):
-    p = random_string()
-    with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
-            ConditionalOperator='OR')
-    with pytest.raises(ClientError, match='ValidationException.*ConditionalOperator'):
-        test_table_s.update_item(Key={'p': p},
-            AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
-            ConditionalOperator='AND')
-
 # All of the above tests tested "Expected" with the UpdateItem operation.
 # We now want to test that it works also with the PutItem and DeleteItems
 # operations. We don't need to check again all the different sub-cases tested
@@ -1146,42 +1063,3 @@ def test_put_item_expected(test_table_s):
     assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 2}
     with pytest.raises(ClientError, match='ConditionalCheckFailedException'):
         test_table_s.put_item(Item={'p': p, 'a': 3}, Expected={'a': {'Value': 1}})
-
-# Reproducer for issue #6573: binary strings should be ordered as unsigned
-# bytes, i.e., byte 128 comes after 127, not before as with signed bytes.
-# Test the five ordering operators: LT, LE, GT, GE, BETWEEN
-def test_update_expected_unsigned_bytes(test_table_s):
-    p = random_string()
-    test_table_s.put_item(Item={'p': p, 'b': bytearray([127])})
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 1, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'LT',
-                        'AttributeValueList': [bytearray([128])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 1
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 2, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'LE',
-                        'AttributeValueList': [bytearray([128])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 2
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 3, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'BETWEEN',
-                        'AttributeValueList': [bytearray([126]), bytearray([128])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 3
-
-    test_table_s.put_item(Item={'p': p, 'b': bytearray([128])})
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 4, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'GT',
-                        'AttributeValueList': [bytearray([127])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 4
-    test_table_s.update_item(Key={'p': p},
-        AttributeUpdates={'z': {'Value': 5, 'Action': 'PUT'}},
-        Expected={'b': {'ComparisonOperator': 'GE',
-                        'AttributeValueList': [bytearray([127])]}}
-    )
-    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['z'] == 5

alternator-test/test_gsi.py

@@ -0,0 +1,801 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests of GSI (Global Secondary Indexes)
+#
+# Note that many of these tests are slower than usual, because many of them
+# need to create new tables and/or new GSIs of different types, operations
+# which are extremely slow in DynamoDB, often taking minutes (!).
+
+import pytest
+import time
+from botocore.exceptions import ClientError, ParamValidationError
+from util import create_test_table, random_string, full_scan, full_query, multiset, list_tables
+
+# GSIs only support eventually consistent reads, so tests that involve
+# writing to a table and then expect to read something from it cannot be
+# guaranteed to succeed without retrying the read. The following utility
+# functions make it easy to write such tests.
+# Note that in practice, there repeated reads are almost never necessary:
+# Amazon claims that "Changes to the table data are propagated to the global
+# secondary indexes within a fraction of a second, under normal conditions"
+# and indeed, in practice, the tests here almost always succeed without a
+# retry.
+def assert_index_query(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_query retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
+
+def assert_index_scan(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_scan retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
+
+# Although quite silly, it is actually allowed to create an index which is
+# identical to the base table.
+def test_gsi_identical(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
+        AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    items = [{'p': random_string(), 'x': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert multiset(items) == multiset(full_scan(table))
+    assert_index_scan(table, 'hello', items)
+    # We can't scan a non-existant index
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_scan(table, IndexName='wrong')
+    table.delete()
+
+# One of the simplest forms of a non-trivial GSI: The base table has a hash
+# and sort key, and the index reverses those roles. Other attributes are just
+# copied.
+@pytest.fixture(scope="session")
+def test_table_gsi_1(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ],
+        )
+    yield table
+    table.delete()
+
+def test_gsi_simple(test_table_gsi_1):
+    items = [{'p': random_string(), 'c': random_string(), 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    c = items[0]['c']
+    # The index allows a query on just a specific sort key, which isn't
+    # allowed on the base table.
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table_gsi_1, KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    expected_items = [x for x in items if x['c'] == c]
+    assert_index_query(test_table_gsi_1, 'hello', expected_items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert_index_scan(test_table_gsi_1, 'hello', full_scan(test_table_gsi_1))
+
+def test_gsi_same_key(test_table_gsi_1):
+    c = random_string();
+    # All these items have the same sort key 'c' but different hash key 'p'
+    items = [{'p': random_string(), 'c': c, 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_1, 'hello', items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+
+# Check we get an appropriate error when trying to read a non-existing index
+# of an existing table. Although the documentation specifies that a
+# ResourceNotFoundException should be returned if "The operation tried to
+# access a nonexistent table or index", in fact in the specific case that
+# the table does exist but an index does not - we get a ValidationException.
+def test_gsi_missing_index(test_table_gsi_1):
+    with pytest.raises(ClientError, match='ValidationException.*wrong_name'):
+        full_query(test_table_gsi_1, IndexName='wrong_name',
+            KeyConditions={'x': {'AttributeValueList': [1], 'ComparisonOperator': 'EQ'}})
+    with pytest.raises(ClientError, match='ValidationException.*wrong_name'):
+        full_scan(test_table_gsi_1, IndexName='wrong_name')
+
+# Nevertheless, if the table itself does not exist, a query should return
+# a ResourceNotFoundException, not ValidationException:
+def test_gsi_missing_table(dynamodb):
+    with pytest.raises(ClientError, match='ResourceNotFoundException'):
+        dynamodb.meta.client.query(TableName='nonexistent_table', IndexName='any_name', KeyConditions={'x': {'AttributeValueList': [1], 'ComparisonOperator': 'EQ'}})
+    with pytest.raises(ClientError, match='ResourceNotFoundException'):
+        dynamodb.meta.client.scan(TableName='nonexistent_table', IndexName='any_name')
+
+# Verify that strongly-consistent reads on GSI are *not* allowed.
+@pytest.mark.xfail(reason="GSI strong consistency not checked")
+def test_gsi_strong_consistency(test_table_gsi_1):
+    with pytest.raises(ClientError, match='ValidationException.*Consistent'):
+        full_query(test_table_gsi_1, KeyConditions={'c': {'AttributeValueList': ['hi'], 'ComparisonOperator': 'EQ'}}, IndexName='hello', ConsistentRead=True)
+    with pytest.raises(ClientError, match='ValidationException.*Consistent'):
+        full_scan(test_table_gsi_1, IndexName='hello', ConsistentRead=True)
+
+# Verify that a GSI is correctly listed in describe_table
+@pytest.mark.xfail(reason="DescribeTable provides index names only, no size or item count")
+def test_gsi_describe(test_table_gsi_1):
+    desc = test_table_gsi_1.meta.client.describe_table(TableName=test_table_gsi_1.name)
+    assert 'Table' in desc
+    assert 'GlobalSecondaryIndexes' in desc['Table']
+    gsis = desc['Table']['GlobalSecondaryIndexes']
+    assert len(gsis) == 1
+    gsi = gsis[0]
+    assert gsi['IndexName'] == 'hello'
+    assert 'IndexSizeBytes' in gsi     # actual size depends on content
+    assert 'ItemCount' in gsi
+    assert gsi['Projection'] == {'ProjectionType': 'ALL'}
+    assert gsi['IndexStatus'] == 'ACTIVE'
+    assert gsi['KeySchema'] == [{'KeyType': 'HASH', 'AttributeName': 'c'},
+                                {'KeyType': 'RANGE', 'AttributeName': 'p'}]
+    # TODO: check also ProvisionedThroughput, IndexArn
+
+# When a GSI's key includes an attribute not in the base table's key, we
+# need to remember to add its type to AttributeDefinitions.
+def test_gsi_missing_attribute_definition(dynamodb):
+    with pytest.raises(ClientError, match='ValidationException.*AttributeDefinitions'):
+        create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ],
+            GlobalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [ { 'AttributeName': 'c', 'KeyType': 'HASH' } ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+
+# test_table_gsi_1_hash_only is a variant of test_table_gsi_1: It's another
+# case where the index doesn't involve non-key attributes. Again the base
+# table has a hash and sort key, but in this case the index has *only* a
+# hash key (which is the base's hash key). In the materialized-view-based
+# implementation, we need to remember the other part of the base key as a
+# clustering key.
+@pytest.fixture(scope="session")
+def test_table_gsi_1_hash_only(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ],
+        )
+    yield table
+    table.delete()
+
+def test_gsi_key_not_in_index(test_table_gsi_1_hash_only):
+    # Test with items with different 'c' values:
+    items = [{'p': random_string(), 'c': random_string(), 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1_hash_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    c = items[0]['c']
+    expected_items = [x for x in items if x['c'] == c]
+    assert_index_query(test_table_gsi_1_hash_only, 'hello', expected_items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    # Test items with the same sort key 'c' but different hash key 'p'
+    c = random_string();
+    items = [{'p': random_string(), 'c': c, 'x': random_string()} for i in range(10)]
+    with test_table_gsi_1_hash_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_1_hash_only, 'hello', items,
+        KeyConditions={'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}})
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert_index_scan(test_table_gsi_1_hash_only, 'hello', full_scan(test_table_gsi_1_hash_only))
+
+
+# A second scenario of GSI. Base table has just hash key, Index has a
+# different hash key - one of the non-key attributes from the base table.
+@pytest.fixture(scope="session")
+def test_table_gsi_2(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_gsi_2(test_table_gsi_2):
+    items1 = [{'p': random_string(), 'x': random_string()} for i in range(10)]
+    x1 = items1[0]['x']
+    x2 = random_string()
+    items2 = [{'p': random_string(), 'x': x2} for i in range(10)]
+    items = items1 + items2
+    with test_table_gsi_2.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['x'] == x1]
+    assert_index_query(test_table_gsi_2, 'hello', expected_items,
+        KeyConditions={'x': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
+    expected_items = [i for i in items if i['x'] == x2]
+    assert_index_query(test_table_gsi_2, 'hello', expected_items,
+        KeyConditions={'x': {'AttributeValueList': [x2], 'ComparisonOperator': 'EQ'}})
+
+# Test that when a table has a GSI, if the indexed attribute is missing, the
+# item is added to the base table but not the index.
+def test_gsi_missing_attribute(test_table_gsi_2):
+    p1 = random_string()
+    x1 = random_string()
+    test_table_gsi_2.put_item(Item={'p':  p1, 'x': x1})
+    p2 = random_string()
+    test_table_gsi_2.put_item(Item={'p':  p2})
+
+    # Both items are now in the base table:
+    assert test_table_gsi_2.get_item(Key={'p':  p1})['Item'] == {'p': p1, 'x': x1}
+    assert test_table_gsi_2.get_item(Key={'p':  p2})['Item'] == {'p': p2}
+
+    # But only the first item is in the index: It can be found using a
+    # Query, and a scan of the index won't find it (but a scan on the base
+    # will).
+    assert_index_query(test_table_gsi_2, 'hello', [{'p': p1, 'x': x1}],
+        KeyConditions={'x': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
+    assert any([i['p'] == p1 for i in full_scan(test_table_gsi_2)])
+    # Note: with eventually consistent read, we can't really be sure that
+    # and item will "never" appear in the index. We do this test last,
+    # so if we had a bug and such item did appear, hopefully we had enough
+    # time for the bug to become visible. At least sometimes.
+    assert not any([i['p'] == p2 for i in full_scan(test_table_gsi_2, IndexName='hello')])
+
+# Test when a table has a GSI, if the indexed attribute has the wrong type,
+# the update operation is rejected, and is added to neither base table nor
+# index. This is different from the case of a *missing* attribute, where
+# the item is added to the base table but not index.
+# The following three tests test_gsi_wrong_type_attribute_{put,update,batch}
+# test updates using PutItem, UpdateItem, and BatchWriteItem respectively.
+def test_gsi_wrong_type_attribute_put(test_table_gsi_2):
+    # PutItem with wrong type for 'x' is rejected, item isn't created even
+    # in the base table.
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*mismatch'):
+        test_table_gsi_2.put_item(Item={'p':  p, 'x': 3})
+    assert not 'Item' in test_table_gsi_2.get_item(Key={'p': p}, ConsistentRead=True)
+
+def test_gsi_wrong_type_attribute_update(test_table_gsi_2):
+    # An UpdateItem with wrong type for 'x' is also rejected, but naturally
+    # if the item already existed, it remains as it was.
+    p = random_string()
+    x = random_string()
+    test_table_gsi_2.put_item(Item={'p':  p, 'x': x})
+    with pytest.raises(ClientError, match='ValidationException.*mismatch'):
+        test_table_gsi_2.update_item(Key={'p':  p}, AttributeUpdates={'x': {'Value': 3, 'Action': 'PUT'}})
+    assert test_table_gsi_2.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'x': x}
+
+def test_gsi_wrong_type_attribute_batch(test_table_gsi_2):
+    # In a BatchWriteItem, if any update is forbidden, the entire batch is
+    # rejected, and none of the updates happen at all.
+    p1 = random_string()
+    p2 = random_string()
+    p3 = random_string()
+    items = [{'p': p1, 'x': random_string()},
+             {'p': p2, 'x': 3},
+             {'p': p3, 'x': random_string()}]
+    with pytest.raises(ClientError, match='ValidationException.*mismatch'):
+        with test_table_gsi_2.batch_writer() as batch:
+            for item in items:
+                batch.put_item(item)
+    for p in [p1, p2, p3]:
+        assert not 'Item' in test_table_gsi_2.get_item(Key={'p': p}, ConsistentRead=True)
+
+# A third scenario of GSI. Index has a hash key and a sort key, both are
+# non-key attributes from the base table. This scenario may be very
+# difficult to implement in Alternator because Scylla's materialized-views
+# implementation only allows one new key column in the view, and here
+# we need two (which, also, aren't actual columns, but map items).
+@pytest.fixture(scope="session")
+def test_table_gsi_3(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'a', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' }
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'a', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'b', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_gsi_3(test_table_gsi_3):
+    items = [{'p': random_string(), 'a': random_string(), 'b': random_string()} for i in range(10)]
+    with test_table_gsi_3.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_3, 'hello', [items[3]],
+        KeyConditions={'a': {'AttributeValueList': [items[3]['a']], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [items[3]['b']], 'ComparisonOperator': 'EQ'}})
+
+@pytest.mark.xfail(reason="GSI in alternator currently have a bug on updating the second regular base column")
+def test_gsi_update_second_regular_base_column(test_table_gsi_3):
+    items = [{'p': random_string(), 'a': random_string(), 'b': random_string(), 'd': random_string()} for i in range(10)]
+    with test_table_gsi_3.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    items[3]['b'] = 'updated'
+    test_table_gsi_3.update_item(Key={'p':  items[3]['p']}, AttributeUpdates={'b': {'Value': 'updated', 'Action': 'PUT'}})
+    assert_index_query(test_table_gsi_3, 'hello', [items[3]],
+        KeyConditions={'a': {'AttributeValueList': [items[3]['a']], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [items[3]['b']], 'ComparisonOperator': 'EQ'}})
+
+
+# A fourth scenario of GSI. Two GSIs on a single base table.
+@pytest.fixture(scope="session")
+def test_table_gsi_4(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'a', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' }
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello_a',
+                'KeySchema': [
+                    { 'AttributeName': 'a', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            },
+            {   'IndexName': 'hello_b',
+                'KeySchema': [
+                    { 'AttributeName': 'b', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+# Test that a base table with two GSIs updates both as expected.
+def test_gsi_4(test_table_gsi_4):
+    items = [{'p': random_string(), 'a': random_string(), 'b': random_string()} for i in range(10)]
+    with test_table_gsi_4.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert_index_query(test_table_gsi_4, 'hello_a', [items[3]],
+        KeyConditions={'a': {'AttributeValueList': [items[3]['a']], 'ComparisonOperator': 'EQ'}})
+    assert_index_query(test_table_gsi_4, 'hello_b', [items[3]],
+        KeyConditions={'b': {'AttributeValueList': [items[3]['b']], 'ComparisonOperator': 'EQ'}})
+
+# Verify that describe_table lists the two GSIs.
+def test_gsi_4_describe(test_table_gsi_4):
+    desc = test_table_gsi_4.meta.client.describe_table(TableName=test_table_gsi_4.name)
+    assert 'Table' in desc
+    assert 'GlobalSecondaryIndexes' in desc['Table']
+    gsis = desc['Table']['GlobalSecondaryIndexes']
+    assert len(gsis) == 2
+    assert multiset([g['IndexName'] for g in gsis]) == multiset(['hello_a', 'hello_b'])
+
+# A scenario for GSI in which the table has both hash and sort key
+@pytest.fixture(scope="session")
+def test_table_gsi_5(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'x', 'KeyType': 'RANGE' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_gsi_5(test_table_gsi_5):
+    items1 = [{'p': random_string(), 'c': random_string(), 'x': random_string()} for i in range(10)]
+    p1, x1 = items1[0]['p'], items1[0]['x']
+    p2, x2 = random_string(), random_string()
+    items2 = [{'p': p2, 'c': random_string(), 'x': x2} for i in range(10)]
+    items = items1 + items2
+    with test_table_gsi_5.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['x'] == x1]
+    assert_index_query(test_table_gsi_5, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'x': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})
+    expected_items = [i for i in items if i['p'] == p2 and i['x'] == x2]
+    assert_index_query(test_table_gsi_5, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'x': {'AttributeValueList': [x2], 'ComparisonOperator': 'EQ'}})
+
+# All tests above involved "ProjectionType: ALL". This test checks how
+# "ProjectionType:: KEYS_ONLY" works. We note that it projects both
+# the index's key, *and* the base table's key. So items which had different
+# base-table keys cannot suddenly become the same item in the index.
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_projection_keys_only(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ])
+    items = [{'p': random_string(), 'x': random_string(), 'y': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    wanted = ['p', 'x']
+    expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+    assert_index_scan(table, 'hello', expected_items)
+    table.delete()
+
+# Test for "ProjectionType:: INCLUDE". The secondary table includes the
+# its own and the base's keys (as in KEYS_ONLY) plus the extra keys given
+# in NonKeyAttributes.
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_projection_include(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'INCLUDE',
+                                'NonKeyAttributes': ['a', 'b'] }
+            }
+        ])
+    # Some items have the projected attributes a,b and some don't:
+    items = [{'p': random_string(), 'x': random_string(), 'a': random_string(), 'b': random_string(), 'y': random_string()} for i in range(10)]
+    items = items + [{'p': random_string(), 'x': random_string(), 'y': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    wanted = ['p', 'x', 'a', 'b']
+    expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+    assert_index_scan(table, 'hello', expected_items)
+    print(len(expected_items))
+    table.delete()
+
+# DynamoDB's says the "Projection" argument of GlobalSecondaryIndexes is
+# mandatory, and indeed Boto3 enforces that it must be passed. The
+# documentation then goes on to claim that the "ProjectionType" member of
+# "Projection" is optional - and Boto3 allows it to be missing. But in
+# fact, it is not allowed to be missing: DynamoDB complains: "Unknown
+# ProjectionType: null".
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_missing_projection_type(dynamodb):
+    with pytest.raises(ClientError, match='ValidationException.*ProjectionType'):
+        create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
+            AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }],
+            GlobalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+                    'Projection': {}
+                }
+            ])
+
+# update_table() for creating a GSI is an asynchronous operation.
+# The table's TableStatus changes from ACTIVE to UPDATING for a short while
+# and then goes back to ACTIVE, but the new GSI's IndexStatus appears as
+# CREATING, until eventually (after a *long* time...) it becomes ACTIVE.
+# During the CREATING phase, at some point the Backfilling attribute also
+# appears, until it eventually disappears. We need to wait until all three
+# markers indicate completion.
+# Unfortunately, while boto3 has a client.get_waiter('table_exists') to
+# wait for a table to exists, there is no such function to wait for an
+# index to come up, so we need to code it ourselves.
+def wait_for_gsi(table, gsi_name):
+    start_time = time.time()
+    # Surprisingly, even for tiny tables this can take a very long time
+    # on DynamoDB - often many minutes!
+    for i in range(300):
+        time.sleep(1)
+        desc = table.meta.client.describe_table(TableName=table.name)
+        table_status = desc['Table']['TableStatus']
+        if table_status != 'ACTIVE':
+            print('%d Table status still %s' % (i, table_status))
+            continue
+        index_desc = [x for x in desc['Table']['GlobalSecondaryIndexes'] if x['IndexName'] == gsi_name]
+        assert len(index_desc) == 1
+        index_status = index_desc[0]['IndexStatus']
+        if index_status != 'ACTIVE':
+            print('%d Index status still %s' % (i, index_status))
+            continue
+        # When the index is ACTIVE, this must be after backfilling completed
+        assert not 'Backfilling' in index_desc[0]
+        print('wait_for_gsi took %d seconds' % (time.time() - start_time))
+        return
+    raise AssertionError("wait_for_gsi did not complete")
+
+# Similarly to how wait_for_gsi() waits for a GSI to finish adding,
+# this function waits for a GSI to be finally deleted.
+def wait_for_gsi_gone(table, gsi_name):
+    start_time = time.time()
+    for i in range(300):
+        time.sleep(1)
+        desc = table.meta.client.describe_table(TableName=table.name)
+        table_status = desc['Table']['TableStatus']
+        if table_status != 'ACTIVE':
+            print('%d Table status still %s' % (i, table_status))
+            continue
+        if 'GlobalSecondaryIndexes' in desc['Table']:
+            index_desc = [x for x in desc['Table']['GlobalSecondaryIndexes'] if x['IndexName'] == gsi_name]
+            if len(index_desc) != 0:
+                index_status = index_desc[0]['IndexStatus']
+                print('%d Index status still %s' % (i, index_status))
+                continue
+        print('wait_for_gsi_gone took %d seconds' % (time.time() - start_time))
+        return
+    raise AssertionError("wait_for_gsi_gone did not complete")
+
+# All tests above involved creating a new table with a GSI up-front. This
+# test will test creating a base table *without* a GSI, putting data in
+# it, and then adding a GSI with the UpdateTable operation. This starts
+# a backfilling stage - where data is copied to the index - and when this
+# stage is done, the index is usable. Items whose indexed column contains
+# the wrong type are silently ignored and not added to the index (it would
+# not have been possible to add such items if the GSI was already configured
+# when they were added).
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_backfill(dynamodb):
+    # First create, and fill, a table without GSI. The items in items1
+    # will have the appropriate string type for 'x' and will later get
+    # indexed. Items in item2 have no value for 'x', and in item3 'x' is in
+    # not a string; So the items in items2 and items3 will be missing
+    # in the index we'll create later.
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[ { 'AttributeName': 'p', 'AttributeType': 'S' } ])
+    items1 = [{'p': random_string(), 'x': random_string(), 'y': random_string()} for i in range(10)]
+    items2 = [{'p': random_string(), 'y': random_string()} for i in range(10)]
+    items3 = [{'p': random_string(), 'x': i} for i in range(10)]
+    items = items1 + items2 + items3
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    assert multiset(items) == multiset(full_scan(table))
+    # Now use UpdateTable to create the GSI
+    dynamodb.meta.client.update_table(TableName=table.name,
+        AttributeDefinitions=[{ 'AttributeName': 'x', 'AttributeType': 'S' }],
+        GlobalSecondaryIndexUpdates=[ {  'Create':
+            {  'IndexName': 'hello',
+                'KeySchema': [{ 'AttributeName': 'x', 'KeyType': 'HASH' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }}])
+    # update_table is an asynchronous operation. We need to wait until it
+    # finishes and the table is backfilled.
+    wait_for_gsi(table, 'hello')
+    # As explained above, only items in items1 got copied to the gsi,
+    # and Scan on them works as expected.
+    # Note that we don't need to retry the reads here (i.e., use the
+    # assert_index_scan() or assert_index_query() functions) because after
+    # we waited for backfilling to complete, we know all the pre-existing
+    # data is already in the index.
+    assert multiset(items1) == multiset(full_scan(table, IndexName='hello'))
+    # We can also use Query on the new GSI, to search on the attribute x:
+    assert multiset([items1[3]]) == multiset(full_query(table,
+        IndexName='hello',
+        KeyConditions={'x': {'AttributeValueList': [items1[3]['x']], 'ComparisonOperator': 'EQ'}}))
+    # Let's also test that we cannot add another index with the same name
+    # that already exists
+    with pytest.raises(ClientError, match='ValidationException.*already exists'):
+        dynamodb.meta.client.update_table(TableName=table.name,
+            AttributeDefinitions=[{ 'AttributeName': 'y', 'AttributeType': 'S' }],
+            GlobalSecondaryIndexUpdates=[ {  'Create':
+                {  'IndexName': 'hello',
+                    'KeySchema': [{ 'AttributeName': 'y', 'KeyType': 'HASH' }],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }}])
+    table.delete()
+
+# Test deleting an existing GSI using UpdateTable
+@pytest.mark.xfail(reason="GSI not supported")
+def test_gsi_delete(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'x', 'KeyType': 'HASH' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    items = [{'p': random_string(), 'x': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # So far, we have the index for "x" and can use it:
+    assert_index_query(table, 'hello', [items[3]],
+        KeyConditions={'x': {'AttributeValueList': [items[3]['x']], 'ComparisonOperator': 'EQ'}})
+    # Now use UpdateTable to delete the GSI for "x"
+    dynamodb.meta.client.update_table(TableName=table.name,
+        GlobalSecondaryIndexUpdates=[{  'Delete':
+            { 'IndexName': 'hello' } }])
+    # update_table is an asynchronous operation. We need to wait until it
+    # finishes and the GSI is removed.
+    wait_for_gsi_gone(table, 'hello')
+    # Now index is gone. We cannot query using it.
+    with pytest.raises(ClientError, match='ValidationException.*hello'):
+        full_query(table, IndexName='hello',
+            KeyConditions={'x': {'AttributeValueList': [items[3]['x']], 'ComparisonOperator': 'EQ'}})
+    table.delete()
+
+# Utility function for creating a new table a GSI with the given name,
+# and, if creation was successful, delete it. Useful for testing which
+# GSI names work.
+def create_gsi(dynamodb, index_name):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }],
+        AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': index_name,
+                'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    # Verify that the GSI wasn't just ignored, as Scylla originally did ;-)
+    assert 'GlobalSecondaryIndexes' in table.meta.client.describe_table(TableName=table.name)['Table']
+    table.delete()
+
+# Like table names (tested in test_table.py), index names must must also
+# be 3-255 characters and match the regex [a-zA-Z0-9._-]+. This test
+# is similar to test_create_table_unsupported_names(), but for GSI names.
+# Note that Scylla is actually more limited in the length of the index
+# names, because both table name and index name, together, have to fit in
+# 221 characters. But we don't verify here this specific limitation.
+def test_gsi_unsupported_names(dynamodb):
+    # Unfortunately, the boto library tests for names shorter than the
+    # minimum length (3 characters) immediately, and failure results in
+    # ParamValidationError. But the other invalid names are passed to
+    # DynamoDB, which returns an HTTP response code, which results in a
+    # CientError exception.
+    with pytest.raises(ParamValidationError):
+        create_gsi(dynamodb, 'n')
+    with pytest.raises(ParamValidationError):
+        create_gsi(dynamodb, 'nn')
+    with pytest.raises(ClientError, match='ValidationException.*nnnnn'):
+        create_gsi(dynamodb, 'n' * 256)
+    with pytest.raises(ClientError, match='ValidationException.*nyh'):
+        create_gsi(dynamodb, 'nyh@test')
+
+# On the other hand, names following the above rules should be accepted. Even
+# names which the Scylla rules forbid, such as a name starting with .
+def test_gsi_non_scylla_name(dynamodb):
+    create_gsi(dynamodb, '.alternator_test')
+
+# Index names with 255 characters are allowed in Dynamo. In Scylla, the
+# limit is different - the sum of both table and index length cannot
+# exceed 211 characters. So we test a much shorter limit.
+# (compare test_create_and_delete_table_very_long_name()).
+def test_gsi_very_long_name(dynamodb):
+    #create_gsi(dynamodb, 'n' * 255)   # works on DynamoDB, but not on Scylla
+    create_gsi(dynamodb, 'n' * 190)
+
+# Verify that ListTables does not list materialized views used for indexes.
+# This is hard to test, because we don't really know which table names
+# should be listed beyond those we created, and don't want to assume that
+# no other test runs in parallel with us. So the method we chose is to use a
+# unique random name for an index, and check that no table contains this
+# name. This assumes that materialized-view names are composed using the
+# index's name (which is currently what we do).
+
+@pytest.fixture(scope="session")
+def test_table_gsi_random_name(dynamodb):
+    index_name = random_string()
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': index_name,
+                'KeySchema': [
+                    { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ],
+        )
+    yield [table, index_name]
+    table.delete()
+
+def test_gsi_list_tables(dynamodb, test_table_gsi_random_name):
+    table, index_name = test_table_gsi_random_name
+    # Check that the random "index_name" isn't a substring of any table name:
+    tables = list_tables(dynamodb)
+    for name in tables:
+        assert not index_name in name
+    # But of course, the table's name should be in the list:
+    assert table.name in tables

alternator-test/test_health.py

@@ -0,0 +1,34 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the health check
+
+import requests
+
+# Test that a health check can be performed with a GET packet
+def test_health_works(dynamodb):
+    url = dynamodb.meta.client._endpoint.host
+    response = requests.get(url)
+    assert response.ok
+    assert response.content.decode('utf-8').strip()  == 'healthy: {}'.format(url.replace('https://', '').replace('http://', ''))
+
+# Test that a health check only works for the root URL ('/')
+def test_health_only_works_for_root_path(dynamodb):
+    url = dynamodb.meta.client._endpoint.host
+    for suffix in ['/abc', '/..', '/-', '/index.htm', '/health']:
+        response = requests.get(url + suffix)
+        assert response.status_code in range(400, 405)

alternator-test/test_item.py

@@ -0,0 +1,402 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the CRUD item operations: PutItem, GetItem, UpdateItem, DeleteItem
+
+import pytest
+from botocore.exceptions import ClientError
+from decimal import Decimal
+from util import random_string, random_bytes
+
+# Basic test for creating a new item with a random name, and reading it back
+# with strong consistency.
+# Only the string type is used for keys and attributes. None of the various
+# optional PutItem features (Expected, ReturnValues, ReturnConsumedCapacity,
+# ReturnItemCollectionMetrics, ConditionalOperator, ConditionExpression,
+# ExpressionAttributeNames, ExpressionAttributeValues) are used, and
+# for GetItem strong consistency is requested as well as all attributes,
+# but no other optional features (AttributesToGet, ReturnConsumedCapacity,
+# ProjectionExpression, ExpressionAttributeNames)
+def test_basic_string_put_and_get(test_table):
+    p = random_string()
+    c = random_string()
+    val = random_string()
+    val2 = random_string()
+    test_table.put_item(Item={'p': p, 'c': c, 'attribute': val, 'another': val2})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item['p'] == p
+    assert item['c'] == c
+    assert item['attribute'] == val
+    assert item['another'] == val2
+
+# Similar to test_basic_string_put_and_get, just uses UpdateItem instead of
+# PutItem. Because the item does not yet exist, it should work the same.
+def test_basic_string_update_and_get(test_table):
+    p = random_string()
+    c = random_string()
+    val = random_string()
+    val2 = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'attribute': {'Value': val, 'Action': 'PUT'}, 'another': {'Value': val2, 'Action': 'PUT'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item['p'] == p
+    assert item['c'] == c
+    assert item['attribute'] == val
+    assert item['another'] == val2
+
+# Test put_item and get_item of various types for the *attributes*,
+# including both scalars as well as nested documents, lists and sets.
+# The full list of types tested here:
+#    number, boolean, bytes, null, list, map, string set, number set,
+#    binary set.
+# The keys are still strings.
+# Note that only top-level attributes are written and read in this test -
+# this test does not attempt to modify *nested* attributes.
+# See https://boto3.amazonaws.com/v1/documentation/api/latest/reference/customizations/dynamodb.html
+# on how to pass these various types to Boto3's put_item().
+def test_put_and_get_attribute_types(test_table):
+    key = {'p': random_string(), 'c': random_string()}
+    test_items = [
+        Decimal("12.345"),
+        42,
+        True,
+        False,
+        b'xyz',
+        None,
+        ['hello', 'world', 42],
+        {'hello': 'world', 'life': 42},
+        {'hello': {'test': 'hi', 'hello': True, 'list': [1, 2, 'hi']}},
+        set(['hello', 'world', 'hi']),
+        set([1, 42, Decimal("3.14")]),
+        set([b'xyz', b'hi']),
+    ]
+    item = { str(i) : test_items[i] for i in range(len(test_items)) }
+    item.update(key)
+    test_table.put_item(Item=item)
+    got_item = test_table.get_item(Key=key, ConsistentRead=True)['Item']
+    assert item == got_item
+
+# The test_empty_* tests below verify support for empty items, with no
+# attributes except the key. This is a difficult case for Scylla, because
+# for an empty row to exist, Scylla needs to add a "CQL row marker".
+# There are several ways to create empty items - via PutItem, UpdateItem
+# and deleting attributes from non-empty items, and we need to check them
+# all, in several test_empty_* tests:
+def test_empty_put(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.put_item(Item={'p': p, 'c': c})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+def test_empty_put_delete(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.put_item(Item={'p': p, 'c': c, 'hello': 'world'})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'hello': {'Action': 'DELETE'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+def test_empty_update(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+def test_empty_update_delete(test_table):
+    p = random_string()
+    c = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'hello': {'Value': 'world', 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'hello': {'Action': 'DELETE'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item == {'p': p, 'c': c}
+
+# Test error handling of UpdateItem passed a bad "Action" field.
+def test_update_bad_action(test_table):
+    p = random_string()
+    c = random_string()
+    val = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'attribute': {'Value': val, 'Action': 'NONEXISTENT'}})
+
+# A more elaborate UpdateItem test, updating different attributes at different
+# times. Includes PUT and DELETE operations.
+def test_basic_string_more_update(test_table):
+    p = random_string()
+    c = random_string()
+    val1 = random_string()
+    val2 = random_string()
+    val3 = random_string()
+    val4 = random_string()
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a3': {'Value': val1, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a1': {'Value': val1, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a2': {'Value': val2, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a1': {'Value': val3, 'Action': 'PUT'}})
+    test_table.update_item(Key={'p': p, 'c': c}, AttributeUpdates={'a3': {'Action': 'DELETE'}})
+    item = test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item']
+    assert item['p'] == p
+    assert item['c'] == c
+    assert item['a1'] == val3
+    assert item['a2'] == val2
+    assert not 'a3' in item
+
+# Test that item operations on a non-existant table name fail with correct
+# error code.
+def test_item_operations_nonexistent_table(dynamodb):
+    with pytest.raises(ClientError, match='ResourceNotFoundException'):
+        dynamodb.meta.client.put_item(TableName='non_existent_table',
+            Item={'a':{'S':'b'}})
+
+# Fetching a non-existant item. According to the DynamoDB doc, "If there is no
+# matching item, GetItem does not return any data and there will be no Item
+# element in the response."
+def test_get_item_missing_item(test_table):
+    p = random_string()
+    c = random_string()
+    assert not "Item" in test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)
+
+# Test that if we have a table with string hash and sort keys, we can't read
+# or write items with other key types to it.
+def test_put_item_wrong_key_type(test_table):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types)
+    test_table.put_item(Item={'p': s, 'c': s})
+    assert test_table.get_item(Key={'p': s, 'c': s}, ConsistentRead=True)['Item'] == {'p': s, 'c': s}
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': b, 'c': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': n, 'c': s})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': s, 'c': b})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': s, 'c': n})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'c': s})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.put_item(Item={'p': s})
+def test_update_item_wrong_key_type(test_table, test_table_s):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types)
+    test_table.update_item(Key={'p': s, 'c': s}, AttributeUpdates={})
+    assert test_table.get_item(Key={'p': s, 'c': s}, ConsistentRead=True)['Item'] == {'p': s, 'c': s}
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': b, 'c': s}, AttributeUpdates={})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': n, 'c': s}, AttributeUpdates={})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': s, 'c': b}, AttributeUpdates={})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': s, 'c': n}, AttributeUpdates={})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'c': s}, AttributeUpdates={})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.update_item(Key={'p': s}, AttributeUpdates={})
+    # Should fail (spurious key columns)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': s, 'spurious': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': s, 'c': s})
+def test_get_item_wrong_key_type(test_table, test_table_s):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types) but have empty result
+    assert not "Item" in test_table.get_item(Key={'p': s, 'c': s}, ConsistentRead=True)
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': b, 'c': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': n, 'c': s})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': b})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': n})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'c': s})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s})
+    # Should fail (spurious key columns)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.get_item(Key={'p': s, 'c': s, 'spurious': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': s, 'c': s})
+def test_delete_item_wrong_key_type(test_table, test_table_s):
+    b = random_bytes()
+    s = random_string()
+    n = Decimal("3.14")
+    # Should succeed (correct key types)
+    test_table.delete_item(Key={'p': s, 'c': s})
+    # Should fail (incorrect hash key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': b, 'c': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': n, 'c': s})
+    # Should fail (incorrect sort key types)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s, 'c': b})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s, 'c': n})
+    # Should fail (missing hash key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'c': s})
+    # Should fail (missing sort key)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s})
+    # Should fail (spurious key columns)
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table.delete_item(Key={'p': s, 'c': s, 'spurious': s})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.delete_item(Key={'p': s, 'c': s})
+
+# Most of the tests here arbitrarily used a table with both hash and sort keys
+# (both strings). Let's check that a table with *only* a hash key works ok
+# too, for PutItem, GetItem, and UpdateItem.
+def test_only_hash_key(test_table_s):
+    s = random_string()
+    test_table_s.put_item(Item={'p': s, 'hello': 'world'})
+    assert test_table_s.get_item(Key={'p': s}, ConsistentRead=True)['Item'] == {'p': s, 'hello': 'world'}
+    test_table_s.update_item(Key={'p': s}, AttributeUpdates={'hi': {'Value': 'there', 'Action': 'PUT'}})
+    assert test_table_s.get_item(Key={'p': s}, ConsistentRead=True)['Item'] == {'p': s, 'hello': 'world', 'hi': 'there'}
+
+# Tests for item operations in tables with non-string hash or sort keys.
+# These tests focus only on the type of the key - everything else is as
+# simple as we can (string attributes, no special options for GetItem
+# and PutItem). These tests also focus on individual items only, and
+# not about the sort order of sort keys - this should be verified in
+# test_query.py, for example.
+def test_bytes_hash_key(test_table_b):
+    # Bytes values are passed using base64 encoding, which has weird cases
+    # depending on len%3 and len%4. So let's try various lengths.
+    for len in range(10,18):
+        p = random_bytes(len)
+        val = random_string()
+        test_table_b.put_item(Item={'p': p, 'attribute': val})
+        assert test_table_b.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'attribute': val}
+def test_bytes_sort_key(test_table_sb):
+    p = random_string()
+    c = random_bytes()
+    val = random_string()
+    test_table_sb.put_item(Item={'p': p, 'c': c, 'attribute': val})
+    assert test_table_sb.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'attribute': val}
+
+# Tests for using a large binary blob as hash key, sort key, or attribute.
+# DynamoDB strictly limits the size of the binary hash key to 2048 bytes,
+# and binary sort key to 1024 bytes, and refuses anything larger. The total
+# size of an item is limited to 400KB, which also limits the size of the
+# largest attributes. For more details on these limits, see
+# https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Limits.html
+# Alternator currently does *not* have these limitations, and can accept much
+# larger keys and attributes, but what we do in the following tests is to verify
+# that items up to DynamoDB's maximum sizes also work well in Alternator.
+def test_large_blob_hash_key(test_table_b):
+    b = random_bytes(2048)
+    test_table_b.put_item(Item={'p': b})
+    assert test_table_b.get_item(Key={'p': b}, ConsistentRead=True)['Item'] == {'p': b}
+def test_large_blob_sort_key(test_table_sb):
+    s = random_string()
+    b = random_bytes(1024)
+    test_table_sb.put_item(Item={'p': s, 'c': b})
+    assert test_table_sb.get_item(Key={'p': s, 'c': b}, ConsistentRead=True)['Item'] == {'p': s, 'c': b}
+def test_large_blob_attribute(test_table):
+    p = random_string()
+    c = random_string()
+    b = random_bytes(409500)  # a bit less than 400KB
+    test_table.put_item(Item={'p': p, 'c': c, 'attribute': b })
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'attribute': b}
+
+# Checks what it is not allowed to use in a single UpdateItem request both
+# old-style AttributeUpdates and new-style UpdateExpression.
+def test_update_item_two_update_methods(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            AttributeUpdates={'a': {'Value': 3, 'Action': 'PUT'}},
+            UpdateExpression='SET b = :val1',
+            ExpressionAttributeValues={':val1': 4})
+
+# Verify that having neither AttributeUpdates nor UpdateExpression is
+# allowed, and results in creation of an empty item.
+def test_update_item_no_update_method(test_table_s):
+    p = random_string()
+    assert not "Item" in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+    test_table_s.update_item(Key={'p': p})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p}
+
+# Test GetItem with the AttributesToGet parameter. Result should include the
+# selected attributes only - if one wants the key attributes as well, one
+# needs to select them explicitly. When no key attributes are selected,
+# some items may have *none* of the selected attributes. Those items are
+# returned too, as empty items - they are not outright missing.
+def test_getitem_attributes_to_get(dynamodb, test_table):
+    p = random_string()
+    c = random_string()
+    item = {'p': p, 'c': c, 'a': 'hello', 'b': 'hi'}
+    test_table.put_item(Item=item)
+    for wanted in [ ['a'],             # only non-key attribute
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # Our item doesn't have this
+                   ]:
+        got_item = test_table.get_item(Key={'p': p, 'c': c}, AttributesToGet=wanted, ConsistentRead=True)['Item']
+        expected_item = {k: item[k] for k in wanted if k in item}
+        assert expected_item == got_item
+
+# Basic test for DeleteItem, with hash key only
+def test_delete_item_hash(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p})
+    assert 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+    test_table_s.delete_item(Key={'p': p})
+    assert not 'Item' in test_table_s.get_item(Key={'p': p}, ConsistentRead=True)
+
+# Basic test for DeleteItem, with hash and sort key
+def test_delete_item_sort(test_table):
+    p = random_string()
+    c = random_string()
+    key = {'p': p, 'c': c}
+    test_table.put_item(Item=key)
+    assert 'Item' in test_table.get_item(Key=key, ConsistentRead=True)
+    test_table.delete_item(Key=key)
+    assert not 'Item' in test_table.get_item(Key=key, ConsistentRead=True)
+
+# Test that PutItem completely replaces an existing item. It shouldn't merge
+# it with a previously existing value, as UpdateItem does!
+# We test for a table with just hash key, and for a table with both hash and
+# sort keys.
+def test_put_item_replace(test_table_s, test_table):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hi'}
+    test_table_s.put_item(Item={'p': p, 'b': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
+    c = random_string()
+    test_table.put_item(Item={'p': p, 'c': c, 'a': 'hi'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 'hi'}
+    test_table.put_item(Item={'p': p, 'c': c, 'b': 'hello'})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'b': 'hello'}

alternator-test/test_lsi.py

@@ -0,0 +1,365 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests of LSI (Local Secondary Indexes)
+#
+# Note that many of these tests are slower than usual, because many of them
+# need to create new tables and/or new LSIs of different types, operations
+# which are extremely slow in DynamoDB, often taking minutes (!).
+
+import pytest
+import time
+from botocore.exceptions import ClientError, ParamValidationError
+from util import create_test_table, random_string, full_scan, full_query, multiset, list_tables
+
+# Currently, Alternator's LSIs only support eventually consistent reads, so tests
+# that involve writing to a table and then expect to read something from it cannot
+# be guaranteed to succeed without retrying the read. The following utility
+# functions make it easy to write such tests.
+def assert_index_query(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_query retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_query(table, IndexName=index_name, **kwargs))
+
+def assert_index_scan(table, index_name, expected_items, **kwargs):
+    for i in range(3):
+        if multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs)):
+            return
+        print('assert_index_scan retrying')
+        time.sleep(1)
+    assert multiset(expected_items) == multiset(full_scan(table, IndexName=index_name, **kwargs))
+
+# Although quite silly, it is actually allowed to create an index which is
+# identical to the base table.
+def test_lsi_identical(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' }],
+        AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }, { 'AttributeName': 'c', 'AttributeType': 'S' }],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [{ 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' }],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    items = [{'p': random_string(), 'c': random_string()} for i in range(10)]
+    with table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # Scanning the entire table directly or via the index yields the same
+    # results (in different order).
+    assert multiset(items) == multiset(full_scan(table))
+    assert_index_scan(table, 'hello', items)
+    # We can't scan a non-existant index
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_scan(table, IndexName='wrong')
+    table.delete()
+
+# Checks that providing a hash key different than the base table is not allowed,
+# and so is providing duplicated keys or no sort key at all
+def test_lsi_wrong(dynamodb):
+    with pytest.raises(ClientError, match='ValidationException.*'):
+        table = create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[
+                        { 'AttributeName': 'p', 'AttributeType': 'S' },
+                        { 'AttributeName': 'a', 'AttributeType': 'S' },
+                        { 'AttributeName': 'b', 'AttributeType': 'S' }
+            ],
+            LocalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [
+                        { 'AttributeName': 'b', 'KeyType': 'HASH' },
+                        { 'AttributeName': 'p', 'KeyType': 'RANGE' }
+                    ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+        table.delete()
+    with pytest.raises(ClientError, match='ValidationException.*'):
+        table = create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[
+                        { 'AttributeName': 'p', 'AttributeType': 'S' },
+                        { 'AttributeName': 'a', 'AttributeType': 'S' },
+                        { 'AttributeName': 'b', 'AttributeType': 'S' }
+            ],
+            LocalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [
+                        { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                        { 'AttributeName': 'p', 'KeyType': 'RANGE' }
+                    ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+        table.delete()
+    with pytest.raises(ClientError, match='ValidationException.*'):
+        table = create_test_table(dynamodb,
+            KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' } ],
+            AttributeDefinitions=[
+                        { 'AttributeName': 'p', 'AttributeType': 'S' },
+                        { 'AttributeName': 'a', 'AttributeType': 'S' },
+                        { 'AttributeName': 'b', 'AttributeType': 'S' }
+            ],
+            LocalSecondaryIndexes=[
+                {   'IndexName': 'hello',
+                    'KeySchema': [
+                        { 'AttributeName': 'p', 'KeyType': 'HASH' }
+                    ],
+                    'Projection': { 'ProjectionType': 'ALL' }
+                }
+            ])
+        table.delete()
+
+# A simple scenario for LSI. Base table has just hash key, Index has an
+# additional sort key - one of the non-key attributes from the base table.
+@pytest.fixture(scope="session")
+def test_table_lsi_1(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' },
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'b', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            }
+        ])
+    yield table
+    table.delete()
+
+def test_lsi_1(test_table_lsi_1):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string()} for i in range(10)]
+    p1, b1 = items1[0]['p'], items1[0]['b']
+    p2, b2 = random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2}]
+    items = items1 + items2
+    with test_table_lsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}})
+    expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}})
+
+# A second scenario of LSI. Base table has both hash and sort keys,
+# a local index is created on each non-key parameter
+@pytest.fixture(scope="session")
+def test_table_lsi_4(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x1', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x2', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x3', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x4', 'AttributeType': 'S' },
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello_' + column,
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': column, 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'ALL' }
+            } for column in ['x1','x2','x3','x4']
+        ])
+    yield table
+    table.delete()
+
+def test_lsi_4(test_table_lsi_4):
+    items1 = [{'p': random_string(), 'c': random_string(),
+               'x1': random_string(), 'x2': random_string(), 'x3': random_string(), 'x4': random_string()} for i in range(10)]
+    i_values = items1[0]
+    i5 = random_string()
+    items2 = [{'p': i5, 'c': i5, 'x1': i5, 'x2': i5, 'x3': i5, 'x4': i5}]
+    items = items1 + items2
+    with test_table_lsi_4.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for column in ['x1', 'x2', 'x3', 'x4']:
+        expected_items = [i for i in items if (i['p'], i[column]) == (i_values['p'], i_values[column])]
+        assert_index_query(test_table_lsi_4, 'hello_' + column, expected_items,
+            KeyConditions={'p': {'AttributeValueList': [i_values['p']], 'ComparisonOperator': 'EQ'},
+                           column: {'AttributeValueList': [i_values[column]], 'ComparisonOperator': 'EQ'}})
+        expected_items = [i for i in items if (i['p'], i[column]) == (i5, i5)]
+        assert_index_query(test_table_lsi_4, 'hello_' + column, expected_items,
+            KeyConditions={'p': {'AttributeValueList': [i5], 'ComparisonOperator': 'EQ'},
+                           column: {'AttributeValueList': [i5], 'ComparisonOperator': 'EQ'}})
+
+def test_lsi_describe(test_table_lsi_4):
+    desc = test_table_lsi_4.meta.client.describe_table(TableName=test_table_lsi_4.name)
+    assert 'Table' in desc
+    assert 'LocalSecondaryIndexes' in desc['Table']
+    lsis = desc['Table']['LocalSecondaryIndexes']
+    assert(sorted([lsi['IndexName'] for lsi in lsis]) == ['hello_x1', 'hello_x2', 'hello_x3', 'hello_x4'])
+    # TODO: check projection and key params
+    # TODO: check also ProvisionedThroughput, IndexArn
+
+# A table with selective projection - only keys are projected into the index
+@pytest.fixture(scope="session")
+def test_table_lsi_keys_only(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'b', 'AttributeType': 'S' }
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'b', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ])
+    yield table
+    table.delete()
+
+# Check that it's possible to extract a non-projected attribute from the index,
+# as the documentation promises
+def test_lsi_get_not_projected_attribute(test_table_lsi_keys_only):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string(), 'd': random_string()} for i in range(10)]
+    p1, b1, d1 = items1[0]['p'], items1[0]['b'], items1[0]['d']
+    p2, b2, d2 = random_string(), random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2, 'd': d2}]
+    items = items1 + items2
+    with test_table_lsi_keys_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1 and i['d'] == d1]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}},
+        Select='ALL_ATTRIBUTES')
+    expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2 and i['d'] == d2]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
+        Select='ALL_ATTRIBUTES')
+    expected_items = [{'d': i['d']} for i in items if i['p'] == p2 and i['b'] == b2 and i['d'] == d2]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
+        Select='SPECIFIC_ATTRIBUTES', AttributesToGet=['d'])
+
+# Check that only projected attributes can be extracted
+@pytest.mark.xfail(reason="LSI in alternator currently only implement full projections")
+def test_lsi_get_all_projected_attributes(test_table_lsi_keys_only):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string(), 'd': random_string()} for i in range(10)]
+    p1, b1, d1 = items1[0]['p'], items1[0]['b'], items1[0]['d']
+    p2, b2, d2 = random_string(), random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2, 'd': d2}]
+    items = items1 + items2
+    with test_table_lsi_keys_only.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [{'p': i['p'], 'c': i['c'],'b': i['b']} for i in items if i['p'] == p1 and i['b'] == b1]
+    assert_index_query(test_table_lsi_keys_only, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}})
+
+# Check that strongly consistent reads are allowed for LSI
+def test_lsi_consistent_read(test_table_lsi_1):
+    items1 = [{'p': random_string(), 'c': random_string(), 'b': random_string()} for i in range(10)]
+    p1, b1 = items1[0]['p'], items1[0]['b']
+    p2, b2 = random_string(), random_string()
+    items2 = [{'p': p2, 'c': p2, 'b': b2}]
+    items = items1 + items2
+    with test_table_lsi_1.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    expected_items = [i for i in items if i['p'] == p1 and i['b'] == b1]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b1], 'ComparisonOperator': 'EQ'}},
+        ConsistentRead=True)
+    expected_items = [i for i in items if i['p'] == p2 and i['b'] == b2]
+    assert_index_query(test_table_lsi_1, 'hello', expected_items,
+        KeyConditions={'p': {'AttributeValueList': [p2], 'ComparisonOperator': 'EQ'},
+                       'b': {'AttributeValueList': [b2], 'ComparisonOperator': 'EQ'}},
+        ConsistentRead=True)
+
+# A table with both gsi and lsi present
+@pytest.fixture(scope="session")
+def test_table_lsi_gsi(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[ { 'AttributeName': 'p', 'KeyType': 'HASH' }, { 'AttributeName': 'c', 'KeyType': 'RANGE' } ],
+        AttributeDefinitions=[
+                    { 'AttributeName': 'p', 'AttributeType': 'S' },
+                    { 'AttributeName': 'c', 'AttributeType': 'S' },
+                    { 'AttributeName': 'x1', 'AttributeType': 'S' },
+        ],
+        GlobalSecondaryIndexes=[
+            {   'IndexName': 'hello_g1',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'x1', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ],
+        LocalSecondaryIndexes=[
+            {   'IndexName': 'hello_l1',
+                'KeySchema': [
+                    { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                    { 'AttributeName': 'x1', 'KeyType': 'RANGE' }
+                ],
+                'Projection': { 'ProjectionType': 'KEYS_ONLY' }
+            }
+        ])
+    yield table
+    table.delete()
+
+# Test that GSI and LSI can coexist, even if they're identical
+def test_lsi_and_gsi(test_table_lsi_gsi):
+    desc = test_table_lsi_gsi.meta.client.describe_table(TableName=test_table_lsi_gsi.name)
+    assert 'Table' in desc
+    assert 'LocalSecondaryIndexes' in desc['Table']
+    assert 'GlobalSecondaryIndexes' in desc['Table']
+    lsis = desc['Table']['LocalSecondaryIndexes']
+    gsis = desc['Table']['GlobalSecondaryIndexes']
+    assert(sorted([lsi['IndexName'] for lsi in lsis]) == ['hello_l1'])
+    assert(sorted([gsi['IndexName'] for gsi in gsis]) == ['hello_g1'])
+
+    items = [{'p': random_string(), 'c': random_string(), 'x1': random_string()} for i in range(17)]
+    p1, c1, x1 = items[0]['p'], items[0]['c'], items[0]['x1']
+    with test_table_lsi_gsi.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+
+    for index in ['hello_g1', 'hello_l1']:
+        expected_items = [i for i in items if i['p'] == p1 and i['x1'] == x1]
+        assert_index_query(test_table_lsi_gsi, index, expected_items,
+            KeyConditions={'p': {'AttributeValueList': [p1], 'ComparisonOperator': 'EQ'},
+                           'x1': {'AttributeValueList': [x1], 'ComparisonOperator': 'EQ'}})

alternator-test/test_nested.py

@@ -1,6 +1,19 @@
-# Copyright 2019-present ScyllaDB
+# Copyright 2019 ScyllaDB
 #
-# SPDX-License-Identifier: AGPL-3.0-or-later
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 
 # Test for operations on items with *nested* attributes.
 

alternator-test/test_projection_expression.py

@@ -0,0 +1,201 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the various operations (GetItem, Query, Scan) with a
+# ProjectionExpression parameter.
+#
+# ProjectionExpression is an expension of the legacy AttributesToGet
+# parameter. Both parameters request that only a subset of the attributes
+# be fetched for each item, instead of all of them. But while AttributesToGet
+# was limited to top-level attributes, ProjectionExpression can request also
+# nested attributes.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string, full_scan, full_query, multiset
+
+# Basic test for ProjectionExpression, requesting only top-level attributes.
+# Result should include the selected attributes only - if one wants the key
+# attributes as well, one needs to select them explicitly. When no key
+# attributes are selected, an item may have *none* of the selected
+# attributes, and returned as an empty item.
+def test_projection_expression_toplevel(test_table):
+    p = random_string()
+    c = random_string()
+    item = {'p': p, 'c': c, 'a': 'hello', 'b': 'hi'}
+    test_table.put_item(Item=item)
+    for wanted in [ ['a'],             # only non-key attribute
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # Our item doesn't have this
+                   ]:
+        got_item = test_table.get_item(Key={'p': p, 'c': c}, ProjectionExpression=",".join(wanted), ConsistentRead=True)['Item']
+        expected_item = {k: item[k] for k in wanted if k in item}
+        assert expected_item == got_item
+
+# Various simple tests for ProjectionExpression's syntax, using only top-evel
+# attributes.
+def test_projection_expression_toplevel_syntax(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a')['Item'] == {'a': 'hello'}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#name': 'a'})['Item'] == {'a': 'hello'}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,b')['Item'] == {'a': 'hello', 'b': 'hi'}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression=' a  ,   b  ')['Item'] == {'a': 'hello', 'b': 'hi'}
+    # Missing or unused names in ExpressionAttributeNames are errors:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#wrong': 'a'})['Item'] == {'a': 'hello'}
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='#name', ExpressionAttributeNames={'#name': 'a', '#unused': 'b'})['Item'] == {'a': 'hello'}
+    # It is not allowed to fetch the same top-level attribute twice (or in
+    # general, list two overlapping attributes). We get an error like
+    # "Invalid ProjectionExpression: Two document paths overlap with each
+    # other; must remove or rewrite one of these paths; path one: [a], path
+    # two: [a]".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,a')['Item']
+    # A comma with nothing after it is a syntax error:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,')['Item']
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression=',a')['Item']
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,,b')['Item']
+    # An empty ProjectionExpression is not allowed. DynamoDB recognizes its
+    # syntax, but then writes: "Invalid ProjectionExpression: The expression
+    # can not be empty".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='')['Item']
+
+# The following two tests are similar to test_projection_expression_toplevel()
+# which tested the GetItem operation - but these test Scan and Query.
+# Both test ProjectionExpression with only top-level attributes.
+def test_projection_expression_scan(filled_test_table):
+    table, items = filled_test_table
+    for wanted in [ ['another'],       # only non-key attributes (one item doesn't have it!)
+                    ['c', 'another'],  # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        got_items = full_scan(table,  ProjectionExpression=",".join(wanted))
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+def test_projection_expression_query(test_table):
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': str(i*10), 'b': str(i*100) } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for wanted in [ ['a'],             # only non-key attributes
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression=",".join(wanted))
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+# The previous tests all fetched only top-level attributes. They could all
+# be written using AttributesToGet instead of ProjectionExpression (and,
+# in fact, we do have similar tests with AttributesToGet in other files),
+# but the previous test checked that the alternative syntax works correctly.
+# The following test checks fetching more elaborate attribute paths from
+# nested documents.
+@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
+def test_projection_expression_path(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={
+        'p': p,
+        'a': {'b': [2, 4, {'x': 'hi', 'y': 'yo'}], 'c': 5},
+        'b': 'hello' 
+        })
+    # Fetching the entire nested document "a" works, of course:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a')['Item'] == {'a': {'b': [2, 4, {'x': 'hi', 'y': 'yo'}], 'c': 5}}
+    # If we fetch a.b, we get only the content of b - but it's still inside
+    # the a dictionary:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b')['Item'] == {'a': {'b': [2, 4, {'x': 'hi', 'y': 'yo'}]}}
+    # Similarly, fetching a.b[0] gives us a one-element array in a dictionary.
+    # Note that [0] is the first element of an array.
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0]')['Item'] == {'a': {'b': [2]}}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[2]')['Item'] == {'a': {'b': [{'x': 'hi', 'y': 'yo'}]}}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[2].y')['Item'] == {'a': {'b': [{'y': 'yo'}]}}
+    # Trying to read any sort of non-existant attribute returns an empty item.
+    # This includes a non-existing top-level attribute, an attempt to read
+    # beyond the end of an array or a non-existant member of a dictionary, as
+    # well as paths which begin with a non-existant prefix.
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='x')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[3]')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.x')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.x.y')['Item'] == {}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[3].x')['Item'] == {}
+    # We can read multiple paths - the result are merged into one object
+    # structured the same was as in the original item:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.b[1]')['Item'] == {'a': {'b': [2, 4]}}
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.c')['Item'] == {'a': {'b': [2], 'c': 5}}
+    # It is not allowed to read the same path multiple times. The error from
+    # DynamoDB looks like: "Invalid ProjectionExpression: Two document paths
+    # overlap with each other; must remove or rewrite one of these paths;
+    # path one: [a, b, [0]], path two: [a, b, [0]]".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a.b[0],a.b[0]')['Item']
+    # Two paths are considered to "overlap" if the content of one path
+    # contains the content of the second path. So requesting both "a" and
+    # "a.b[0]" is not allowed.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a,a.b[0]')['Item']
+
+@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
+def test_query_projection_expression_path(test_table):
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': {'x': str(i*10), 'y': 'hi'}, 'b': 'hello' } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression="a.x")
+    expected_items = [{'a': {'x': x['a']['x']}} for x in items]
+    assert multiset(expected_items) == multiset(got_items)
+
+@pytest.mark.xfail(reason="ProjectionExpression does not yet support attribute paths")
+def test_scan_projection_expression_path(test_table):
+    # This test is similar to test_query_projection_expression_path above,
+    # but uses a scan instead of a query. The scan will generate unrelated
+    # partitions created by other tests (hopefully not too many...) that we
+    # need to ignore. We also need to ask for "p" too, so we can filter by it.
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': {'x': str(i*10), 'y': 'hi'}, 'b': 'hello' } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = [ x for x in full_scan(test_table, ProjectionExpression="p, a.x") if x['p'] == p]
+    expected_items = [{'p': p, 'a': {'x': x['a']['x']}} for x in items]
+    assert multiset(expected_items) == multiset(got_items)
+
+# It is not allowed to use both ProjectionExpression and its older cousin,
+# AttributesToGet, together. If trying to do this, DynamoDB produces an error
+# like "Can not use both expression and non-expression parameters in the same
+# request: Non-expression parameters: {AttributesToGet} Expression
+# parameters: {ProjectionExpression}
+def test_projection_expression_and_attributes_to_get(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
+    with pytest.raises(ClientError, match='ValidationException.*both'):
+        test_table_s.get_item(Key={'p': p}, ConsistentRead=True, ProjectionExpression='a', AttributesToGet=['b'])['Item']
+    with pytest.raises(ClientError, match='ValidationException.*both'):
+        full_scan(test_table_s,  ProjectionExpression='a', AttributesToGet=['a'])
+    with pytest.raises(ClientError, match='ValidationException.*both'):
+        full_query(test_table_s, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, ProjectionExpression='a', AttributesToGet=['a'])

alternator-test/test_query.py

@@ -0,0 +1,358 @@
+# -*- coding: utf-8 -*-
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the Query operation
+
+import random
+import pytest
+from botocore.exceptions import ClientError
+from decimal import Decimal
+from util import random_string, random_bytes, full_query, multiset
+from boto3.dynamodb.conditions import Key, Attr
+
+# Test that scanning works fine with in-stock paginator
+def test_query_basic_restrictions(dynamodb, filled_test_table):
+    test_table, items = filled_test_table
+    paginator = dynamodb.meta.client.get_paginator('query')
+
+    # EQ
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long']) == multiset(got_items)
+
+    # LT
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['12'], 'ComparisonOperator': 'LT'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] < '12']) == multiset(got_items)
+
+    # LE
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['14'], 'ComparisonOperator': 'LE'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] <= '14']) == multiset(got_items)
+
+    # GT
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['15'], 'ComparisonOperator': 'GT'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] > '15']) == multiset(got_items)
+
+    # GE
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['14'], 'ComparisonOperator': 'GE'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] >= '14']) == multiset(got_items)
+
+    # BETWEEN
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['155', '164'], 'ComparisonOperator': 'BETWEEN'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] >= '155' and item['c'] <= '164']) == multiset(got_items)
+
+    # BEGINS_WITH
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': ['11'], 'ComparisonOperator': 'BEGINS_WITH'}
+        }):
+        print([item for item in items if item['p'] == 'long' and item['c'].startswith('11')])
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'].startswith('11')]) == multiset(got_items)
+
+# Test that KeyConditionExpression parameter is supported
+@pytest.mark.xfail(reason="KeyConditionExpression not supported yet")
+def test_query_key_condition_expression(dynamodb, filled_test_table):
+    test_table, items = filled_test_table
+    paginator = dynamodb.meta.client.get_paginator('query')
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditionExpression=Key("p").eq("long") & Key("c").lt("12")):
+        got_items += page['Items']
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['c'] < '12']) == multiset(got_items)
+
+def test_begins_with(dynamodb, test_table):
+    paginator = dynamodb.meta.client.get_paginator('query')
+    items = [{'p': 'unorthodox_chars', 'c': sort_key, 'str': 'a'} for sort_key in [u'ÿÿÿ', u'cÿbÿ', u'cÿbÿÿabg'] ]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+
+    # TODO(sarna): Once bytes type is supported, /xFF character should be tested
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': [u'ÿÿ'], 'ComparisonOperator': 'BEGINS_WITH'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert sorted([d['c'] for d in got_items]) == sorted([d['c'] for d in items if d['c'].startswith(u'ÿÿ')])
+
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name, KeyConditions={
+            'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
+            'c' : {'AttributeValueList': [u'cÿbÿ'], 'ComparisonOperator': 'BEGINS_WITH'}
+        }):
+        got_items += page['Items']
+    print(got_items)
+    assert sorted([d['c'] for d in got_items]) == sorted([d['c'] for d in items if d['c'].startswith(u'cÿbÿ')])
+
+def test_begins_with_wrong_type(dynamodb, test_table_sn):
+    paginator = dynamodb.meta.client.get_paginator('query')
+    with pytest.raises(ClientError, match='ValidationException'):
+        for page in paginator.paginate(TableName=test_table_sn.name, KeyConditions={
+                'p' : {'AttributeValueList': ['unorthodox_chars'], 'ComparisonOperator': 'EQ'},
+                'c' : {'AttributeValueList': [17], 'ComparisonOperator': 'BEGINS_WITH'}
+                }):
+            pass
+
+# Items returned by Query should be sorted by the sort key. The following
+# tests verify that this is indeed the case, for the three allowed key types:
+# strings, binary, and numbers. These tests test not just the Query operation,
+# but inherently that the sort-key sorting works.
+def test_query_sort_order_string(test_table):
+    # Insert a lot of random items in one new partition:
+    # str(i) has a non-obvious sort order (e.g., "100" comes before "2") so is a nice test.
+    p = random_string()
+    items = [{'p': p, 'c': str(i)} for i in range(128)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    assert len(items) == len(got_items)
+    # Extract just the sort key ("c") from the items
+    sort_keys = [x['c'] for x in items]
+    got_sort_keys = [x['c'] for x in got_items]
+    # Verify that got_sort_keys are already sorted (in string order)
+    assert sorted(got_sort_keys) == got_sort_keys
+    # Verify that got_sort_keys are a sorted version of the expected sort_keys
+    assert sorted(sort_keys) == got_sort_keys
+def test_query_sort_order_bytes(test_table_sb):
+    # Insert a lot of random items in one new partition:
+    # We arbitrarily use random_bytes with a random length.
+    p = random_string()
+    items = [{'p': p, 'c': random_bytes(10)} for i in range(128)]
+    with test_table_sb.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    got_items = full_query(test_table_sb, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    assert len(items) == len(got_items)
+    sort_keys = [x['c'] for x in items]
+    got_sort_keys = [x['c'] for x in got_items]
+    # Boto3's "Binary" objects are sorted as if bytes are signed integers.
+    # This isn't the order that DynamoDB itself uses (byte 0 should be first,
+    # not byte -128). Sorting the byte array ".value" works.
+    assert sorted(got_sort_keys, key=lambda x: x.value) == got_sort_keys
+    assert sorted(sort_keys) == got_sort_keys
+def test_query_sort_order_number(test_table_sn):
+    # This is a list of numbers, sorted in correct order, and each suitable
+    # for accurate representation by Alternator's number type.
+    numbers = [
+        Decimal("-2e10"),
+        Decimal("-7.1e2"),
+        Decimal("-4.1"),
+        Decimal("-0.1"),
+        Decimal("-1e-5"),
+        Decimal("0"),
+        Decimal("2e-5"),
+        Decimal("0.15"),
+        Decimal("1"),
+        Decimal("1.00000000000000000000000001"),
+        Decimal("3.14159"),
+        Decimal("3.1415926535897932384626433832795028841"),
+        Decimal("31.4"),
+        Decimal("1.4e10"),
+    ]
+    # Insert these numbers, in random order, into one partition:
+    p = random_string()
+    items = [{'p': p, 'c': num} for num in random.sample(numbers, len(numbers))]
+    with test_table_sn.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    # Finally, verify that we get back exactly the same numbers (with identical
+    # precision), and in their original sorted order.
+    got_items = full_query(test_table_sn, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    got_sort_keys = [x['c'] for x in got_items]
+    assert got_sort_keys == numbers
+
+def test_query_filtering_attributes_equality(filled_test_table):
+    test_table, items = filled_test_table
+
+    query_filter = {
+        "attribute" : {
+            "AttributeValueList" : [ "xxxx" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx']) == multiset(got_items)
+
+    query_filter = {
+        "attribute" : {
+            "AttributeValueList" : [ "xxxx" ],
+            "ComparisonOperator": "EQ"
+        },
+        "another" : {
+            "AttributeValueList" : [ "yy" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
+
+# Test that FilterExpression works as expected
+@pytest.mark.xfail(reason="FilterExpression not supported yet")
+def test_query_filter_expression(filled_test_table):
+    test_table, items = filled_test_table
+
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, FilterExpression=Attr("attribute").eq("xxxx"))
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx']) == multiset(got_items)
+
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, FilterExpression=Attr("attribute").eq("xxxx") & Attr("another").eq("yy"))
+    print(got_items)
+    assert multiset([item for item in items if item['p'] == 'long' and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
+
+# QueryFilter can only contain non-key attributes in order to be compatible
+def test_query_filtering_key_equality(filled_test_table):
+    test_table, items = filled_test_table
+
+    with pytest.raises(ClientError, match='ValidationException'):
+        query_filter = {
+            "c" : {
+                "AttributeValueList" : [ "5" ],
+                "ComparisonOperator": "EQ"
+            }
+        }
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+        print(got_items)
+
+    with pytest.raises(ClientError, match='ValidationException'):
+        query_filter = {
+            "attribute" : {
+                "AttributeValueList" : [ "x" ],
+                "ComparisonOperator": "EQ"
+            },
+            "p" : {
+                "AttributeValueList" : [ "5" ],
+                "ComparisonOperator": "EQ"
+            }
+        }
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': ['long'], 'ComparisonOperator': 'EQ'}}, QueryFilter=query_filter)
+        print(got_items)
+
+# Test Query with the AttributesToGet parameter. Result should include the
+# selected attributes only - if one wants the key attributes as well, one
+# needs to select them explicitly. When no key attributes are selected,
+# some items may have *none* of the selected attributes. Those items are
+# returned too, as empty items - they are not outright missing.
+def test_query_attributes_to_get(dynamodb, test_table):
+    p = random_string()
+    items = [{'p': p, 'c': str(i), 'a': str(i*10), 'b': str(i*100) } for i in range(10)]
+    with test_table.batch_writer() as batch:
+        for item in items:
+            batch.put_item(item)
+    for wanted in [ ['a'],             # only non-key attributes
+                    ['c', 'a'],        # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}}, AttributesToGet=wanted)
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+# Test that in a table with both hash key and sort key, which keys we can
+# Query by: We can Query by the hash key, by a combination of both hash and
+# sort keys, but *cannot* query by just the sort key, and obviously not
+# by any non-key column.
+def test_query_which_key(test_table):
+    p = random_string()
+    c = random_string()
+    p2 = random_string()
+    c2 = random_string()
+    item1 = {'p': p, 'c': c}
+    item2 = {'p': p, 'c': c2}
+    item3 = {'p': p2, 'c': c}
+    for i in [item1, item2, item3]:
+        test_table.put_item(Item=i)
+    # Query by hash key only:
+    got_items = full_query(test_table, KeyConditions={'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'}})
+    expected_items = [item1, item2]
+    assert multiset(expected_items) == multiset(got_items)
+    # Query by hash key *and* sort key (this is basically a GetItem):
+    got_items = full_query(test_table, KeyConditions={
+        'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'},
+        'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+    })
+    expected_items = [item1]
+    assert multiset(expected_items) == multiset(got_items)
+    # Query by sort key alone is not allowed. DynamoDB reports:
+    # "Query condition missed key schema element: p".
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })
+    # Query by a non-key isn't allowed, for the same reason - that the
+    # actual hash key (p) is missing in the query:
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'z': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })
+    # If we try both p and a non-key we get a complaint that the sort
+    # key is missing: "Query condition missed key schema element: c"
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'},
+            'z': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })
+    # If we try p, c and another key, we get an error that
+    # "Conditions can be of length 1 or 2 only".
+    with pytest.raises(ClientError, match='ValidationException'):
+        full_query(test_table, KeyConditions={
+            'p': {'AttributeValueList': [p], 'ComparisonOperator': 'EQ'},
+            'c': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'},
+            'z': {'AttributeValueList': [c], 'ComparisonOperator': 'EQ'}
+        })

alternator-test/test_scan.py

@@ -0,0 +1,191 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the Scan operation
+
+import pytest
+from botocore.exceptions import ClientError
+from util import random_string, full_scan, multiset
+from boto3.dynamodb.conditions import Attr
+
+# Test that scanning works fine with/without pagination
+def test_scan_basic(filled_test_table):
+    test_table, items = filled_test_table
+    for limit in [None,1,2,4,33,50,100,9007,16*1024*1024]:
+        pos = None
+        got_items = []
+        while True:
+            if limit:
+                response = test_table.scan(Limit=limit, ExclusiveStartKey=pos) if pos else test_table.scan(Limit=limit)
+                assert len(response['Items']) <= limit
+            else:
+                response = test_table.scan(ExclusiveStartKey=pos) if pos else test_table.scan()
+            pos = response.get('LastEvaluatedKey', None)
+            got_items += response['Items']
+            if not pos:
+                break
+
+        assert len(items) == len(got_items)
+        assert multiset(items) == multiset(got_items)
+
+def test_scan_with_paginator(dynamodb, filled_test_table):
+    test_table, items = filled_test_table
+    paginator = dynamodb.meta.client.get_paginator('scan')
+
+    got_items = []
+    for page in paginator.paginate(TableName=test_table.name):
+        got_items += page['Items']
+
+    assert len(items) == len(got_items)
+    assert multiset(items) == multiset(got_items)
+
+    for page_size in [1, 17, 1234]:
+        got_items = []
+        for page in paginator.paginate(TableName=test_table.name, PaginationConfig={'PageSize': page_size}):
+            got_items += page['Items']
+
+    assert len(items) == len(got_items)
+    assert multiset(items) == multiset(got_items)
+
+# Although partitions are scanned in seemingly-random order, inside a
+# partition items must be returned by Scan sorted in sort-key order.
+# This test verifies this, for string sort key. We'll need separate
+# tests for the other sort-key types (number and binary)
+def test_scan_sort_order_string(filled_test_table):
+    test_table, items = filled_test_table
+    got_items = full_scan(test_table)
+    assert len(items) == len(got_items)
+    # Extract just the sort key ("c") from the partition "long"
+    items_long = [x['c'] for x in items if x['p'] == 'long']
+    got_items_long = [x['c'] for x in got_items if x['p'] == 'long']
+    # Verify that got_items_long are already sorted (in string order)
+    assert sorted(got_items_long) == got_items_long
+    # Verify that got_items_long are a sorted version of the expected items_long
+    assert sorted(items_long) == got_items_long
+
+# Test Scan with the AttributesToGet parameter. Result should include the
+# selected attributes only - if one wants the key attributes as well, one
+# needs to select them explicitly. When no key attributes are selected,
+# some items may have *none* of the selected attributes. Those items are
+# returned too, as empty items - they are not outright missing.
+def test_scan_attributes_to_get(dynamodb, filled_test_table):
+    table, items = filled_test_table
+    for wanted in [ ['another'],       # only non-key attributes (one item doesn't have it!)
+                    ['c', 'another'],  # a key attribute (sort key) and non-key
+                    ['p', 'c'],        # entire key
+                    ['nonexistent']    # none of the items have this attribute!
+                   ]:
+        print(wanted)
+        got_items = full_scan(table, AttributesToGet=wanted)
+        expected_items = [{k: x[k] for k in wanted if k in x} for x in items]
+        assert multiset(expected_items) == multiset(got_items)
+
+def test_scan_with_attribute_equality_filtering(dynamodb, filled_test_table):
+    table, items = filled_test_table
+    scan_filter = {
+        "attribute" : {
+            "AttributeValueList" : [ "xxxxx" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    got_items = full_scan(table, ScanFilter=scan_filter)
+    expected_items = [item for item in items if "attribute" in item.keys() and item["attribute"] == "xxxxx" ]
+    assert multiset(expected_items) == multiset(got_items)
+
+    scan_filter = {
+        "another" : {
+            "AttributeValueList" : [ "y" ],
+            "ComparisonOperator": "EQ"
+        },
+        "attribute" : {
+            "AttributeValueList" : [ "xxxxx" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    got_items = full_scan(table, ScanFilter=scan_filter)
+    expected_items = [item for item in items if "attribute" in item.keys() and item["attribute"] == "xxxxx" and item["another"] == "y" ]
+    assert multiset(expected_items) == multiset(got_items)
+
+# Test that FilterExpression works as expected
+@pytest.mark.xfail(reason="FilterExpression not supported yet")
+def test_scan_filter_expression(filled_test_table):
+    test_table, items = filled_test_table
+
+    got_items = full_scan(test_table, FilterExpression=Attr("attribute").eq("xxxx"))
+    print(got_items)
+    assert multiset([item for item in items if 'attribute' in item.keys() and item['attribute'] == 'xxxx']) == multiset(got_items)
+
+    got_items = full_scan(test_table, FilterExpression=Attr("attribute").eq("xxxx") & Attr("another").eq("yy"))
+    print(got_items)
+    assert multiset([item for item in items if 'attribute' in item.keys() and 'another' in item.keys() and item['attribute'] == 'xxxx' and item['another'] == 'yy']) == multiset(got_items)
+
+def test_scan_with_key_equality_filtering(dynamodb, filled_test_table):
+    table, items = filled_test_table
+    scan_filter_p = {
+        "p" : {
+            "AttributeValueList" : [ "7" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    scan_filter_c = {
+        "c" : {
+            "AttributeValueList" : [ "9" ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    scan_filter_p_and_attribute = {
+        "p" : {
+            "AttributeValueList" : [ "7" ],
+            "ComparisonOperator": "EQ"
+        },
+        "attribute" : {
+            "AttributeValueList" : [ "x"*7 ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+    scan_filter_c_and_another = {
+        "c" : {
+            "AttributeValueList" : [ "9" ],
+            "ComparisonOperator": "EQ"
+        },
+        "another" : {
+            "AttributeValueList" : [ "y"*16 ],
+            "ComparisonOperator": "EQ"
+        }
+    }
+
+    # Filtering on the hash key
+    got_items = full_scan(table, ScanFilter=scan_filter_p)
+    expected_items = [item for item in items if "p" in item.keys() and item["p"] == "7" ]
+    assert multiset(expected_items) == multiset(got_items)
+
+    # Filtering on the sort key
+    got_items = full_scan(table, ScanFilter=scan_filter_c)
+    expected_items = [item for item in items if "c" in item.keys() and item["c"] == "9"]
+    assert multiset(expected_items) == multiset(got_items)
+
+    # Filtering on the hash key and an attribute
+    got_items = full_scan(table, ScanFilter=scan_filter_p_and_attribute)
+    expected_items = [item for item in items if "p" in item.keys() and "another" in item.keys() and item["p"] == "7" and item["another"] == "y"*16]
+    assert multiset(expected_items) == multiset(got_items)
+
+    # Filtering on the sort key and an attribute
+    got_items = full_scan(table, ScanFilter=scan_filter_c_and_another)
+    expected_items = [item for item in items if "c" in item.keys() and "another" in item.keys() and item["c"] == "9" and item["another"] == "y"*16]
+    assert multiset(expected_items) == multiset(got_items)

alternator-test/test_table.py

@@ -0,0 +1,276 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for basic table operations: CreateTable, DeleteTable, ListTables.
+
+import pytest
+from botocore.exceptions import ClientError
+from util import list_tables, test_table_name, create_test_table, random_string
+
+# Utility function for create a table with a given name and some valid
+# schema.. This function initiates the table's creation, but doesn't
+# wait for the table to actually become ready.
+def create_table(dynamodb, name, BillingMode='PAY_PER_REQUEST', **kwargs):
+    return dynamodb.create_table(
+        TableName=name,
+        BillingMode=BillingMode,
+        KeySchema=[
+            {
+                'AttributeName': 'p',
+                'KeyType': 'HASH'
+            },
+            {
+                'AttributeName': 'c',
+                'KeyType': 'RANGE'
+            }
+        ],
+        AttributeDefinitions=[
+            {
+                'AttributeName': 'p',
+                'AttributeType': 'S'
+            },
+            {
+                'AttributeName': 'c',
+                'AttributeType': 'S'
+            },
+        ],
+        **kwargs
+    )
+
+# Utility function for creating a table with a given name, and then deleting
+# it immediately, waiting for these operations to complete. Since the wait
+# uses DescribeTable, this function requires all of CreateTable, DescribeTable
+# and DeleteTable to work correctly.
+# Note that in DynamoDB, table deletion takes a very long time, so tests
+# successfully using this function are very slow.
+def create_and_delete_table(dynamodb, name, **kwargs):
+    table = create_table(dynamodb, name, **kwargs)
+    table.meta.client.get_waiter('table_exists').wait(TableName=name)
+    table.delete()
+    table.meta.client.get_waiter('table_not_exists').wait(TableName=name)
+
+##############################################################################
+
+# Test creating a table, and then deleting it, waiting for each operation
+# to have completed before proceeding. Since the wait uses DescribeTable,
+# this tests requires all of CreateTable, DescribeTable and DeleteTable to
+# function properly in their basic use cases.
+# Unfortunately, this test is extremely slow with DynamoDB because deleting
+# a table is extremely slow until it really happens.
+def test_create_and_delete_table(dynamodb):
+    create_and_delete_table(dynamodb, 'alternator_test')
+
+# DynamoDB documentation specifies that table names must be 3-255 characters,
+# and match the regex [a-zA-Z0-9._-]+. Names not matching these rules should
+# be rejected, and no table be created.
+def test_create_table_unsupported_names(dynamodb):
+    from botocore.exceptions import ParamValidationError, ClientError
+    # Intererstingly, the boto library tests for names shorter than the
+    # minimum length (3 characters) immediately, and failure results in
+    # ParamValidationError. But the other invalid names are passed to
+    # DynamoDB, which returns an HTTP response code, which results in a
+    # CientError exception.
+    with pytest.raises(ParamValidationError):
+        create_table(dynamodb, 'n')
+    with pytest.raises(ParamValidationError):
+        create_table(dynamodb, 'nn')
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, 'n' * 256)
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, 'nyh@test')
+
+# On the other hand, names following the above rules should be accepted. Even
+# names which the Scylla rules forbid, such as a name starting with .
+def test_create_and_delete_table_non_scylla_name(dynamodb):
+    create_and_delete_table(dynamodb, '.alternator_test')
+
+# names with 255 characters are allowed in Dynamo, but they are not currently
+# supported in Scylla because we create a directory whose name is the table's
+# name followed by 33 bytes (underscore and UUID). So currently, we only
+# correctly support names with length up to 222.
+def test_create_and_delete_table_very_long_name(dynamodb):
+    # In the future, this should work:
+    #create_and_delete_table(dynamodb, 'n' * 255)
+    # But for now, only 222 works:
+    create_and_delete_table(dynamodb, 'n' * 222)
+    # We cannot test the following on DynamoDB because it will succeed
+    # (DynamoDB allows up to 255 bytes)
+    #with pytest.raises(ClientError, match='ValidationException'):
+    #   create_table(dynamodb, 'n' * 223)
+
+# Tests creating a table with an invalid schema should return a
+# ValidationException error.
+def test_create_table_invalid_schema(dynamodb):
+    # The name of the table "created" by this test shouldn't matter, the
+    # creation should not succeed anyway.
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'p', 'KeyType': 'HASH' },
+                { 'AttributeName': 'c', 'KeyType': 'HASH' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'p', 'AttributeType': 'S' },
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'p', 'AttributeType': 'S' },
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'c', 'KeyType': 'RANGE' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'c', 'KeyType': 'HASH' },
+                { 'AttributeName': 'p', 'KeyType': 'RANGE' },
+                { 'AttributeName': 'z', 'KeyType': 'RANGE' }
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'c', 'AttributeType': 'S' },
+                { 'AttributeName': 'p', 'AttributeType': 'S' },
+                { 'AttributeName': 'z', 'AttributeType': 'S' }
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'c', 'KeyType': 'HASH' },
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'z', 'AttributeType': 'S' }
+            ],
+        )
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(
+            TableName='name_doesnt_matter',
+            BillingMode='PAY_PER_REQUEST',
+            KeySchema=[
+                { 'AttributeName': 'k', 'KeyType': 'HASH' },
+            ],
+            AttributeDefinitions=[
+                { 'AttributeName': 'k', 'AttributeType': 'Q' }
+            ],
+        )
+
+# Test that trying to create a table that already exists fails in the
+# appropriate way (ResourceInUseException)
+def test_create_table_already_exists(dynamodb, test_table):
+    with pytest.raises(ClientError, match='ResourceInUseException'):
+        create_table(dynamodb, test_table.name)
+
+# Test that BillingMode error path works as expected - only the values
+# PROVISIONED or PAY_PER_REQUEST are allowed. The former requires
+# ProvisionedThroughput to be set, the latter forbids it.
+# If BillingMode is outright missing, it defaults (as original
+# DynamoDB did) to PROVISIONED so ProvisionedThroughput is allowed.
+def test_create_table_billing_mode_errors(dynamodb, test_table):
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(), BillingMode='unknown')
+    # billing mode is case-sensitive
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(), BillingMode='pay_per_request')
+    # PAY_PER_REQUEST cannot come with a ProvisionedThroughput:
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(),
+            BillingMode='PAY_PER_REQUEST', ProvisionedThroughput={'ReadCapacityUnits': 10, 'WriteCapacityUnits': 10})
+    # On the other hand, PROVISIONED requires ProvisionedThroughput:
+    # By the way, ProvisionedThroughput not only needs to appear, it must
+    # have both ReadCapacityUnits and WriteCapacityUnits - but we can't test
+    # this with boto3, because boto3 has its own verification that if
+    # ProvisionedThroughput is given, it must have the correct form.
+    with pytest.raises(ClientError, match='ValidationException'):
+        create_table(dynamodb, test_table_name(), BillingMode='PROVISIONED')
+    # If BillingMode is completely missing, it defaults to PROVISIONED, so
+    # ProvisionedThroughput is required
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.create_table(TableName=test_table_name(),
+            KeySchema=[{ 'AttributeName': 'p', 'KeyType': 'HASH' }],
+            AttributeDefinitions=[{ 'AttributeName': 'p', 'AttributeType': 'S' }])
+
+# Our first implementation had a special column name called "attrs" where
+# we stored a map for all non-key columns. If the user tried to name one
+# of the key columns with this same name, the result was a disaster - Scylla
+# goes into a bad state after trying to write data with two updates to same-
+# named columns.
+special_column_name1 = 'attrs'
+special_column_name2 = ':attrs'
+@pytest.fixture(scope="session")
+def test_table_special_column_name(dynamodb):
+    table = create_test_table(dynamodb,
+        KeySchema=[
+            { 'AttributeName': special_column_name1, 'KeyType': 'HASH' },
+            { 'AttributeName': special_column_name2, 'KeyType': 'RANGE' }
+        ],
+        AttributeDefinitions=[
+            { 'AttributeName': special_column_name1, 'AttributeType': 'S' },
+            { 'AttributeName': special_column_name2, 'AttributeType': 'S' },
+        ],
+    )
+    yield table
+    table.delete()
+@pytest.mark.xfail(reason="special attrs column not yet hidden correctly")
+def test_create_table_special_column_name(test_table_special_column_name):
+    s = random_string()
+    c = random_string()
+    h = random_string()
+    expected = {special_column_name1: s, special_column_name2: c, 'hello': h}
+    test_table_special_column_name.put_item(Item=expected)
+    got = test_table_special_column_name.get_item(Key={special_column_name1: s, special_column_name2: c}, ConsistentRead=True)['Item']
+    assert got == expected
+
+# Test that all tables we create are listed, and pagination works properly.
+# Note that the DyanamoDB setup we run this against may have hundreds of
+# other tables, for all we know. We just need to check that the tables we
+# created are indeed listed.
+def test_list_tables_paginated(dynamodb, test_table, test_table_s, test_table_b):
+    my_tables_set = {table.name for table in [test_table, test_table_s, test_table_b]}
+    for limit in [1, 2, 3, 4, 50, 100]:
+        print("testing limit={}".format(limit))
+        list_tables_set = set(list_tables(dynamodb, limit))
+        assert my_tables_set.issubset(list_tables_set)
+
+# Test that pagination limit is validated
+def test_list_tables_wrong_limit(dynamodb):
+    # lower limit (min. 1) is imposed by boto3 library checks
+    with pytest.raises(ClientError, match='ValidationException'):
+        dynamodb.meta.client.list_tables(Limit=101)

alternator-test/test_update_expression.py

@@ -0,0 +1,854 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Tests for the UpdateItem operations with an UpdateExpression parameter
+
+import random
+import string
+import pytest
+from botocore.exceptions import ClientError
+from decimal import Decimal
+from util import random_string
+
+# The simplest test of using UpdateExpression to set a top-level attribute,
+# instead of the older AttributeUpdates parameter.
+# Checks only one "SET" action in an UpdateExpression.
+def test_update_expression_set(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 4}
+
+# An empty UpdateExpression is NOT allowed, and generates a "The expression
+# can not be empty" error. This contrasts with an empty AttributeUpdates which
+# is allowed, and results in the creation of an empty item if it didn't exist
+# yet (see test_empty_update()).
+def test_update_expression_empty(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='')
+
+# A basic test with multiple SET actions in one expression
+def test_update_expression_set_multi(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET x = :val1, y = :val1',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'x': 4, 'y': 4}
+
+# SET can be used to copy an existing attribute to a new one
+def test_update_expression_set_copy(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET b = a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hello'}
+    # Copying an non-existing attribute generates an error
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c = z')
+    # It turns out that attributes to be copied are read before the SET
+    # starts to write, so "SET x = :val1, y = x" does not work...
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET x = :val1, y = x', ExpressionAttributeValues={':val1': 4})
+    # SET z=z does nothing if z exists, or fails if it doesn't
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hello'}
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET z = z')
+    # We can also use name references in either LHS or RHS of SET, e.g.,
+    # SET #one = #two. We need to also take the references used in the RHS
+    # when we want to complain about unused names in ExpressionAttributeNames.
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #one = #two',
+         ExpressionAttributeNames={'#one': 'c', '#two': 'a'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hello', 'c': 'hello'}
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #one = #two',
+             ExpressionAttributeNames={'#one': 'c', '#two': 'a', '#three': 'z'})
+
+# Test for read-before-write action where the value to be read is nested inside a - operator
+def test_update_expression_set_nested_copy(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #n = :two',
+         ExpressionAttributeNames={'#n': 'n'}, ExpressionAttributeValues={':two': 2})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #nn = :seven - #n',
+         ExpressionAttributeNames={'#nn': 'nn', '#n': 'n'}, ExpressionAttributeValues={':seven': 7})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'n': 2, 'nn': 5}
+
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #nnn = :nnn',
+         ExpressionAttributeNames={'#nnn': 'nnn'}, ExpressionAttributeValues={':nnn': [2,4]})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #nnnn = list_append(:val1, #nnn)',
+         ExpressionAttributeNames={'#nnnn': 'nnnn', '#nnn': 'nnn'}, ExpressionAttributeValues={':val1': [1,3]})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'n': 2, 'nn': 5, 'nnn': [2,4], 'nnnn': [1,3,2,4]}
+
+# Test for getting a key value with read-before-write
+def test_update_expression_set_key(test_table_sn):
+    p = random_string()
+    test_table_sn.update_item(Key={'p': p, 'c': 7});
+    test_table_sn.update_item(Key={'p': p, 'c': 7}, UpdateExpression='SET #n = #p',
+         ExpressionAttributeNames={'#n': 'n', '#p': 'p'})
+    test_table_sn.update_item(Key={'p': p, 'c': 7}, UpdateExpression='SET #nn = #c + #c',
+         ExpressionAttributeNames={'#nn': 'nn', '#c': 'c'})
+    assert test_table_sn.get_item(Key={'p': p, 'c': 7}, ConsistentRead=True)['Item'] == {'p': p, 'c': 7, 'n': p, 'nn': 14}
+
+# Simple test for the "REMOVE" action
+def test_update_expression_remove(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': 'hi'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello', 'b': 'hi'}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hi'}
+
+# Demonstrate that although all DynamoDB examples give UpdateExpression
+# action names in uppercase - e.g., "SET", it can actually be any case.
+def test_update_expression_action_case(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET b = :val1', ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 3}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='set b = :val1', ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 4}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='sEt b = :val1', ExpressionAttributeValues={':val1': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 5}
+
+# Demonstrate that whitespace is ignored in UpdateExpression parsing.
+def test_update_expression_action_whitespace(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='set b = :val1', ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 4}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='  set   b=:val1  ', ExpressionAttributeValues={':val1': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 5}
+
+# In UpdateExpression, the attribute name can appear directly in the expression
+# (without a "#placeholder" notation) only if it is a single "token" as
+# determined by DynamoDB's lexical analyzer rules: Such token is composed of
+# alphanumeric characters whose first character must be alphabetic. Other
+# names cause the parser to see multiple tokens, and produce syntax errors.
+def test_update_expression_name_token(test_table_s):
+    p = random_string()
+    # Alphanumeric names starting with an alphabetical character work
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET alnum = :val1', ExpressionAttributeValues={':val1': 1})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['alnum'] == 1
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET Alpha_Numeric_123 = :val1', ExpressionAttributeValues={':val1': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['Alpha_Numeric_123'] == 2
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET A123_ = :val1', ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['A123_'] == 3
+    # But alphanumeric names cannot start with underscore or digits.
+    # DynamoDB's lexical analyzer doesn't recognize them, and produces
+    # a ValidationException looking like:
+    #   Invalid UpdateExpression: Syntax error; token: "_", near: "SET _123"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET _123 = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET _abc = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET 123a = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET 123 = :val1', ExpressionAttributeValues={':val1': 3})
+    # Various other non-alpha-numeric characters, split a token and NOT allowed
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET hi-there = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET hi$there = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET "hithere" = :val1', ExpressionAttributeValues={':val1': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET !hithere = :val1', ExpressionAttributeValues={':val1': 3})
+
+    # In addition to the literal names, DynamoDB also allows references to any
+    # name, using the "#reference" syntax. It turns out the reference name is
+    # also a token following the rules as above, with one interesting point:
+    # since "#" already started the token, the next character may be any
+    # alphanumeric and doesn't need to be only alphabetical.
+    # Note that the reference target - the actual attribute name - can include
+    # absolutely any characters, and we use silly_name below as an example
+    silly_name = '3can include any character!.#='
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #Alpha_Numeric_123 = :val1', ExpressionAttributeValues={':val1': 4}, ExpressionAttributeNames={'#Alpha_Numeric_123': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 4
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #123a = :val1', ExpressionAttributeValues={':val1': 5}, ExpressionAttributeNames={'#123a': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 5
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #123 = :val1', ExpressionAttributeValues={':val1': 6}, ExpressionAttributeNames={'#123': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 6
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #_ = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#_': silly_name})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'][silly_name] == 7
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #hi-there = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#hi-there': silly_name})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #!hi = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#!hi': silly_name})
+    # Just a "#" is not enough as a token. Interestingly, DynamoDB will
+    # find the bad name in ExpressionAttributeNames before it actually tries
+    # to parse UpdateExpression, but we can verify the parse fails too by
+    # using a valid but irrelevant name in ExpressionAttributeNames:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET # = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#': silly_name})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET # = :val1', ExpressionAttributeValues={':val1': 7}, ExpressionAttributeNames={'#a': silly_name})
+
+    # There is also the value references, ":reference", for the right-hand
+    # side of an assignment. These have similar naming rules like "#reference".
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :Alpha_Numeric_123', ExpressionAttributeValues={':Alpha_Numeric_123': 8})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 8
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :123a', ExpressionAttributeValues={':123a': 9})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 9
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :123', ExpressionAttributeValues={':123': 10})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 10
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :_', ExpressionAttributeValues={':_': 11})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 11
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :hi!there', ExpressionAttributeValues={':hi!there': 12})
+    # Just a ":" is not enough as a token.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :', ExpressionAttributeValues={':': 7})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :', ExpressionAttributeValues={':a': 7})
+    # Trying to use a :reference on the left-hand side of an assignment will
+    # not work. In DynamoDB, it's a different type of token (and generates
+    # syntax error).
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET :a = :b', ExpressionAttributeValues={':a': 1, ':b': 2})
+
+# Multiple actions are allowed in one expression, but actions are divided
+# into clauses (SET, REMOVE, DELETE, ADD) and each of those can only appear
+# once.
+def test_update_expression_multi(test_table_s):
+    p = random_string()
+    # We can have two SET actions in one SET clause:
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1, b = :val2', ExpressionAttributeValues={':val1': 1, ':val2': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 1, 'b': 2}
+    # But not two SET clauses - we get error "The "SET" section can only be used once in an update expression"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1 SET b = :val2', ExpressionAttributeValues={':val1': 1, ':val2': 2})
+    # We can have a REMOVE and a SET clause (note no comma between clauses):
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a SET b = :val2', ExpressionAttributeValues={':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 3}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c = :val2 REMOVE b', ExpressionAttributeValues={':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'c': 3}
+    # The same clause (e.g., SET) cannot be used twice, even if interleaved with something else
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1 REMOVE a SET b = :val2', ExpressionAttributeValues={':val1': 1, ':val2': 2})
+
+# Trying to modify the same item twice in the same update is forbidden.
+# For "SET a=:v REMOVE a" DynamoDB says: "Invalid UpdateExpression: Two
+# document paths overlap with each other; must remove or rewrite one of
+# these paths; path one: [a], path two: [a]". 
+# It is actually good for Scylla that such updates are forbidden, because had
+# we allowed "SET a=:v REMOVE a" the result would be surprising - because data
+# wins over a delete with the same timestamp, so "a" would be set despite the
+# REMOVE command appearing later in the command line.
+def test_update_expression_multi_overlap(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+    # Neither "REMOVE a SET a = :v" nor "SET a = :v REMOVE a" are allowed:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a SET a = :v', ExpressionAttributeValues={':v': 'hi'})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :v REMOVE a', ExpressionAttributeValues={':v': 'yo'})
+    # It's also not allowed to set a twice in the same clause
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :v1, a = :v2', ExpressionAttributeValues={':v1': 'yo', ':v2': 'he'})
+    # Obviously, the paths are compared after the name references are evaluated
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #a1 = :v1, #a2 = :v2', ExpressionAttributeValues={':v1': 'yo', ':v2': 'he'}, ExpressionAttributeNames={'#a1': 'a', '#a2': 'a'})
+
+# The problem isn't just with identical paths - we can't modify two paths that
+# "overlap" in the sense that one is the ancestor of the other.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_multi_overlap_nested(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*overlap'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1, a.b = :val2',
+            ExpressionAttributeValues={':val1': {'b': 7}, ':val2': 'there'})
+    test_table_s.put_item(Item={'p': p, 'a': {'b': {'c': 2}}})
+    with pytest.raises(ClientError, match='ValidationException.*overlap'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.b = :val1, a.b.c = :val2',
+            ExpressionAttributeValues={':val1': 'hi', ':val2': 'there'})
+
+# In the previous test we saw that *modifying* the same item twice in the same
+# update is forbidden; But it is allowed to *read* an item in the same update
+# that also modifies it, and we check this here.
+def test_update_expression_multi_with_copy(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': 'hello'}
+    # "REMOVE a SET b = a" works: as noted in test_update_expression_set_copy()
+    # the value of 'a' is read before the actual REMOVE operation happens.
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a SET b = a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 'hello'}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c = b REMOVE b')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'c': 'hello'}
+
+
+# Test case where a :val1 is referenced, without being defined
+def test_update_expression_set_missing_value(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1',
+            ExpressionAttributeValues={':val2': 4})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1')
+
+# It is forbidden for ExpressionAttributeValues to contain values not used
+# by the expression. DynamoDB produces an error like: "Value provided in
+# ExpressionAttributeValues unused in expressions: keys: {:val1}"
+def test_update_expression_spurious_value(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a = :val1',
+            ExpressionAttributeValues={':val1': 3, ':val2': 4})
+
+# Test case where a #name is referenced, without being defined
+def test_update_expression_set_missing_name(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET #name = :val1',
+            ExpressionAttributeValues={':val2': 4},
+            ExpressionAttributeNames={'#wrongname': 'hello'})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET #name = :val1',
+            ExpressionAttributeValues={':val2': 4})
+
+# It is forbidden for ExpressionAttributeNames to contain names not used
+# by the expression. DynamoDB produces an error like: "Value provided in
+# ExpressionAttributeNames unused in expressions: keys: {#b}"
+def test_update_expression_spurious_name(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #a = :val1',
+            ExpressionAttributeNames={'#a': 'hello', '#b': 'hi'},
+            ExpressionAttributeValues={':val1': 3, ':val2': 4})
+
+# Test that the key attributes (hash key or sort key) cannot be modified
+# by an update
+def test_update_expression_cannot_modify_key(test_table):
+    p = random_string()
+    c = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='SET p = :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='SET c = :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='REMOVE p')
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='REMOVE c')
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='ADD p :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='ADD c :val1', ExpressionAttributeValues={':val1': 4})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='DELETE p :val1', ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    with pytest.raises(ClientError, match='ValidationException.*key'):
+        test_table.update_item(Key={'p': p, 'c': c},
+            UpdateExpression='DELETE c :val1', ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    # As sanity check, verify we *can* modify a non-key column
+    test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='SET a = :val1', ExpressionAttributeValues={':val1': 4})
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c, 'a': 4}
+    test_table.update_item(Key={'p': p, 'c': c}, UpdateExpression='REMOVE a')
+    assert test_table.get_item(Key={'p': p, 'c': c}, ConsistentRead=True)['Item'] == {'p': p, 'c': c}
+
+# Test that trying to start an expression with some nonsense like HELLO
+# instead of SET, REMOVE, ADD or DELETE, fails.
+def test_update_expression_non_existant_clause(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='HELLO b = :val1',
+            ExpressionAttributeValues={':val1': 4})
+
+# Test support for "SET a = :val1 + :val2", "SET a = :val1 - :val2"
+# Only exactly these combinations work - e.g., it's a syntax error to
+# try to add three. Trying to add a string fails.
+def test_update_expression_plus_basic(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 + :val2',
+        ExpressionAttributeValues={':val1': 4, ':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 7}
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 - :val2',
+        ExpressionAttributeValues={':val1': 5, ':val2': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': 3}
+    # Only the addition of exactly two values is supported!
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1 + :val2 + :val3',
+            ExpressionAttributeValues={':val1': 4, ':val2': 3, ':val3': 2})
+    # Only numeric values can be added - other things like strings or lists
+    # cannot be added, and we get an error like "Incorrect operand type for
+    # operator or function; operator or function: +, operand type: S".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1 + :val2',
+            ExpressionAttributeValues={':val1': 'dog', ':val2': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = :val1 + :val2',
+            ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['1', '2']})
+
+# While most of the Alternator code just saves high-precision numbers
+# unchanged, the "+" and "-" operations need to calculate with them, and
+# we should check the calculation isn't done with some lower-precision
+# representation, e.g., double
+def test_update_expression_plus_precision(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 + :val2',
+        ExpressionAttributeValues={':val1': Decimal("1"), ':val2': Decimal("10000000000000000000000")})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': Decimal("10000000000000000000001")}
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val2 - :val1',
+        ExpressionAttributeValues={':val1': Decimal("1"), ':val2': Decimal("10000000000000000000000")})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'b': Decimal("9999999999999999999999")}
+
+# Test support for "SET a = b + :val2" et al., i.e., a version of the
+# above test_update_expression_plus_basic with read before write.
+def test_update_expression_plus_rmw(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = a + :val1',
+        ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 5
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = :val1 + a',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 9
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = :val1 + a',
+        ExpressionAttributeValues={':val1': 1})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 10
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = b + a')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 19
+
+# Test the list_append() function in SET, for the most basic use case of
+# concatenating two value references. Because this is the first test of
+# functions in SET, we also test some generic features of how functions
+# are parsed.
+def test_update_expression_list_append_basic(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(:val1, :val2)',
+        ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': ['hi', 7]})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': [4, 'hello', 'hi', 7]}
+    # Unlike the operation name "SET", function names are case-sensitive!
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = LIST_APPEND(:val1, :val2)',
+            ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': ['hi', 7]})
+    # As usual, spaces are ignored by the parser
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(:val1, :val2)',
+        ExpressionAttributeValues={':val1': ['a'], ':val2': ['b']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['a', 'b']}
+    # The list_append function only allows two parameters. The parser can
+    # correctly parse fewer or more, but then an error is generated: "Invalid
+    # UpdateExpression: Incorrect number of operands for operator or function;
+    # operator or function: list_append, number of operands: 1".
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(:val1)',
+            ExpressionAttributeValues={':val1': ['a']})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(:val1, :val2, :val3)',
+            ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': [7], ':val3': ['a']})
+    # If list_append is used on value which isn't a list, we get
+    # error: "Invalid UpdateExpression: Incorrect operand type for operator
+    # or function; operator or function: list_append, operand type: S"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(:val1, :val2)',
+            ExpressionAttributeValues={':val1': [4, 'hello'], ':val2': 'hi'})
+
+# Additional list_append() tests, also using attribute paths as parameters
+# (i.e., read-modify-write).
+def test_update_expression_list_append(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = :val1',
+        ExpressionAttributeValues={':val1': ['hi', 2]})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] ==['hi', 2]
+    # Often, list_append is used to append items to a list attribute
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(a, :val1)',
+        ExpressionAttributeValues={':val1': [4, 'hello']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['hi', 2, 4, 'hello']
+    # But it can also be used to just concatenate in other ways:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(:val1, a)',
+        ExpressionAttributeValues={':val1': ['dog']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['dog', 'hi', 2, 4, 'hello']
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = list_append(a, :val1)',
+        ExpressionAttributeValues={':val1': ['cat']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == ['dog', 'hi', 2, 4, 'hello', 'cat']
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET c = list_append(a, b)')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['c'] == ['dog', 'hi', 2, 4, 'hello', 'dog', 'hi', 2, 4, 'hello', 'cat']
+    # As usual, #references are allowed instead of inline names:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET #name1 = list_append(#name2,:val1)',
+        ExpressionAttributeValues={':val1': [8]},
+        ExpressionAttributeNames={'#name1': 'a', '#name2': 'a'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['dog', 'hi', 2, 4, 'hello', 8]
+
+# Test the "if_not_exists" function in SET
+# The test also checks additional features of function-call parsing.
+def test_update_expression_if_not_exists(test_table_s):
+    p = random_string()
+    # Since attribute a doesn't exist, set it:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = if_not_exists(a, :val1)',
+        ExpressionAttributeValues={':val1': 2})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    # Now the attribute does exist, so set does nothing:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = if_not_exists(a, :val1)',
+        ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    # if_not_exists can also be used to check one attribute and set another,
+    # but note that if_not_exists(a, :val) means a's value if it exists,
+    # otherwise :val!
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(c, :val1)',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 4
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 2
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(c, :val1)',
+        ExpressionAttributeValues={':val1': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 5
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(a, :val1)',
+        ExpressionAttributeValues={':val1': 6})
+    # note how because 'a' does exist, its value is copied, overwriting b's
+    # value:
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 2
+    # The parser expects function parameters to be value references, paths,
+    # or nested call to functions. Other crap will cause syntax errors:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(non@sense, :val1)',
+            ExpressionAttributeValues={':val1': 6})
+    # if_not_exists() requires that the first parameter be a path. However,
+    # the parser doesn't know this, and allows for a function parameter
+    # also a value reference or a function call. If try one of these other
+    # things the parser succeeds, but we get a later error, looking like:
+    # "Invalid UpdateExpression: Operator or function requires a document
+    # path; operator or function: if_not_exists"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(if_not_exists(a, :val2), :val1)',
+            ExpressionAttributeValues={':val1': 6, ':val2': 3})
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(:val2, :val1)',
+            ExpressionAttributeValues={':val1': 6, ':val2': 3})
+    # Surprisingly, if the wrong argument is a :val value reference, the
+    # parser first tries to look it up in ExpressionAttributeValues (and
+    # fails if it's missing), before realizing any value reference would be
+    # wrong... So the following fails like the above does - but with a
+    # different error message (which we do not check here): "Invalid
+    # UpdateExpression: An expression attribute value used in expression
+    # is not defined; attribute value: :val2"
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET b = if_not_exists(:val2, :val1)',
+            ExpressionAttributeValues={':val1': 6})
+
+# When the expression parser parses a function call f(value, value), each
+# value may itself be a function call - ad infinitum. So expressions like
+# list_append(if_not_exists(a, :val1), :val2) are legal and so is deeper
+# nesting.
+@pytest.mark.xfail(reason="for unknown reason, DynamoDB does not allow nesting list_append")
+def test_update_expression_function_nesting(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(if_not_exists(a, :val1), :val2)',
+            ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['cat', 'dog']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['a', 'b', 'cat', 'dog']
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET a = list_append(if_not_exists(a, :val1), :val2)',
+            ExpressionAttributeValues={':val1': ['a', 'b'], ':val2': ['1', '2']})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == ['a', 'b', 'cat', 'dog', '1', '2']
+    # I don't understand why the following expression isn't accepted, but it
+    # isn't! It produces a "Invalid UpdateExpression: The function is not
+    # allowed to be used this way in an expression; function: list_append".
+    # I don't know how to explain it. In any case, the *parsing* works -
+    # this is not a syntax error - the failure is in some verification later.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(list_append(:val1, :val2), :val3)',
+                ExpressionAttributeValues={':val1': ['a'], ':val2': ['1'], ':val3': ['hi']})
+    # Ditto, the following passes the parser but fails some later check with
+    # the same error message as above.
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = list_append(list_append(list_append(:val1, :val2), :val3), :val4)',
+                ExpressionAttributeValues={':val1': ['a'], ':val2': ['1'], ':val3': ['hi'], ':val4': ['yo']})
+
+# Verify how in SET expressions, "+" (or "-") nests with functions.
+# We discover that f(x)+f(y) works but f(x+y) does NOT (results in a syntax
+# error on the "+"). This means that the parser has two separate rules:
+# 1.  set_action: SET path = value + value
+# 2.  value: VALREF | NAME | NAME (value, ...)
+def test_update_expression_function_plus_nesting(test_table_s):
+    p = random_string()
+    # As explained above, this - with "+" outside the expression, works:
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='SET b = if_not_exists(b, :val1)+:val2',
+            ExpressionAttributeValues={':val1': 2, ':val2': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['b'] == 5
+    # ...but this - with the "+" inside an expression parameter, is a syntax
+    # error:
+    with pytest.raises(ClientError, match='ValidationException'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET c = if_not_exists(c, :val1+:val2)',
+                ExpressionAttributeValues={':val1': 5, ':val2': 4})
+
+# This test tries to use an undefined function "f". This, obviously, fails,
+# but where we to actually print the error we would see "Invalid
+# UpdateExpression: Invalid function name; function: f". Not a syntax error.
+# This means that the parser accepts any alphanumeric name as a function
+# name, and only later use of this function fails because it's not one of
+# the supported file.
+def test_update_expression_unknown_function(test_table_s):
+    p = random_string()
+    with pytest.raises(ClientError, match='ValidationException.*f'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = f(b,c,d)')
+    with pytest.raises(ClientError, match='ValidationException.*f123_hi'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = f123_hi(b,c,d)')
+    # Just like unreferenced column names parsed by the DynamoDB parser,
+    # function names must also start with an alphabetic character. Trying
+    # to use _f as a function name will result with an actual syntax error,
+    # on the "_" token.
+    with pytest.raises(ClientError, match='ValidationException.*yntax error'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='SET a = _f(b,c,d)')
+
+# Test "ADD" operation for numbers
+def test_update_expression_add_numbers(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 3, 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': 4})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == 7
+    # If the value to be added isn't a number, we get an error like "Invalid
+    # UpdateExpression: Incorrect operand type for operator or function;
+    # operator: ADD, operand type: STRING".
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='ADD a :val1',
+            ExpressionAttributeValues={':val1': 'hello'})
+    # Similarly, if the attribute we're adding to isn't a number, we get an
+    # error like "An operand in the update expression has an incorrect data
+    # type"
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='ADD b :val1',
+            ExpressionAttributeValues={':val1': 1})
+
+# Test "ADD" operation for sets
+def test_update_expression_add_sets(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': set(['dog', 'cat', 'mouse']), 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': set(['pig'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog', 'cat', 'mouse', 'pig'])
+
+    # TODO: right now this test won't detect duplicated values in the returned result,
+    # because boto3 parses a set out of the returned JSON anyway. This check should leverage
+    # lower level API (if exists) to ensure that the JSON contains no duplicates
+    # in the set representation. It has been verified manually.
+    test_table_s.put_item(Item={'p': p, 'a': set(['beaver', 'lynx', 'coati']), 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='ADD a :val1',
+        ExpressionAttributeValues={':val1': set(['coati', 'beaver', 'badger'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['beaver', 'badger', 'lynx', 'coati'])
+
+    # The value to be added needs to be a set of the same type - it can't
+    # be a single element or anything else. If the value has the wrong type,
+    # we get an error like "Invalid UpdateExpression: Incorrect operand type
+    # for operator or function; operator: ADD, operand type: STRING".
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='ADD a :val1',
+            ExpressionAttributeValues={':val1': 'hello'})
+
+# Test "DELETE" operation for sets
+def test_update_expression_delete_sets(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': set(['dog', 'cat', 'mouse']), 'b': 'hi'})
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='DELETE a :val1',
+        ExpressionAttributeValues={':val1': set(['cat', 'mouse'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog'])
+    # Deleting an element not present in the set is not an error - it just
+    # does nothing
+    test_table_s.update_item(Key={'p': p},
+        UpdateExpression='DELETE a :val1',
+        ExpressionAttributeValues={':val1': set(['pig'])})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] == set(['dog'])
+    # The value to be deleted must be a set of the same type - it can't
+    # be a single element or anything else. If the value has the wrong type,
+    # we get an error like "Invalid UpdateExpression: Incorrect operand type
+    # for operator or function; operator: DELETE, operand type: STRING".
+    with pytest.raises(ClientError, match='ValidationException.*type'):
+        test_table_s.update_item(Key={'p': p},
+            UpdateExpression='DELETE a :val1',
+            ExpressionAttributeValues={':val1': 'hello'})
+
+######## Tests for paths and nested attribute updates:
+
+# A dot inside a name in ExpressionAttributeNames is a literal dot, and
+# results in a top-level attribute with an actual dot in its name - not
+# a nested attribute path.
+def test_update_expression_dot_in_name(test_table_s):
+    p = random_string()
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET #a = :val1',
+        ExpressionAttributeValues={':val1': 3},
+        ExpressionAttributeNames={'#a': 'a.b'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a.b': 3}
+
+# A basic test for direct update of a nested attribute: One of the top-level
+# attributes is itself a document, and we update only one of that document's
+# nested attributes.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_attribute_dot(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 4}, 'd': 5}
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c = :val1',
+        ExpressionAttributeValues={':val1': 7})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 7}, 'd': 5}
+    # Of course we can also add new nested attributes, not just modify
+    # existing ones:
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.d = :val1',
+        ExpressionAttributeValues={':val1': 3})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 7, 'd': 3}, 'd': 5}
+
+# Similar test, for a list: one of the top-level attributes is a list, we
+# can update one of its items.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_attribute_index(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': ['one', 'two', 'three']})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[1] = :val1',
+        ExpressionAttributeValues={':val1': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['one', 'hello', 'three']}
+
+# Test that just like happens in top-level attributes, also in nested
+# attributes, setting them replaces the old value - potentially an entire
+# nested document, by the whole value (which may have a different type)
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_different_type(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': {'one': 1, 'two': 2}}})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c = :val1',
+        ExpressionAttributeValues={':val1': 7})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': {'b': 3, 'c': 7}}
+
+# Yet another test of a nested attribute update. This one uses deeper
+# level of nesting (dots and indexes), adds #name references to the mix.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_deep(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': ['hi', {'x': {'y': [3, 5, 7]}}]}})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c[1].#name.y[1] = :val1',
+        ExpressionAttributeValues={':val1': 9}, ExpressionAttributeNames={'#name': 'x'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] ==  {'b': 3, 'c': ['hi', {'x': {'y': [3, 9, 7]}}]}
+    # A deep path can also appear on the right-hand-side of an assignment
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.z = a.c[1].#name.y[1]',
+        ExpressionAttributeNames={'#name': 'x'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a']['z'] ==  9
+
+# A REMOVE operation can be used to remove nested attributes, and also
+# individual list items.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_update_expression_nested_remove(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': {'b': 3, 'c': ['hi', {'x': {'y': [3, 5, 7]}, 'q': 2}]}})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='REMOVE a.c[1].x.y[1], a.c[1].q')
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item']['a'] ==  {'b': 3, 'c': ['hi', {'x': {'y': [3, 7]}}]}
+
+# The DynamoDB documentation specifies: "When you use SET to update a list
+# element, the contents of that element are replaced with the new data that
+# you specify. If the element does not already exist, SET will append the
+# new element at the end of the list."
+# So if we take a three-element list a[7], and set a[7], the new element
+# will be put at the end of the list, not position 7 specifically.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_nested_attribute_update_array_out_of_bounds(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': ['one', 'two', 'three']})
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[7] = :val1',
+        ExpressionAttributeValues={':val1': 'hello'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['one', 'two', 'three', 'hello']}
+    # The DynamoDB documentation also says: "If you add multiple elements
+    # in a single SET operation, the elements are sorted in order by element
+    # number.
+    test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[84] = :val1, a[37] = :val2',
+        ExpressionAttributeValues={':val1': 'a1', ':val2': 'a2'})
+    assert test_table_s.get_item(Key={'p': p}, ConsistentRead=True)['Item'] == {'p': p, 'a': ['one', 'two', 'three', 'hello', 'a2', 'a1']}
+
+# Test what happens if we try to write to a.b, which would only make sense if
+# a were a nested document, but a doesn't exist, or exists and is NOT a nested
+# document but rather a scalar or list or something.
+# DynamoDB actually detects this case and prints an error:
+#   ClientError: An error occurred (ValidationException) when calling the
+#   UpdateItem operation: The document path provided in the update expression
+#   is invalid for update
+# Because Scylla doesn't read before write, it cannot detect this as an error,
+# so we'll probably want to allow for that possibility as well.
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_nested_attribute_update_bad_path_dot(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello', 'b': ['hi']})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a.c = :val1',
+            ExpressionAttributeValues={':val1': 7})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET b.c = :val1',
+            ExpressionAttributeValues={':val1': 7})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET c.c = :val1',
+            ExpressionAttributeValues={':val1': 7})
+
+
+# Similarly for other types of bad paths - using [0] on something which
+# isn't an array,
+@pytest.mark.xfail(reason="nested updates not yet implemented")
+def test_nested_attribute_update_bad_path_array(test_table_s):
+    p = random_string()
+    test_table_s.put_item(Item={'p': p, 'a': 'hello'})
+    with pytest.raises(ClientError, match='ValidationException.*path'):
+        test_table_s.update_item(Key={'p': p}, UpdateExpression='SET a[0] = :val1',
+            ExpressionAttributeValues={':val1': 7})

alternator-test/util.py

@@ -0,0 +1,121 @@
+# Copyright 2019 ScyllaDB
+#
+# This file is part of Scylla.
+#
+# Scylla is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Scylla is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+
+# Various utility functions which are useful for multiple tests
+
+import string
+import random
+import collections
+import time
+
+def random_string(length=10, chars=string.ascii_uppercase + string.digits):
+    return ''.join(random.choice(chars) for x in range(length))
+
+def random_bytes(length=10):
+    return bytearray(random.getrandbits(8) for _ in range(length))
+
+# Utility functions for scan and query into an array of items:
+# TODO: add to full_scan and full_query by default ConsistentRead=True, as
+# it's not useful for tests without it!
+def full_scan(table, **kwargs):
+    response = table.scan(**kwargs)
+    items = response['Items']
+    while 'LastEvaluatedKey' in response:
+        response = table.scan(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
+        items.extend(response['Items'])
+    return items
+
+# Utility function for fetching the entire results of a query into an array of items
+def full_query(table, **kwargs):
+    response = table.query(**kwargs)
+    items = response['Items']
+    while 'LastEvaluatedKey' in response:
+        response = table.query(ExclusiveStartKey=response['LastEvaluatedKey'], **kwargs)
+        items.extend(response['Items'])
+    return items
+
+# To compare two lists of items (each is a dict) without regard for order,
+# "==" is not good enough because it will fail if the order is different.
+# The following function, multiset() converts the list into a multiset
+# (set with duplicates) where order doesn't matter, so the multisets can
+# be compared.
+
+def freeze(item):
+    if isinstance(item, dict):
+        return frozenset((key, freeze(value)) for key, value in item.items())
+    elif isinstance(item, list):
+        return tuple(freeze(value) for value in item)
+    return item
+
+def multiset(items):
+    return collections.Counter([freeze(item) for item in items])
+
+
+test_table_prefix = 'alternator_test_'
+def test_table_name():
+    current_ms = int(round(time.time() * 1000))
+    # In the off chance that test_table_name() is called twice in the same millisecond...
+    if test_table_name.last_ms >= current_ms:
+        current_ms = test_table_name.last_ms + 1
+    test_table_name.last_ms = current_ms
+    return test_table_prefix + str(current_ms)
+test_table_name.last_ms = 0
+
+def create_test_table(dynamodb, **kwargs):
+    name = test_table_name()
+    print("fixture creating new table {}".format(name))
+    table = dynamodb.create_table(TableName=name,
+        BillingMode='PAY_PER_REQUEST', **kwargs)
+    waiter = table.meta.client.get_waiter('table_exists')
+    # recheck every second instead of the default, lower, frequency. This can
+    # save a few seconds on AWS with its very slow table creation, but can
+    # more on tests on Scylla with its faster table creation turnaround.
+    waiter.config.delay = 1
+    waiter.config.max_attempts = 200
+    waiter.wait(TableName=name)
+    return table
+
+# DynamoDB's ListTables request returns up to a single page of table names
+# (e.g., up to 100) and it is up to the caller to call it again and again
+# to get the next page. This is a utility function which calls it repeatedly
+# as much as necessary to get the entire list.
+# We deliberately return a list and not a set, because we want the caller
+# to be able to recognize bugs in ListTables which causes the same table
+# to be returned twice.
+def list_tables(dynamodb, limit=100):
+    ret = []
+    pos = None
+    while True:
+        if pos:
+            page = dynamodb.meta.client.list_tables(Limit=limit, ExclusiveStartTableName=pos);
+        else:
+            page = dynamodb.meta.client.list_tables(Limit=limit);
+        results = page.get('TableNames', None)
+        assert(results)
+        ret = ret + results
+        newpos = page.get('LastEvaluatedTableName', None)
+        if not newpos:
+            break;
+        # It doesn't make sense for Dynamo to tell us we need more pages, but
+        # not send anything in *this* page!
+        assert len(results) > 0
+        assert newpos != pos
+        # Note that we only checked that we got back tables, not that we got
+        # any new tables not already in ret. So a buggy implementation might
+        # still cause an endless loop getting the same tables again and again.
+        pos = newpos
+    return ret

alternator/auth.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "alternator/error.hh"
@@ -11,6 +24,7 @@
 #include <string>
 #include <string_view>
 #include <gnutls/crypto.h>
+#include <seastar/util/defer.hh>
 #include "hashers.hh"
 #include "bytes.hh"
 #include "alternator/auth.hh"
@@ -18,12 +32,8 @@
 #include "auth/common.hh"
 #include "auth/password_authenticator.hh"
 #include "auth/roles-metadata.hh"
-#include "service/storage_proxy.hh"
-#include "alternator/executor.hh"
-#include "cql3/selection/selection.hh"
-#include "query-result-set.hh"
-#include "cql3/result_set.hh"
-#include <seastar/core/coroutine.hh>
+#include "cql3/query_processor.hh"
+#include "cql3/untyped_result_set.hh"
 
 namespace alternator {
 
@@ -52,21 +62,12 @@ static std::string apply_sha256(std::string_view msg) {
     return to_hex(hasher.finalize());
 }
 
-static std::string apply_sha256(const std::vector<temporary_buffer<char>>& msg) {
-    sha256_hasher hasher;
-    for (const temporary_buffer<char>& buf : msg) {
-        hasher.update(buf.get(), buf.size());
-    }
-    return to_hex(hasher.finalize());
-}
-
 static std::string format_time_point(db_clock::time_point tp) {
     time_t time_point_repr = db_clock::to_time_t(tp);
     std::string time_point_str;
     time_point_str.resize(17);
-    ::tm time_buf;
     // strftime prints the terminating null character as well
-    std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", ::gmtime_r(&time_point_repr, &time_buf));
+    std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", std::gmtime(&time_point_repr));
     time_point_str.resize(16);
     return time_point_str;
 }
@@ -76,12 +77,12 @@ void check_expiry(std::string_view signature_date) {
     std::string expiration_str = format_time_point(db_clock::now() - 15min);
     std::string validity_str = format_time_point(db_clock::now() + 15min);
     if (signature_date < expiration_str) {
-        throw api_error::invalid_signature(
+        throw api_error("InvalidSignatureException",
                 fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
                 signature_date, expiration_str));
     }
     if (signature_date > validity_str) {
-        throw api_error::invalid_signature(
+        throw api_error("InvalidSignatureException",
                 fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
                 signature_date, validity_str));
     }
@@ -89,16 +90,16 @@ void check_expiry(std::string_view signature_date) {
 
 std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
         std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
-        const std::vector<temporary_buffer<char>>& body_content, std::string_view region, std::string_view service, std::string_view query_string) {
+        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string) {
     auto amz_date_it = signed_headers_map.find("x-amz-date");
     if (amz_date_it == signed_headers_map.end()) {
-        throw api_error::invalid_signature("X-Amz-Date header is mandatory for signature verification");
+        throw api_error("InvalidSignatureException", "X-Amz-Date header is mandatory for signature verification");
     }
     std::string_view amz_date = amz_date_it->second;
     check_expiry(amz_date);
     std::string_view datestamp = amz_date.substr(0, 8);
     if (datestamp != orig_datestamp) {
-        throw api_error::invalid_signature(
+        throw api_error("InvalidSignatureException",
                 format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
                         orig_datestamp, datestamp));
     }
@@ -122,37 +123,24 @@ std::string get_signature(std::string_view access_key_id, std::string_view secre
     return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
 }
 
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username) {
-    schema_ptr schema = proxy.data_dictionary().find_schema("system_auth", "roles");
-    partition_key pk = partition_key::from_single_value(*schema, utf8_type->decompose(username));
-    dht::partition_range_vector partition_ranges{dht::partition_range(dht::decorate_key(*schema, pk))};
-    std::vector<query::clustering_range> bounds{query::clustering_range::make_open_ended_both_sides()};
-    const column_definition* salted_hash_col = schema->get_column_definition(bytes("salted_hash"));
-    if (!salted_hash_col) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("Credentials cannot be fetched for: {}", username)));
-    }
-    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col});
-    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id}, selection->get_query_options());
-    auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice,
-            proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
+future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username) {
+    static const sstring query = format("SELECT salted_hash FROM {} WHERE {} = ?",
+            auth::meta::roles_table::qualified_name(), auth::meta::roles_table::role_col_name);
+
     auto cl = auth::password_authenticator::consistency_for_user(username);
-
-    service::client_state client_state{service::client_state::internal_tag()};
-    service::storage_proxy::coordinator_query_result qr = co_await proxy.query(schema, std::move(command), std::move(partition_ranges), cl,
-            service::storage_proxy::coordinator_query_options(executor::default_timeout(), empty_service_permit(), client_state));
-
-    cql3::selection::result_set_builder builder(*selection, gc_clock::now(), cql_serialization_format::latest());
-    query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
-
-    auto result_set = builder.build();
-    if (result_set->empty()) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("User not found: {}", username)));
-    }
-    const bytes_opt& salted_hash = result_set->rows().front().front(); // We only asked for 1 row and 1 column
-    if (!salted_hash) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("No password found for user: {}", username)));
-    }
-    co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
+    auto timeout = auth::internal_distributed_timeout_config();
+    return qp.process(query, cl, timeout, {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
+        auto res = f.get0();
+        auto salted_hash = std::optional<sstring>();
+        if (res->empty()) {
+            throw api_error("UnrecognizedClientException", fmt::format("User not found: {}", username));
+        }
+        salted_hash = res->one().get_opt<sstring>("salted_hash");
+        if (!salted_hash) {
+            throw api_error("UnrecognizedClientException", fmt::format("No password found for user: {}", username));
+        }
+        return make_ready_future<std::string>(*salted_hash);
+    });
 }
 
 }

alternator/auth.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -14,20 +27,20 @@
 #include "gc_clock.hh"
 #include "utils/loading_cache.hh"
 
-namespace service {
-class storage_proxy;
+namespace cql3 {
+class query_processor;
 }
 
 namespace alternator {
 
 using hmac_sha256_digest = std::array<char, 32>;
 
-using key_cache = utils::loading_cache<std::string, std::string, 1>;
+using key_cache = utils::loading_cache<std::string, std::string>;
 
 std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
         std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
-        const std::vector<temporary_buffer<char>>& body_content, std::string_view region, std::string_view service, std::string_view query_string);
+        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string);
 
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username);
+future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username);
 
 }

alternator/base64.cc

@@ -0,0 +1,111 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+// The DynamoAPI dictates that "binary" (a.k.a. "bytes" or "blob") values
+// be encoded in the JSON API as base64-encoded strings. This is code to
+// convert byte arrays to base64-encoded strings, and back.
+
+#include "base64.hh"
+
+#include <ctype.h>
+
+
+// Arrays for quickly converting to and from an integer between 0 and 63,
+// and the character used in base64 encoding to represent it.
+static class base64_chars {
+public:
+    static constexpr const char* to =
+            "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+    int8_t from[255];
+    base64_chars() {
+        static_assert(strlen(to) == 64);
+        for (int i = 0; i < 255; i++) {
+            from[i] = 255; // signal invalid character
+        }
+        for (int i = 0; i < 64; i++) {
+            from[(unsigned) to[i]] = i;
+        }
+    }
+} base64_chars;
+
+std::string base64_encode(bytes_view in) {
+    std::string ret;
+    ret.reserve(((4 * in.size() / 3) + 3) & ~3);
+    int i = 0;
+    unsigned char chunk3[3]; // chunk of input
+    for (auto byte : in) {
+        chunk3[i++] = byte;
+        if (i == 3) {
+            ret += base64_chars.to[ (chunk3[0] & 0xfc) >> 2 ];
+            ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
+            ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
+            ret += base64_chars.to[ chunk3[2] & 0x3f ];
+            i = 0;
+        }
+    }
+    if (i) {
+        // i can be 1 or 2.
+        for(int j = i; j < 3; j++)
+            chunk3[j] = '\0';
+        ret += base64_chars.to[ ( chunk3[0] & 0xfc) >> 2 ];
+        ret += base64_chars.to[ ((chunk3[0] & 0x03) << 4) + ((chunk3[1] & 0xf0) >> 4) ];
+        if (i == 2) {
+            ret += base64_chars.to[ ((chunk3[1] & 0x0f) << 2) + ((chunk3[2] & 0xc0) >> 6) ];
+        } else {
+            ret += '=';
+        }
+        ret += '=';
+    }
+    return ret;
+}
+
+bytes base64_decode(std::string_view in) {
+    int i = 0;
+    int8_t chunk4[4]; // chunk of input, each byte converted to 0..63;
+    std::string ret;
+    ret.reserve(in.size() * 3 / 4);
+    for (unsigned char c : in) {
+        uint8_t dc = base64_chars.from[c];
+        if (dc == 255) {
+            // Any unexpected character, include the "=" character usually
+            // used for padding, signals the end of the decode.
+            break;
+        }
+        chunk4[i++] = dc;
+        if (i == 4) {
+            ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
+            ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
+            ret += ((chunk4[2] & 0x3) << 6) + chunk4[3];
+            i = 0;
+        }
+    }
+    if (i) {
+        // i can be 2 or 3, meaning 1 or 2 more output characters
+        if (i>=2)
+            ret += (chunk4[0] << 2) + ((chunk4[1] & 0x30) >> 4);
+        if (i==3)
+            ret += ((chunk4[1] & 0xf) << 4) + ((chunk4[2] & 0x3c) >> 2);
+    }
+    // FIXME: This copy is sad. The problem is we need back "bytes"
+    // but "bytes" doesn't have efficient append and std::string.
+    // To fix this we need to use bytes' "uninitialized" feature.
+    return bytes(ret.begin(), ret.end());
+}

alternator/base64.hh

@@ -0,0 +1,34 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include <string_view>
+#include "bytes.hh"
+#include "rjson.hh"
+
+std::string base64_encode(bytes_view);
+
+bytes base64_decode(std::string_view);
+
+inline bytes base64_decode(const rjson::value& v) {
+  return base64_decode(std::string_view(v.GetString(), v.GetStringLength()));
+}

alternator/conditions.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <list>
@@ -13,16 +26,9 @@
 #include "alternator/error.hh"
 #include "cql3/constants.hh"
 #include <unordered_map>
-#include "utils/rjson.hh"
+#include "rjson.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
-#include <stdexcept>
-#include <boost/algorithm/cxx11/all_of.hpp>
-#include <boost/algorithm/cxx11/any_of.hpp>
-#include "utils/overloaded_functor.hh"
-
-#include "expressions.hh"
+#include "base64.hh"
 
 namespace alternator {
 
@@ -41,20 +47,61 @@ comparison_operator_type get_comparison_operator(const rjson::value& comparison_
             {"NOT_NULL", comparison_operator_type::NOT_NULL},
             {"BETWEEN", comparison_operator_type::BETWEEN},
             {"BEGINS_WITH", comparison_operator_type::BEGINS_WITH},
-            {"CONTAINS", comparison_operator_type::CONTAINS},
-            {"NOT_CONTAINS", comparison_operator_type::NOT_CONTAINS},
-    };
+    }; //TODO: CONTAINS
     if (!comparison_operator.IsString()) {
-        throw api_error::validation(format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
+        throw api_error("ValidationException", format("Invalid comparison operator definition {}", rjson::print(comparison_operator)));
     }
     std::string op = comparison_operator.GetString();
     auto it = ops.find(op);
     if (it == ops.end()) {
-        throw api_error::validation(format("Unsupported comparison operator {}", op));
+        throw api_error("ValidationException", format("Unsupported comparison operator {}", op));
     }
     return it->second;
 }
 
+static ::shared_ptr<cql3::restrictions::single_column_restriction::contains> make_map_element_restriction(const column_definition& cdef, std::string_view key, const rjson::value& value) {
+    bytes raw_key = utf8_type->from_string(sstring_view(key.data(), key.size()));
+    auto key_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_key)));
+    bytes raw_value = serialize_item(value);
+    auto entry_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_value)));
+    return make_shared<cql3::restrictions::single_column_restriction::contains>(cdef, std::move(key_value), std::move(entry_value));
+}
+
+static ::shared_ptr<cql3::restrictions::single_column_restriction::EQ> make_key_eq_restriction(const column_definition& cdef, const rjson::value& value) {
+    bytes raw_value = get_key_from_typed_value(value, cdef, type_to_string(cdef.type));
+    auto restriction_value = ::make_shared<cql3::constants::value>(cql3::raw_value::make_value(std::move(raw_value)));
+    return make_shared<cql3::restrictions::single_column_restriction::EQ>(cdef, std::move(restriction_value));
+}
+
+::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter) {
+    clogger.trace("Getting filtering restrictions for: {}", rjson::print(query_filter));
+    auto filtering_restrictions = ::make_shared<cql3::restrictions::statement_restrictions>(schema, true);
+    for (auto it = query_filter.MemberBegin(); it != query_filter.MemberEnd(); ++it) {
+        std::string_view column_name(it->name.GetString(), it->name.GetStringLength());
+        const rjson::value& condition = it->value;
+
+        const rjson::value& comp_definition = rjson::get(condition, "ComparisonOperator");
+        const rjson::value& attr_list = rjson::get(condition, "AttributeValueList");
+        comparison_operator_type op = get_comparison_operator(comp_definition);
+
+        if (op != comparison_operator_type::EQ) {
+            throw api_error("ValidationException", "Filtering is currently implemented for EQ operator only");
+        }
+        if (attr_list.Size() != 1) {
+            throw api_error("ValidationException", format("EQ restriction needs exactly 1 attribute value: {}", rjson::print(attr_list)));
+        }
+        if (const column_definition* cdef = schema->get_column_definition(to_bytes(column_name.data()))) {
+            // Primary key restriction
+            filtering_restrictions->add_restriction(make_key_eq_restriction(*cdef, attr_list[0]), false, true);
+        } else {
+            // Regular column restriction
+            filtering_restrictions->add_restriction(make_map_element_restriction(attrs_col, column_name, attr_list[0]), false, true);
+        }
+
+    }
+    return filtering_restrictions;
+}
+
 namespace {
 
 struct size_check {
@@ -86,209 +133,61 @@ struct nonempty : public size_check {
 
 // Check that array has the expected number of elements
 static void verify_operand_count(const rjson::value* array, const size_check& expected, const rjson::value& op) {
-    if (!array && expected(0)) {
-        // If expected() allows an empty AttributeValueList, it is also fine
-        // that it is missing.
-        return;
-    }
     if (!array || !array->IsArray()) {
-        throw api_error::validation("With ComparisonOperator, AttributeValueList must be given and an array");
+        throw api_error("ValidationException", "With ComparisonOperator, AttributeValueList must be given and an array");
     }
     if (!expected(array->Size())) {
-        throw api_error::validation(
+        throw api_error("ValidationException",
                         format("{} operator requires AttributeValueList {}, instead found list size {}",
                                op, expected.what(), array->Size()));
     }
 }
 
-struct rjson_engaged_ptr_comp {
-    bool operator()(const rjson::value* p1, const rjson::value* p2) const {
-        return rjson::single_value_comp()(*p1, *p2);
-    }
-};
-
-// It's not enough to compare underlying JSON objects when comparing sets,
-// as internally they're stored in an array, and the order of elements is
-// not important in set equality. See issue #5021
-static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2) {
-    if (!set1.IsArray() || !set2.IsArray() || set1.Size() != set2.Size()) {
-        return false;
-    }
-    std::set<const rjson::value*, rjson_engaged_ptr_comp> set1_raw;
-    for (auto it = set1.Begin(); it != set1.End(); ++it) {
-        set1_raw.insert(&*it);
-    }
-    for (const auto& a : set2.GetArray()) {
-        if (!set1_raw.contains(&a)) {
-            return false;
-        }
-    }
-    return true;
-}
-// Moreover, the JSON being compared can be a nested document with outer
-// layers of lists and maps and some inner set - and we need to get to that
-// inner set to compare it correctly with check_EQ_for_sets() (issue #8514).
-static bool check_EQ(const rjson::value* v1, const rjson::value& v2);
-static bool check_EQ_for_lists(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsArray() || !list2.IsArray() || list1.Size() != list2.Size()) {
-        return false;
-    }
-    auto it1 = list1.Begin();
-    auto it2 = list2.Begin();
-    while (it1 != list1.End()) {
-        // Note: Alternator limits an item's depth (rjson::parse() limits
-        // it to around 37 levels), so this recursion is safe.
-        if (!check_EQ(&*it1, *it2)) {
-            return false;
-        }
-        ++it1;
-        ++it2;
-    }
-    return true;
-}
-static bool check_EQ_for_maps(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsObject() || !list2.IsObject() || list1.MemberCount() != list2.MemberCount()) {
-        return false;
-    }
-    for (auto it1 = list1.MemberBegin(); it1 != list1.MemberEnd(); ++it1) {
-        auto it2 = list2.FindMember(it1->name);
-        if (it2 == list2.MemberEnd() || !check_EQ(&it1->value, it2->value)) {
-            return false;
-        }
-    }
-    return true;
-}
-
 // Check if two JSON-encoded values match with the EQ relation
 static bool check_EQ(const rjson::value* v1, const rjson::value& v2) {
-    if (v1 && v1->IsObject() && v1->MemberCount() == 1 && v2.IsObject() && v2.MemberCount() == 1) {
-        auto it1 = v1->MemberBegin();
-        auto it2 = v2.MemberBegin();
-        if (it1->name != it2->name) {
-            return false;
-        }
-        if (it1->name == "SS" || it1->name == "NS" || it1->name == "BS") {
-            return check_EQ_for_sets(it1->value, it2->value);
-        } else if(it1->name == "L") {
-            return check_EQ_for_lists(it1->value, it2->value);
-        } else if(it1->name == "M") {
-            return check_EQ_for_maps(it1->value, it2->value);
-        } else {
-            // Other, non-nested types (number, string, etc.) can be compared
-            // literally, comparing their JSON representation.
-            return it1->value == it2->value;
-        }
-    } else {
-        // If v1 and/or v2 are missing (IsNull()) the result should be false.
-        // In the unlikely case that the object is malformed (issue #8070),
-        // let's also return false.
-        return false;
-    }
+    return v1 && *v1 == v2;
 }
 
 // Check if two JSON-encoded values match with the NE relation
 static bool check_NE(const rjson::value* v1, const rjson::value& v2) {
-    return !check_EQ(v1, v2);
+    return !v1 || *v1 != v2; // null is unequal to anything.
 }
 
 // Check if two JSON-encoded values match with the BEGINS_WITH relation
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
-                       bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
-        if (v1_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v1->MemberBegin()->name != "S" && v1->MemberBegin()->name != "B") {
-        if (v1_from_query) {
-            throw api_error::validation(format("begins_with supports only string or binary type, got: {}", *v1));
-        } else {
-            bad = true;
-        }
-    }
+static bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2) {
+    // BEGINS_WITH requires that its single operand (v2) be a string or
+    // binary - otherwise it's a validation error. However, problems with
+    // the stored attribute (v1) will just return false (no match).
     if (!v2.IsObject() || v2.MemberCount() != 1) {
-        if (v2_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
-        if (v2_from_query) {
-            throw api_error::validation(format("begins_with() supports only string or binary type, got: {}", v2));
-        } else {
-            bad = true;
-        }
+        throw api_error("ValidationException", format("BEGINS_WITH operator encountered malformed AttributeValue: {}", v2));
     }
-    if (bad) {
+    auto it2 = v2.MemberBegin();
+    if (it2->name != "S" && it2->name != "B") {
+        throw api_error("ValidationException", format("BEGINS_WITH operator requires String or Binary in AttributeValue, got {}", it2->name));
+    }
+
+
+    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
         return false;
     }
     auto it1 = v1->MemberBegin();
-    auto it2 = v2.MemberBegin();
     if (it1->name != it2->name) {
         return false;
     }
-    if (it2->name == "S") {
-        return rjson::to_string_view(it1->value).starts_with(rjson::to_string_view(it2->value));
-    } else /* it2->name == "B" */ {
-        return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
-    }
-}
-
-static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
-    return (type2 == "S" && type1 == "SS") || (type2 == "N" && type1 == "NS") || (type2 == "B" && type1 == "BS");
-}
-
-// Check if two JSON-encoded values match with the CONTAINS relation
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
-    if (!v1) {
-        return false;
-    }
-    const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
-    if (kv1.name == "S" && kv2.name == "S") {
-        return rjson::to_string_view(kv1.value).find(rjson::to_string_view(kv2.value)) != std::string_view::npos;
-    } else if (kv1.name == "B" && kv2.name == "B") {
-        return rjson::base64_decode(kv1.value).find(rjson::base64_decode(kv2.value)) != bytes::npos;
-    } else if (is_set_of(kv1.name, kv2.name)) {
-        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
-            if (*i == kv2.value) {
-                return true;
-            }
-        }
-    } else if (kv1.name == "L") {
-        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
-            if (!i->IsObject() || i->MemberCount() != 1) {
-                clogger.error("check_CONTAINS received a list whose element is malformed");
-                return false;
-            }
-            const auto& el = *i->MemberBegin();
-            if (el.name == kv2.name && el.value == kv2.value) {
-                return true;
-            }
-        }
-    }
-    return false;
-}
-
-// Check if two JSON-encoded values match with the NOT_CONTAINS relation
-static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
-    if (!v1) {
-        return false;
-    }
-    return !check_CONTAINS(v1, v2);
+    std::string_view val1(it1->value.GetString(), it1->value.GetStringLength());
+    std::string_view val2(it2->value.GetString(), it2->value.GetStringLength());
+    return val1.substr(0, val2.size()) == val2;
 }
 
 // Check if a JSON-encoded value equals any element of an array, which must have at least one element.
 static bool check_IN(const rjson::value* val, const rjson::value& array) {
     if (!array[0].IsObject() || array[0].MemberCount() != 1) {
-        throw api_error::validation(
+        throw api_error("ValidationException",
                         format("IN operator encountered malformed AttributeValue: {}", array[0]));
     }
     const auto& type = array[0].MemberBegin()->name;
     if (type != "S" && type != "N" && type != "B") {
-        throw api_error::validation(
+        throw api_error("ValidationException",
                         "IN operator requires AttributeValueList elements to be of type String, Number, or Binary ");
     }
     if (!val) {
@@ -297,7 +196,7 @@ static bool check_IN(const rjson::value* val, const rjson::value& array) {
     bool have_match = false;
     for (const auto& elem : array.GetArray()) {
         if (!elem.IsObject() || elem.MemberCount() != 1 || elem.MemberBegin()->name != type) {
-            throw api_error::validation(
+            throw api_error("ValidationException",
                             "IN operator requires all AttributeValueList elements to have the same type ");
         }
         if (!have_match && *val == elem) {
@@ -308,19 +207,6 @@ static bool check_IN(const rjson::value* val, const rjson::value& array) {
     return have_match;
 }
 
-// Another variant of check_IN, this one for ConditionExpression. It needs to
-// check whether the first element in the given vector is equal to any of the
-// others.
-static bool check_IN(const std::vector<rjson::value>& array) {
-    const rjson::value* first = &array[0];
-    for (unsigned i = 1; i < array.size(); i++) {
-        if (check_EQ(first, array[i])) {
-            return true;
-        }
-    }
-    return false;
-}
-
 static bool check_NULL(const rjson::value* val) {
     return val == nullptr;
 }
@@ -329,152 +215,52 @@ static bool check_NOT_NULL(const rjson::value* val) {
     return val != nullptr;
 }
 
-// Only types S, N or B (string, number or bytes) may be compared by the
-// various comparion operators - lt, le, gt, ge, and between.
-// Note that in particular, if the value is missing (v->IsNull()), this
-// check returns false.
-static bool check_comparable_type(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return false;
-    }
-    const rjson::value& type = v.MemberBegin()->name;
-    return type == "S" || type == "N" || type == "B";
-}
-
 // Check if two JSON-encoded values match with cmp.
 template <typename Comparator>
-bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp,
-                   bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !check_comparable_type(*v1)) {
-        if (v1_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
+bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp) {
+    if (!v2.IsObject() || v2.MemberCount() != 1) {
+        throw api_error("ValidationException",
+                        format("{} requires a single AttributeValue of type String, Number, or Binary",
+                               cmp.diagnostic()));
     }
-    if (!check_comparable_type(v2)) {
-        if (v2_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
+    const auto& kv2 = *v2.MemberBegin();
+    if (kv2.name != "S" && kv2.name != "N" && kv2.name != "B") {
+        throw api_error("ValidationException",
+                        format("{} requires a single AttributeValue of type String, Number, or Binary",
+                               cmp.diagnostic()));
     }
-    if (bad) {
+    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
         return false;
     }
     const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
     if (kv1.name != kv2.name) {
         return false;
     }
     if (kv1.name == "N") {
-        return cmp(unwrap_number(*v1, cmp.diagnostic), unwrap_number(v2, cmp.diagnostic));
+        return cmp(unwrap_number(*v1, cmp.diagnostic()), unwrap_number(v2, cmp.diagnostic()));
     }
     if (kv1.name == "S") {
         return cmp(std::string_view(kv1.value.GetString(), kv1.value.GetStringLength()),
                    std::string_view(kv2.value.GetString(), kv2.value.GetStringLength()));
     }
     if (kv1.name == "B") {
-        return cmp(rjson::base64_decode(kv1.value), rjson::base64_decode(kv2.value));
+        return cmp(base64_decode(kv1.value), base64_decode(kv2.value));
     }
-    // cannot reach here, as check_comparable_type() verifies the type is one
-    // of the above options.
+    clogger.error("check_compare panic: LHS type equals RHS type, but one is in {N,S,B} while the other isn't");
     return false;
 }
 
 struct cmp_lt {
     template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs < rhs; }
-    // We cannot use the normal comparison operators like "<" on the bytes
-    // type, because they treat individual bytes as signed but we need to
-    // compare them as *unsigned*. So we need a specialization for bytes.
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) < 0; }
-    static constexpr const char* diagnostic = "LT operator";
-};
-
-struct cmp_le {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs <= rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) <= 0; }
-    static constexpr const char* diagnostic = "LE operator";
-};
-
-struct cmp_ge {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs >= rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) >= 0; }
-    static constexpr const char* diagnostic = "GE operator";
+    const char* diagnostic() const { return "LT operator"; }
 };
 
 struct cmp_gt {
-    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return lhs > rhs; }
-    bool operator()(const bytes& lhs, const bytes& rhs) const { return compare_unsigned(lhs, rhs) > 0; }
-    static constexpr const char* diagnostic = "GT operator";
+    // bytes only has <
+    template <typename T> bool operator()(const T& lhs, const T& rhs) const { return rhs < lhs; }
+    const char* diagnostic() const { return "GT operator"; }
 };
 
-// True if v is between lb and ub, inclusive.  Throws or returns false
-// (depending on bounds_from_query parameter) if lb > ub.
-template <typename T>
-static bool check_BETWEEN(const T& v, const T& lb, const T& ub, bool bounds_from_query) {
-    if (cmp_lt()(ub, lb)) {
-        if (bounds_from_query) {
-            throw api_error::validation(
-                format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
-        } else {
-            return false;
-        }
-    }
-    return cmp_ge()(v, lb) && cmp_le()(v, ub);
-}
-
-static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const rjson::value& ub,
-                          bool v_from_query, bool lb_from_query, bool ub_from_query) {
-    if ((v && v_from_query && !check_comparable_type(*v)) ||
-        (lb_from_query && !check_comparable_type(lb)) ||
-        (ub_from_query && !check_comparable_type(ub))) {
-        throw api_error::validation("between allow only the types String, Number, or Binary");
-
-    }
-    if (!v || !v->IsObject() || v->MemberCount() != 1 ||
-        !lb.IsObject() || lb.MemberCount() != 1 ||
-        !ub.IsObject() || ub.MemberCount() != 1) {
-        return false;
-    }
-
-    const auto& kv_v = *v->MemberBegin();
-    const auto& kv_lb = *lb.MemberBegin();
-    const auto& kv_ub = *ub.MemberBegin();
-    bool bounds_from_query = lb_from_query && ub_from_query;
-    if (kv_lb.name != kv_ub.name) {
-        if (bounds_from_query) {
-           throw api_error::validation(
-                format("BETWEEN operator requires the same type for lower and upper bound; instead got {} and {}",
-                       kv_lb.name, kv_ub.name));
-        } else {
-            return false;
-        }
-    }
-    if (kv_v.name != kv_lb.name) { // Cannot compare different types, so v is NOT between lb and ub.
-        return false;
-    }
-    if (kv_v.name == "N") {
-        const char* diag = "BETWEEN operator";
-        return check_BETWEEN(unwrap_number(*v, diag), unwrap_number(lb, diag), unwrap_number(ub, diag), bounds_from_query);
-    }
-    if (kv_v.name == "S") {
-        return check_BETWEEN(std::string_view(kv_v.value.GetString(), kv_v.value.GetStringLength()),
-                             std::string_view(kv_lb.value.GetString(), kv_lb.value.GetStringLength()),
-                             std::string_view(kv_ub.value.GetString(), kv_ub.value.GetStringLength()),
-                             bounds_from_query);
-    }
-    if (kv_v.name == "B") {
-        return check_BETWEEN(rjson::base64_decode(kv_v.value), rjson::base64_decode(kv_lb.value), rjson::base64_decode(kv_ub.value), bounds_from_query);
-    }
-    if (v_from_query) {
-        throw api_error::validation(
-            format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
-               kv_lb.name));
-    } else {
-        return false;
-    }
-}
-
 // Verify one Expect condition on one attribute (whose content is "got")
 // for the verify_expected() below.
 // This function returns true or false depending on whether the condition
@@ -490,24 +276,24 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
     // and requires a different combinations of parameters in the request
     if (value) {
         if (exists && (!exists->IsBool() || exists->GetBool() != true)) {
-            throw api_error::validation("Cannot combine Value with Exists!=true");
+            throw api_error("ValidationException", "Cannot combine Value with Exists!=true");
         }
         if (comparison_operator) {
-            throw api_error::validation("Cannot combine Value with ComparisonOperator");
+            throw api_error("ValidationException", "Cannot combine Value with ComparisonOperator");
         }
         return check_EQ(got, *value);
     } else if (exists) {
         if (comparison_operator) {
-            throw api_error::validation("Cannot combine Exists with ComparisonOperator");
+            throw api_error("ValidationException", "Cannot combine Exists with ComparisonOperator");
         }
         if (!exists->IsBool() || exists->GetBool() != false) {
-            throw api_error::validation("Exists!=false requires Value");
+            throw api_error("ValidationException", "Exists!=false requires Value");
         }
         // Remember Exists=false, so we're checking that the attribute does *not* exist:
         return !got;
     } else {
         if (!comparison_operator) {
-            throw api_error::validation("Missing ComparisonOperator, Value or Exists");
+            throw api_error("ValidationException", "Missing ComparisonOperator, Value or Exists");
         }
         comparison_operator_type op = get_comparison_operator(*comparison_operator);
         switch (op) {
@@ -519,19 +305,13 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
             return check_NE(got, (*attribute_value_list)[0]);
         case comparison_operator_type::LT:
             verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_lt{}, false, true);
-        case comparison_operator_type::LE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_le{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_lt{});
         case comparison_operator_type::GT:
             verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_gt{}, false, true);
-        case comparison_operator_type::GE:
-            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_ge{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_gt{});
         case comparison_operator_type::BEGINS_WITH:
             verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_BEGINS_WITH(got, (*attribute_value_list)[0], false, true);
+            return check_BEGINS_WITH(got, (*attribute_value_list)[0]);
         case comparison_operator_type::IN:
             verify_operand_count(attribute_value_list, nonempty(), *comparison_operator);
             return check_IN(got, *attribute_value_list);
@@ -541,198 +321,67 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
         case comparison_operator_type::NOT_NULL:
             verify_operand_count(attribute_value_list, empty(), *comparison_operator);
             return check_NOT_NULL(got);
-        case comparison_operator_type::BETWEEN:
-            verify_operand_count(attribute_value_list, exact_size(2), *comparison_operator);
-            return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1],
-                                 false, true, true);
-        case comparison_operator_type::CONTAINS:
-            {
-                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-                // Expected's "CONTAINS" has this artificial limitation.
-                // ConditionExpression's "contains()" does not...
-                const rjson::value& arg = (*attribute_value_list)[0];
-                const auto& argtype = (*arg.MemberBegin()).name;
-                if (argtype != "S" && argtype != "N" && argtype != "B") {
-                    throw api_error::validation(
-                            format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
-                                    "got {} instead", argtype));
-                }
-                return check_CONTAINS(got, arg);
-            }
-        case comparison_operator_type::NOT_CONTAINS:
-            {
-                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-                // Expected's "NOT_CONTAINS" has this artificial limitation.
-                // ConditionExpression's "contains()" does not...
-                const rjson::value& arg = (*attribute_value_list)[0];
-                const auto& argtype = (*arg.MemberBegin()).name;
-                if (argtype != "S" && argtype != "N" && argtype != "B") {
-                    throw api_error::validation(
-                            format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
-                                    "got {} instead", argtype));
-                }
-                return check_NOT_CONTAINS(got, arg);
-            }
+        default:
+            // FIXME: implement all the missing types, so there will be no default here.
+            throw api_error("ValidationException", format("ComparisonOperator {} is not yet supported", *comparison_operator));
         }
-        throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));
     }
 }
 
-conditional_operator_type get_conditional_operator(const rjson::value& req) {
-    const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
-    if (!conditional_operator) {
-        return conditional_operator_type::MISSING;
-    }
-    if (!conditional_operator->IsString()) {
-        throw api_error::validation("'ConditionalOperator' parameter, if given, must be a string");
-    }
-    auto s = rjson::to_string_view(*conditional_operator);
-    if (s == "AND") {
-        return conditional_operator_type::AND;
-    } else if (s == "OR") {
-        return conditional_operator_type::OR;
-    } else {
-        throw api_error::validation(
-                format("'ConditionalOperator' parameter must be AND, OR or missing. Found {}.", s));
-    }
-}
-
-// Check if the existing values of the item (previous_item) match the
+// Verify that the existing values of the item (previous_item) match the
 // conditions given by the Expected and ConditionalOperator parameters
 // (if they exist) in the request (an UpdateItem, PutItem or DeleteItem).
-// This function can throw an ValidationException API error if there
+// This function will throw a ConditionalCheckFailedException API error
+// if the values do not match the condition, or ValidationException if there
 // are errors in the format of the condition itself.
-bool verify_expected(const rjson::value& req, const rjson::value* previous_item) {
+void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item) {
     const rjson::value* expected = rjson::find(req, "Expected");
-    auto conditional_operator = get_conditional_operator(req);
-    if (conditional_operator != conditional_operator_type::MISSING &&
-        (!expected || (expected->IsObject() && expected->GetObject().ObjectEmpty()))) {
-            throw api_error::validation("'ConditionalOperator' parameter cannot be specified for missing or empty Expression");
-    }
     if (!expected) {
-        return true;
+        return;
     }
     if (!expected->IsObject()) {
-        throw api_error::validation("'Expected' parameter, if given, must be an object");
+        throw api_error("ValidationException", "'Expected' parameter, if given, must be an object");
+    }
+    // ConditionalOperator can be "AND" for requiring all conditions, or
+    // "OR" for requiring one condition, and defaults to "AND" if missing.
+    const rjson::value* conditional_operator = rjson::find(req, "ConditionalOperator");
+    bool require_all = true;
+    if (conditional_operator) {
+        if (!conditional_operator->IsString()) {
+            throw api_error("ValidationException", "'ConditionalOperator' parameter, if given, must be a string");
+        }
+        std::string_view s(conditional_operator->GetString(), conditional_operator->GetStringLength());
+        if (s == "AND") {
+            // require_all is already true
+        } else if (s == "OR") {
+            require_all = false;
+        } else {
+            throw api_error("ValidationException", "'ConditionalOperator' parameter must be AND, OR or missing");
+        }
+        if (expected->GetObject().ObjectEmpty()) {
+            throw api_error("ValidationException", "'ConditionalOperator' parameter cannot be specified for empty Expression");
+        }
     }
-    bool require_all = conditional_operator != conditional_operator_type::OR;
-    return verify_condition(*expected, require_all, previous_item);
-}
 
-bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item) {
-    for (auto it = condition.MemberBegin(); it != condition.MemberEnd(); ++it) {
+    for (auto it = expected->MemberBegin(); it != expected->MemberEnd(); ++it) {
         const rjson::value* got = nullptr;
-        if (previous_item) {
-            got = rjson::find(*previous_item, rjson::to_string_view(it->name));
+        if (previous_item && previous_item->IsObject() && previous_item->HasMember("Item")) {
+            got = rjson::find((*previous_item)["Item"], rjson::string_ref_type(it->name.GetString()));
         }
         bool success = verify_expected_one(it->value, got);
         if (success && !require_all) {
             // When !require_all, one success is enough!
-            return true;
+            return;
         } else if (!success && require_all) {
             // When require_all, one failure is enough!
-            return false;
+            throw api_error("ConditionalCheckFailedException", "Failed condition.");
         }
     }
     // If we got here and require_all, none of the checks failed, so succeed.
     // If we got here and !require_all, all of the checks failed, so fail.
-    return require_all;
-}
-
-static bool calculate_primitive_condition(const parsed::primitive_condition& cond,
-        const rjson::value* previous_item) {
-    std::vector<rjson::value> calculated_values;
-    calculated_values.reserve(cond._values.size());
-    for (const parsed::value& v : cond._values) {
-        calculated_values.push_back(calculate_value(v,
-                cond._op == parsed::primitive_condition::type::VALUE ?
-                        calculate_value_caller::ConditionExpressionAlone :
-                        calculate_value_caller::ConditionExpression,
-                previous_item));
-    }
-    switch (cond._op) {
-    case parsed::primitive_condition::type::BETWEEN:
-        if (calculated_values.size() != 3) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error(format("Wrong number of values {} in BETWEEN primitive_condition", cond._values.size()));
-        }
-        return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2],
-                             cond._values[0].is_constant(), cond._values[1].is_constant(), cond._values[2].is_constant());
-    case parsed::primitive_condition::type::IN:
-        return check_IN(calculated_values);
-    case parsed::primitive_condition::type::VALUE:
-        if (calculated_values.size() != 1) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error(format("Unexpected values in primitive_condition", cond._values.size()));
-        }
-        // Unwrap the boolean wrapped as the value (if it is a boolean)
-        if (calculated_values[0].IsObject() && calculated_values[0].MemberCount() == 1) {
-            auto it = calculated_values[0].MemberBegin();
-            if (it->name == "BOOL" && it->value.IsBool()) {
-                return it->value.GetBool();
-            }
-        }
-        throw api_error::validation(
-                format("ConditionExpression: condition results in a non-boolean value: {}",
-                        calculated_values[0]));
-    default:
-        // All the rest of the operators have exactly two parameters (and unless
-        // we have a bug in the parser, that's what we have in the parsed object:
-        if (calculated_values.size() != 2) {
-            throw std::logic_error(format("Wrong number of values {} in primitive_condition object", cond._values.size()));
-        }
-    }
-    switch (cond._op) {
-    case parsed::primitive_condition::type::EQ:
-        return check_EQ(&calculated_values[0], calculated_values[1]);
-    case parsed::primitive_condition::type::NE:
-        return check_NE(&calculated_values[0], calculated_values[1]);
-    case parsed::primitive_condition::type::GT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::GE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::LT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    case parsed::primitive_condition::type::LE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_le{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
-    default:
-        // Shouldn't happen unless we have a bug in the parser
-        throw std::logic_error(format("Unknown type {} in primitive_condition object", (int)(cond._op)));
+    if (!require_all) {
+        throw api_error("ConditionalCheckFailedException", "None of ORed Expect conditions were successful.");
     }
 }
 
-// Check if the existing values of the item (previous_item) match the
-// conditions given by the given parsed ConditionExpression.
-bool verify_condition_expression(
-        const parsed::condition_expression& condition_expression,
-        const rjson::value* previous_item) {
-    if (condition_expression.empty()) {
-        return true;
-    }
-    bool ret = std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) -> bool {
-            return calculate_primitive_condition(cond, previous_item);
-        },
-        [&] (const parsed::condition_expression::condition_list& list) -> bool {
-            auto verify_condition = [&] (const parsed::condition_expression& e) {
-                return verify_condition_expression(e, previous_item);
-            };
-            switch (list.op) {
-            case '&':
-                return boost::algorithm::all_of(list.conditions, verify_condition);
-            case '|':
-                return boost::algorithm::any_of(list.conditions, verify_condition);
-            default:
-                // Shouldn't happen unless we have a bug in the parser
-                throw std::logic_error("bad operator in condition_list");
-            }
-        }
-    }, condition_expression._expression);
-    return condition_expression._negated ? !ret : ret;
-}
-
 }

alternator/conditions.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -20,29 +33,17 @@
 
 #include "cql3/restrictions/statement_restrictions.hh"
 #include "serialization.hh"
-#include "expressions_types.hh"
 
 namespace alternator {
 
 enum class comparison_operator_type {
-    EQ, NE, LE, LT, GE, GT, IN, BETWEEN, CONTAINS, NOT_CONTAINS, IS_NULL, NOT_NULL, BEGINS_WITH
+    EQ, NE, LE, LT, GE, GT, IN, BETWEEN, CONTAINS, IS_NULL, NOT_NULL, BEGINS_WITH
 };
 
 comparison_operator_type get_comparison_operator(const rjson::value& comparison_operator);
 
-enum class conditional_operator_type {
-    AND, OR, MISSING
-};
-conditional_operator_type get_conditional_operator(const rjson::value& req);
+::shared_ptr<cql3::restrictions::statement_restrictions> get_filtering_restrictions(schema_ptr schema, const column_definition& attrs_col, const rjson::value& query_filter);
 
-bool verify_expected(const rjson::value& req, const rjson::value* previous_item);
-bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);
-
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2);
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
-
-bool verify_condition_expression(
-        const parsed::condition_expression& condition_expression,
-        const rjson::value* previous_item);
+void verify_expected(const rjson::value& req, const std::unique_ptr<rjson::value>& previous_item);
 
 }

alternator/controller.cc

@@ -1,159 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <seastar/net/dns.hh>
-#include "controller.hh"
-#include "server.hh"
-#include "executor.hh"
-#include "rmw_operation.hh"
-#include "db/config.hh"
-#include "cdc/generation_service.hh"
-#include "service/memory_limiter.hh"
-#include "auth/service.hh"
-#include "service/qos/service_level_controller.hh"
-
-using namespace seastar;
-
-namespace alternator {
-
-static logging::logger logger("alternator_controller");
-
-controller::controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config)
-    : _gossiper(gossiper)
-    , _proxy(proxy)
-    , _mm(mm)
-    , _sys_dist_ks(sys_dist_ks)
-    , _cdc_gen_svc(cdc_gen_svc)
-    , _memory_limiter(memory_limiter)
-    , _auth_service(auth_service)
-    , _sl_controller(sl_controller)
-    , _config(config)
-{
-}
-
-sstring controller::name() const {
-    return "alternator";
-}
-
-sstring controller::protocol() const {
-    return "dynamodb";
-}
-
-sstring controller::protocol_version() const {
-    return version;
-}
-
-std::vector<socket_address> controller::listen_addresses() const {
-    return _listen_addresses;
-}
-
-future<> controller::start_server() {
-    return seastar::async([this] {
-        _listen_addresses.clear();
-
-        auto preferred = _config.listen_interface_prefer_ipv6() ? std::make_optional(net::inet_address::family::INET6) : std::nullopt;
-        auto family = _config.enable_ipv6_dns_lookup() || preferred ? std::nullopt : std::make_optional(net::inet_address::family::INET);
-
-        // Create an smp_service_group to be used for limiting the
-        // concurrency when forwarding Alternator request between
-        // shards - if necessary for LWT.
-        smp_service_group_config c;
-        c.max_nonlocal_requests = 5000;
-        _ssg = create_smp_service_group(c).get0();
-
-        rmw_operation::set_default_write_isolation(_config.alternator_write_isolation());
-        executor::set_default_timeout(std::chrono::milliseconds(_config.alternator_timeout_in_ms()));
-
-        net::inet_address addr = utils::resolve(_config.alternator_address, family).get0();
-
-        auto get_cdc_metadata = [] (cdc::generation_service& svc) { return std::ref(svc.get_cdc_metadata()); };
-
-        _executor.start(std::ref(_gossiper), std::ref(_proxy), std::ref(_mm), std::ref(_sys_dist_ks), sharded_parameter(get_cdc_metadata, std::ref(_cdc_gen_svc)), _ssg.value()).get();
-        _server.start(std::ref(_executor), std::ref(_proxy), std::ref(_gossiper), std::ref(_auth_service), std::ref(_sl_controller)).get();
-        // Note: from this point on, if start_server() throws for any reason,
-        // it must first call stop_server() to stop the executor and server
-        // services we just started - or Scylla will cause an assertion
-        // failure when the controller object is destroyed in the exception
-        // unwinding.
-        std::optional<uint16_t> alternator_port;
-        if (_config.alternator_port()) {
-            alternator_port = _config.alternator_port();
-            _listen_addresses.push_back({addr, *alternator_port});
-        }
-        std::optional<uint16_t> alternator_https_port;
-        std::optional<tls::credentials_builder> creds;
-        if (_config.alternator_https_port()) {
-            alternator_https_port = _config.alternator_https_port();
-            _listen_addresses.push_back({addr, *alternator_https_port});
-            creds.emplace();
-            auto opts = _config.alternator_encryption_options();
-            if (opts.empty()) {
-                // Earlier versions mistakenly configured Alternator's
-                // HTTPS parameters via the "server_encryption_option"
-                // configuration parameter. We *temporarily* continue
-                // to allow this, for backward compatibility.
-                opts = _config.server_encryption_options();
-                if (!opts.empty()) {
-                logger.warn("Setting server_encryption_options to configure "
-                        "Alternator's HTTPS encryption is deprecated. Please "
-                        "switch to setting alternator_encryption_options instead.");
-                }
-            }
-            opts.erase("require_client_auth");
-            opts.erase("truststore");
-            try {
-                utils::configure_tls_creds_builder(creds.value(), std::move(opts)).get();
-            } catch(...) {
-                logger.error("Failed to set up Alternator TLS credentials: {}", std::current_exception());
-                stop_server().get();
-                std::throw_with_nested(std::runtime_error("Failed to set up Alternator TLS credentials"));
-            }
-        }
-        bool alternator_enforce_authorization = _config.alternator_enforce_authorization();
-        _server.invoke_on_all(
-                [this, addr, alternator_port, alternator_https_port, creds = std::move(creds), alternator_enforce_authorization] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, creds, alternator_enforce_authorization,
-                    &_memory_limiter.local().get_semaphore(),
-                    _config.max_concurrent_requests_per_shard);
-        }).handle_exception([this, addr, alternator_port, alternator_https_port] (std::exception_ptr ep) {
-            logger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF", ep);
-            return stop_server().then([ep = std::move(ep)] { return make_exception_future<>(ep); });
-        }).then([addr, alternator_port, alternator_https_port] {
-            logger.info("Alternator server listening on {}, HTTP port {}, HTTPS port {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF");
-        }).get();
-    });
-}
-
-future<> controller::stop_server() {
-    return seastar::async([this] {
-        if (!_ssg) {
-            return;
-        }
-        _server.stop().get();
-        _executor.stop().get();
-        _listen_addresses.clear();
-        destroy_smp_service_group(_ssg.value()).get();
-    });
-}
-
-future<> controller::request_stop_server() {
-    return stop_server();
-}
-
-}

alternator/controller.hh

@@ -1,94 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include <seastar/core/sharded.hh>
-#include <seastar/core/smp.hh>
-
-#include "protocol_server.hh"
-
-namespace service {
-class storage_proxy;
-class migration_manager;
-class memory_limiter;
-}
-
-namespace db {
-class system_distributed_keyspace;
-class config;
-}
-
-namespace cdc {
-class generation_service;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
-
-namespace auth {
-class service;
-}
-
-namespace qos {
-class service_level_controller;
-}
-
-namespace alternator {
-
-// This is the official DynamoDB API version.
-// It represents the last major reorganization of that API, and all the features
-// that were added since did NOT increment this version string.
-constexpr const char* version = "2012-08-10";
-
-using namespace seastar;
-
-class executor;
-class server;
-
-class controller : public protocol_server {
-    sharded<gms::gossiper>& _gossiper;
-    sharded<service::storage_proxy>& _proxy;
-    sharded<service::migration_manager>& _mm;
-    sharded<db::system_distributed_keyspace>& _sys_dist_ks;
-    sharded<cdc::generation_service>& _cdc_gen_svc;
-    sharded<service::memory_limiter>& _memory_limiter;
-    sharded<auth::service>& _auth_service;
-    sharded<qos::service_level_controller>& _sl_controller;
-    const db::config& _config;
-
-    std::vector<socket_address> _listen_addresses;
-    sharded<executor> _executor;
-    sharded<server> _server;
-    std::optional<smp_service_group> _ssg;
-
-public:
-    controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config);
-
-    virtual sstring name() const override;
-    virtual sstring protocol() const override;
-    virtual sstring protocol_version() const override;
-    virtual std::vector<socket_address> listen_addresses() const override;
-    virtual future<> start_server() override;
-    virtual future<> stop_server() override;
-    virtual future<> request_stop_server() override;
-};
-
-}

alternator/error.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -13,15 +26,12 @@
 
 namespace alternator {
 
-// api_error contains a DynamoDB error message to be returned to the user.
-// It can be returned by value (see executor::request_return_type) or thrown.
-// The DynamoDB's error messages are described in detail in
+// DynamoDB's error messages are described in detail in
 // https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
-// An error message has an HTTP code (almost always 400), a type, e.g.,
-// "ResourceNotFoundException", and a human readable message.
-// Eventually alternator::api_handler will convert a returned or thrown
-// api_error into a JSON object, and that is returned to the user.
-class api_error final : public std::exception {
+// Ah An error message has a "type", e.g., "ResourceNotFoundException", a coarser
+// HTTP code (almost always, 400), and a human readable message. Eventually these
+// will be wrapped into a JSON object returned to the client.
+class api_error : public std::exception {
 public:
     using status_type = httpd::reply::status_type;
     status_type _http_code;
@@ -32,61 +42,8 @@ public:
         , _type(std::move(type))
         , _msg(std::move(msg))
     { }
-
-    // Factory functions for some common types of DynamoDB API errors
-    static api_error validation(std::string msg) {
-        return api_error("ValidationException", std::move(msg));
-    }
-    static api_error resource_not_found(std::string msg) {
-        return api_error("ResourceNotFoundException", std::move(msg));
-    }
-    static api_error resource_in_use(std::string msg) {
-        return api_error("ResourceInUseException", std::move(msg));
-    }
-    static api_error invalid_signature(std::string msg) {
-        return api_error("InvalidSignatureException", std::move(msg));
-    }
-    static api_error missing_authentication_token(std::string msg) {
-        return api_error("MissingAuthenticationTokenException", std::move(msg));
-    }
-    static api_error unrecognized_client(std::string msg) {
-        return api_error("UnrecognizedClientException", std::move(msg));
-    }
-    static api_error unknown_operation(std::string msg) {
-        return api_error("UnknownOperationException", std::move(msg));
-    }
-    static api_error access_denied(std::string msg) {
-        return api_error("AccessDeniedException", std::move(msg));
-    }
-    static api_error conditional_check_failed(std::string msg) {
-        return api_error("ConditionalCheckFailedException", std::move(msg));
-    }
-    static api_error expired_iterator(std::string msg) {
-        return api_error("ExpiredIteratorException", std::move(msg));
-    }
-    static api_error trimmed_data_access_exception(std::string msg) {
-        return api_error("TrimmedDataAccessException", std::move(msg));
-    }
-    static api_error request_limit_exceeded(std::string msg) {
-        return api_error("RequestLimitExceeded", std::move(msg));
-    }
-    static api_error serialization(std::string msg) {
-        return api_error("SerializationException", std::move(msg));
-    }
-    static api_error table_not_found(std::string msg) {
-        return api_error("TableNotFoundException", std::move(msg));
-    }
-    static api_error internal(std::string msg) {
-        return api_error("InternalServerError", std::move(msg), reply::status_type::internal_server_error);
-    }
-
-    // Provide the "std::exception" interface, to make it easier to print this
-    // exception in log messages. Note that this function is *not* used to
-    // format the error to send it back to the client - server.cc has
-    // generate_error_reply() to format an api_error as the DynamoDB protocol
-    // requires.
-    virtual const char* what() const noexcept override;
-    mutable std::string _what_string;
+    api_error() = default;
+    virtual const char* what() const noexcept override { return _msg.c_str(); }
 };
 
 }

alternator/executor.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,231 +25,47 @@
 #include <seastar/http/httpd.hh>
 #include "seastarx.hh"
 #include <seastar/json/json_elements.hh>
-#include <seastar/core/sharded.hh>
 
+#include "service/storage_proxy.hh"
 #include "service/migration_manager.hh"
 #include "service/client_state.hh"
-#include "service_permit.hh"
-#include "db/timeout_clock.hh"
 
-#include "alternator/error.hh"
 #include "stats.hh"
-#include "utils/rjson.hh"
-
-namespace db {
-    class system_distributed_keyspace;
-}
-
-namespace query {
-class partition_slice;
-class result;
-}
-
-namespace cql3::selection {
-    class selection;
-}
-
-namespace service {
-    class storage_proxy;
-}
-
-namespace cdc {
-    class metadata;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
 
 namespace alternator {
 
-class rmw_operation;
-
-struct make_jsonable : public json::jsonable {
-    rjson::value _value;
-public:
-    explicit make_jsonable(rjson::value&& value);
-    std::string to_json() const override;
-};
-
-/**
- * Make return type for serializing the object "streamed",
- * i.e. direct to HTTP output stream. Note: only useful for
- * (very) large objects as there are overhead issues with this
- * as well, but for massive lists of return objects this can
- * help avoid large allocations/many re-allocs
- */ 
-json::json_return_type make_streamed(rjson::value&&);
-
-struct json_string : public json::jsonable {
-    std::string _value;
-public:
-    explicit json_string(std::string&& value);
-    std::string to_json() const override;
-};
-
-namespace parsed {
-class path;
-};
-
-schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
-bool is_alternator_keyspace(const sstring& ks_name);
-// Wraps the db::get_tags_of_table and throws if the table is missing the tags extension.
-const std::map<sstring, sstring>& get_tags_of_table_or_throw(schema_ptr schema);
-
-// An attribute_path_map object is used to hold data for various attributes
-// paths (parsed::path) in a hierarchy of attribute paths. Each attribute path
-// has a root attribute, and then modified by member and index operators -
-// for example in "a.b[2].c" we have "a" as the root, then ".b" member, then
-// "[2]" index, and finally ".c" member.
-// Data can be added to an attribute_path_map using the add() function, but
-// requires that attributes with data not be *overlapping* or *conflicting*:
-//
-// 1. Two attribute paths which are identical or an ancestor of one another
-//    are considered *overlapping* and not allowed. If a.b.c has data,
-//    we can't add more data in a.b.c or any of its descendants like a.b.c.d.
-//
-// 2. Two attribute paths which need the same parent to have both a member and
-//    an index are considered *conflicting* and not allowed. E.g., if a.b has
-//    data, you can't add a[1]. The meaning of adding both would be that the
-//    attribute a is both a map and an array, which isn't sensible.
-//
-// These two requirements are common to the two places where Alternator uses
-// this abstraction to describe how a hierarchical item is to be transformed:
-//
-// 1. In ProjectExpression: for filtering from a full top-level attribute
-//    only the parts for which user asked in ProjectionExpression.
-//
-// 2. In UpdateExpression: for taking the previous value of a top-level
-//    attribute, and modifying it based on the instructions in the user
-//    wrote in UpdateExpression.
-
-template<typename T>
-class attribute_path_map_node {
-public:
-    using data_t = T;
-    // We need the extra unique_ptr<> here because libstdc++ unordered_map
-    // doesn't work with incomplete types :-(
-    using members_t =  std::unordered_map<std::string, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The indexes list is sorted because DynamoDB requires handling writes
-    // beyond the end of a list in index order.
-    using indexes_t = std::map<unsigned, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The prohibition on "overlap" and "conflict" explained above means
-    // That only one of data, members or indexes is non-empty.
-    std::optional<std::variant<data_t, members_t, indexes_t>> _content;
-
-    bool is_empty() const { return !_content; }
-    bool has_value() const { return _content && std::holds_alternative<data_t>(*_content); }
-    bool has_members() const { return _content && std::holds_alternative<members_t>(*_content); }
-    bool has_indexes() const { return _content && std::holds_alternative<indexes_t>(*_content); }
-    // get_members() assumes that has_members() is true
-    members_t& get_members() { return std::get<members_t>(*_content); }
-    const members_t& get_members() const { return std::get<members_t>(*_content); }
-    indexes_t& get_indexes() { return std::get<indexes_t>(*_content); }
-    const indexes_t& get_indexes() const { return std::get<indexes_t>(*_content); }
-    T& get_value() { return std::get<T>(*_content); }
-    const T& get_value() const { return std::get<T>(*_content); }
-};
-
-template<typename T>
-using attribute_path_map = std::unordered_map<std::string, attribute_path_map_node<T>>;
-
-using attrs_to_get_node = attribute_path_map_node<std::monostate>;
-// attrs_to_get lists which top-level attribute are needed, and possibly also
-// which part of the top-level attribute is really needed (when nested
-// attribute paths appeared in the query).
-// Most code actually uses optional<attrs_to_get>. There, a disengaged
-// optional means we should get all attributes, not specific ones.
-using attrs_to_get = attribute_path_map<std::monostate>;
-
-
-class executor : public peering_sharded_service<executor> {
-    gms::gossiper& _gossiper;
+class executor {
     service::storage_proxy& _proxy;
     service::migration_manager& _mm;
-    db::system_distributed_keyspace& _sdks;
-    cdc::metadata& _cdc_metadata;
-    // An smp_service_group to be used for limiting the concurrency when
-    // forwarding Alternator request between shards - if necessary for LWT.
-    smp_service_group _ssg;
 
 public:
     using client_state = service::client_state;
-    using request_return_type = std::variant<json::json_return_type, api_error>;
     stats _stats;
     static constexpr auto ATTRS_COLUMN_NAME = ":attrs";
-    static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
-    static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.alternator.";
+    static constexpr auto KEYSPACE_NAME = "alternator";
 
-    executor(gms::gossiper& gossiper, service::storage_proxy& proxy, service::migration_manager& mm, db::system_distributed_keyspace& sdks, cdc::metadata& cdc_metadata, smp_service_group ssg)
-        : _gossiper(gossiper), _proxy(proxy), _mm(mm), _sdks(sdks), _cdc_metadata(cdc_metadata), _ssg(ssg) {}
+    executor(service::storage_proxy& proxy, service::migration_manager& mm) : _proxy(proxy), _mm(mm) {}
 
-    future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> delete_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> put_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> delete_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_tables(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> scan(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_endpoints(client_state& client_state, service_permit permit, rjson::value request, std::string host_header);
-    future<request_return_type> batch_write_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> batch_get_item(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> query(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
-    future<request_return_type> tag_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> untag_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_tags_of_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> list_streams(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_stream(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_shard_iterator(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> get_records(client_state& client_state, tracing::trace_state_ptr, service_permit permit, rjson::value request);
-    future<request_return_type> describe_continuous_backups(client_state& client_state, service_permit permit, rjson::value request);
+    future<json::json_return_type> create_table(client_state& client_state, std::string content);
+    future<json::json_return_type> describe_table(client_state& client_state, std::string content);
+    future<json::json_return_type> delete_table(client_state& client_state, std::string content);
+    future<json::json_return_type> put_item(client_state& client_state, std::string content);
+    future<json::json_return_type> get_item(client_state& client_state, std::string content);
+    future<json::json_return_type> delete_item(client_state& client_state, std::string content);
+    future<json::json_return_type> update_item(client_state& client_state, std::string content);
+    future<json::json_return_type> list_tables(client_state& client_state, std::string content);
+    future<json::json_return_type> scan(client_state& client_state, std::string content);
+    future<json::json_return_type> describe_endpoints(client_state& client_state, std::string content, std::string host_header);
+    future<json::json_return_type> batch_write_item(client_state& client_state, std::string content);
+    future<json::json_return_type> batch_get_item(client_state& client_state, std::string content);
+    future<json::json_return_type> query(client_state& client_state, std::string content);
 
     future<> start();
     future<> stop() { return make_ready_future<>(); }
 
-    static sstring table_name(const schema&);
-    static db::timeout_clock::time_point default_timeout();
-    static void set_default_timeout(db::timeout_clock::duration timeout);
-private:
-    static db::timeout_clock::duration s_default_timeout;
-public:
-    static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);
+    future<> maybe_create_keyspace();
 
-private:
-    friend class rmw_operation;
-
-    static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr);
-    static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&);
-    
-public:
-    static std::optional<rjson::value> describe_single_item(schema_ptr,
-        const query::partition_slice&,
-        const cql3::selection::selection&,
-        const query::result&,
-        const std::optional<attrs_to_get>&);
-
-    static std::vector<rjson::value> describe_multi_item(schema_ptr schema,
-        const query::partition_slice& slice,
-        const cql3::selection::selection& selection,
-        const query::result& query_result,
-        const std::optional<attrs_to_get>& attrs_to_get);
-
-    static void describe_single_item(const cql3::selection::selection&,
-        const std::vector<bytes_opt>&,
-        const std::optional<attrs_to_get>&,
-        rjson::value&,
-        bool = false);
-
-    static void add_stream_options(const rjson::value& stream_spec, schema_builder&, service::storage_proxy& sp);
-    static void supplement_table_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
-    static void supplement_table_stream_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
+    static void maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
 };
 
 }

alternator/expressions.cc

@@ -1,35 +1,39 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "expressions.hh"
-#include "serialization.hh"
-#include "utils/base64.hh"
-#include "conditions.hh"
 #include "alternator/expressionsLexer.hpp"
 #include "alternator/expressionsParser.hpp"
-#include "utils/overloaded_functor.hh"
-#include "error.hh"
 
-#include "seastarx.hh"
+#include <seastarx.hh>
 
 #include <seastar/core/print.hh>
 #include <seastar/util/log.hh>
 
-#include <boost/algorithm/cxx11/any_of.hpp>
-#include <boost/algorithm/cxx11/all_of.hpp>
-
 #include <functional>
-#include <unordered_map>
 
 namespace alternator {
 
 template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
-Result do_with_parser(std::string_view input, Func&& f) {
+Result do_with_parser(std::string input, Func&& f) {
     expressionsLexer::InputStreamType input_stream{
         reinterpret_cast<const ANTLR_UINT8*>(input.data()),
         ANTLR_ENC_UTF8,
@@ -44,7 +48,7 @@ Result do_with_parser(std::string_view input, Func&& f) {
 }
 
 parsed::update_expression
-parse_update_expression(std::string_view query) {
+parse_update_expression(std::string query) {
     try {
         return do_with_parser(query,  std::mem_fn(&expressionsParser::update_expression));
     } catch (...) {
@@ -53,7 +57,7 @@ parse_update_expression(std::string_view query) {
 }
 
 std::vector<parsed::path>
-parse_projection_expression(std::string_view query) {
+parse_projection_expression(std::string query) {
     try {
         return do_with_parser(query,  std::mem_fn(&expressionsParser::projection_expression));
     } catch (...) {
@@ -61,19 +65,13 @@ parse_projection_expression(std::string_view query) {
     }
 }
 
-parsed::condition_expression
-parse_condition_expression(std::string_view query) {
-    try {
-        return do_with_parser(query,  std::mem_fn(&expressionsParser::condition_expression));
-    } catch (...) {
-        throw expressions_syntax_error(format("Failed parsing ConditionExpression '{}': {}", query, std::current_exception()));
-    }
-}
+template<class... Ts> struct overloaded : Ts... { using Ts::operator()...; };
+template<class... Ts> overloaded(Ts...) -> overloaded<Ts...>;
 
 namespace parsed {
 
 void update_expression::add(update_expression::action a) {
-    std::visit(overloaded_functor {
+    std::visit(overloaded {
         [&] (action::set&)    { seen_set = true; },
         [&] (action::remove&) { seen_remove = true; },
         [&] (action::add&)    { seen_add = true; },
@@ -96,645 +94,5 @@ void update_expression::append(update_expression other) {
     seen_del |= other.seen_del;
 }
 
-void condition_expression::append(condition_expression&& a, char op) {
-    std::visit(overloaded_functor {
-        [&] (condition_list& x) {
-            // If 'a' has a single condition, we could, instead of inserting
-            // it insert its single condition (possibly negated if a._negated)
-            // But considering it we don't evaluate these expressions many
-            // times, this optimization is not worth extra code complexity.
-            if (!x.conditions.empty() && x.op != op) {
-                // Shouldn't happen unless we have a bug in the parser
-                throw std::logic_error("condition_expression::append called with mixed operators");
-            }
-            x.conditions.push_back(std::move(a));
-            x.op = op;
-        },
-        [&] (primitive_condition& x) {
-            // Shouldn't happen unless we have a bug in the parser
-            throw std::logic_error("condition_expression::append called on primitive_condition");
-        }
-    }, _expression);
-}
-
-void path::check_depth_limit() {
-    if (1 + _operators.size() > depth_limit) {
-        throw expressions_syntax_error(format("Document path exceeded {} nesting levels", depth_limit));
-    }
-}
-
-std::ostream& operator<<(std::ostream& os, const path& p) {
-    os << p.root();
-    for (const auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                os << '.' << member;
-            },
-            [&] (unsigned index) {
-                os << '[' << index << ']';
-            }
-        }, op);
-    }
-    return os;
-}
-
 } // namespace parsed
-
-// The following resolve_*() functions resolve references in parsed
-// expressions of different types. Resolving a parsed expression means
-// replacing:
-//  1. In parsed::path objects, replace references like "#name" with the
-//     attribute name from ExpressionAttributeNames,
-//  2. In parsed::constant objects, replace references like ":value" with
-//     the value from ExpressionAttributeValues.
-// These function also track which name and value references were used, to
-// allow complaining if some remain unused.
-// Note that the resolve_*() functions modify the expressions in-place,
-// so if we ever intend to cache parsed expression, we need to pass a copy
-// into this function.
-//
-// Doing the "resolving" stage before the evaluation stage has two benefits.
-// First, it allows us to be compatible with DynamoDB in catching unused
-// names and values (see issue #6572). Second, in the FilterExpression case,
-// we need to resolve the expression just once but then use it many times
-// (once for each item to be filtered).
-
-static std::optional<std::string> resolve_path_component(const std::string& column_name,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    if (column_name.size() > 0 && column_name.front() == '#') {
-        if (!expression_attribute_names) {
-            throw api_error::validation(
-                    format("ExpressionAttributeNames missing, entry '{}' required by expression", column_name));
-        }
-        const rjson::value* value = rjson::find(*expression_attribute_names, column_name);
-        if (!value || !value->IsString()) {
-            throw api_error::validation(
-                    format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
-        }
-        used_attribute_names.emplace(column_name);
-        return std::string(rjson::to_string_view(*value));
-    }
-    return std::nullopt;
-}
-
-static void resolve_path(parsed::path& p,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    std::optional<std::string> r = resolve_path_component(p.root(), expression_attribute_names, used_attribute_names);
-    if (r) {
-        p.set_root(std::move(*r));
-    }
-    for (auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (std::string& s) {
-                r = resolve_path_component(s, expression_attribute_names, used_attribute_names);
-                if (r) {
-                    s = std::move(*r);
-                }
-            },
-            [&] (unsigned index) {
-                // nothing to resolve
-            }
-        }, op);
-    }
-}
-
-static void resolve_constant(parsed::constant& c,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (const std::string& valref) {
-            if (!expression_attribute_values) {
-                throw api_error::validation(
-                        format("ExpressionAttributeValues missing, entry '{}' required by expression", valref));
-            }
-            const rjson::value* value = rjson::find(*expression_attribute_values, valref);
-            if (!value) {
-                throw api_error::validation(
-                        format("ExpressionAttributeValues missing entry '{}' required by expression", valref));
-            }
-            if (value->IsNull()) {
-                throw api_error::validation(
-                        format("ExpressionAttributeValues null value for entry '{}' required by expression", valref));
-            }
-            validate_value(*value, "ExpressionAttributeValues");
-            used_attribute_values.emplace(valref);
-            c.set(*value);
-        },
-        [&] (const parsed::constant::literal& lit) {
-            // Nothing to do, already resolved
-        }
-    }, c._value);
-
-}
-
-void resolve_value(parsed::value& rhs,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (parsed::constant& c) {
-            resolve_constant(c, expression_attribute_values, used_attribute_values);
-        },
-        [&] (parsed::value::function_call& f) {
-            for (parsed::value& value : f._parameters) {
-                resolve_value(value, expression_attribute_names, expression_attribute_values,
-                        used_attribute_names, used_attribute_values);
-            }
-        },
-        [&] (parsed::path& p) {
-            resolve_path(p, expression_attribute_names, used_attribute_names);
-        }
-    }, rhs._value);
-}
-
-void resolve_set_rhs(parsed::set_rhs& rhs,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    resolve_value(rhs._v1, expression_attribute_names, expression_attribute_values,
-            used_attribute_names, used_attribute_values);
-    if (rhs._op != 'v') {
-        resolve_value(rhs._v2, expression_attribute_names, expression_attribute_values,
-                used_attribute_names, used_attribute_values);
-    }
-}
-
-void resolve_update_expression(parsed::update_expression& ue,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    for (parsed::update_expression::action& action : ue.actions()) {
-        resolve_path(action._path, expression_attribute_names, used_attribute_names);
-        std::visit(overloaded_functor {
-            [&] (parsed::update_expression::action::set& a) {
-                resolve_set_rhs(a._rhs, expression_attribute_names, expression_attribute_values,
-                        used_attribute_names, used_attribute_values);
-            },
-            [&] (parsed::update_expression::action::remove& a) {
-                // nothing to do
-            },
-            [&] (parsed::update_expression::action::add& a) {
-                resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
-            },
-            [&] (parsed::update_expression::action::del& a) {
-                resolve_constant(a._valref, expression_attribute_values, used_attribute_values);
-            }
-        }, action._action);
-    }
-}
-
-static void resolve_primitive_condition(parsed::primitive_condition& pc,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    for (parsed::value& value : pc._values) {
-        resolve_value(value,
-                expression_attribute_names, expression_attribute_values,
-                used_attribute_names, used_attribute_values);
-    }
-}
-
-void resolve_condition_expression(parsed::condition_expression& ce,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values) {
-    std::visit(overloaded_functor {
-        [&] (parsed::primitive_condition& cond) {
-            resolve_primitive_condition(cond,
-                    expression_attribute_names, expression_attribute_values,
-                    used_attribute_names, used_attribute_values);
-        },
-        [&] (parsed::condition_expression::condition_list& list) {
-            for (parsed::condition_expression& cond : list.conditions) {
-                resolve_condition_expression(cond,
-                        expression_attribute_names, expression_attribute_values,
-                            used_attribute_names, used_attribute_values);
-
-            }
-        }
-    }, ce._expression);
-}
-
-void resolve_projection_expression(std::vector<parsed::path>& pe,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    for (parsed::path& p : pe) {
-        resolve_path(p, expression_attribute_names, used_attribute_names);
-    }
-}
-
-// condition_expression_on() checks whether a condition_expression places any
-// condition on the given attribute. It can be useful, for example, for
-// checking whether the condition tries to restrict a key column.
-
-static bool value_on(const parsed::value& v, std::string_view attribute) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) {
-            return false;
-        },
-        [&] (const parsed::value::function_call& f) {
-            for (const parsed::value& value : f._parameters) {
-                if (value_on(value, attribute)) {
-                    return true;
-                }
-            }
-            return false;
-        },
-        [&] (const parsed::path& p) {
-            return p.root() == attribute;
-        }
-    }, v._value);
-}
-
-static bool primitive_condition_on(const parsed::primitive_condition& pc, std::string_view attribute) {
-    for (const parsed::value& value : pc._values) {
-        if (value_on(value, attribute)) {
-            return true;
-        }
-    }
-    return false;
-}
-
-bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) {
-            return primitive_condition_on(cond, attribute);
-        },
-        [&] (const parsed::condition_expression::condition_list& list) {
-            for (const parsed::condition_expression& cond : list.conditions) {
-                if (condition_expression_on(cond, attribute)) {
-                    return true;
-                }
-            }
-            return false;
-        }
-    }, ce._expression);
-}
-
-// for_condition_expression_on() runs a given function over all the attributes
-// mentioned in the expression. If the same attribute is mentioned more than
-// once, the function will be called more than once for the same attribute.
-
-static void for_value_on(const parsed::value& v, const noncopyable_function<void(std::string_view)>& func) {
-    std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) { },
-        [&] (const parsed::value::function_call& f) {
-            for (const parsed::value& value : f._parameters) {
-                for_value_on(value, func);
-            }
-        },
-        [&] (const parsed::path& p) {
-            func(p.root());
-        }
-    }, v._value);
-}
-
-void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func) {
-    std::visit(overloaded_functor {
-        [&] (const parsed::primitive_condition& cond) {
-            for (const parsed::value& value : cond._values) {
-                for_value_on(value, func);
-            }
-        },
-        [&] (const parsed::condition_expression::condition_list& list) {
-            for (const parsed::condition_expression& cond : list.conditions) {
-                for_condition_expression_on(cond, func);
-            }
-        }
-    }, ce._expression);
-}
-
-// The following calculate_value() functions calculate, or evaluate, a parsed
-// expression. The parsed expression is assumed to have been "resolved", with
-// the matching resolve_* function.
-
-// calculate_size() is ConditionExpression's size() function, i.e., it takes
-// a JSON-encoded value and returns its "size" as defined differently for the
-// different types - also as a JSON-encoded number.
-// It return a JSON-encoded "null" value if this value's type has no size
-// defined. Comparisons against this non-numeric value will later fail.
-static rjson::value calculate_size(const rjson::value& v) {
-    // NOTE: If v is improperly formatted for our JSON value encoding, it
-    // must come from the request itself, not from the database, so it makes
-    // sense to throw a ValidationException if we see such a problem.
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(format("invalid object: {}", v));
-    }
-    auto it = v.MemberBegin();
-    int ret;
-    if (it->name == "S") {
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("invalid string: {}", v));
-        }
-        ret = it->value.GetStringLength();
-    } else if (it->name == "NS" || it->name == "SS" || it->name == "BS" || it->name == "L") {
-        if (!it->value.IsArray()) {
-            throw api_error::validation(format("invalid set: {}", v));
-        }
-        ret = it->value.Size();
-    } else if (it->name == "M") {
-        if (!it->value.IsObject()) {
-            throw api_error::validation(format("invalid map: {}", v));
-        }
-        ret = it->value.MemberCount();
-    } else if (it->name == "B") {
-        if (!it->value.IsString()) {
-            throw api_error::validation(format("invalid byte string: {}", v));
-        }
-        ret = base64_decoded_len(rjson::to_string_view(it->value));
-    } else {
-        rjson::value json_ret = rjson::empty_object();
-        rjson::add(json_ret, "null", rjson::value(true));
-        return json_ret;
-    }
-    rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "N", rjson::from_string(std::to_string(ret)));
-    return json_ret;
-}
-
-static const rjson::value& calculate_value(const parsed::constant& c) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant::literal& v) -> const rjson::value& {
-            return *v;
-        },
-        [&] (const std::string& valref) -> const rjson::value& {
-            // Shouldn't happen, we should have called resolve_value() earlier
-            // and replaced the value reference by the literal constant.
-            throw std::logic_error("calculate_value() called before resolve_value()");
-        }
-    }, c._value);
-}
-
-static rjson::value to_bool_json(bool b) {
-    rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "BOOL", rjson::value(b));
-    return json_ret;
-}
-
-static bool known_type(std::string_view type) {
-    static thread_local const std::unordered_set<std::string_view> types = {
-            "N", "S", "B", "NS", "SS", "BS", "L", "M", "NULL", "BOOL"
-    };
-    return types.contains(type);
-}
-
-using function_handler_type = rjson::value(calculate_value_caller, const rjson::value*, const parsed::value::function_call&);
-static const
-std::unordered_map<std::string_view, function_handler_type*> function_handlers {
-    {"list_append", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::UpdateExpression) {
-                throw api_error::validation(
-                        format("{}: list_append() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: list_append() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            rjson::value ret = list_concatenate(v1, v2);
-            if (ret.IsNull()) {
-                throw api_error::validation("UpdateExpression: list_append() given a non-list");
-            }
-            return ret;
-        }
-    },
-    {"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::UpdateExpression) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: if_not_exists() must include path as its first argument", caller));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return v1.IsNull() ? std::move(v2) : std::move(v1);
-        }
-    },
-    {"size", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpression) {
-                throw api_error::validation(
-                        format("{}: size() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: size() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return calculate_size(v);
-        }
-    },
-    {"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: attribute_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: attribute_exists()'s parameter must be a path", caller));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return to_bool_json(!v.IsNull());
-        }
-    },
-    {"attribute_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists() not allowed here", caller));
-            }
-            if (f._parameters.size() != 1) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists() accepts 1 parameter, got {}", caller, f._parameters.size()));
-            }
-            if (!std::holds_alternative<parsed::path>(f._parameters[0]._value)) {
-                throw api_error::validation(
-                        format("{}: attribute_not_exists()'s parameter must be a path", caller));
-            }
-            rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return to_bool_json(v.IsNull());
-        }
-    },
-    {"attribute_type", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: attribute_type() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: attribute_type() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            // There is no real reason for the following check (not
-            // allowing the type to come from a document attribute), but
-            // DynamoDB does this check, so we do too...
-            if (!f._parameters[1].is_constant()) {
-                throw api_error::validation(
-                        format("{}: attribute_types()'s first parameter must be an expression attribute", caller));
-            }
-            rjson::value v0 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v1 = calculate_value(f._parameters[1], caller, previous_item);
-            if (v1.IsObject() && v1.MemberCount() == 1 && v1.MemberBegin()->name == "S") {
-                // If the type parameter is not one of the legal types
-                // we should generate an error, not a failed condition:
-                if (!known_type(rjson::to_string_view(v1.MemberBegin()->value))) {
-                    throw api_error::validation(
-                            format("{}: attribute_types()'s second parameter, {}, is not a known type",
-                                    caller, v1.MemberBegin()->value));
-                }
-                if (v0.IsObject() && v0.MemberCount() == 1) {
-                    return to_bool_json(v1.MemberBegin()->value == v0.MemberBegin()->name);
-                } else {
-                    return to_bool_json(false);
-                }
-            } else {
-                throw api_error::validation(
-                        format("{}: attribute_type() second parameter must refer to a string, got {}", caller, v1));
-            }
-        }
-    },
-    {"begins_with", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: begins_with() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: begins_with() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_BEGINS_WITH(v1.IsNull() ? nullptr : &v1,  v2,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
-        }
-    },
-    {"contains", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
-            if (caller != calculate_value_caller::ConditionExpressionAlone) {
-                throw api_error::validation(
-                        format("{}: contains() not allowed here", caller));
-            }
-            if (f._parameters.size() != 2) {
-                throw api_error::validation(
-                        format("{}: contains() accepts 2 parameters, got {}", caller, f._parameters.size()));
-            }
-            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
-            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1,  v2));
-        }
-    },
-};
-
-// Given a parsed::path and an item read from the table, extract the value
-// of a certain attribute path, such as "a" or "a.b.c[3]". Returns a null
-// value if the item or the requested attribute does not exist.
-// Note that the item is assumed to be encoded in JSON using DynamoDB
-// conventions - each level of a nested document is a map with one key -
-// a type (e.g., "M" for map) - and its value is the representation of
-// that value.
-static rjson::value extract_path(const rjson::value* item,
-        const parsed::path& p, calculate_value_caller caller) {
-    if (!item) {
-        return rjson::null_value();
-    }
-    const rjson::value* v = rjson::find(*item, p.root());
-    if (!v) {
-        return rjson::null_value();
-    }
-    for (const auto& op : p.operators()) {
-        if (!v->IsObject() || v->MemberCount() != 1) {
-            // This shouldn't happen. We shouldn't have stored malformed
-            // objects. But today Alternator does not validate the structure
-            // of nested documents before storing them, so this can happen on
-            // read.
-            throw api_error::validation(format("{}: malformed item read: {}", *item));
-        }
-        const char* type = v->MemberBegin()->name.GetString();
-        v = &(v->MemberBegin()->value);
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                if (type[0] == 'M' && v->IsObject()) {
-                    v = rjson::find(*v, member);
-                } else {
-                    v = nullptr;
-                }
-            },
-            [&] (unsigned index) {
-                if (type[0] == 'L' && v->IsArray() && index < v->Size()) {
-                    v = &(v->GetArray()[index]);
-                } else {
-                    v = nullptr;
-                }
-            }
-        }, op);
-        if (!v) {
-            return rjson::null_value();
-        }
-    }
-    return rjson::copy(*v);
-}
-
-// Given a parsed::value, which can refer either to a constant value from
-// ExpressionAttributeValues, to the value of some attribute, or to a function
-// of other values, this function calculates the resulting value.
-// "caller" determines which expression - ConditionExpression or
-// UpdateExpression - is asking for this value. We need to know this because
-// DynamoDB allows a different choice of functions for different expressions.
-rjson::value calculate_value(const parsed::value& v,
-        calculate_value_caller caller,
-        const rjson::value* previous_item) {
-    return std::visit(overloaded_functor {
-        [&] (const parsed::constant& c) -> rjson::value {
-            return rjson::copy(calculate_value(c));
-        },
-        [&] (const parsed::value::function_call& f) -> rjson::value {
-            auto function_it = function_handlers.find(std::string_view(f._function_name));
-            if (function_it == function_handlers.end()) {
-                throw api_error::validation(
-                        format("{}: unknown function '{}' called.", caller, f._function_name));
-            }
-            return function_it->second(caller, previous_item, f);
-        },
-        [&] (const parsed::path& p) -> rjson::value {
-            return extract_path(previous_item, p, caller);
-        }
-    }, v._value);
-}
-
-// Same as calculate_value() above, except takes a set_rhs, which may be
-// either a single value, or v1+v2 or v1-v2.
-rjson::value calculate_value(const parsed::set_rhs& rhs,
-        const rjson::value* previous_item) {
-    switch (rhs._op) {
-    case 'v':
-        return calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-    case '+': {
-        rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-        rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
-        return number_add(v1, v2);
-    }
-    case '-': {
-        rjson::value v1 = calculate_value(rhs._v1, calculate_value_caller::UpdateExpression, previous_item);
-        rjson::value v2 = calculate_value(rhs._v2, calculate_value_caller::UpdateExpression, previous_item);
-        return number_subtract(v1, v2);
-    }
-    }
-    // Can't happen
-    return rjson::null_value();
-}
-
 } // namespace alternator

alternator/expressions.g

@@ -1,9 +1,25 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
+ *
+ * This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
+ * top-level directory for licensing information.
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -129,12 +145,6 @@ REMOVE: R E M O V E;
 ADD: A D D;
 DELETE: D E L E T E;
 
-AND: A N D;
-OR: O R;
-NOT: N O T;
-BETWEEN: B E T W E E N;
-IN: I N;
-
 fragment ALPHA: 'A'..'Z' | 'a'..'z';
 fragment DIGIT: '0'..'9';
 fragment ALNUM: ALPHA | DIGIT | '_';
@@ -155,19 +165,19 @@ path returns [parsed::path p]:
       | '[' INTEGER ']'           { $p.add_index(std::stoi($INTEGER.text)); }
     )*;
 
-value returns [parsed::value v]:
-      VALREF       { $v.set_valref($VALREF.text); }
-    | path         { $v.set_path($path.p); }
-    | NAME         { $v.set_func_name($NAME.text); }
-     '(' x=value   { $v.add_func_parameter($x.v); }
-     (',' x=value  { $v.add_func_parameter($x.v); })*
+update_expression_set_value returns [parsed::value v]:
+      VALREF                             { $v.set_valref($VALREF.text); }
+    | path                               { $v.set_path($path.p); }
+    | NAME                               { $v.set_func_name($NAME.text); }
+     '(' x=update_expression_set_value   { $v.add_func_parameter($x.v); }
+     (',' x=update_expression_set_value  { $v.add_func_parameter($x.v); })*
      ')'
     ;
 
 update_expression_set_rhs returns [parsed::set_rhs rhs]:
-    v=value  { $rhs.set_value(std::move($v.v)); }
-    (   '+' v=value  { $rhs.set_plus(std::move($v.v)); }
-      | '-' v=value  { $rhs.set_minus(std::move($v.v)); }
+    v=update_expression_set_value  { $rhs.set_value(std::move($v.v)); }
+    (   '+' v=update_expression_set_value  { $rhs.set_plus(std::move($v.v)); }
+      | '-' v=update_expression_set_value  { $rhs.set_minus(std::move($v.v)); }
     )?
     ;
 
@@ -202,48 +212,3 @@ update_expression returns [parsed::update_expression e]:
 projection_expression returns [std::vector<parsed::path> v]:
     p=path      { $v.push_back(std::move($p.p)); }
     (',' p=path { $v.push_back(std::move($p.p)); } )* EOF;
-
-
-primitive_condition returns [parsed::primitive_condition c]:
-      v=value         { $c.add_value(std::move($v.v));
-                        $c.set_operator(parsed::primitive_condition::type::VALUE); }
-      (  (  '='       { $c.set_operator(parsed::primitive_condition::type::EQ); }
-          | '<' '>'   { $c.set_operator(parsed::primitive_condition::type::NE); }
-          | '<'       { $c.set_operator(parsed::primitive_condition::type::LT); }
-          | '<' '='   { $c.set_operator(parsed::primitive_condition::type::LE); }
-          | '>'       { $c.set_operator(parsed::primitive_condition::type::GT); }
-          | '>' '='   { $c.set_operator(parsed::primitive_condition::type::GE); }
-         )
-         v=value      { $c.add_value(std::move($v.v)); }
-       | BETWEEN      { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
-         v=value      { $c.add_value(std::move($v.v)); }
-         AND
-         v=value      { $c.add_value(std::move($v.v)); }
-       | IN '('       { $c.set_operator(parsed::primitive_condition::type::IN); }
-         v=value      { $c.add_value(std::move($v.v)); }
-         (',' v=value { $c.add_value(std::move($v.v)); })*
-         ')'
-      )?
-    ;
-
-// The following rules for parsing boolean expressions are verbose and
-// somewhat strange because of Antlr 3's limitations on recursive rules,
-// common rule prefixes, and (lack of) support for operator precedence.
-// These rules could have been written more clearly using a more powerful
-// parser generator - such as Yacc.
-boolean_expression returns [parsed::condition_expression e]:
-	  b=boolean_expression_1       { $e.append(std::move($b.e), '|'); }
-	  (OR b=boolean_expression_1   { $e.append(std::move($b.e), '|'); } )*
-	;
-boolean_expression_1 returns [parsed::condition_expression e]:
-	  b=boolean_expression_2       { $e.append(std::move($b.e), '&'); }
-	  (AND b=boolean_expression_2  { $e.append(std::move($b.e), '&'); } )*
-	;
-boolean_expression_2 returns [parsed::condition_expression e]:
-	  p=primitive_condition        { $e.set_primitive(std::move($p.c)); }
-	| NOT b=boolean_expression_2   { $e = std::move($b.e); $e.apply_not(); }
-	| '(' b=boolean_expression ')' { $e = std::move($b.e); }
-    ;
-
-condition_expression returns [parsed::condition_expression e]:
-    boolean_expression { e=std::move($boolean_expression.e); } EOF;

alternator/expressions.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -11,13 +24,8 @@
 #include <string>
 #include <stdexcept>
 #include <vector>
-#include <unordered_set>
-#include <string_view>
-
-#include <seastar/util/noncopyable_function.hh>
 
 #include "expressions_types.hh"
-#include "utils/rjson.hh"
 
 namespace alternator {
 
@@ -26,64 +34,8 @@ public:
     using runtime_error::runtime_error;
 };
 
-parsed::update_expression parse_update_expression(std::string_view query);
-std::vector<parsed::path> parse_projection_expression(std::string_view query);
-parsed::condition_expression parse_condition_expression(std::string_view query);
-
-void resolve_update_expression(parsed::update_expression& ue,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values);
-void resolve_projection_expression(std::vector<parsed::path>& pe,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names);
-void resolve_condition_expression(parsed::condition_expression& ce,
-        const rjson::value* expression_attribute_names,
-        const rjson::value* expression_attribute_values,
-        std::unordered_set<std::string>& used_attribute_names,
-        std::unordered_set<std::string>& used_attribute_values);
-
-void validate_value(const rjson::value& v, const char* caller);
-
-bool condition_expression_on(const parsed::condition_expression& ce, std::string_view attribute);
-
-// for_condition_expression_on() runs the given function on the attributes
-// that the expression uses. It may run for the same attribute more than once
-// if the same attribute is used more than once in the expression.
-void for_condition_expression_on(const parsed::condition_expression& ce, const noncopyable_function<void(std::string_view)>& func);
-
-// calculate_value() behaves slightly different (especially, different
-// functions supported) when used in different types of expressions, as
-// enumerated in this enum:
-enum class calculate_value_caller {
-    UpdateExpression, ConditionExpression, ConditionExpressionAlone
-};
-
-inline std::ostream& operator<<(std::ostream& out, calculate_value_caller caller) {
-    switch (caller) {
-        case calculate_value_caller::UpdateExpression:
-            out << "UpdateExpression";
-            break;
-        case calculate_value_caller::ConditionExpression:
-            out << "ConditionExpression";
-            break;
-        case calculate_value_caller::ConditionExpressionAlone:
-            out << "ConditionExpression";
-            break;
-        default:
-            out << "unknown type of expression";
-            break;
-    }
-    return out;
-}
-
-rjson::value calculate_value(const parsed::value& v,
-        calculate_value_caller caller,
-        const rjson::value* previous_item);
-
-rjson::value calculate_value(const parsed::set_rhs& rhs,
-        const rjson::value* previous_item);
+parsed::update_expression parse_update_expression(std::string query);
+std::vector<parsed::path> parse_projection_expression(std::string query);
 
 
 } /* namespace alternator */

alternator/expressions_types.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,10 +25,6 @@
 #include <string>
 #include <variant>
 
-#include <seastar/core/shared_ptr.hh>
-
-#include "utils/rjson.hh"
-
 /*
  * Parsed representation of expressions and their components.
  *
@@ -36,23 +45,15 @@ class path {
     // dot (e.g., ".xyz").
     std::string _root;
     std::vector<std::variant<std::string, unsigned>> _operators;
-    // It is useful to limit the depth of a user-specified path, because is
-    // allows us to use recursive algorithms without worrying about recursion
-    // depth. DynamoDB officially limits the length of paths to 32 components
-    // (including the root) so let's use the same limit.
-    static constexpr unsigned depth_limit = 32;
-    void check_depth_limit();
 public:
     void set_root(std::string root) {
         _root = std::move(root);
     }
     void add_index(unsigned i) {
         _operators.emplace_back(i);
-        check_depth_limit();
     }
     void add_dot(std::string(name)) {
         _operators.emplace_back(std::move(name));
-        check_depth_limit();
     }
     const std::string& root() const {
         return _root;
@@ -60,36 +61,12 @@ public:
     bool has_operators() const {
         return !_operators.empty();
     }
-    const std::vector<std::variant<std::string, unsigned>>& operators() const {
-        return _operators;
-    }
-    std::vector<std::variant<std::string, unsigned>>& operators() {
-        return _operators;
-    }
-    friend std::ostream& operator<<(std::ostream&, const path&);
-};
-
-// When an expression is first parsed, all constants are references, like
-// ":val1", into ExpressionAttributeValues. This uses std::string() variant.
-// The resolve_value() function replaces these constants by the JSON item
-// extracted from the ExpressionAttributeValues.
-struct constant {
-    // We use lw_shared_ptr<rjson::value> just to make rjson::value copyable,
-    // to make this entire object copyable as ANTLR needs.
-    using literal = lw_shared_ptr<rjson::value>;
-    std::variant<std::string, literal> _value;
-    void set(const rjson::value& v) {
-        _value = make_lw_shared<rjson::value>(rjson::copy(v));
-    }
-    void set(std::string& s) {
-        _value = s;
-    }
 };
 
 // "value" is is a value used in the right hand side of an assignment
-// expression, "SET a = ...". It can be a constant (a reference to a value
-// included in the request, e.g., ":val"), a path to an attribute from the
-// existing item (e.g., "a.b[3].c"), or a function of other such values.
+// expression, "SET a = ...". It can be a reference to a value included in
+// the request (":val"), a path to an attribute from the existing item
+// (e.g., "a.b[3].c"), or a function of other such values.
 // Note that the real right-hand-side of an assignment is actually a bit
 // more general - it allows either a value, or a value+value or value-value -
 // see class set_rhs below.
@@ -98,12 +75,9 @@ struct value {
         std::string _function_name;
         std::vector<value> _parameters;
     };
-    std::variant<constant, path, function_call> _value;
-    void set_constant(constant c) {
-        _value = std::move(c);
-    }
+    std::variant<std::string, path, function_call> _value;
     void set_valref(std::string s) {
-        _value = constant { std::move(s) };
+        _value = std::move(s);
     }
     void set_path(path p) {
         _value = std::move(p);
@@ -114,15 +88,6 @@ struct value {
     void add_func_parameter(value v) {
         std::get<function_call>(_value)._parameters.emplace_back(std::move(v));
     }
-    bool is_constant() const {
-        return std::holds_alternative<constant>(_value);
-    }
-    bool is_path() const {
-        return std::holds_alternative<path>(_value);
-    }
-    bool is_func() const {
-        return std::holds_alternative<function_call>(_value);
-    }
 };
 
 // The right-hand-side of a SET in an update expression can be either a
@@ -156,10 +121,10 @@ public:
         struct remove {
         };
         struct add {
-            constant _valref;
+            std::string _valref;
         };
         struct del {
-            constant _valref;
+            std::string _valref;
         };
         std::variant<set, remove, add, del> _action;
 
@@ -173,11 +138,11 @@ public:
         }
         void assign_add(path p, std::string v) {
             _path = std::move(p);
-            _action = add { constant { std::move(v) } };
+            _action = add { std::move(v) };
         }
         void assign_del(path p, std::string v) {
             _path = std::move(p);
-            _action = del { constant { std::move(v) } };
+            _action = del { std::move(v) };
         }
     };
 private:
@@ -195,62 +160,6 @@ public:
     const std::vector<action>& actions() const {
         return _actions;
     }
-    std::vector<action>& actions() {
-        return _actions;
-    }
-};
-
-// A primitive_condition is a condition expression involving one condition,
-// while the full condition_expression below adds boolean logic over these
-// primitive conditions.
-// The supported primitive conditions are:
-// 1. Binary operators - v1 OP v2, where OP is =, <>, <, <=, >, or >= and
-//    v1 and v2 are values - from the item (an attribute path), the query
-//    (a ":val" reference), or a function of the the above (only the size()
-//    function is supported).
-// 2. Ternary operator - v1 BETWEEN v2 and v3 (means v1 >= v2 AND v1 <= v3).
-// 3. N-ary operator - v1 IN ( v2, v3, ... )
-// 4. A single function call (attribute_exists etc.). The parser actually
-//    accepts a more general "value" here but later stages reject a value
-//    which is not a function call (because DynamoDB does it too).
-class primitive_condition {
-public:
-    enum class type {
-        UNDEFINED, VALUE, EQ, NE, LT, LE, GT, GE, BETWEEN, IN
-    };
-    type _op = type::UNDEFINED;
-    std::vector<value> _values;
-    void set_operator(type op) {
-        _op = op;
-    }
-    void add_value(value&& v) {
-        _values.push_back(std::move(v));
-    }
-    bool empty() const {
-        return _op == type::UNDEFINED;
-    }
-};
-
-class condition_expression {
-public:
-    bool _negated = false; // If true, the entire condition is negated
-    struct condition_list {
-        char op = '|'; // '&' or '|'
-        std::vector<condition_expression> conditions;
-    };
-    std::variant<primitive_condition, condition_list> _expression = condition_list();
-
-    void set_primitive(primitive_condition&& p) {
-        _expression = std::move(p);
-    }
-    void append(condition_expression&& c, char op);
-    void apply_not() {
-        _negated = !_negated;
-    }
-    bool empty() const {
-        return std::holds_alternative<condition_list>(_expression) &&
-               std::get<condition_list>(_expression).conditions.empty();
-    }
 };
 
 } // namespace parsed

alternator/rjson.cc

@@ -0,0 +1,120 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "rjson.hh"
+#include "error.hh"
+#include <seastar/core/print.hh>
+
+namespace rjson {
+
+static allocator the_allocator;
+
+std::string print(const rjson::value& value) {
+    string_buffer buffer;
+    writer writer(buffer);
+    value.Accept(writer);
+    return std::string(buffer.GetString());
+}
+
+rjson::value copy(const rjson::value& value) {
+    return rjson::value(value, the_allocator);
+}
+
+rjson::value parse(const std::string& str) {
+    return parse_raw(str.c_str(), str.size());
+}
+
+rjson::value parse_raw(const char* c_str, size_t size) {
+    rjson::document d;
+    d.Parse(c_str, size);
+    if (d.HasParseError()) {
+        throw rjson::error(format("Parsing JSON failed: {}", GetParseError_En(d.GetParseError())));
+    }
+    rjson::value& v = d;
+    return std::move(v);
+}
+
+rjson::value& get(rjson::value& value, rjson::string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    if (member_it != value.MemberEnd())
+        return member_it->value;
+    else {
+        throw rjson::error(format("JSON parameter {} not found", name));
+    }
+}
+
+const rjson::value& get(const rjson::value& value, rjson::string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    if (member_it != value.MemberEnd())
+        return member_it->value;
+    else {
+        throw rjson::error(format("JSON parameter {} not found", name));
+    }
+}
+
+rjson::value from_string(const std::string& str) {
+    return rjson::value(str.c_str(), str.size(), the_allocator);
+}
+
+rjson::value from_string(const sstring& str) {
+    return rjson::value(str.c_str(), str.size(), the_allocator);
+}
+
+rjson::value from_string(const char* str, size_t size) {
+    return rjson::value(str, size, the_allocator);
+}
+
+const rjson::value* find(const rjson::value& value, string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    return member_it != value.MemberEnd() ? &member_it->value : nullptr;
+}
+
+rjson::value* find(rjson::value& value, string_ref_type name) {
+    auto member_it = value.FindMember(name);
+    return member_it != value.MemberEnd() ? &member_it->value : nullptr;
+}
+
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member) {
+    base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), std::move(member), the_allocator);
+}
+
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member) {
+    base.AddMember(rjson::value(name.c_str(), name.size(), the_allocator), rjson::value(member), the_allocator);
+}
+
+void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member) {
+    base.AddMember(name, std::move(member), the_allocator);
+}
+
+void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member) {
+    base.AddMember(name, rjson::value(member), the_allocator);
+}
+
+void push_back(rjson::value& base_array, rjson::value&& item) {
+    base_array.PushBack(std::move(item), the_allocator);
+
+}
+
+} // end namespace rjson
+
+std::ostream& std::operator<<(std::ostream& os, const rjson::value& v) {
+    return os << rjson::print(v);
+}

alternator/rjson.hh

@@ -0,0 +1,159 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+/*
+ * rjson is a wrapper over rapidjson library, providing fast JSON parsing and generation.
+ *
+ * rapidjson has strict copy elision policies, which, among other things, involves
+ * using provided char arrays without copying them and allows copying objects only explicitly.
+ * As such, one should be careful when passing strings with limited liveness
+ * (e.g. data underneath local std::strings) to rjson functions, because created JSON objects
+ * may end up relying on dangling char pointers. All rjson functions that create JSONs from strings
+ * by rjson have both APIs for string_ref_type (more optimal, used when the string is known to live
+ * at least as long as the object, e.g. a static char array) and for std::strings. The more optimal
+ * variants should be used *only* if the liveness of the string is guaranteed, otherwise it will
+ * result in undefined behaviour.
+ * Also, bear in mind that methods exposed by rjson::value are generic, but some of them
+ * work fine only for specific types. In case the type does not match, an rjson::error will be thrown.
+ * Examples of such mismatched usages is calling MemberCount() on a JSON value not of object type
+ * or calling Size() on a non-array value.
+ */
+
+#include <string>
+#include <stdexcept>
+
+namespace rjson {
+class error : public std::exception {
+    std::string _msg;
+public:
+    error() = default;
+    error(const std::string& msg) : _msg(msg) {}
+
+    virtual const char* what() const noexcept override { return _msg.c_str(); }
+};
+}
+
+// rapidjson configuration macros
+#define RAPIDJSON_HAS_STDSTRING 1
+// Default rjson policy is to use assert() - which is dangerous for two reasons:
+// 1. assert() can be turned off with -DNDEBUG
+// 2. assert() crashes a program
+// Fortunately, the default policy can be overridden, and so rapidjson errors will
+// throw an rjson::error exception instead.
+#define RAPIDJSON_ASSERT(x) do { if (!(x)) throw rjson::error(std::string("JSON error: condition not met: ") + #x); } while (0)
+
+#include <rapidjson/document.h>
+#include <rapidjson/writer.h>
+#include <rapidjson/stringbuffer.h>
+#include <rapidjson/error/en.h>
+#include <seastar/core/sstring.hh>
+#include "seastarx.hh"
+
+namespace rjson {
+
+using allocator = rapidjson::CrtAllocator;
+using encoding = rapidjson::UTF8<>;
+using document = rapidjson::GenericDocument<encoding, allocator>;
+using value = rapidjson::GenericValue<encoding, allocator>;
+using string_ref_type = value::StringRefType;
+using string_buffer = rapidjson::GenericStringBuffer<encoding>;
+using writer = rapidjson::Writer<string_buffer, encoding>;
+using type = rapidjson::Type;
+
+// Returns an object representing JSON's null
+inline rjson::value null_value() {
+    return rjson::value(rapidjson::kNullType);
+}
+
+// Returns an empty JSON object - {}
+inline rjson::value empty_object() {
+    return rjson::value(rapidjson::kObjectType);
+}
+
+// Returns an empty JSON array - []
+inline rjson::value empty_array() {
+    return rjson::value(rapidjson::kArrayType);
+}
+
+// Returns an empty JSON string - ""
+inline rjson::value empty_string() {
+    return rjson::value(rapidjson::kStringType);
+}
+
+// Convert the JSON value to a string with JSON syntax, the opposite of parse().
+// The representation is dense - without any redundant indentation.
+std::string print(const rjson::value& value);
+
+// Copies given JSON value - involves allocation
+rjson::value copy(const rjson::value& value);
+
+// Parses a JSON value from given string or raw character array.
+// The string/char array liveness does not need to be persisted,
+// as both parse() and parse_raw() will allocate member names and values.
+// Throws rjson::error if parsing failed.
+rjson::value parse(const std::string& str);
+rjson::value parse_raw(const char* c_str, size_t size);
+
+// Creates a JSON value (of JSON string type) out of internal string representations.
+// The string value is copied, so str's liveness does not need to be persisted.
+rjson::value from_string(const std::string& str);
+rjson::value from_string(const sstring& str);
+rjson::value from_string(const char* str, size_t size);
+
+// Returns a pointer to JSON member if it exists, nullptr otherwise
+rjson::value* find(rjson::value& value, rjson::string_ref_type name);
+const rjson::value* find(const rjson::value& value, rjson::string_ref_type name);
+
+// Returns a reference to JSON member if it exists, throws otherwise
+rjson::value& get(rjson::value& value, rjson::string_ref_type name);
+const rjson::value& get(const rjson::value& value, rjson::string_ref_type name);
+
+// Sets a member in given JSON object by moving the member - allocates the name.
+// Throws if base is not a JSON object.
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::value&& member);
+
+// Sets a string member in given JSON object by assigning its reference - allocates the name.
+// NOTICE: member string liveness must be ensured to be at least as long as base's.
+// Throws if base is not a JSON object.
+void set_with_string_name(rjson::value& base, const std::string& name, rjson::string_ref_type member);
+
+// Sets a member in given JSON object by moving the member.
+// NOTICE: name liveness must be ensured to be at least as long as base's.
+// Throws if base is not a JSON object.
+void set(rjson::value& base, rjson::string_ref_type name, rjson::value&& member);
+
+// Sets a string member in given JSON object by assigning its reference.
+// NOTICE: name liveness must be ensured to be at least as long as base's.
+// NOTICE: member liveness must be ensured to be at least as long as base's.
+// Throws if base is not a JSON object.
+void set(rjson::value& base, rjson::string_ref_type name, rjson::string_ref_type member);
+
+// Adds a value to a JSON list by moving the item to its end.
+// Throws if base_array is not a JSON array.
+void push_back(rjson::value& base_array, rjson::value&& item);
+
+} // end namespace rjson
+
+namespace std {
+std::ostream& operator<<(std::ostream& os, const rjson::value& v);
+}

alternator/rmw_operation.hh

@@ -1,114 +0,0 @@
-/*
- * Copyright 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include "seastarx.hh"
-#include "service/paxos/cas_request.hh"
-#include "utils/rjson.hh"
-#include "executor.hh"
-
-namespace alternator {
-
-// An rmw_operation encapsulates the common logic of all the item update
-// operations which may involve a read of the item before the write
-// (so-called Read-Modify-Write operations). These operations include PutItem,
-// UpdateItem and DeleteItem: All of these may be conditional operations (the
-// "Expected" parameter) which requir a read before the write, and UpdateItem
-// may also have an update expression which refers to the item's old value.
-//
-// The code below supports running the read and the write together as one
-// transaction using LWT (this is why rmw_operation is a subclass of
-// cas_request, as required by storage_proxy::cas()), but also has optional
-// modes not using LWT.
-class rmw_operation : public service::cas_request, public enable_shared_from_this<rmw_operation> {
-public:
-    // The following options choose which mechanism to use for isolating
-    // parallel write operations:
-    // * The FORBID_RMW option forbids RMW (read-modify-write) operations
-    //   such as conditional updates. For the remaining write-only
-    //   operations, ordinary quorum writes are isolated enough.
-    // * The LWT_ALWAYS option always uses LWT (lightweight transactions)
-    //   for any write operation - whether or not it also has a read.
-    // * The LWT_RMW_ONLY option uses LWT only for RMW operations, and uses
-    //   ordinary quorum writes for write-only operations.
-    //   This option is not safe if the user may send both RMW and write-only
-    //   operations on the same item.
-    // * The UNSAFE_RMW option does read-modify-write operations as separate
-    //   read and write. It is unsafe - concurrent RMW operations are not
-    //   isolated at all. This option will likely be removed in the future.
-    enum class write_isolation {
-        FORBID_RMW, LWT_ALWAYS, LWT_RMW_ONLY, UNSAFE_RMW
-    };
-    static constexpr auto WRITE_ISOLATION_TAG_KEY = "system:write_isolation";
-
-    static write_isolation get_write_isolation_for_schema(schema_ptr schema);
-
-    static write_isolation default_write_isolation;
-public:
-    static void set_default_write_isolation(std::string_view mode);
-
-protected:
-    // The full request JSON
-    rjson::value _request;
-    // All RMW operations involve a single item with a specific partition
-    // and optional clustering key, in a single table, so the following
-    // information is common to all of them:
-    schema_ptr _schema;
-    partition_key _pk = partition_key::make_empty();
-    clustering_key _ck = clustering_key::make_empty();
-    write_isolation _write_isolation;
-
-    // All RMW operations can have a ReturnValues parameter from the following
-    // choices. But note that only UpdateItem actually supports all of them:
-    enum class returnvalues {
-        NONE, ALL_OLD, UPDATED_OLD, ALL_NEW, UPDATED_NEW
-    } _returnvalues;
-    static returnvalues parse_returnvalues(const rjson::value& request);
-    // When _returnvalues != NONE, apply() should store here, in JSON form,
-    // the values which are to be returned in the "Attributes" field.
-    // The default null JSON means do not return an Attributes field at all.
-    // This field is marked "mutable" so that the const apply() can modify
-    // it (see explanation below), but note that because apply() may be
-    // called more than once, if apply() will sometimes set this field it
-    // must set it (even if just to the default empty value) every time.
-    mutable rjson::value _return_attributes;
-public:
-    // The constructor of a rmw_operation subclass should parse the request
-    // and try to discover as many input errors as it can before really
-    // attempting the read or write operations.
-    rmw_operation(service::storage_proxy& proxy, rjson::value&& request);
-    // rmw_operation subclasses (update_item_operation, put_item_operation
-    // and delete_item_operation) shall implement an apply() function which
-    // takes the previous value of the item (if it was read) and creates the
-    // write mutation. If the previous value of item does not pass the needed
-    // conditional expression, apply() should return an empty optional.
-    // apply() may throw if it encounters input errors not discovered during
-    // the constructor.
-    // apply() may be called more than once in case of contention, so it must
-    // not change the state saved in the object (issue #7218 was caused by
-    // violating this). We mark apply() "const" to let the compiler validate
-    // this for us. The output-only field _return_attributes is marked
-    // "mutable" above so that apply() can still write to it.
-    virtual std::optional<mutation> apply(std::unique_ptr<rjson::value> previous_item, api::timestamp_type ts) const = 0;
-    // Convert the above apply() into the signature needed by cas_request:
-    virtual std::optional<mutation> apply(foreign_ptr<lw_shared_ptr<query::result>> qr, const query::partition_slice& slice, api::timestamp_type ts) override;
-    virtual ~rmw_operation() = default;
-    schema_ptr schema() const { return _schema; }
-    const rjson::value& request() const { return _request; }
-    rjson::value&& move_request() && { return std::move(_request); }
-    future<executor::request_return_type> execute(service::storage_proxy& proxy,
-            service::client_state& client_state,
-            tracing::trace_state_ptr trace_state,
-            service_permit permit,
-            bool needs_read_before_write,
-            stats& stats);
-    std::optional<shard_id> shard_for_execute(bool needs_read_before_write);
-};
-
-} // namespace alternator

alternator/serialization.cc

@@ -1,29 +1,37 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
+#include "base64.hh"
 #include "log.hh"
 #include "serialization.hh"
 #include "error.hh"
 #include "rapidjson/writer.h"
 #include "concrete_types.hh"
-#include "cql3/type_json.hh"
-#include "position_in_partition.hh"
 
 static logging::logger slogger("alternator-serialization");
 
 namespace alternator {
 
-bool is_alternator_keyspace(const sstring& ks_name);
-
-type_info type_info_from_string(std::string_view type) {
-    static thread_local const std::unordered_map<std::string_view, type_info> type_infos = {
+type_info type_info_from_string(std::string type) {
+    static thread_local const std::unordered_map<std::string, type_info> type_infos = {
         {"S", {alternator_type::S, utf8_type}},
         {"B", {alternator_type::B, bytes_type}},
         {"BOOL", {alternator_type::BOOL, boolean_type}},
@@ -56,36 +64,32 @@ struct from_json_visitor {
 
     void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), from_json_visitor{v, bo}); };
     void operator()(const string_type_impl& t) {
-        bo.write(t.from_string(rjson::to_string_view(v)));
+        bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
     }
     void operator()(const bytes_type_impl& t) const {
-        bo.write(rjson::base64_decode(v));
+        bo.write(base64_decode(v));
     }
     void operator()(const boolean_type_impl& t) const {
         bo.write(boolean_type->decompose(v.GetBool()));
     }
     void operator()(const decimal_type_impl& t) const {
-        try {
-            bo.write(t.from_string(rjson::to_string_view(v)));
-        } catch (const marshal_exception& e) {
-            throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", v));
-        }
+        bo.write(t.from_string(sstring_view(v.GetString(), v.GetStringLength())));
     }
     // default
     void operator()(const abstract_type& t) const {
-        bo.write(from_json_object(t, v, cql_serialization_format::internal()));
+        bo.write(t.from_json_object(Json::Value(rjson::print(v)), cql_serialization_format::internal()));
     }
 };
 
 bytes serialize_item(const rjson::value& item) {
     if (item.IsNull() || item.MemberCount() != 1) {
-        throw api_error::validation(format("An item can contain only one attribute definition: {}", item));
+        throw api_error("ValidationException", format("An item can contain only one attribute definition: {}", item));
     }
     auto it = item.MemberBegin();
-    type_info type_info = type_info_from_string(rjson::to_string_view(it->name)); // JSON keys are guaranteed to be strings
+    type_info type_info = type_info_from_string(it->name.GetString()); // JSON keys are guaranteed to be strings
 
     if (type_info.atype == alternator_type::NOT_SUPPORTED_YET) {
-        slogger.trace("Non-optimal serialization of type {}", it->name);
+        slogger.trace("Non-optimal serialization of type {}", it->name.GetString());
         return bytes{int8_t(type_info.atype)} + to_bytes(rjson::print(item));
     }
 
@@ -103,27 +107,27 @@ struct to_json_visitor {
 
     void operator()(const reversed_type_impl& t) const { visit(*t.underlying_type(), to_json_visitor{deserialized, type_ident, bv}); };
     void operator()(const decimal_type_impl& t) const {
-        auto s = to_json_string(*decimal_type, bytes(bv));
+        auto s = decimal_type->to_json_string(bytes(bv));
         //FIXME(sarna): unnecessary copy
-        rjson::add_with_string_name(deserialized, type_ident, rjson::from_string(s));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(s));
     }
     void operator()(const string_type_impl& t) {
-        rjson::add_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
     }
     void operator()(const bytes_type_impl& t) const {
         std::string b64 = base64_encode(bv);
-        rjson::add_with_string_name(deserialized, type_ident, rjson::from_string(b64));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(b64));
     }
     // default
     void operator()(const abstract_type& t) const {
-        rjson::add_with_string_name(deserialized, type_ident, rjson::parse(to_json_string(t, bytes(bv))));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::parse(t.to_string(bytes(bv))));
     }
 };
 
 rjson::value deserialize_item(bytes_view bv) {
     rjson::value deserialized(rapidjson::kObjectType);
     if (bv.empty()) {
-        throw api_error::validation("Serialized value empty");
+        throw api_error("ValidationException", "Serialized value empty");
     }
 
     alternator_type atype = alternator_type(bv[0]);
@@ -131,7 +135,7 @@ rjson::value deserialize_item(bytes_view bv) {
 
     if (atype == alternator_type::NOT_SUPPORTED_YET) {
         slogger.trace("Non-optimal deserialization of alternator type {}", int8_t(atype));
-        return rjson::parse(std::string_view(reinterpret_cast<const char *>(bv.data()), bv.size()));
+        return rjson::parse_raw(reinterpret_cast<const char *>(bv.data()), bv.size());
     }
     type_representation type_representation = represent_type(atype);
     visit(*type_representation.dtype, to_json_visitor{deserialized, type_representation.ident, bv});
@@ -148,59 +152,34 @@ std::string type_to_string(data_type type) {
     };
     auto it = types.find(type);
     if (it == types.end()) {
-        // fall back to string, in order to be able to present
-        // internal Scylla types in a human-readable way
-        return "S";
+        throw std::runtime_error(format("Unknown type {}", type->name()));
     }
     return it->second;
 }
 
 bytes get_key_column_value(const rjson::value& item, const column_definition& column) {
     std::string column_name = column.name_as_text();
-    const rjson::value* key_typed_value = rjson::find(item, column_name);
-    if (!key_typed_value) {
-        throw api_error::validation(format("Key column {} not found", column_name));
+    std::string expected_type = type_to_string(column.type);
+
+    const rjson::value& key_typed_value = rjson::get(item, rjson::value::StringRefType(column_name.c_str()));
+    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1) {
+        throw api_error("ValidationException",
+                format("Missing or invalid value object for key column {}: {}", column_name, item));
     }
-    return get_key_from_typed_value(*key_typed_value, column);
+    return get_key_from_typed_value(key_typed_value, column, expected_type);
 }
 
-// Parses the JSON encoding for a key value, which is a map with a single
-// entry whose key is the type and the value is the encoded value.
-// If this type does not match the desired "type_str", an api_error::validation
-// error is thrown (the "name" parameter is the name of the column which will
-// mentioned in the exception message).
-// If the type does match, a reference to the encoded value is returned.
-static const rjson::value& get_typed_value(const rjson::value& key_typed_value, std::string_view type_str, std::string_view name, std::string_view value_name) {
-    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
-            !key_typed_value.MemberBegin()->value.IsString()) {
-        throw api_error::validation(
-                format("Malformed value object for {} {}: {}",
-                        value_name, name, key_typed_value));
-    }
-
+bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column, const std::string& expected_type) {
     auto it = key_typed_value.MemberBegin();
-    if (rjson::to_string_view(it->name) != type_str) {
-        throw api_error::validation(
-                format("Type mismatch: expected type {} for {} {}, got type {}",
-                        type_str, value_name, name, it->name));
-    }
-    return it->value;
-}
-
-// Parses the JSON encoding for a key value, which is a map with a single
-// entry, whose key is the type (expected to match the key column's type)
-// and the value is the encoded value.
-bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column) {
-    auto& value = get_typed_value(key_typed_value, type_to_string(column.type), column.name_as_text(), "key column");
-    std::string_view value_view = rjson::to_string_view(value);
-    if (value_view.empty()) {
-        throw api_error::validation(
-                format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
+    if (it->name.GetString() != expected_type) {
+        throw api_error("ValidationException",
+                format("Type mismatch: expected type {} for key column {}, got type {}",
+                        expected_type, column.name_as_text(), it->name.GetString()));
     }
     if (column.type == bytes_type) {
-        return rjson::base64_decode(value);
+        return base64_decode(it->value);
     } else {
-        return column.type->from_string(value_view);
+        return column.type->from_string(it->value.GetString());
     }
 
 }
@@ -215,14 +194,11 @@ rjson::value json_key_column_value(bytes_view cell, const column_definition& col
         // FIXME: use specialized Alternator number type, not the more
         // general "decimal_type". A dedicated type can be more efficient
         // in storage space and in parsing speed.
-        auto s = to_json_string(*decimal_type, bytes(cell));
+        auto s = decimal_type->to_json_string(bytes(cell));
         return rjson::from_string(s);
     } else {
-        // Support for arbitrary key types is useful for parsing values of virtual tables,
-        // which can involve any type supported by Scylla.
-        // In order to guarantee that the returned type is parsable by alternator clients,
-        // they are represented simply as strings.
-        return rjson::from_string(column.type->to_string(bytes(cell)));
+        // We shouldn't get here, we shouldn't see such key columns.
+        throw std::runtime_error(format("Unexpected key type: {}", column.type->name()));
     }
 }
 
@@ -251,192 +227,22 @@ clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
     return clustering_key::from_exploded(raw_ck);
 }
 
-position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema) {
-    auto ck = ck_from_json(item, schema);
-    if (is_alternator_keyspace(schema->ks_name())) {
-        return position_in_partition::for_key(std::move(ck));
-    }
-    const auto region_item = rjson::find(item, scylla_paging_region);
-    const auto weight_item = rjson::find(item, scylla_paging_weight);
-    if (bool(region_item) != bool(weight_item)) {
-        throw api_error::validation("Malformed value object: region and weight has to be either both missing or both present");
-    }
-    partition_region region;
-    bound_weight weight;
-    if (region_item) {
-        auto region_view = rjson::to_string_view(get_typed_value(*region_item, "S", scylla_paging_region, "key region"));
-        auto weight_view = rjson::to_string_view(get_typed_value(*weight_item, "N", scylla_paging_weight, "key weight"));
-        auto region = parse_partition_region(region_view);
-        if (weight_view == "-1") {
-            weight = bound_weight::before_all_prefixed;
-        } else if (weight_view == "0") {
-            weight = bound_weight::equal;
-        } else if (weight_view == "1") {
-            weight = bound_weight::after_all_prefixed;
-        } else {
-            throw std::runtime_error(fmt::format("Invalid value for weight: {}", weight_view));
-        }
-        return position_in_partition(region, weight, region == partition_region::clustered ? std::optional(std::move(ck)) : std::nullopt);
-    }
-    if (ck.is_empty()) {
-        return position_in_partition(position_in_partition::partition_start_tag_t());
-    }
-    return position_in_partition::for_key(std::move(ck));
-}
-
 big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
     if (!v.IsObject() || v.MemberCount() != 1) {
-        throw api_error::validation(format("{}: invalid number object", diagnostic));
+        throw api_error("ValidationException", format("{}: invalid number object", diagnostic));
     }
     auto it = v.MemberBegin();
     if (it->name != "N") {
-        throw api_error::validation(format("{}: expected number, found type '{}'", diagnostic, it->name));
+        throw api_error("ValidationException", format("{}: expected number, found type '{}'", diagnostic, it->name));
     }
-    try {
-        if (!it->value.IsString()) {
-            // We shouldn't reach here. Callers normally validate their input
-            // earlier with validate_value().
-            throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
-        }
-        return big_decimal(rjson::to_string_view(it->value));
-    } catch (const marshal_exception& e) {
-        throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", it->value));
+    if (it->value.IsNumber()) {
+         // FIXME(sarna): should use big_decimal constructor with numeric values directly:
+        return big_decimal(rjson::print(it->value));
     }
-}
-
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return std::nullopt;
+    if (!it->value.IsString()) {
+        throw api_error("ValidationException", format("{}: improperly formatted number constant", diagnostic));
     }
-    auto it = v.MemberBegin();
-    if (it->name != "N" || !it->value.IsString()) {
-        return std::nullopt;
-    }
-    try {
-        return big_decimal(rjson::to_string_view(it->value));
-    } catch (const marshal_exception& e) {
-        return std::nullopt;
-    }
-}
-
-const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return {"", nullptr};
-    }
-    auto it = v.MemberBegin();
-    const std::string it_key = it->name.GetString();
-    if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
-        return {std::move(it_key), nullptr};
-    }
-    return std::make_pair(it_key, &(it->value));
-}
-
-const rjson::value* unwrap_list(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return nullptr;
-    }
-    auto it = v.MemberBegin();
-    if (it->name != std::string("L")) {
-        return nullptr;
-    }
-    return &(it->value);
-}
-
-// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
-// sum, again as a JSON-encoded number.
-rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
-    auto n1 = unwrap_number(v1, "UpdateExpression");
-    auto n2 = unwrap_number(v2, "UpdateExpression");
-    rjson::value ret = rjson::empty_object();
-    std::string str_ret = std::string((n1 + n2).to_string());
-    rjson::add(ret, "N", rjson::from_string(str_ret));
-    return ret;
-}
-
-rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
-    auto n1 = unwrap_number(v1, "UpdateExpression");
-    auto n2 = unwrap_number(v2, "UpdateExpression");
-    rjson::value ret = rjson::empty_object();
-    std::string str_ret = std::string((n1 - n2).to_string());
-    rjson::add(ret, "N", rjson::from_string(str_ret));
-    return ret;
-}
-
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
-// return the sum of both sets, again as a set value.
-rjson::value set_sum(const rjson::value& v1, const rjson::value& v2) {
-    auto [set1_type, set1] = unwrap_set(v1);
-    auto [set2_type, set2] = unwrap_set(v2);
-    if (set1_type != set2_type) {
-        throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
-    }
-    if (!set1 || !set2) {
-        throw api_error::validation("UpdateExpression: ADD operation for sets must be given sets as arguments");
-    }
-    rjson::value sum = rjson::copy(*set1);
-    std::set<rjson::value, rjson::single_value_comp> set1_raw;
-    for (auto it = sum.Begin(); it != sum.End(); ++it) {
-        set1_raw.insert(rjson::copy(*it));
-    }
-    for (const auto& a : set2->GetArray()) {
-        if (!set1_raw.contains(a)) {
-            rjson::push_back(sum, rjson::copy(a));
-        }
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::add_with_string_name(ret, set1_type, std::move(sum));
-    return ret;
-}
-
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
-// return the difference of s1 - s2, again as a set value.
-// DynamoDB does not allow empty sets, so if resulting set is empty, return
-// an unset optional instead.
-std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2) {
-    auto [set1_type, set1] = unwrap_set(v1);
-    auto [set2_type, set2] = unwrap_set(v2);
-    if (set1_type != set2_type) {
-        throw api_error::validation(format("Set DELETE type mismatch: {} and {}", set1_type, set2_type));
-    }
-    if (!set1 || !set2) {
-        throw api_error::validation("UpdateExpression: DELETE operation can only be performed on a set");
-    }
-    std::set<rjson::value, rjson::single_value_comp> set1_raw;
-    for (auto it = set1->Begin(); it != set1->End(); ++it) {
-        set1_raw.insert(rjson::copy(*it));
-    }
-    for (const auto& a : set2->GetArray()) {
-        set1_raw.erase(a);
-    }
-    if (set1_raw.empty()) {
-        return std::nullopt;
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::add_with_string_name(ret, set1_type, rjson::empty_array());
-    rjson::value& result_set = ret[set1_type];
-    for (const auto& a : set1_raw) {
-        rjson::push_back(result_set, rjson::copy(a));
-    }
-    return ret;
-}
-
-// Take two JSON-encoded list values (remember that a list value is
-// {"L": [...the actual list]}) and return the concatenation, again as
-// a list value.
-// Returns a null value if one of the arguments is not actually a list.
-rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2) {
-    const rjson::value* list1 = unwrap_list(v1);
-    const rjson::value* list2 = unwrap_list(v2);
-    if (!list1 || !list2) {
-        return rjson::null_value();
-    }
-    rjson::value cat = rjson::copy(*list1);
-    for (const auto& a : list2->GetArray()) {
-        rjson::push_back(cat, rjson::copy(a));
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::add(ret, "L", std::move(cat));
-    return ret;
+    return big_decimal(it->value.GetString());
 }
 
 }

alternator/serialization.hh

@@ -1,24 +1,34 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include <string>
 #include <string_view>
-#include <optional>
 #include "types.hh"
-#include "schema_fwd.hh"
+#include "schema.hh"
 #include "keys.hh"
-#include "utils/rjson.hh"
+#include "rjson.hh"
 #include "utils/big_decimal.hh"
 
-class position_in_partition;
-
 namespace alternator {
 
 enum class alternator_type : int8_t {
@@ -35,10 +45,7 @@ struct type_representation {
     data_type dtype;
 };
 
-inline constexpr std::string_view scylla_paging_region(":scylla:paging:region");
-inline constexpr std::string_view scylla_paging_weight(":scylla:paging:weight");
-
-type_info type_info_from_string(std::string_view type);
+type_info type_info_from_string(std::string type);
 type_representation represent_type(alternator_type atype);
 
 bytes serialize_item(const rjson::value& item);
@@ -47,47 +54,13 @@ rjson::value deserialize_item(bytes_view bv);
 std::string type_to_string(data_type type);
 
 bytes get_key_column_value(const rjson::value& item, const column_definition& column);
-bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column);
+bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column, const std::string& expected_type);
 rjson::value json_key_column_value(bytes_view cell, const column_definition& column);
 
 partition_key pk_from_json(const rjson::value& item, schema_ptr schema);
 clustering_key ck_from_json(const rjson::value& item, schema_ptr schema);
-position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema);
 
 // If v encodes a number (i.e., it is a {"N": [...]}, returns an object representing it.  Otherwise,
 // raises ValidationException with diagnostic.
 big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);
-
-// try_unwrap_number is like unwrap_number, but returns an unset optional
-// when the given v does not encode a number.
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v);
-
-// Check if a given JSON object encodes a set (i.e., it is a {"SS": [...]}, or "NS", "BS"
-// and returns set's type and a pointer to that set. If the object does not encode a set,
-// returned value is {"", nullptr}
-const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v);
-
-// Check if a given JSON object encodes a list (i.e., it is a {"L": [...]}
-// and returns a pointer to that list.
-const rjson::value* unwrap_list(const rjson::value& v);
-
-// Take two JSON-encoded numeric values ({"N": "thenumber"}) and return the
-// sum, again as a JSON-encoded number.
-rjson::value number_add(const rjson::value& v1, const rjson::value& v2);
-rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2);
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual set]}) and
-// return the sum of both sets, again as a set value.
-rjson::value set_sum(const rjson::value& v1, const rjson::value& v2);
-// Take two JSON-encoded set values (e.g. {"SS": [...the actual list]}) and
-// return the difference of s1 - s2, again as a set value.
-// DynamoDB does not allow empty sets, so if resulting set is empty, return
-// an unset optional instead.
-std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2);
-// Take two JSON-encoded list values (remember that a list value is
-// {"L": [...the actual list]}) and return the concatenation, again as
-// a list value.
-// Returns a null value if one of the arguments is not actually a list.
-rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2);
-
-
 }

alternator/server.cc

@@ -1,29 +1,34 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "alternator/server.hh"
 #include "log.hh"
 #include <seastar/http/function_handlers.hh>
-#include <seastar/http/short_streams.hh>
-#include <seastar/core/coroutine.hh>
 #include <seastar/json/json_elements.hh>
-#include <seastar/util/defer.hh>
-#include <seastar/util/short_streams.hh>
-#include "seastarx.hh"
+#include <seastarx.hh>
 #include "error.hh"
-#include "service/qos/service_level_controller.hh"
-#include "utils/rjson.hh"
+#include "rjson.hh"
 #include "auth.hh"
 #include <cctype>
-#include "service/storage_proxy.hh"
-#include "gms/gossiper.hh"
-#include "utils/overloaded_functor.hh"
-#include "utils/fb_utilities.hh"
+#include "cql3/query_processor.hh"
 
 static logging::logger slogger("alternator-server");
 
@@ -52,40 +57,6 @@ inline std::vector<std::string_view> split(std::string_view text, char separator
     return tokens;
 }
 
-// Handle CORS (Cross-origin resource sharing) in the HTTP request:
-// If the request has the "Origin" header specifying where the script which
-// makes this request comes from, we need to reply with the header
-// "Access-Control-Allow-Origin: *" saying that this (and any) origin is fine.
-// Additionally, if preflight==true (i.e., this is an OPTIONS request),
-// the script can also "request" in headers that the server allows it to use
-// some HTTP methods and headers in the followup request, and the server
-// should respond by "allowing" them in the response headers.
-// We also add the header "Access-Control-Expose-Headers" to let the script
-// access additional headers in the response.
-// This handle_CORS() should be used when handling any HTTP method - both the
-// usual GET and POST, and also the "preflight" OPTIONS method.
-static void handle_CORS(const request& req, reply& rep, bool preflight) {
-    if (!req.get_header("origin").empty()) {
-        rep.add_header("Access-Control-Allow-Origin", "*");
-        // This is the list that DynamoDB returns for expose headers. I am
-        // not sure why not just return "*" here, what's the risk?
-        rep.add_header("Access-Control-Expose-Headers", "x-amzn-RequestId,x-amzn-ErrorType,x-amzn-ErrorMessage,Date");
-        if (preflight) {
-            sstring s = req.get_header("Access-Control-Request-Headers");
-            if (!s.empty()) {
-                rep.add_header("Access-Control-Allow-Headers", std::move(s));
-            }
-            s = req.get_header("Access-Control-Request-Method");
-            if (!s.empty()) {
-                rep.add_header("Access-Control-Allow-Methods", std::move(s));
-            }
-            // Our CORS response never change anyway, let the browser cache it
-            // for two hours (Chrome's maximum):
-            rep.add_header("Access-Control-Max-Age", "7200");
-        }
-    }
-}
-
 // DynamoDB HTTP error responses are structured as follows
 // https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
 // Our handlers throw an exception to report an error. If the exception
@@ -94,183 +65,100 @@ static void handle_CORS(const request& req, reply& rep, bool preflight) {
 // Internal Server Error.
 class api_handler : public handler_base {
 public:
-    api_handler(const std::function<future<executor::request_return_type>(std::unique_ptr<request> req)>& _handle) : _f_handle(
-         [this, _handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
-         return seastar::futurize_invoke(_handle, std::move(req)).then_wrapped([this, rep = std::move(rep)](future<executor::request_return_type> resf) mutable {
+    api_handler(const future_json_function& _handle) : _f_handle(
+         [_handle](std::unique_ptr<request> req, std::unique_ptr<reply> rep) {
+         return seastar::futurize_apply(_handle, std::move(req)).then_wrapped([rep = std::move(rep)](future<json::json_return_type> resf) mutable {
              if (resf.failed()) {
                  // Exceptions of type api_error are wrapped as JSON and
                  // returned to the client as expected. Other types of
                  // exceptions are unexpected, and returned to the user
                  // as an internal server error:
+                 api_error ret;
                  try {
                      resf.get();
                  } catch (api_error &ae) {
-                     generate_error_reply(*rep, ae);
+                     ret = ae;
                  } catch (rjson::error & re) {
-                     generate_error_reply(*rep,
-                             api_error::validation(re.what()));
+                     ret = api_error("ValidationException", re.what());
                  } catch (...) {
-                     generate_error_reply(*rep,
-                             api_error::internal(format("Internal server error: {}", std::current_exception())));
+                     ret = api_error(
+                             "Internal Server Error",
+                             format("Internal server error: {}", std::current_exception()),
+                             reply::status_type::internal_server_error);
                  }
+                 // FIXME: what is this version number?
+                 rep->_content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + ret._type + "\"," +
+                         "\"message\":\"" + ret._msg + "\"}";
+                 rep->_status = ret._http_code;
+                 slogger.trace("api_handler error case: {}", rep->_content);
                  return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
              }
+             slogger.trace("api_handler success case");
              auto res = resf.get0();
-             std::visit(overloaded_functor {
-                 [&] (const json::json_return_type& json_return_value) {
-                     slogger.trace("api_handler success case");
-                     if (json_return_value._body_writer) {
-                         // Unfortunately, write_body() forces us to choose
-                         // from a fixed and irrelevant list of "mime-types"
-                         // at this point. But we'll override it with the
-                         // one (application/x-amz-json-1.0) below.
-                         rep->write_body("json", std::move(json_return_value._body_writer));
-                     } else {
-                         rep->_content += json_return_value._res;
-                     }
-                 },
-                 [&] (const api_error& err) {
-                     generate_error_reply(*rep, err);
-                 }
-             }, res);
-
+             if (res._body_writer) {
+                 rep->write_body("json", std::move(res._body_writer));
+             } else {
+                 rep->_content += res._res;
+             }
              return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
          });
-    }) { }
+    }), _type("json") { }
 
     api_handler(const api_handler&) = default;
     future<std::unique_ptr<reply>> handle(const sstring& path,
             std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        handle_CORS(*req, *rep, false);
         return _f_handle(std::move(req), std::move(rep)).then(
                 [this](std::unique_ptr<reply> rep) {
-                    rep->set_mime_type("application/x-amz-json-1.0");
-                    rep->done();
+                    rep->done(_type);
                     return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
                 });
     }
 
 protected:
-    void generate_error_reply(reply& rep, const api_error& err) {
-        rjson::value results = rjson::empty_object();
-        rjson::add(results, "__type", rjson::from_string("com.amazonaws.dynamodb.v20120810#" + err._type));
-        rjson::add(results, "message", err._msg);
-        rep._content = rjson::print(std::move(results));
-        rep._status = err._http_code;
-        slogger.trace("api_handler error case: {}", rep._content);
-    }
-
     future_handler_function _f_handle;
+    sstring _type;
 };
 
-class gated_handler : public handler_base {
-    seastar::gate& _gate;
-public:
-    gated_handler(seastar::gate& gate) : _gate(gate) {}
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) = 0;
-    virtual future<std::unique_ptr<reply>> handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) final override {
-        return with_gate(_gate, [this, &path, req = std::move(req), rep = std::move(rep)] () mutable {
-            return do_handle(path, std::move(req), std::move(rep));
-        });
-    }
-};
-
-class health_handler : public gated_handler {
-public:
-    health_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
-protected:
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        handle_CORS(*req, *rep, false);
+class health_handler : public handler_base {
+    virtual future<std::unique_ptr<reply>> handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
         rep->set_status(reply::status_type::ok);
         rep->write_body("txt", format("healthy: {}", req->get_header("Host")));
         return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
     }
 };
 
-class local_nodelist_handler : public gated_handler {
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
-public:
-    local_nodelist_handler(seastar::gate& pending_requests, service::storage_proxy& proxy, gms::gossiper& gossiper)
-        : gated_handler(pending_requests)
-        , _proxy(proxy)
-        , _gossiper(gossiper) {}
-protected:
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        rjson::value results = rjson::empty_array();
-        // It's very easy to get a list of all live nodes on the cluster,
-        // using _gossiper().get_live_members(). But getting
-        // just the list of live nodes in this DC needs more elaborate code:
-        auto& topology = _proxy.get_token_metadata_ptr()->get_topology();
-        sstring local_dc = topology.get_datacenter();
-        std::unordered_set<gms::inet_address> local_dc_nodes = topology.get_datacenter_endpoints().at(local_dc);
-        for (auto& ip : local_dc_nodes) {
-            if (_gossiper.is_alive(ip)) {
-                rjson::push_back(results, rjson::from_string(ip.to_sstring()));
-            }
-        }
-        rep->set_status(reply::status_type::ok);
-        rep->set_content_type("json");
-        rep->_content = rjson::print(results);
-        return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-    }
-};
-
-// The CORS (Cross-origin resource sharing) protocol can send an OPTIONS
-// request before ("pre-flight") the main request. The response to this
-// request can be empty, but needs to have the right headers (which we
-// fill with handle_CORS())
-class options_handler : public gated_handler {
-public:
-    options_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
-protected:
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        handle_CORS(*req, *rep, true);
-        rep->set_status(reply::status_type::ok);
-        rep->write_body("txt", sstring(""));
-        return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-    }
-};
-
-future<std::string> server::verify_signature(const request& req, const chunked_content& content) {
+future<> server::verify_signature(const request& req) {
     if (!_enforce_authorization) {
         slogger.debug("Skipping authorization");
-        return make_ready_future<std::string>();
+        return make_ready_future<>();
     }
     auto host_it = req._headers.find("Host");
     if (host_it == req._headers.end()) {
-        throw api_error::invalid_signature("Host header is mandatory for signature verification");
+        throw api_error("InvalidSignatureException", "Host header is mandatory for signature verification");
     }
     auto authorization_it = req._headers.find("Authorization");
-    if (authorization_it == req._headers.end()) {
-        throw api_error::missing_authentication_token("Authorization header is mandatory for signature verification");
+    if (host_it == req._headers.end()) {
+        throw api_error("InvalidSignatureException", "Authorization header is mandatory for signature verification");
     }
     std::string host = host_it->second;
-    std::string_view authorization_header = authorization_it->second;
-    auto pos = authorization_header.find_first_of(' ');
-    if (pos == std::string_view::npos || authorization_header.substr(0, pos) != "AWS4-HMAC-SHA256") {
-        throw api_error::invalid_signature(format("Authorization header must use AWS4-HMAC-SHA256 algorithm: {}", authorization_header));
-    }
-    authorization_header.remove_prefix(pos+1);
+    std::vector<std::string_view> credentials_raw = split(authorization_it->second, ' ');
     std::string credential;
     std::string user_signature;
     std::string signed_headers_str;
     std::vector<std::string_view> signed_headers;
-    do {
-        // Either one of a comma or space can mark the end of an entry
-        pos = authorization_header.find_first_of(" ,");
-        std::string_view entry = authorization_header.substr(0, pos);
-        if (pos != std::string_view::npos) {
-            authorization_header.remove_prefix(pos + 1);
-        }
-        if (entry.empty()) {
-            continue;
-        }
+    for (std::string_view entry : credentials_raw) {
         std::vector<std::string_view> entry_split = split(entry, '=');
         if (entry_split.size() != 2) {
+            if (entry != "AWS4-HMAC-SHA256") {
+                throw api_error("InvalidSignatureException", format("Only AWS4-HMAC-SHA256 algorithm is supported. Found: {}", entry));
+            }
             continue;
         }
         std::string_view auth_value = entry_split[1];
+        // Commas appear as an additional (quite redundant) delimiter
+        if (auth_value.back() == ',') {
+            auth_value.remove_suffix(1);
+        }
         if (entry_split[0] == "Credential") {
             credential = std::string(auth_value);
         } else if (entry_split[0] == "Signature") {
@@ -280,11 +168,10 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
             signed_headers = split(auth_value, ';');
             std::sort(signed_headers.begin(), signed_headers.end());
         }
-    } while (pos != std::string_view::npos);
-
+    }
     std::vector<std::string_view> credential_split = split(credential, '/');
     if (credential_split.size() != 5) {
-        throw api_error::validation(format("Incorrect credential information format: {}", credential));
+        throw api_error("ValidationException", format("Incorrect credential information format: {}", credential));
     }
     std::string user(credential_split[0]);
     std::string datestamp(credential_split[1]);
@@ -305,10 +192,10 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
         }
     }
 
-    auto cache_getter = [&proxy = _proxy] (std::string username) {
-        return get_key_from_roles(proxy, std::move(username));
+    auto cache_getter = [] (std::string username) {
+        return get_key_from_roles(cql3::get_query_processor().local(), std::move(username));
     };
-    return _key_cache.get_ptr(user, cache_getter).then([this, &req, &content,
+    return _key_cache.get_ptr(user, cache_getter).then([this, &req,
                                                     user = std::move(user),
                                                     host = std::move(host),
                                                     datestamp = std::move(datestamp),
@@ -318,108 +205,37 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
                                                     service = std::move(service),
                                                     user_signature = std::move(user_signature)] (key_cache::value_ptr key_ptr) {
         std::string signature = get_signature(user, *key_ptr, std::string_view(host), req._method,
-                datestamp, signed_headers_str, signed_headers_map, content, region, service, "");
+                datestamp, signed_headers_str, signed_headers_map, req.content, region, service, "");
 
         if (signature != std::string_view(user_signature)) {
             _key_cache.remove(user);
-            throw api_error::unrecognized_client("The security token included in the request is invalid.");
+            throw api_error("UnrecognizedClientException", "The security token included in the request is invalid.");
         }
-        return user;
     });
 }
 
-static tracing::trace_state_ptr create_tracing_session(tracing::tracing& tracing_instance) {
-    tracing::trace_state_props_set props;
-    props.set<tracing::trace_state_props::full_tracing>();
-    props.set_if<tracing::trace_state_props::log_slow_query>(tracing_instance.slow_query_tracing_enabled());
-    return tracing_instance.create_session(tracing::trace_type::QUERY, props);
-}
-
-// truncated_content_view() prints a potentially long chunked_content for
-// debugging purposes. In the common case when the content is not excessively
-// long, it just returns a view into the given content, without any copying.
-// But when the content is very long, it is truncated after some arbitrary
-// max_len (or one chunk, whichever comes first), with "<truncated>" added at
-// the end. To do this modification to the string, we need to create a new
-// std::string, so the caller must pass us a reference to one, "buf", where
-// we can store the content. The returned view is only alive for as long this
-// buf is kept alive.
-static std::string_view truncated_content_view(const chunked_content& content, std::string& buf) {
-    constexpr size_t max_len = 1024;
-    if (content.empty()) {
-        return std::string_view();
-    } else if (content.size() == 1 && content.begin()->size() <= max_len) {
-        return std::string_view(content.begin()->get(), content.begin()->size());
-    } else {
-        buf = std::string(content.begin()->get(), std::min(content.begin()->size(), max_len)) + "<truncated>";
-        return std::string_view(buf);
-    }
-}
-
-static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_state, std::string_view username, sstring_view op, const chunked_content& query) {
-    tracing::trace_state_ptr trace_state;
-    tracing::tracing& tracing_instance = tracing::tracing::get_local_tracing_instance();
-    if (tracing_instance.trace_next_query() || tracing_instance.slow_query_tracing_enabled()) {
-        trace_state = create_tracing_session(tracing_instance);
-        std::string buf;
-        tracing::add_session_param(trace_state, "alternator_op", op);
-        tracing::add_query(trace_state, truncated_content_view(query, buf));
-        tracing::begin(trace_state, format("Alternator {}", op), client_state.get_client_address());
-        if (!username.empty()) {
-            tracing::set_username(trace_state, auth::authenticated_user(username));
-        }
-    }
-    return trace_state;
-}
-
-future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request> req) {
-    _executor._stats.total_operations++;
+future<json::json_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
     sstring target = req->get_header(TARGET);
     std::vector<std::string_view> split_target = split(target, '.');
     //NOTICE(sarna): Target consists of Dynamo API version followed by a dot '.' and operation type (e.g. CreateTable)
     std::string op = split_target.empty() ? std::string() : std::string(split_target.back());
-    // JSON parsing can allocate up to roughly 2x the size of the raw
-    // document, + a couple of bytes for maintenance.
-    // TODO: consider the case where req->content_length is missing. Maybe
-    // we need to take the content_length_limit and return some of the units
-    // when we finish read_content_and_verify_signature?
-    size_t mem_estimate = req->content_length * 2 + 8000;
-    auto units_fut = get_units(*_memory_limiter, mem_estimate);
-    if (_memory_limiter->waiters()) {
-        ++_executor._stats.requests_blocked_memory;
-    }
-    auto units = co_await std::move(units_fut);
-    assert(req->content_stream);
-    chunked_content content = co_await util::read_entire_stream(*req->content_stream);
-    auto username = co_await verify_signature(*req, content);
-
-    if (slogger.is_enabled(log_level::trace)) {
-        std::string buf;
-        slogger.trace("Request: {} {} {}", op, truncated_content_view(content, buf), req->_headers);
-    }
-    auto callback_it = _callbacks.find(op);
-    if (callback_it == _callbacks.end()) {
-        _executor._stats.unsupported_operations++;
-        co_return api_error::unknown_operation(format("Unsupported operation {}", op));
-    }
-    if (_pending_requests.get_count() >= _max_concurrent_requests) {
-        _executor._stats.requests_shed++;
-        co_return api_error::request_limit_exceeded(format("too many in-flight requests (configured via max_concurrent_requests_per_shard): {}", _pending_requests.get_count()));
-    }
-    _pending_requests.enter();
-    auto leave = defer([this] () noexcept { _pending_requests.leave(); });
-    //FIXME: Client state can provide more context, e.g. client's endpoint address
-    // We use unique_ptr because client_state cannot be moved or copied
-    executor::client_state client_state = username.empty()
-        ? service::client_state{service::client_state::internal_tag()}
-        : service::client_state{service::client_state::internal_tag(), _auth_service, _sl_controller, username};
-    co_await client_state.maybe_update_per_service_level_params();
-
-    tracing::trace_state_ptr trace_state = maybe_trace_query(client_state, username, op, content);
-    tracing::trace(trace_state, op);
-    rjson::value json_request = co_await _json_parser.parse(std::move(content));
-    co_return co_await callback_it->second(_executor, client_state, trace_state,
-            make_service_permit(std::move(units)), std::move(json_request), std::move(req));
+    slogger.trace("Request: {} {}", op, req->content);
+    return verify_signature(*req).then([this, op, req = std::move(req)] () mutable {
+        auto callback_it = _callbacks.find(op);
+        if (callback_it == _callbacks.end()) {
+            _executor.local()._stats.unsupported_operations++;
+            throw api_error("UnknownOperationException",
+                    format("Unsupported operation {}", op));
+        }
+        //FIXME: Client state can provide more context, e.g. client's endpoint address
+        // We use unique_ptr because client_state cannot be moved or copied
+        return do_with(std::make_unique<executor::client_state>(executor::client_state::internal_tag()), [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (std::unique_ptr<executor::client_state>& client_state) mutable {
+            client_state->set_raw_keyspace(executor::KEYSPACE_NAME);
+            executor::maybe_trace_query(*client_state, op, req->content);
+            tracing::trace(client_state->get_trace_state(), op);
+            return callback_it->second(_executor.local(), *client_state, std::move(req));
+        });
+    });
 }
 
 void server::set_routes(routes& r) {
@@ -427,206 +243,69 @@ void server::set_routes(routes& r) {
         return handle_api_request(std::move(req));
     });
 
-    r.put(operation_type::POST, "/", req_handler);
-    r.put(operation_type::GET, "/", new health_handler(_pending_requests));
-    // The "/localnodes" request is a new Alternator feature, not supported by
-    // DynamoDB and not required for DynamoDB compatibility. It allows a
-    // client to enquire - using a trivial HTTP request without requiring
-    // authentication - the list of all live nodes in the same data center of
-    // the Alternator cluster. The client can use this list to balance its
-    // request load to all the nodes in the same geographical region.
-    // Note that this API exposes - openly without authentication - the
-    // information on the cluster's members inside one data center. We do not
-    // consider this to be a security risk, because an attacker can already
-    // scan an entire subnet for nodes responding to the health request,
-    // or even just scan for open ports.
-    r.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests, _proxy, _gossiper));
-    r.put(operation_type::OPTIONS, "/", new options_handler(_pending_requests));
+    r.add(operation_type::POST, url("/"), req_handler);
+    r.add(operation_type::GET, url("/"), new health_handler);
 }
 
 //FIXME: A way to immediately invalidate the cache should be considered,
 // e.g. when the system table which stores the keys is changed.
 // For now, this propagation may take up to 1 minute.
-server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gossiper, auth::service& auth_service, qos::service_level_controller& sl_controller)
-        : _http_server("http-alternator")
-        , _https_server("https-alternator")
-        , _executor(exec)
-        , _proxy(proxy)
-        , _gossiper(gossiper)
-        , _auth_service(auth_service)
-        , _sl_controller(sl_controller)
-        , _key_cache(1024, 1min, slogger)
-        , _enforce_authorization(false)
-        , _enabled_servers{}
-        , _pending_requests{}
+server::server(seastar::sharded<executor>& e)
+        : _executor(e), _key_cache(1024, 1min, slogger), _enforce_authorization(false)
       , _callbacks{
-        {"CreateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.create_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DescribeTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DeleteTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.delete_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"UpdateTable", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.update_table(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"PutItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.put_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"UpdateItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.update_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"GetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DeleteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.delete_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"ListTables", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.list_tables(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"Scan", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.scan(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_endpoints(client_state, std::move(permit), std::move(json_request), req->get_header("Host"));
-        }},
-        {"BatchWriteItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.batch_write_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"BatchGetItem", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.batch_get_item(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"Query", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.query(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"TagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.tag_resource(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"UntagResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.untag_resource(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"ListTagsOfResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.list_tags_of_resource(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"UpdateTimeToLive", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.update_time_to_live(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"DescribeTimeToLive", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_time_to_live(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"ListStreams", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.list_streams(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"DescribeStream", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_stream(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"GetShardIterator", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.get_shard_iterator(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"GetRecords", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.get_records(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
-        }},
-        {"DescribeContinuousBackups", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_continuous_backups(client_state, std::move(permit), std::move(json_request));
-        }},
+        {"CreateTable", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) {
+            return e.maybe_create_keyspace().then([&e, &client_state, req = std::move(req)] { return e.create_table(client_state, req->content); }); }
+        },
+        {"DescribeTable", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.describe_table(client_state, req->content); }},
+        {"DeleteTable", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.delete_table(client_state, req->content); }},
+        {"PutItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.put_item(client_state, req->content); }},
+        {"UpdateItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.update_item(client_state, req->content); }},
+        {"GetItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.get_item(client_state, req->content); }},
+        {"DeleteItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.delete_item(client_state, req->content); }},
+        {"ListTables", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.list_tables(client_state, req->content); }},
+        {"Scan", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.scan(client_state, req->content); }},
+        {"DescribeEndpoints", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.describe_endpoints(client_state, req->content, req->get_header("Host")); }},
+        {"BatchWriteItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.batch_write_item(client_state, req->content); }},
+        {"BatchGetItem", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.batch_get_item(client_state, req->content); }},
+        {"Query", [] (executor& e, executor::client_state& client_state, std::unique_ptr<request> req) { return e.query(client_state, req->content); }},
     } {
 }
 
-future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-        bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests) {
-    _memory_limiter = memory_limiter;
+future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds, bool enforce_authorization) {
     _enforce_authorization = enforce_authorization;
-    _max_concurrent_requests = std::move(max_concurrent_requests);
     if (!port && !https_port) {
         return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
                 " must be specified in order to init an alternator HTTP server instance"));
     }
     return seastar::async([this, addr, port, https_port, creds] {
-        _executor.start().get();
+        try {
+            _executor.invoke_on_all([] (executor& e) {
+                return e.start();
+            }).get();
 
-        if (port) {
-            set_routes(_http_server._routes);
-            _http_server.set_content_length_limit(server::content_length_limit);
-            _http_server.set_content_streaming(true);
-            _http_server.listen(socket_address{addr, *port}).get();
-            _enabled_servers.push_back(std::ref(_http_server));
-        }
-        if (https_port) {
-            set_routes(_https_server._routes);
-            _https_server.set_content_length_limit(server::content_length_limit);
-            _https_server.set_content_streaming(true);
-            _https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
-                if (ep) {
-                    slogger.warn("Exception loading {}: {}", files, ep);
-                } else {
-                    slogger.info("Reloaded {}", files);
-                }
-            }).get0());
-            _https_server.listen(socket_address{addr, *https_port}).get();
-            _enabled_servers.push_back(std::ref(_https_server));
+            if (port) {
+                _control.start().get();
+                _control.set_routes(std::bind(&server::set_routes, this, std::placeholders::_1)).get();
+                _control.listen(socket_address{addr, *port}).get();
+                slogger.info("Alternator HTTP server listening on {} port {}", addr, *port);
+            }
+            if (https_port) {
+                _https_control.start().get();
+                _https_control.set_routes(std::bind(&server::set_routes, this, std::placeholders::_1)).get();
+                _https_control.server().invoke_on_all([creds] (http_server& serv) {
+                    return serv.set_tls_credentials(creds->build_server_credentials());
+                }).get();
+
+                _https_control.listen(socket_address{addr, *https_port}).get();
+                slogger.info("Alternator HTTPS server listening on {} port {}", addr, *https_port);
+            }
+        } catch (...) {
+            slogger.warn("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
+                    addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF", std::current_exception());
+            throw;
         }
     });
 }
 
-future<> server::stop() {
-    return parallel_for_each(_enabled_servers, [] (http_server& server) {
-        return server.stop();
-    }).then([this] {
-        return _pending_requests.close();
-    }).then([this] {
-        return _json_parser.stop();
-    });
-}
-
-server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
-        while (true) {
-            _document_waiting.wait().get();
-            if (_as.abort_requested()) {
-                return;
-            }
-            try {
-                _parsed_document = rjson::parse_yieldable(std::move(_raw_document));
-                _current_exception = nullptr;
-            } catch (...) {
-                _current_exception = std::current_exception();
-            }
-            _document_parsed.signal();
-        }
-    })) {
-}
-
-future<rjson::value> server::json_parser::parse(chunked_content&& content) {
-    if (content.size() < yieldable_parsing_threshold) {
-        return make_ready_future<rjson::value>(rjson::parse(std::move(content)));
-    }
-    return with_semaphore(_parsing_sem, 1, [this, content = std::move(content)] () mutable {
-        _raw_document = std::move(content);
-        _document_waiting.signal();
-        return _document_parsed.wait().then([this] {
-            if (_current_exception) {
-                return make_exception_future<rjson::value>(_current_exception);
-            }
-            return make_ready_future<rjson::value>(std::move(_parsed_document));
-        });
-    });
-}
-
-future<> server::json_parser::stop() {
-    _as.request_abort();
-    _document_waiting.signal();
-    _document_parsed.broken();
-    return std::move(_run_parse_json_thread);
-}
-
-const char* api_error::what() const noexcept {
-    if (_what_string.empty()) {
-        _what_string = format("{} {}: {}", static_cast<int>(_http_code), _type, _msg);
-    }
-    return _what_string.c_str();
-}
-
 }
 

alternator/server.hh

@@ -1,83 +1,53 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "alternator/executor.hh"
 #include <seastar/core/future.hh>
-#include <seastar/core/condition-variable.hh>
 #include <seastar/http/httpd.hh>
 #include <seastar/net/tls.hh>
 #include <optional>
-#include "alternator/auth.hh"
-#include "service/qos/service_level_controller.hh"
-#include "utils/small_vector.hh"
-#include "utils/updateable_value.hh"
-#include <seastar/core/units.hh>
+#include <alternator/auth.hh>
 
 namespace alternator {
 
-using chunked_content = rjson::chunked_content;
-
 class server {
-    static constexpr size_t content_length_limit = 16*MB;
-    using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
-            tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<request>)>;
+    using alternator_callback = std::function<future<json::json_return_type>(executor&, executor::client_state&, std::unique_ptr<request>)>;
     using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
 
-    http_server _http_server;
-    http_server _https_server;
-    executor& _executor;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
-    auth::service& _auth_service;
-    qos::service_level_controller& _sl_controller;
-
+    seastar::httpd::http_server_control _control;
+    seastar::httpd::http_server_control _https_control;
+    seastar::sharded<executor>& _executor;
     key_cache _key_cache;
     bool _enforce_authorization;
-    utils::small_vector<std::reference_wrapper<seastar::httpd::http_server>, 2> _enabled_servers;
-    gate _pending_requests;
     alternator_callbacks_map _callbacks;
-
-    semaphore* _memory_limiter;
-    utils::updateable_value<uint32_t> _max_concurrent_requests;
-
-    class json_parser {
-        static constexpr size_t yieldable_parsing_threshold = 16*KB;
-        chunked_content _raw_document;
-        rjson::value _parsed_document;
-        std::exception_ptr _current_exception;
-        semaphore _parsing_sem{1};
-        condition_variable _document_waiting;
-        condition_variable _document_parsed;
-        abort_source _as;
-        future<> _run_parse_json_thread;
-    public:
-        json_parser();
-        // Moving a chunked_content into parse() allows parse() to free each
-        // chunk as soon as it is parsed, so when chunks are relatively small,
-        // we don't need to store the sum of unparsed and parsed sizes.
-        future<rjson::value> parse(chunked_content&& content);
-        future<> stop();
-    };
-    json_parser _json_parser;
-
 public:
-    server(executor& executor, service::storage_proxy& proxy, gms::gossiper& gossiper, auth::service& service, qos::service_level_controller& sl_controller);
+    server(seastar::sharded<executor>& executor);
 
-    future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-            bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests);
-    future<> stop();
+    seastar::future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds, bool enforce_authorization);
 private:
     void set_routes(seastar::httpd::routes& r);
-    // If verification succeeds, returns the authenticated user's username
-    future<std::string> verify_signature(const seastar::httpd::request&, const chunked_content&);
-    future<executor::request_return_type> handle_api_request(std::unique_ptr<request> req);
+    future<> verify_signature(const seastar::httpd::request& r);
+    future<json::json_return_type> handle_api_request(std::unique_ptr<request>&& req);
 };
 
 }

alternator/stats.cc

@@ -1,13 +1,26 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "stats.hh"
-#include "utils/histogram_metrics_helper.hh"
+
 #include <seastar/core/metrics.hh>
 
 namespace alternator {
@@ -24,8 +37,7 @@ stats::stats() : api_operations{} {
                         seastar::metrics::description("number of operations via Alternator API"), {op(CamelCaseName)}),
 #define OPERATION_LATENCY(name, CamelCaseName) \
                 seastar::metrics::make_histogram("op_latency", \
-                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return to_metrics_histogram(api_operations.name);}),
-            OPERATION(batch_get_item, "BatchGetItem")
+                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return api_operations.name.get_histogram(1,20);}),
             OPERATION(batch_write_item, "BatchWriteItem")
             OPERATION(create_backup, "CreateBackup")
             OPERATION(create_global_table, "CreateGlobalTable")
@@ -65,11 +77,6 @@ stats::stats() : api_operations{} {
             OPERATION_LATENCY(get_item_latency, "GetItem")
             OPERATION_LATENCY(delete_item_latency, "DeleteItem")
             OPERATION_LATENCY(update_item_latency, "UpdateItem")
-            OPERATION(list_streams, "ListStreams")
-            OPERATION(describe_stream, "DescribeStream")
-            OPERATION(get_shard_iterator, "GetShardIterator")
-            OPERATION(get_records, "GetRecords")
-            OPERATION_LATENCY(get_records_latency, "GetRecords")
     });
     _metrics.add_group("alternator", {
             seastar::metrics::make_total_operations("unsupported_operations", unsupported_operations,
@@ -78,14 +85,6 @@ stats::stats() : api_operations{} {
                     seastar::metrics::description("number of total operations via Alternator API")),
             seastar::metrics::make_total_operations("reads_before_write", reads_before_write,
                     seastar::metrics::description("number of performed read-before-write operations")),
-            seastar::metrics::make_total_operations("write_using_lwt", write_using_lwt,
-                    seastar::metrics::description("number of writes that used LWT")),
-            seastar::metrics::make_total_operations("shard_bounce_for_lwt", shard_bounce_for_lwt,
-                    seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements")),
-            seastar::metrics::make_total_operations("requests_blocked_memory", requests_blocked_memory,
-                    seastar::metrics::description("Counts a number of requests blocked due to memory pressure.")),
-            seastar::metrics::make_total_operations("requests_shed", requests_shed,
-                    seastar::metrics::description("Counts a number of requests shed due to overload.")),
             seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
                     seastar::metrics::description("number of rows read during filtering operations")),
             seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,

alternator/stats.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -61,25 +74,16 @@ public:
         uint64_t update_item = 0;
         uint64_t update_table = 0;
         uint64_t update_time_to_live = 0;
-        uint64_t list_streams = 0;
-        uint64_t describe_stream = 0;
-        uint64_t get_shard_iterator = 0;
-        uint64_t get_records = 0;
 
-        utils::time_estimated_histogram put_item_latency;
-        utils::time_estimated_histogram get_item_latency;
-        utils::time_estimated_histogram delete_item_latency;
-        utils::time_estimated_histogram update_item_latency;
-        utils::time_estimated_histogram get_records_latency;
+        utils::estimated_histogram put_item_latency;
+        utils::estimated_histogram get_item_latency;
+        utils::estimated_histogram delete_item_latency;
+        utils::estimated_histogram update_item_latency;
     } api_operations;
     // Miscellaneous event counters
     uint64_t total_operations = 0;
     uint64_t unsupported_operations = 0;
     uint64_t reads_before_write = 0;
-    uint64_t write_using_lwt = 0;
-    uint64_t shard_bounce_for_lwt = 0;
-    uint64_t requests_blocked_memory = 0;
-    uint64_t requests_shed = 0;
     // CQL-derived stats
     cql3::cql_stats cql_stats;
 private:

alternator/ttl.cc

@@ -1,825 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <chrono>
-#include <cstdint>
-#include <optional>
-#include <seastar/core/sstring.hh>
-#include <seastar/core/coroutine.hh>
-#include <seastar/core/sleep.hh>
-#include <seastar/core/future.hh>
-#include <seastar/core/lowres_clock.hh>
-#include <seastar/coroutine/maybe_yield.hh>
-#include <boost/multiprecision/cpp_int.hpp>
-
-#include "gms/gossiper.hh"
-#include "gms/inet_address.hh"
-#include "inet_address_vectors.hh"
-#include "locator/abstract_replication_strategy.hh"
-#include "log.hh"
-#include "gc_clock.hh"
-#include "replica/database.hh"
-#include "service_permit.hh"
-#include "timestamp.hh"
-#include "service/storage_proxy.hh"
-#include "service/pager/paging_state.hh"
-#include "service/pager/query_pagers.hh"
-#include "gms/feature_service.hh"
-#include "sstables/types.hh"
-#include "mutation.hh"
-#include "types.hh"
-#include "types/map.hh"
-#include "utils/rjson.hh"
-#include "utils/big_decimal.hh"
-#include "utils/fb_utilities.hh"
-#include "cql3/selection/selection.hh"
-#include "cql3/values.hh"
-#include "cql3/query_options.hh"
-#include "cql3/column_identifier.hh"
-#include "alternator/executor.hh"
-#include "alternator/controller.hh"
-#include "alternator/serialization.hh"
-#include "dht/sharder.hh"
-#include "db/config.hh"
-#include "db/tags/utils.hh"
-
-#include "ttl.hh"
-
-static logging::logger tlogger("alternator_ttl");
-
-namespace alternator {
-
-// We write the expiration-time attribute enabled on a table using a
-// tag TTL_TAG_KEY.
-// Currently, the *value* of this tag is simply the name of the attribute,
-// and the expiration scanner interprets it as an Alternator attribute name -
-// It can refer to a real column or if that doesn't exist, to a member of
-// the ":attrs" map column. Although this is designed for Alternator, it may
-// be good enough for CQL as well (there, the ":attrs" column won't exist).
-static const sstring TTL_TAG_KEY("system:ttl_attribute");
-
-future<executor::request_return_type> executor::update_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.update_time_to_live++;
-    if (!_proxy.data_dictionary().features().alternator_ttl) {
-        co_return api_error::unknown_operation("UpdateTimeToLive not yet supported. Experimental support is available if the 'alternator-ttl' experimental feature is enabled on all nodes.");
-    }
-
-    schema_ptr schema = get_table(_proxy, request);
-    rjson::value* spec = rjson::find(request, "TimeToLiveSpecification");
-    if (!spec || !spec->IsObject()) {
-        co_return api_error::validation("UpdateTimeToLive missing mandatory TimeToLiveSpecification");
-    }
-    const rjson::value* v = rjson::find(*spec, "Enabled");
-    if (!v || !v->IsBool()) {
-        co_return api_error::validation("UpdateTimeToLive requires boolean Enabled");
-    }
-    bool enabled = v->GetBool();
-    v = rjson::find(*spec, "AttributeName");
-    if (!v || !v->IsString()) {
-        co_return api_error::validation("UpdateTimeToLive requires string AttributeName");
-    }
-    // Although the DynamoDB documentation specifies that attribute names
-    // should be between 1 and 64K bytes, in practice, it only allows
-    // between 1 and 255 bytes. There are no other limitations on which
-    // characters are allowed in the name.
-    if (v->GetStringLength() < 1 || v->GetStringLength() > 255) {
-        co_return api_error::validation("The length of AttributeName must be between 1 and 255");
-    }
-    sstring attribute_name(v->GetString(), v->GetStringLength());
-
-    std::map<sstring, sstring> tags_map = get_tags_of_table_or_throw(schema);
-    if (enabled) {
-        if (tags_map.contains(TTL_TAG_KEY)) {
-            co_return api_error::validation("TTL is already enabled");
-        }
-        tags_map[TTL_TAG_KEY] = attribute_name;
-    } else {
-        auto i = tags_map.find(TTL_TAG_KEY);
-        if (i == tags_map.end()) {
-            co_return api_error::validation("TTL is already disabled");
-        } else if (i->second != attribute_name) {
-            co_return api_error::validation(format(
-                "Requested to disable TTL on attribute {}, but a different attribute {} is enabled.",
-                attribute_name, i->second));
-        }
-        tags_map.erase(TTL_TAG_KEY);
-    }
-    co_await db::update_tags(_mm, schema, std::move(tags_map));
-    // Prepare the response, which contains a TimeToLiveSpecification
-    // basically identical to the request's
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveSpecification", std::move(*spec));
-    co_return make_jsonable(std::move(response));
-}
-
-future<executor::request_return_type> executor::describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.describe_time_to_live++;
-    schema_ptr schema = get_table(_proxy, request);
-    std::map<sstring, sstring> tags_map = get_tags_of_table_or_throw(schema);
-    rjson::value desc = rjson::empty_object();
-    auto i = tags_map.find(TTL_TAG_KEY);
-    if (i == tags_map.end()) {
-        rjson::add(desc, "TimeToLiveStatus", "DISABLED");
-    } else {
-        rjson::add(desc, "TimeToLiveStatus", "ENABLED");
-        rjson::add(desc, "AttributeName", rjson::from_string(i->second));
-    }
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveDescription", std::move(desc));
-    co_return make_jsonable(std::move(response));
-}
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLive request.
-//
-// Here is a brief overview of how the expiration service works:
-//
-// An expiration thread on each shard periodically scans the items (i.e.,
-// rows) owned by this shard, looking for items whose chosen expiration-time
-// attribute indicates they are expired, and deletes those items.
-// The expiration-time "attribute" can be either an actual Scylla column
-// (must be numeric) or an Alternator "attribute" - i.e., an element in
-// the ATTRS_COLUMN_NAME map<utf8,bytes> column where the numeric expiration
-// time is encoded in DynamoDB's JSON encoding inside the bytes value.
-// To avoid scanning the same items RF times in RF replicas, only one node is
-// responsible for scanning a token range at a time. Normally, this is the
-// node owning this range as a "primary range" (the first node in the ring
-// with this range), but when this node is down, the secondary owner (the
-// second in the ring) may take over.
-// An expiration thread is reponsible for all tables which need expiration
-// scans. Currently, the different tables are scanned sequentially (not in
-// parallel).
-// The expiration thread scans item using CL=QUORUM to ensures that it reads
-// a consistent expiration-time attribute. This means that the items are read
-// locally and in addition QUORUM-1 additional nodes (one additional node
-// when RF=3) need to read the data and send digests.
-// When the expiration thread decides that an item has expired and wants
-// to delete it, it does it using a CL=QUORUM write. This allows this
-// deletion to be visible for consistent (quorum) reads. The deletion,
-// like user deletions, will also appear on the CDC log and therefore
-// Alternator Streams if enabled - currently as ordinary deletes (the
-// userIdentity flag is currently missing this is issue #11523).
-expiration_service::expiration_service(data_dictionary::database db, service::storage_proxy& proxy, gms::gossiper& g)
-        : _db(db)
-        , _proxy(proxy)
-        , _gossiper(g)
-{
-}
-
-// Convert the big_decimal used to represent expiration time to an integer.
-// Any fractional part is dropped. If the number is negative or invalid,
-// 0 is returned, and if it's too high, the maximum unsigned long is returned.
-static unsigned long bigdecimal_to_ul(const big_decimal& bd) {
-    // The big_decimal format has an integer mantissa of arbitrary length
-    // "unscaled_value" and then a (power of 10) exponent "scale".
-    if (bd.unscaled_value() <= 0) {
-        return 0;
-    }
-    if (bd.scale() == 0) {
-        // The fast path, when the expiration time is an integer, scale==0.
-        return static_cast<unsigned long>(bd.unscaled_value());
-    }
-    // Because the mantissa can be of arbitrary length, we work on it
-    // as a string. TODO: find a less ugly algorithm.
-    auto str = bd.unscaled_value().str();
-    if (bd.scale() > 0) {
-        int len = str.length();
-        if (len < bd.scale()) {
-            return 0;
-        }
-        str = str.substr(0, len-bd.scale());
-    } else {
-        if (bd.scale() < -20) {
-            return std::numeric_limits<unsigned long>::max();
-        }
-        for (int i = 0; i < -bd.scale(); i++) {
-            str.push_back('0');
-        }
-    }
-    // strtoul() returns ULONG_MAX if the number is too large, or 0 if not
-    // a number.
-    return strtoul(str.c_str(), nullptr, 10);
-}
-
-// The following is_expired() functions all check if an item with the given
-// expiration time has expired, according to the DynamoDB API rules.
-// The rules are:
-// 1. If the expiration time attribute's value is not a number type,
-//    the item is not expired.
-// 2. The expiration time is measured in seconds since the UNIX epoch.
-// 3. If the expiration time is more than 5 years in the past, it is assumed
-//    to be malformed and ignored - and the item does not expire.
-static bool is_expired(gc_clock::time_point expiration_time, gc_clock::time_point now) {
-    return expiration_time <= now &&
-           expiration_time > now - std::chrono::years(5);
-}
-
-static bool is_expired(const big_decimal& expiration_time, gc_clock::time_point now) {
-    unsigned long t = bigdecimal_to_ul(expiration_time);
-    // We assume - and the assumption turns out to be correct - that the
-    // epoch of gc_clock::time_point and the one used by the DynamoDB protocol
-    // are the same (the UNIX epoch in UTC). The resolution (seconds) is also
-    // the same.
-    return is_expired(gc_clock::time_point(gc_clock::duration(std::chrono::seconds(t))), now);
-}
-static bool is_expired(const rjson::value& expiration_time, gc_clock::time_point now) {
-    std::optional<big_decimal> n = try_unwrap_number(expiration_time);
-    return n && is_expired(*n, now);
-}
-
-// expire_item() expires an item - i.e., deletes it as appropriate for
-// expiration - with CL=QUORUM and (FIXME!) in a way Alternator Streams
-// understands it is an expiration event - not a user-initiated deletion.
-static future<> expire_item(service::storage_proxy& proxy,
-                            const service::query_state& qs,
-                            const std::vector<bytes_opt>& row,
-                            schema_ptr schema,
-                            api::timestamp_type ts) {
-    // Prepare the row key to delete
-    // NOTICE: the order of columns is guaranteed by the fact that selection::wildcard
-    // is used, which indicates that columns appear in the order defined by
-    // schema::all_columns_in_select_order() - partition key columns goes first,
-    // immediately followed by clustering key columns
-    std::vector<bytes> exploded_pk;
-    const unsigned pk_size = schema->partition_key_size();
-    const unsigned ck_size = schema->clustering_key_size();
-    for (unsigned c = 0; c < pk_size; ++c) {
-        const auto& row_c = row[c];
-        if (!row_c) {
-            // This shouldn't happen - all key columns must have values.
-            // But if it ever happens, let's just *not* expire the item.
-            // FIXME: log or increment a metric if this happens.
-            return make_ready_future<>();
-        }
-        exploded_pk.push_back(*row_c);
-    }
-    auto pk = partition_key::from_exploded(exploded_pk);
-    mutation m(schema, pk);
-    // If there's no clustering key, a tombstone should be created directly
-    // on a partition, not on a clustering row - otherwise it will look like
-    // an open-ended range tombstone, which will crash on KA/LA sstable format.
-    // See issue #6035
-    if (ck_size == 0) {
-        m.partition().apply(tombstone(ts, gc_clock::now()));
-    } else {
-        std::vector<bytes> exploded_ck;
-        for (unsigned c = pk_size; c < pk_size + ck_size; ++c) {
-            const auto& row_c = row[c];
-            if (!row_c) {
-                // This shouldn't happen - all key columns must have values.
-                // But if it ever happens, let's just *not* expire the item.
-                // FIXME: log or increment a metric if this happens.
-                return make_ready_future<>();
-            }
-            exploded_ck.push_back(*row_c);
-        }
-        auto ck = clustering_key::from_exploded(exploded_ck);
-        m.partition().clustered_row(*schema, ck).apply(tombstone(ts, gc_clock::now()));
-    }
-    std::vector<mutation> mutations;
-    mutations.push_back(std::move(m));
-    return proxy.mutate(std::move(mutations),
-        db::consistency_level::LOCAL_QUORUM,
-        executor::default_timeout(), // FIXME - which timeout?
-        qs.get_trace_state(), qs.get_permit(),
-        db::allow_per_partition_rate_limit::no);
-}
-
-static size_t random_offset(size_t min, size_t max) {
-    static thread_local std::default_random_engine re{std::random_device{}()};
-    std::uniform_int_distribution<size_t> dist(min, max);
-    return dist(re);
-}
-
-// Get a list of secondary token ranges for the given node, and the primary
-// node responsible for each of these token ranges.
-// A "secondary range" is a range of tokens where for each token, the second
-// node (in ring order) out of the RF replicas that hold this token is the
-// given node.
-// In the expiration scanner, we want to scan a secondary range but only if
-// this range's primary node is down. For this we need to return not just
-// a list of this node's secondary ranges - but also the primary owner of
-// each of those ranges.
-static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary_ranges(
-        const locator::effective_replication_map_ptr& erm,
-        gms::inet_address ep) {
-    const auto& tm = *erm->get_token_metadata_ptr();
-    const auto& sorted_tokens = tm.sorted_tokens();
-    std::vector<std::pair<dht::token_range, gms::inet_address>> ret;
-    if (sorted_tokens.empty()) {
-        on_internal_error(tlogger, "Token metadata is empty");
-    }
-    auto prev_tok = sorted_tokens.back();
-    for (const auto& tok : sorted_tokens) {
-        inet_address_vector_replica_set eps = erm->get_natural_endpoints(tok);
-        if (eps.size() <= 1 || eps[1] != ep) {
-            prev_tok = tok;
-            continue;
-        }
-        // Add the range (prev_tok, tok] to ret. However, if the range wraps
-        // around, split it to two non-wrapping ranges.
-        if (prev_tok < tok) {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        } else {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    std::nullopt},
-                eps[0]);
-            ret.emplace_back(
-                dht::token_range{
-                    std::nullopt,
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        }
-        prev_tok = tok;
-    }
-    return ret;
-}
-
-
-// A class for iterating over all the token ranges *owned* by this shard.
-// To avoid code duplication, it is a template with two distinct cases -
-// <primary> and <secondary>:
-//
-// In the <primary> case, we consider a token *owned* by this shard if:
-// 1. This node is a replica for this token.
-// 2. Moreover, this node is the *primary* replica of the token (i.e., the
-//    first replica in the ring).
-// 3. In this node, this shard is responsible for this token.
-// We will use this definition of which shard in the cluster owns which tokens
-// to split the expiration scanner's work between all the shards of the
-// system.
-//
-// In the <secondary> case, we consider a token *owned* by this shard if:
-// 1. This node is the *secondary* replica for this token (i.e., the second
-//    replica in the ring).
-// 2. The primary replica for this token is currently marked down.
-// 3. In this node, this shard is responsible for this token.
-// We use the <secondary> case to handle the possibility that some of the
-// nodes in the system are down. A dead node will not be expiring
-// the tokens owned by it, so we want the secondary owner to take over its
-// primary ranges.
-//
-// FIXME: need to decide how to choose primary ranges in multi-DC setup!
-// We could call get_primary_ranges_within_dc() below instead of get_primary_ranges().
-// NOTICE: Iteration currently starts from a random token range in order to improve
-// the chances of covering all ranges during a scan when restarts occur.
-// A more deterministic way would be to regularly persist the scanning state,
-// but that incurs overhead that we want to avoid if not needed.
-enum primary_or_secondary_t {primary, secondary};
-template<primary_or_secondary_t primary_or_secondary>
-class token_ranges_owned_by_this_shard {
-    // ranges_holder_primary holds just the primary ranges themselves
-    class ranges_holder_primary {
-        const dht::token_range_vector _token_ranges;
-     public:
-        ranges_holder_primary(const locator::effective_replication_map_ptr& erm, gms::gossiper& g, gms::inet_address ep)
-            : _token_ranges(erm->get_primary_ranges(ep)) {}
-        std::size_t size() const { return _token_ranges.size(); }
-        const dht::token_range& operator[](std::size_t i) const {
-            return _token_ranges[i];
-        }
-        bool should_skip(std::size_t i) const {
-            return false;
-        }
-    };
-    // ranges_holder<secondary> holds the secondary token ranges plus each
-    // range's primary owner, needed to implement should_skip().
-    class ranges_holder_secondary {
-        std::vector<std::pair<dht::token_range, gms::inet_address>> _token_ranges;
-        gms::gossiper& _gossiper;
-     public:
-        ranges_holder_secondary(const locator::effective_replication_map_ptr& erm, gms::gossiper& g, gms::inet_address ep)
-            : _token_ranges(get_secondary_ranges(erm, ep))
-            , _gossiper(g) {}
-        std::size_t size() const { return _token_ranges.size(); }
-        const dht::token_range& operator[](std::size_t i) const {
-            return _token_ranges[i].first;
-        }
-        // range i should be skipped if its primary owner is alive.
-        bool should_skip(std::size_t i) const {
-            return _gossiper.is_alive(_token_ranges[i].second);
-        }
-    };
-
-    schema_ptr _s;
-    // _token_ranges will contain a list of token ranges owned by this node.
-    // We'll further need to split each such range to the pieces owned by
-    // the current shard, using _intersecter.
-    using ranges_holder = std::conditional_t<
-            primary_or_secondary == primary_or_secondary_t::primary,
-            ranges_holder_primary,
-            ranges_holder_secondary>;
-    const ranges_holder _token_ranges;
-    // NOTICE: _range_idx is used modulo _token_ranges size when accessing
-    // the data to ensure that it doesn't go out of bounds
-    size_t _range_idx;
-    size_t _end_idx;
-    std::optional<dht::selective_token_range_sharder> _intersecter;
-public:
-    token_ranges_owned_by_this_shard(replica::database& db, gms::gossiper& g, schema_ptr s)
-        :  _s(s)
-        , _token_ranges(db.find_keyspace(s->ks_name()).get_effective_replication_map(),
-                g, utils::fb_utilities::get_broadcast_address())
-        , _range_idx(random_offset(0, _token_ranges.size() - 1))
-        , _end_idx(_range_idx + _token_ranges.size())
-    {
-        tlogger.debug("Generating token ranges starting from base range {} of {}", _range_idx, _token_ranges.size());
-    }
-
-    // Return the next token_range owned by this shard, or nullopt when the
-    // iteration ends.
-    std::optional<dht::token_range> next() {
-        // We may need three or more iterations in the following loop if a
-        // vnode doesn't intersect with the given shard at all (such a small
-        // vnode is unlikely, but possible). The loop cannot be infinite
-        // because each iteration of the loop advances _range_idx.
-        for (;;) {
-            if (_intersecter) {
-                std::optional<dht::token_range> ret = _intersecter->next();
-                if (ret) {
-                    return ret;
-                }
-                // done with this range, go to next one
-                ++_range_idx;
-                _intersecter = std::nullopt;
-            }
-            if (_range_idx == _end_idx) {
-                return std::nullopt;
-            }
-            // If should_skip(), the range should be skipped. This happens for
-            // a secondary range whose primary owning node is still alive.
-            while (_token_ranges.should_skip(_range_idx % _token_ranges.size())) {
-                ++_range_idx;
-                if (_range_idx == _end_idx) {
-                    return std::nullopt;
-                }
-            }
-            _intersecter.emplace(_s->get_sharder(), _token_ranges[_range_idx % _token_ranges.size()], this_shard_id());
-        }
-    }
-
-    // Same as next(), just return a partition_range instead of token_range
-    std::optional<dht::partition_range> next_partition_range() {
-        std::optional<dht::token_range> ret = next();
-        if (ret) {
-            return dht::to_partition_range(*ret);
-        } else {
-            return std::nullopt;
-        }
-    }
-};
-
-// Precomputed information needed to perform a scan on partition ranges
-struct scan_ranges_context {
-    schema_ptr s;
-    bytes column_name;
-    std::optional<std::string> member;
-
-    ::shared_ptr<cql3::selection::selection> selection;
-    std::unique_ptr<service::query_state> query_state_ptr;
-    std::unique_ptr<cql3::query_options> query_options;
-    ::lw_shared_ptr<query::read_command> command;
-
-    scan_ranges_context(schema_ptr s, service::storage_proxy& proxy, bytes column_name, std::optional<std::string> member)
-        : s(s)
-        , column_name(column_name)
-        , member(member)
-    {
-        // FIXME: don't read the entire items - read only parts of it.
-        // We must read the key columns (to be able to delete) and also
-        // the requested attribute. If the requested attribute is a map's
-        // member we may be forced to read the entire map - but it would
-        // be good if we can read only the single item of the map - it
-        // should be possible (and a must for issue #7751!).
-        lw_shared_ptr<service::pager::paging_state> paging_state = nullptr;
-        auto regular_columns = boost::copy_range<query::column_id_vector>(
-            s->regular_columns() | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.id; }));
-        selection = cql3::selection::selection::wildcard(s);
-        query::partition_slice::option_set opts = selection->get_query_options();
-        opts.set<query::partition_slice::option::allow_short_read>();
-        // It is important that the scan bypass cache to avoid polluting it:
-        opts.set<query::partition_slice::option::bypass_cache>();
-        std::vector<query::clustering_range> ck_bounds{query::clustering_range::make_open_ended_both_sides()};
-        auto partition_slice = query::partition_slice(std::move(ck_bounds), {}, std::move(regular_columns), opts);
-        command = ::make_lw_shared<query::read_command>(s->id(), s->version(), partition_slice, proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
-        executor::client_state client_state{executor::client_state::internal_tag()};
-        tracing::trace_state_ptr trace_state;
-        // NOTICE: empty_service_permit is used because the TTL service has fixed parallelism
-        query_state_ptr = std::make_unique<service::query_state>(client_state, trace_state, empty_service_permit());
-        // FIXME: What should we do on multi-DC? Will we run the expiration on the same ranges on all
-        // DCs or only once for each range? If the latter, we need to change the CLs in the
-        // scanner and deleter.
-        db::consistency_level cl = db::consistency_level::LOCAL_QUORUM;
-        query_options = std::make_unique<cql3::query_options>(cl, std::vector<cql3::raw_value>{});
-        query_options = std::make_unique<cql3::query_options>(std::move(query_options), std::move(paging_state));
-    }
-};
-
-// Scan data in a list of token ranges in one table, looking for expired
-// items and deleting them.
-// Because of issue #9167, partition_ranges must have a single partition
-// range for this code to work correctly.
-static future<> scan_table_ranges(
-        service::storage_proxy& proxy,
-        const scan_ranges_context& scan_ctx,
-        dht::partition_range_vector&& partition_ranges,
-        abort_source& abort_source,
-        named_semaphore& page_sem,
-        expiration_service::stats& expiration_stats)
-{
-    const schema_ptr& s = scan_ctx.s;
-    assert (partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
-    auto p = service::pager::query_pagers::pager(proxy, s, scan_ctx.selection, *scan_ctx.query_state_ptr,
-            *scan_ctx.query_options, scan_ctx.command, std::move(partition_ranges), nullptr);
-    while (!p->is_exhausted()) {
-        if (abort_source.abort_requested()) {
-            co_return;
-        }
-        auto units = co_await get_units(page_sem, 1);
-        // We don't to limit page size in number of rows because there is a
-        // builtin limit of the page's size in bytes. Setting this limit to 1
-        // is useful for debugging the paging code with moderate-size data.
-        uint32_t limit = std::numeric_limits<uint32_t>::max();
-        // FIXME: which timeout?
-        // FIXME: if read times out, need to retry it.
-        std::unique_ptr<cql3::result_set> rs = co_await p->fetch_page(limit, gc_clock::now(), executor::default_timeout());
-        auto rows = rs->rows();
-        auto meta = rs->get_metadata().get_names();
-        std::optional<unsigned> expiration_column;
-        for (unsigned i = 0; i < meta.size(); i++) {
-            const cql3::column_specification& col = *meta[i];
-            if (col.name->name() == scan_ctx.column_name) {
-                expiration_column = i;
-                break;
-            }
-        }
-        if (!expiration_column) {
-            continue;
-        }
-        for (const auto& row : rows) {
-            const bytes_opt& cell = row[*expiration_column];
-            if (!cell) {
-                continue;
-            }
-            auto v = meta[*expiration_column]->type->deserialize(*cell);
-            bool expired = false;
-            // FIXME: don't recalculate "now" all the time
-            auto now = gc_clock::now();
-            if (scan_ctx.member) {
-                // In this case, the expiration-time attribute we're
-                // looking for is a member in a map, saved serialized
-                // into bytes using Alternator's serialization (basically
-                // a JSON serialized into bytes)
-                // FIXME: is it possible to find a specific member of a map
-                // without iterating through it like we do here and compare
-                // the key?
-                for (const auto& entry : value_cast<map_type_impl::native_type>(v)) {
-                    std::string attr_name = value_cast<sstring>(entry.first);
-                    if (value_cast<sstring>(entry.first) == *scan_ctx.member) {
-                        bytes value = value_cast<bytes>(entry.second);
-                        rjson::value json = deserialize_item(value);
-                        expired = is_expired(json, now);
-                        break;
-                    }
-                }
-            } else {
-                // For a real column to contain an expiration time, it
-                // must be a numeric type.
-                // FIXME: Currently we only support decimal_type (which is
-                // what Alternator uses), but other numeric types can be
-                // supported as well to make this feature more useful in CQL.
-                // Note that kind::decimal is also checked above.
-                big_decimal n = value_cast<big_decimal>(v);
-                expired = is_expired(n, now);
-            }
-            if (expired) {
-                expiration_stats.items_deleted++;
-                // FIXME: maybe don't recalculate new_timestamp() all the time
-                // FIXME: if expire_item() throws on timeout, we need to retry it.
-                auto ts = api::new_timestamp();
-                co_await expire_item(proxy, *scan_ctx.query_state_ptr, row, s, ts);
-            }
-        }
-        // FIXME: once in a while, persist p->state(), so on reboot
-        // we don't start from scratch.
-    }
-}
-
-// scan_table() scans, in one table, data "owned" by this shard, looking for
-// expired items and deleting them.
-// We consider each node to "own" its primary token ranges, i.e., the tokens
-// that this node is their first replica in the ring. Inside the node, each
-// shard "owns" subranges of the node's token ranges - according to the node's
-// sharding algorithm.
-// When a node goes down, the token ranges owned by it will not be scanned
-// and items in those token ranges will not expire, so in the future (FIXME)
-// this function should additionally work on token ranges whose primary owner
-// is down and this node is the range's secondary owner.
-// If the TTL (expiration-time scanning) feature is not enabled for this
-// table, scan_table() returns false without doing anything. Remember that the
-// TTL feature may be enabled later so this function will need to be called
-// again when the feature is enabled.
-// Currently this function scans the entire table (or, rather the parts owned
-// by this shard) at full rate, once. In the future (FIXME) we should consider
-// how to pace this scan, how and when to repeat it, how to interleave or
-// parallelize scanning of multiple tables, and how to continue scans after a
-// reboot.
-static future<bool> scan_table(
-    service::storage_proxy& proxy,
-    data_dictionary::database db,
-    gms::gossiper& gossiper,
-    schema_ptr s,
-    abort_source& abort_source,
-    named_semaphore& page_sem,
-    expiration_service::stats& expiration_stats)
-{
-    // Check if an expiration-time attribute is enabled for this table.
-    // If not, just return false immediately.
-    // FIXME: the setting of the TTL may change in the middle of a long scan!
-    std::optional<std::string> attribute_name = db::find_tag(*s, TTL_TAG_KEY);
-    if (!attribute_name) {
-        co_return false;
-    }
-    // attribute_name may be one of the schema's columns (in Alternator, this
-    // means it's a key column), or an element in Alternator's attrs map
-    // encoded in Alternator's JSON encoding.
-    // FIXME: To make this less Alternators-specific, we should encode in the
-    // single key's value three things:
-    // 1. The name of a column
-    // 2. Optionally if column is a map, a member in the map
-    // 3. The deserializer for the value: CQL or Alternator (JSON).
-    // The deserializer can be guessed: If the given column or map item is
-    // numeric, it can be used directly. If it is a "bytes" type, it needs to
-    // be deserialized using Alternator's deserializer.
-    bytes column_name = to_bytes(*attribute_name);
-    const column_definition *cd = s->get_column_definition(column_name);
-    std::optional<std::string> member;
-    if (!cd) {
-        member = std::move(attribute_name);
-        column_name = bytes(executor::ATTRS_COLUMN_NAME);
-        cd = s->get_column_definition(column_name);
-        tlogger.info("table {} TTL enabled with attribute {} in {}", s->cf_name(), *member, executor::ATTRS_COLUMN_NAME);
-    } else {
-        tlogger.info("table {} TTL enabled with attribute {}", s->cf_name(), *attribute_name);
-    }
-    if (!cd) {
-        tlogger.info("table {} TTL column is missing, not scanning", s->cf_name());
-        co_return false;
-    }
-    data_type column_type = cd->type;
-    // Verify that the column has the right type: If "member" exists
-    // the column must be a map, and if it doesn't, the column must
-    // (currently) be a decimal_type. If the column has the wrong type
-    // nothing can get expired in this table, and it's pointless to
-    // scan it.
-    if ((member && column_type->get_kind() != abstract_type::kind::map) ||
-        (!member && column_type->get_kind() != abstract_type::kind::decimal)) {
-        tlogger.info("table {} TTL column has unsupported type, not scanning", s->cf_name());
-        co_return false;
-    }
-    expiration_stats.scan_table++;
-    // FIXME: need to pace the scan, not do it all at once.
-    scan_ranges_context scan_ctx{s, proxy, std::move(column_name), std::move(member)};
-    token_ranges_owned_by_this_shard<primary> my_ranges(db.real_database(), gossiper, s);
-    while (std::optional<dht::partition_range> range = my_ranges.next_partition_range()) {
-        // Note that because of issue #9167 we need to run a separate
-        // query on each partition range, and can't pass several of
-        // them into one partition_range_vector.
-        dht::partition_range_vector partition_ranges;
-        partition_ranges.push_back(std::move(*range));
-        // FIXME: if scanning a single range fails, including network errors,
-        // we fail the entire scan (and rescan from the beginning). Need to
-        // reconsider this. Saving the scan position might be a good enough
-        // solution for this problem.
-        co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem, expiration_stats);
-    }
-    // If each node only scans its own primary ranges, then when any node is
-    // down part of the token range will not get scanned. This can be viewed
-    // as acceptable (when the comes back online, it will resume its scan),
-    // but as noted in issue #9787, we can allow more prompt expiration
-    // by tasking another node to take over scanning of the dead node's primary
-    // ranges. What we do here is that this node will also check expiration
-    // on its *secondary* ranges - but only those whose primary owner is down.
-    token_ranges_owned_by_this_shard<secondary> my_secondary_ranges(db.real_database(), gossiper, s);
-    while (std::optional<dht::partition_range> range = my_secondary_ranges.next_partition_range()) {
-        expiration_stats.secondary_ranges_scanned++;
-        dht::partition_range_vector partition_ranges;
-        partition_ranges.push_back(std::move(*range));
-        co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem, expiration_stats);
-    }
-    co_return true;
-}
-
-
-future<> expiration_service::run() {
-    // FIXME: don't just tight-loop, think about timing, pace, and
-    // store position in durable storage, etc.
-    // FIXME: think about working on different tables in parallel.
-    // also need to notice when a new table is added, a table is
-    // deleted or when ttl is enabled or disabled for a table!
-    for (;;) {
-        auto start = lowres_clock::now();
-        // _db.tables() may change under our feet during a
-        // long-living loop, so we must keep our own copy of the list of
-        // schemas.
-        std::vector<schema_ptr> schemas;
-        for (auto cf : _db.get_tables()) {
-            schemas.push_back(cf.schema());
-        }
-        for (schema_ptr s : schemas) {
-            co_await coroutine::maybe_yield();
-            if (shutting_down()) {
-                co_return;
-            }
-            try {
-                co_await scan_table(_proxy, _db, _gossiper, s, _abort_source, _page_sem, _expiration_stats);
-            } catch (...) {
-                // The scan of a table may fail in the middle for many
-                // reasons, including network failure and even the table
-                // being removed. We'll continue scanning this table later
-                // (if it still exists). In any case it's important to catch
-                // the exception and not let the scanning service die for
-                // good.
-                // If the table has been deleted, it is expected that the scan
-                // will fail at some point, and even a warning is excessive.
-                if (_db.has_schema(s->ks_name(), s->cf_name())) {
-                    tlogger.warn("table {}.{} expiration scan failed: {}",
-                        s->ks_name(), s->cf_name(), std::current_exception());
-                } else {
-                    tlogger.info("expiration scan failed when table {}.{} was deleted",
-                        s->ks_name(), s->cf_name());
-                }
-            }
-        }
-        _expiration_stats.scan_passes++;
-        // The TTL scanner runs above once over all tables, at full steam.
-        // After completing such a scan, we sleep until it's time start
-        // another scan. TODO: If the scan went too fast, we can slow it down
-        // in the next iteration by reducing the scanner's scheduling-group
-        // share (if using a separate scheduling group), or introduce
-        // finer-grain sleeps into the scanning code.
-        std::chrono::milliseconds scan_duration(std::chrono::duration_cast<std::chrono::milliseconds>(lowres_clock::now() - start));
-        std::chrono::milliseconds period(long(_db.get_config().alternator_ttl_period_in_seconds() * 1000));
-        if (scan_duration < period) {
-            try {
-                tlogger.info("sleeping {} seconds until next period", (period - scan_duration).count()/1000.0);
-                co_await seastar::sleep_abortable(period - scan_duration, _abort_source);
-            } catch(seastar::sleep_aborted&) {}
-        } else {
-                tlogger.warn("scan took {} seconds, longer than period - not sleeping", scan_duration.count()/1000.0);
-        }
-    }
-}
-
-future<> expiration_service::start() {
-    // Called by main() on each shard to start the expiration-service
-    // thread. Just runs run() in the background and allows stop().
-    if (_db.features().alternator_ttl) {
-        if (!shutting_down()) {
-            _end = run().handle_exception([] (std::exception_ptr ep) {
-                tlogger.error("expiration_service failed: {}", ep);
-            });
-        }
-    }
-    return make_ready_future<>();
-}
-
-future<> expiration_service::stop() {
-    if (_abort_source.abort_requested()) {
-        throw std::logic_error("expiration_service::stop() called a second time");
-    }
-    _abort_source.request_abort();
-    if (!_end) {
-        // if _end is was not set, start() was never called
-        return make_ready_future<>();
-    }
-    return std::move(*_end);
-}
-
-expiration_service::stats::stats() {
-    _metrics.add_group("expiration", {
-        seastar::metrics::make_total_operations("scan_passes", scan_passes,
-            seastar::metrics::description("number of passes over the database")),
-        seastar::metrics::make_total_operations("scan_table", scan_table,
-            seastar::metrics::description("number of table scans (counting each scan of each table that enabled expiration)")),
-        seastar::metrics::make_total_operations("items_deleted", items_deleted,
-            seastar::metrics::description("number of items deleted after expiration")),
-        seastar::metrics::make_total_operations("secondary_ranges_scanned", secondary_ranges_scanned,
-            seastar::metrics::description("number of token ranges scanned by this node while their primary owner was down")),
-    });
-}
-
-
-} // namespace alternator

alternator/ttl.hh

@@ -1,80 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include "seastarx.hh"
-#include <seastar/core/sharded.hh>
-#include <seastar/core/abort_source.hh>
-#include <seastar/core/semaphore.hh>
-#include "data_dictionary/data_dictionary.hh"
-
-namespace gms {
-class gossiper;
-}
-
-namespace replica {
-class database;
-}
-
-namespace service {
-    class storage_proxy;
-}
-
-namespace alternator {
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLeave request.
-class expiration_service final : public seastar::peering_sharded_service<expiration_service> {
-public:
-    // Object holding per-shard statistics related to the expiration service.
-    // While this object is alive, these metrics are also registered to be
-    // visible by the metrics REST API, with the "expiration_" prefix.
-    class stats {
-    public:
-        stats();
-        uint64_t scan_passes = 0;
-        uint64_t scan_table = 0;
-        uint64_t items_deleted = 0;
-        uint64_t secondary_ranges_scanned = 0;
-    private:
-        // The metric_groups object holds this stat object's metrics registered
-        // as long as the stats object is alive.
-        seastar::metrics::metric_groups _metrics;
-    };
-private:
-    data_dictionary::database _db;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
-    // _end is set by start(), and resolves when the the background service
-    // started by it ends. To ask the background service to end, _abort_source
-    // should be triggered. stop() below uses both _abort_source and _end.
-    std::optional<future<>> _end;
-    abort_source _abort_source;
-    // Ensures that at most 1 page of scan results at a time is processed by the TTL service
-    named_semaphore _page_sem{1, named_semaphore_exception_factory{"alternator_ttl"}};
-    bool shutting_down() { return _abort_source.abort_requested(); }
-    stats _expiration_stats;
-public:
-    // sharded_service<expiration_service>::start() creates this object on
-    // all shards, so calls this constructor on each shard. Later, the
-    // additional start() function should be invoked on all shards.
-    expiration_service(data_dictionary::database, service::storage_proxy&, gms::gossiper&);
-    future<> start();
-    future<> run();
-    // sharded_service<expiration_service>::stop() calls the following stop()
-    // method on each shard. This stop() asks the service on this shard to
-    // shut down as quickly as it can. The returned future indicates when the
-    // service is no longer running.
-    // stop() may be called even before start(), but may only be called once -
-    // calling it twice will result in an exception.
-    future<> stop();
-};
-
-} // namespace alternator

api/api-doc/authorization_cache.json

@@ -1,29 +0,0 @@
-{
-  "apiVersion":"0.0.1",
-  "swaggerVersion":"1.2",
-  "basePath":"{{Protocol}}://{{Host}}",
-  "resourcePath":"/authorization_cache",
-  "produces":[
-    "application/json"
-  ],
-  "apis":[
-    {
-      "path":"/authorization_cache/reset",
-      "operations":[
-        {
-          "method":"POST",
-          "summary":"Reset cache",
-          "type":"void",
-          "nickname":"authorization_cache_reset",
-          "produces":[
-            "application/json"
-          ],
-          "parameters":[
-          ]
-        }
-      ]
-    }
-  ],
-  "models":{
-  }
-}

api/api-doc/cache_service.json

@@ -13,7 +13,7 @@
             {
                "method":"GET",
                "summary":"get row cache save period in seconds",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_save_period_in_seconds",
                "produces":[
                   "application/json"
@@ -35,7 +35,7 @@
                      "description":"row cache save period in seconds",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -48,7 +48,7 @@
             {
                "method":"GET",
                "summary":"get key cache save period in seconds",
-               "type": "long",
+               "type":"int",
                "nickname":"get_key_cache_save_period_in_seconds",
                "produces":[
                   "application/json"
@@ -70,7 +70,7 @@
                      "description":"key cache save period in seconds",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -83,7 +83,7 @@
             {
                "method":"GET",
                "summary":"get counter cache save period in seconds",
-               "type": "long",
+               "type":"int",
                "nickname":"get_counter_cache_save_period_in_seconds",
                "produces":[
                   "application/json"
@@ -105,7 +105,7 @@
                      "description":"counter cache save period in seconds",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -118,7 +118,7 @@
             {
                "method":"GET",
                "summary":"get row cache keys to save",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_keys_to_save",
                "produces":[
                   "application/json"
@@ -140,7 +140,7 @@
                      "description":"row cache keys to save",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -153,7 +153,7 @@
             {
                "method":"GET",
                "summary":"get key cache keys to save",
-               "type": "long",
+               "type":"int",
                "nickname":"get_key_cache_keys_to_save",
                "produces":[
                   "application/json"
@@ -175,7 +175,7 @@
                      "description":"key cache keys to save",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -188,7 +188,7 @@
             {
                "method":"GET",
                "summary":"get counter cache keys to save",
-               "type": "long",
+               "type":"int",
                "nickname":"get_counter_cache_keys_to_save",
                "produces":[
                   "application/json"
@@ -210,7 +210,7 @@
                      "description":"counter cache keys to save",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -448,7 +448,7 @@
         {
           "method": "GET",
           "summary": "Get key entries",
-          "type": "long",
+          "type": "int",
           "nickname": "get_key_entries",
           "produces": [
             "application/json"
@@ -568,7 +568,7 @@
         {
           "method": "GET",
           "summary": "Get row entries",
-          "type": "long",
+          "type": "int",
           "nickname": "get_row_entries",
           "produces": [
             "application/json"
@@ -688,7 +688,7 @@
         {
           "method": "GET",
           "summary": "Get counter entries",
-          "type": "long",
+          "type": "int",
           "nickname": "get_counter_entries",
           "produces": [
             "application/json"

api/api-doc/column_family.json

@@ -70,7 +70,7 @@
             {
                "method":"POST",
                "summary":"Force a major compaction of this column family",
-               "type":"void",
+               "type":"string",
                "nickname":"force_major_compaction",
                "produces":[
                   "application/json"
@@ -89,7 +89,7 @@
                      "description":"true if the output of the major compaction should be split in several sstables",
                      "required":false,
                      "allowMultiple":false,
-                     "type":"boolean",
+                     "type":"bool",
                      "paramType":"query"
                   }
                ]
@@ -121,7 +121,7 @@
                      "description":"The minimum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -172,7 +172,7 @@
                      "description":"The maximum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -223,7 +223,7 @@
                      "description":"The maximum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   },
                   {
@@ -231,7 +231,7 @@
                      "description":"The minimum number of sstables in queue before compaction kicks off",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -380,54 +380,16 @@
          "operations":[
             {
                "method":"GET",
-               "summary":"check if the auto_compaction property is enabled for a given table",
+               "summary":"check if the auto compaction disabled",
                "type":"boolean",
-               "nickname":"get_auto_compaction",
+               "nickname":"is_auto_compaction_disabled",
                "produces":[
                   "application/json"
                ],
                "parameters":[
                   {
                      "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            },
-            {
-               "method":"POST",
-               "summary":"Enable table auto compaction",
-               "type":"void",
-               "nickname":"enable_auto_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Disable table auto compaction",
-               "type":"void",
-               "nickname":"disable_auto_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
+                     "description":"The column family name in keyspace:name format",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -582,7 +544,7 @@
                "summary":"sstable count for each level. empty unless leveled compaction is used",
                "type":"array",
                "items":{
-                  "type": "long"
+                  "type":"int"
                },
                "nickname":"get_sstable_count_per_level",
                "produces":[
@@ -674,7 +636,7 @@
                      "description":"Duration (in milliseconds) of monitoring operation",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   },
                   {
@@ -682,7 +644,7 @@
                     "description":"number of the top partitions to list",
                     "required":false,
                     "allowMultiple":false,
-                    "type": "long",
+                    "type":"int",
                     "paramType":"query"
                  },
                  {
@@ -690,7 +652,7 @@
                     "description":"capacity of stream summary: determines amount of resources used in query processing",
                     "required":false,
                     "allowMultiple":false,
-                    "type": "long",
+                    "type":"int",
                     "paramType":"query"
                  }
               ]
@@ -959,7 +921,7 @@
             {
                "method":"GET",
                "summary":"Get memtable switch count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_memtable_switch_count",
                "produces":[
                   "application/json"
@@ -983,7 +945,7 @@
             {
                "method":"GET",
                "summary":"Get all memtable switch count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_memtable_switch_count",
                "produces":[
                   "application/json"
@@ -1120,7 +1082,7 @@
             {
                "method":"GET",
                "summary":"Get read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_read_latency",
                "produces":[
                   "application/json"
@@ -1273,7 +1235,7 @@
             {
                "method":"GET",
                "summary":"Get all read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_read_latency",
                "produces":[
                   "application/json"
@@ -1289,7 +1251,7 @@
             {
                "method":"GET",
                "summary":"Get range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_range_latency",
                "produces":[
                   "application/json"
@@ -1313,7 +1275,7 @@
             {
                "method":"GET",
                "summary":"Get all range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_range_latency",
                "produces":[
                   "application/json"
@@ -1329,7 +1291,7 @@
             {
                "method":"GET",
                "summary":"Get write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_write_latency",
                "produces":[
                   "application/json"
@@ -1482,7 +1444,7 @@
             {
                "method":"GET",
                "summary":"Get all write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_write_latency",
                "produces":[
                   "application/json"
@@ -1498,7 +1460,7 @@
             {
                "method":"GET",
                "summary":"Get pending flushes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_pending_flushes",
                "produces":[
                   "application/json"
@@ -1522,7 +1484,7 @@
             {
                "method":"GET",
                "summary":"Get all pending flushes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_pending_flushes",
                "produces":[
                   "application/json"
@@ -1538,7 +1500,7 @@
             {
                "method":"GET",
                "summary":"Get pending compactions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_pending_compactions",
                "produces":[
                   "application/json"
@@ -1562,7 +1524,7 @@
             {
                "method":"GET",
                "summary":"Get all pending compactions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_pending_compactions",
                "produces":[
                   "application/json"
@@ -1578,7 +1540,7 @@
             {
                "method":"GET",
                "summary":"Get live ss table count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_live_ss_table_count",
                "produces":[
                   "application/json"
@@ -1602,7 +1564,7 @@
             {
                "method":"GET",
                "summary":"Get all live ss table count",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_live_ss_table_count",
                "produces":[
                   "application/json"
@@ -1618,7 +1580,7 @@
             {
                "method":"GET",
                "summary":"Get live disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_live_disk_space_used",
                "produces":[
                   "application/json"
@@ -1642,7 +1604,7 @@
             {
                "method":"GET",
                "summary":"Get all live disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_live_disk_space_used",
                "produces":[
                   "application/json"
@@ -1658,7 +1620,7 @@
             {
                "method":"GET",
                "summary":"Get total disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_disk_space_used",
                "produces":[
                   "application/json"
@@ -1682,7 +1644,7 @@
             {
                "method":"GET",
                "summary":"Get all total disk space used",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_total_disk_space_used",
                "produces":[
                   "application/json"
@@ -2138,7 +2100,7 @@
             {
                "method":"GET",
                "summary":"Get speculative retries",
-               "type": "long",
+               "type":"int",
                "nickname":"get_speculative_retries",
                "produces":[
                   "application/json"
@@ -2162,7 +2124,7 @@
             {
                "method":"GET",
                "summary":"Get all speculative retries",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_speculative_retries",
                "produces":[
                   "application/json"
@@ -2242,7 +2204,7 @@
             {
                "method":"GET",
                "summary":"Get row cache hit out of range",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_hit_out_of_range",
                "produces":[
                   "application/json"
@@ -2266,7 +2228,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache hit out of range",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_hit_out_of_range",
                "produces":[
                   "application/json"
@@ -2282,7 +2244,7 @@
             {
                "method":"GET",
                "summary":"Get row cache hit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_hit",
                "produces":[
                   "application/json"
@@ -2306,7 +2268,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache hit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_hit",
                "produces":[
                   "application/json"
@@ -2322,7 +2284,7 @@
             {
                "method":"GET",
                "summary":"Get row cache miss",
-               "type": "long",
+               "type":"int",
                "nickname":"get_row_cache_miss",
                "produces":[
                   "application/json"
@@ -2346,7 +2308,7 @@
             {
                "method":"GET",
                "summary":"Get all row cache miss",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_row_cache_miss",
                "produces":[
                   "application/json"
@@ -2362,7 +2324,7 @@
             {
                "method":"GET",
                "summary":"Get cas prepare",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_prepare",
                "produces":[
                   "application/json"
@@ -2386,7 +2348,7 @@
             {
                "method":"GET",
                "summary":"Get cas propose",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_propose",
                "produces":[
                   "application/json"
@@ -2410,7 +2372,7 @@
             {
                "method":"GET",
                "summary":"Get cas commit",
-               "type": "long",
+               "type":"int",
                "nickname":"get_cas_commit",
                "produces":[
                   "application/json"
@@ -2925,10 +2887,6 @@
          "id":"toppartitions_query_results",
          "description":"nodetool toppartitions query results",
          "properties":{
-            "read_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
             "read":{
                "type":"array",
                "items":{
@@ -2936,10 +2894,6 @@
                },
                "description":"Read results"
             },
-            "write_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
             "write":{
                "type":"array",
                "items":{

api/api-doc/compaction_manager.json

@@ -102,47 +102,7 @@
                "parameters":[
                   {
                      "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/compaction_manager/stop_keyspace_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Stop all running compaction-like tasks in the given keyspace and tables having the provided type.",
-               "type":"void",
-               "nickname":"stop_keyspace_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to stop compaction in",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"tables",
-                     "description":"Comma-separated tables to stop compaction in",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
+                     "description":"the type of compaction to stop. Can be one of: - COMPACTION - VALIDATION - CLEANUP - SCRUB - INDEX_BUILD",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",
@@ -158,7 +118,7 @@
         {
           "method": "GET",
           "summary": "Get pending tasks",
-          "type": "long",
+          "type": "int",
           "nickname": "get_pending_tasks",
           "produces": [
             "application/json"
@@ -221,7 +181,7 @@
         {
           "method": "GET",
           "summary": "Get bytes compacted",
-          "type": "long",
+          "type": "int",
           "nickname": "get_bytes_compacted",
           "produces": [
             "application/json"
@@ -237,7 +197,7 @@
          "description":"A row merged information",
          "properties":{
             "key":{
-               "type": "long",
+               "type":"int",
                "description":"The number of sstable"
             },
             "value":{

api/api-doc/error_injection.json

@@ -1,90 +0,0 @@
-{
-   "apiVersion":"0.0.1",
-   "swaggerVersion":"1.2",
-   "basePath":"{{Protocol}}://{{Host}}",
-   "resourcePath":"/error_injection",
-   "produces":[
-      "application/json"
-   ],
-   "apis":[
-      {
-         "path":"/v2/error_injection/injection/{injection}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Activate an injection that triggers an error in code",
-               "type":"void",
-               "nickname":"enable_injection",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"injection",
-                     "description":"injection name, should correspond to an injection added in code",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"one_shot",
-                     "description":"boolean flag indicating whether the injection should be enabled to trigger only once",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Deactivate an injection previously activated by the API",
-               "type":"void",
-               "nickname":"disable_injection",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"injection",
-                     "description":"injection name",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/v2/error_injection/injection",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"List all enabled injections on all shards, i.e. injections that will trigger an error in the code",
-               "type":"array",
-               "items":{
-                  "type":"string"
-               },
-               "nickname":"get_enabled_injections_on_all",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Deactivate all injections previously activated on all shards by the API",
-               "type":"void",
-               "nickname":"disable_on_all",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      }
-   ]
-}

api/api-doc/failure_detector.json

@@ -110,7 +110,7 @@
             {
                "method":"GET",
                "summary":"Get count down endpoint",
-               "type": "long",
+               "type":"int",
                "nickname":"get_down_endpoint_count",
                "produces":[
                   "application/json"
@@ -126,7 +126,7 @@
             {
                "method":"GET",
                "summary":"Get count up endpoint",
-               "type": "long",
+               "type":"int",
                "nickname":"get_up_endpoint_count",
                "produces":[
                   "application/json"
@@ -180,11 +180,11 @@
                     "description": "The endpoint address"
                 },
                 "generation": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The heart beat generation"
                 },
                 "version": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The heart beat version"
                 },
                 "update_time": {
@@ -209,7 +209,7 @@
            "description": "Holds a version value for an application state",
                "properties": {
                 "application_state": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The application state enum index"
                 },
                 "value": {
@@ -217,7 +217,7 @@
                     "description": "The version value"
                 },
                 "version": {
-                    "type": "long",
+                    "type": "int",
                     "description": "The application state version"
                 }
             }

api/api-doc/gossiper.json

@@ -75,7 +75,7 @@
             {
                "method":"GET",
                "summary":"Returns files which are pending for archival attempt. Does NOT include failed archive attempts",
-               "type": "long",
+               "type":"int",
                "nickname":"get_current_generation_number",
                "produces":[
                   "application/json"
@@ -99,7 +99,7 @@
             {
                "method":"GET",
                "summary":"Get heart beat version for a node",
-               "type": "long",
+               "type":"int",
                "nickname":"get_current_heart_beat_version",
                "produces":[
                   "application/json"
@@ -148,30 +148,6 @@
                ]
             }
          ]
-      },
-      {
-         "path":"/gossiper/force_remove_endpoint/{addr}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Force remove an endpoint from gossip",
-               "type":"void",
-               "nickname":"force_remove_endpoint",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"addr",
-                     "description":"The endpoint address",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
       }
    ]
 }

api/api-doc/hinted_handoff.json

@@ -7,61 +7,6 @@
       "application/json"
    ],
    "apis":[
-      {
-         "path":"/hinted_handoff/sync_point",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Creates a hints sync point. It can be used to wait until hints between given nodes are replayed. A sync point allows you to wait for hints accumulated at the moment of its creation - it won't wait for hints generated later. A sync point is described entirely by its ID - there is no state kept server-side, so there is no need to delete it.",
-               "type":"string",
-               "nickname":"create_hints_sync_point",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"target_hosts",
-                     "description":"A list of nodes towards which hints should be replayed. Multiple hosts can be listed by separating them with commas. If not provided or empty, the point will resolve when current hints towards all nodes in the cluster are sent.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            },
-            {
-               "method":"GET",
-               "summary":"Get the status of a hints sync point, possibly waiting for it to be reached.",
-               "type":"string",
-               "enum":[
-                  "DONE",
-                  "IN_PROGRESS"
-               ],
-               "nickname":"get_hints_sync_point",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"id",
-                     "description":"The ID of the hint sync point which should be checked or waited on",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"timeout",
-                     "description":"Timeout in seconds after which the query returns even if hints are still being replayed. No value or 0 will cause the query to return immediately. A negative value will cause the query to wait until the sync point is reached",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/hinted_handoff/hints",
          "operations":[
@@ -154,7 +99,7 @@
         {
           "method": "GET",
           "summary": "Get create hint count",
-          "type": "long",
+          "type": "int",
           "nickname": "get_create_hint_count",
           "produces": [
             "application/json"
@@ -178,7 +123,7 @@
         {
           "method": "GET",
           "summary": "Get not stored hints count",
-          "type": "long",
+          "type": "int",
           "nickname": "get_not_stored_hints_count",
           "produces": [
             "application/json"

api/api-doc/messaging_service.json

@@ -76,7 +76,7 @@
                "items":{
                   "type":"message_counter"
                },
-               "nickname":"get_replied_messages",
+               "nickname":"get_completed_messages",
                "produces":[
                   "application/json"
                ],
@@ -191,7 +191,7 @@
             {
                "method":"GET",
                "summary":"Get the version number",
-               "type": "long",
+               "type":"int",
                "nickname":"get_version",
                "produces":[
                   "application/json"
@@ -249,10 +249,10 @@
                  "MIGRATION_REQUEST",
                  "PREPARE_MESSAGE",
                  "PREPARE_DONE_MESSAGE",
-                 "UNUSED__STREAM_MUTATION",
+                 "STREAM_MUTATION",
                  "STREAM_MUTATION_DONE",
                  "COMPLETE_MESSAGE",
-                 "UNUSED__REPAIR_CHECKSUM_RANGE",
+                 "REPAIR_CHECKSUM_RANGE",
                  "GET_SCHEMA_VERSION"
                ]
             }

api/api-doc/storage_proxy.json

@@ -68,7 +68,7 @@
                "summary":"Get the hinted handoff enabled by dc",
                "type":"array",
                "items":{
-                  "type":"array"
+                  "type":"mapper_list"
                },
                "nickname":"get_hinted_handoff_enabled_by_dc",
                "produces":[
@@ -105,7 +105,7 @@
             {
                "method":"GET",
                "summary":"Get the max hint window",
-               "type": "long",
+               "type":"int",
                "nickname":"get_max_hint_window",
                "produces":[
                   "application/json"
@@ -128,7 +128,7 @@
                      "description":"max hint window in ms",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -141,7 +141,7 @@
             {
                "method":"GET",
                "summary":"Get max hints in progress",
-               "type": "long",
+               "type":"int",
                "nickname":"get_max_hints_in_progress",
                "produces":[
                   "application/json"
@@ -164,7 +164,7 @@
                      "description":"max hints in progress",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -177,7 +177,7 @@
             {
                "method":"GET",
                "summary":"get hints in progress",
-               "type": "long",
+               "type":"int",
                "nickname":"get_hints_in_progress",
                "produces":[
                   "application/json"
@@ -602,7 +602,7 @@
         {
           "method": "GET",
           "summary": "Get cas write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_cas_write_metrics_unfinished_commit",
           "produces": [
             "application/json"
@@ -632,7 +632,7 @@
         {
           "method": "GET",
           "summary": "Get cas write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_cas_write_metrics_condition_not_met",
           "produces": [
             "application/json"
@@ -641,28 +641,13 @@
         }
       ]
     },
-    {
-      "path": "/storage_proxy/metrics/cas_write/failed_read_round_optimization",
-      "operations": [
-        {
-          "method": "GET",
-          "summary": "Get cas write metrics",
-          "type": "long",
-          "nickname": "get_cas_write_metrics_failed_read_round_optimization",
-          "produces": [
-            "application/json"
-          ],
-          "parameters": []
-        }
-      ]
-    },
     {
       "path": "/storage_proxy/metrics/cas_read/unfinished_commit",
       "operations": [
         {
           "method": "GET",
           "summary": "Get cas read metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_cas_read_metrics_unfinished_commit",
           "produces": [
             "application/json"
@@ -692,7 +677,7 @@
         {
           "method": "GET",
           "summary": "Get read metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_read_metrics_timeouts",
           "produces": [
             "application/json"
@@ -707,7 +692,7 @@
         {
           "method": "GET",
           "summary": "Get read metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_read_metrics_unavailables",
           "produces": [
             "application/json"
@@ -842,7 +827,7 @@
         {
           "method": "GET",
           "summary": "Get range metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_range_metrics_timeouts",
           "produces": [
             "application/json"
@@ -857,7 +842,7 @@
         {
           "method": "GET",
           "summary": "Get range metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_range_metrics_unavailables",
           "produces": [
             "application/json"
@@ -902,7 +887,7 @@
         {
           "method": "GET",
           "summary": "Get write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_write_metrics_timeouts",
           "produces": [
             "application/json"
@@ -917,7 +902,7 @@
         {
           "method": "GET",
           "summary": "Get write metrics",
-          "type": "long",
+          "type": "int",
           "nickname": "get_write_metrics_unavailables",
           "produces": [
             "application/json"
@@ -1023,7 +1008,7 @@
             {
                "method":"GET",
                "summary":"Get read latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_read_latency",
                "produces":[
                   "application/json"
@@ -1055,7 +1040,7 @@
             {
                "method":"GET",
                "summary":"Get write latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_write_latency",
                "produces":[
                   "application/json"
@@ -1087,7 +1072,7 @@
             {
                "method":"GET",
                "summary":"Get range latency",
-               "type": "long",
+               "type":"int",
                "nickname":"get_range_latency",
                "produces":[
                   "application/json"

api/api-doc/storage_service.json

@@ -104,68 +104,6 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/toppartitions/",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Toppartitions query",
-               "type":"toppartitions_query_results",
-               "nickname":"toppartitions_generic",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"table_filters",
-                     "description":"Optional list of table name filters in keyspace:name format",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"array",
-                     "items":{
-                        "type":"string"
-                     },
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"keyspace_filters",
-                     "description":"Optional list of keyspace filters",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"array",
-                     "items":{
-                        "type":"string"
-                     },
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"duration",
-                     "description":"Duration (in milliseconds) of monitoring operation",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  },
-                  {
-                    "name":"list_size",
-                    "description":"number of the top partitions to list",
-                    "required":false,
-                    "allowMultiple":false,
-                    "type": "long",
-                    "paramType":"query"
-                 },
-                 {
-                    "name":"capacity",
-                    "description":"capacity of stream summary: determines amount of resources used in query processing",
-                    "required":false,
-                    "allowMultiple":false,
-                    "type": "long",
-                    "paramType":"query"
-                 }
-              ]
-            }
-         ]
-      },
       {
          "path":"/storage_service/nodes/leaving",
          "operations":[
@@ -520,7 +458,7 @@
             {
                "method":"GET",
                "summary":"Return the generation value for this node.",
-               "type": "long",
+               "type":"int",
                "nickname":"get_current_generation_number",
                "produces":[
                   "application/json"
@@ -573,21 +511,6 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/cdc_streams_check_and_repair",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Checks that CDC streams reflect current cluster topology and regenerates them if not.",
-               "type":"void",
-               "nickname":"cdc_streams_check_and_repair",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      },
       {
          "path":"/storage_service/snapshots",
          "operations":[
@@ -624,7 +547,7 @@
                   },
                   {
                      "name":"kn",
-                     "description":"Keyspace(s) to snapshot. Multiple keyspaces can be provided using a comma-separated list. If omitted, snapshot all keyspaces.",
+                     "description":"Comma seperated keyspaces name to snapshot",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -632,19 +555,11 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Table(s) to snapshot. Multiple tables (in a single keyspace) can be provided using a comma-separated list. If omitted, snapshot all tables in the given keyspace(s).",
+                     "description":"the column family to snapshot",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"sf",
-                     "description":"Skip flush. When set to \"true\", do not flush memtables before snapshotting (snapshot will not contain unflushed data)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
                   }
                ]
             },
@@ -667,15 +582,7 @@
                   },
                   {
                      "name":"kn",
-                     "description":"Comma-separated keyspaces name that their snapshot will be deleted",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"an optional table name that its snapshot will be deleted",
+                     "description":"Comma seperated keyspaces name to snapshot",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -723,7 +630,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -739,7 +646,7 @@
             {
                "method":"POST",
                "summary":"Trigger a cleanup of keys on a single keyspace",
-               "type": "long",
+               "type":"int",
                "nickname":"force_keyspace_cleanup",
                "produces":[
                   "application/json"
@@ -755,39 +662,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/storage_service/keyspace_offstrategy_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Perform offstrategy compaction, if needed, in a single keyspace",
-               "type":"boolean",
-               "nickname":"perform_keyspace_offstrategy_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to operate on",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"Comma-separated table names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -802,8 +677,8 @@
          "operations":[
             {
                "method":"GET",
-               "summary":"Scrub (deserialize + reserialize at the latest version, resolving corruptions if any) the given keyspace. If columnFamilies array is empty, all CFs are scrubbed. Scrubbed CFs will be snapshotted first, if disableSnapshot is false. Scrub has the following modes: Abort (default) - abort scrub if corruption is detected; Skip (same as `skip_corrupted=true`) skip over corrupt data, omitting them from the output; Segregate - segregate data into multiple sstables if needed, such that each sstable contains data with valid order; Validate - read (no rewrite) and validate data, logging any problems found.",
-               "type": "long",
+               "summary":"Scrub (deserialize + reserialize at the latest version, skipping bad rows if any) the given keyspace. If columnFamilies array is empty, all CFs are scrubbed. Scrubbed CFs will be snapshotted first, if disableSnapshot is false",
+               "type":"int",
                "nickname":"scrub",
                "produces":[
                   "application/json"
@@ -825,33 +700,6 @@
                      "type":"boolean",
                      "paramType":"query"
                   },
-                  {
-                     "name":"scrub_mode",
-                     "description":"How to handle corrupt data (overrides 'skip_corrupted'); ",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "ABORT",
-                        "SKIP",
-                        "SEGREGATE",
-                        "VALIDATE"
-                     ],
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"quarantine_mode",
-                     "description":"Controls whether to scrub quarantined sstables (default INCLUDE)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "INCLUDE",
-                        "EXCLUDE",
-                        "ONLY"
-                     ],
-                     "paramType":"query"
-                  },
                   {
                      "name":"keyspace",
                      "description":"The keyspace to query about",
@@ -862,7 +710,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -878,7 +726,7 @@
             {
                "method":"GET",
                "summary":"Rewrite all sstables to the latest version. Unlike scrub, it doesn't skip bad rows and do not snapshot sstables first.",
-               "type": "long",
+               "type":"int",
                "nickname":"upgrade_sstables",
                "produces":[
                   "application/json"
@@ -902,7 +750,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -934,7 +782,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -952,7 +800,7 @@
                "summary":"Return an array with the ids of the currently active repairs",
                "type":"array",
                "items":{
-                  "type": "long"
+                  "type":"int"
                },
                "nickname":"get_active_repair_async",
                "produces":[
@@ -962,50 +810,13 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/repair_status/",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Query the repair status and return when the repair is finished or timeout",
-               "type":"string",
-               "enum":[
-                  "RUNNING",
-                  "SUCCESSFUL",
-                  "FAILED"
-               ],
-               "nickname":"repair_await_completion",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"id",
-                     "description":"The repair ID to check for status",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"timeout",
-                     "description":"Seconds to wait before the query returns even if the repair is not finished. The value -1 or not providing this parameter means no timeout",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/storage_service/repair_async/{keyspace}",
          "operations":[
             {
                "method":"POST",
                "summary":"Invoke repair asynchronously. You can track repair progress by using the get supplying id",
-               "type": "long",
+               "type":"int",
                "nickname":"repair_async",
                "produces":[
                   "application/json"
@@ -1099,14 +910,6 @@
                      "type":"string",
                      "paramType":"query"
                   },
-                  {
-                     "name":"ignore_nodes",
-                     "description":"Which hosts are to ignore in this repair. Multiple hosts can be listed separated by commas.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
                   {
                      "name":"trace",
                      "description":"If the value is the string 'true' with any capitalization, enable tracing of the repair.",
@@ -1144,7 +947,7 @@
                      "description":"The repair ID to check for status",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -1228,7 +1031,7 @@
          "operations":[
             {
                "method":"POST",
-               "summary":"Removes a node from the cluster. Replicated data that logically belonged to this node is redistributed among the remaining nodes.",
+               "summary":"Removes token (and all data associated with enpoint that had it) from the ring",
                "type":"void",
                "nickname":"remove_node",
                "produces":[
@@ -1242,14 +1045,6 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"ignore_nodes",
-                     "description":"Comma-separated list of dead nodes to ignore in removenode operation. Use the same method for all nodes to ignore: either Host IDs or ip addresses.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                   }
                ]
             }
@@ -1482,18 +1277,18 @@
                   },
                   {
                      "name":"dynamic_update_interval",
-                     "description":"interval in ms (default 100)",
+                     "description":"integer, in ms (default 100)",
                      "required":false,
                      "allowMultiple":false,
-                     "type":"long",
+                     "type":"integer",
                      "paramType":"query"
                   },
                   {
                      "name":"dynamic_reset_interval",
-                     "description":"interval in ms (default 600,000)",
+                     "description":"integer, in ms (default 600,000)",
                      "required":false,
                      "allowMultiple":false,
-                     "type":"long",
+                     "type":"integer",
                      "paramType":"query"
                   },
                   {
@@ -1698,7 +1493,7 @@
                      "description":"Stream throughput",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -1706,7 +1501,7 @@
             {
                "method":"GET",
                "summary":"Get stream throughput mb per sec",
-               "type": "long",
+               "type":"int",
                "nickname":"get_stream_throughput_mb_per_sec",
                "produces":[
                   "application/json"
@@ -1722,7 +1517,7 @@
             {
                "method":"GET",
                "summary":"get compaction throughput mb per sec",
-               "type": "long",
+               "type":"int",
                "nickname":"get_compaction_throughput_mb_per_sec",
                "produces":[
                   "application/json"
@@ -1744,7 +1539,7 @@
                      "description":"compaction throughput",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -1901,22 +1696,6 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"load_and_stream",
-                     "description":"Load the sstables and stream to all replica nodes that owns the data",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"primary_replica_only",
-                     "description":"Load the sstables and stream to primary replica node that owns the data. Repair is needed after the load and stream process",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                   }
                ]
             }
@@ -2027,14 +1806,6 @@
                      "allowMultiple":false,
                      "type":"long",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"fast",
-                     "description":"Lightweight tracing mode: if true, slow queries tracing records only session headers",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
                   }
                ]
             },
@@ -2073,7 +1844,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -2100,7 +1871,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -2172,7 +1943,7 @@
             {
                "method":"GET",
                "summary":"Returns the threshold for warning of queries with many tombstones",
-               "type": "long",
+               "type":"int",
                "nickname":"get_tombstone_warn_threshold",
                "produces":[
                   "application/json"
@@ -2194,7 +1965,7 @@
                      "description":"tombstone debug threshold",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2207,7 +1978,7 @@
             {
                "method":"GET",
                "summary":"",
-               "type": "long",
+               "type":"int",
                "nickname":"get_tombstone_failure_threshold",
                "produces":[
                   "application/json"
@@ -2229,7 +2000,7 @@
                      "description":"tombstone debug threshold",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2242,7 +2013,7 @@
             {
                "method":"GET",
                "summary":"Returns the threshold for rejecting queries due to a large batch size",
-               "type": "long",
+               "type":"int",
                "nickname":"get_batch_size_failure_threshold",
                "produces":[
                   "application/json"
@@ -2264,7 +2035,7 @@
                      "description":"batch size debug threshold",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2288,7 +2059,7 @@
                      "description":"throttle in kb",
                      "required":true,
                      "allowMultiple":false,
-                     "type": "long",
+                     "type":"int",
                      "paramType":"query"
                   }
                ]
@@ -2301,7 +2072,7 @@
             {
                "method":"GET",
                "summary":"Get load",
-               "type": "long",
+               "type":"int",
                "nickname":"get_metrics_load",
                "produces":[
                   "application/json"
@@ -2317,7 +2088,7 @@
             {
                "method":"GET",
                "summary":"Get exceptions",
-               "type": "long",
+               "type":"int",
                "nickname":"get_exceptions",
                "produces":[
                   "application/json"
@@ -2333,7 +2104,7 @@
             {
                "method":"GET",
                "summary":"Get total hints in progress",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_hints_in_progress",
                "produces":[
                   "application/json"
@@ -2349,7 +2120,7 @@
             {
                "method":"GET",
                "summary":"Get total hints",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_hints",
                "produces":[
                   "application/json"
@@ -2533,10 +2304,6 @@
             "threshold":{
                "type":"long",
                "description":"The slow query logging threshold in microseconds. Queries that takes longer, will be logged"
-            },
-            "fast":{
-               "type":"boolean",
-               "description":"Is lightweight tracing mode enabled. In that mode tracing ignore events and tracks only sessions."
             }
          }
       },
@@ -2641,7 +2408,7 @@
             "version":{
                "type":"string",
                "enum":[
-                  "ka", "la", "mc", "md", "me"
+                  "ka", "la", "mc"
                ],
                "description":"SSTable version"
             },

api/api-doc/stream_manager.json

@@ -32,7 +32,7 @@
             {
                "method":"GET",
                "summary":"Get number of active outbound streams",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_active_streams_outbound",
                "produces":[
                   "application/json"
@@ -48,7 +48,7 @@
             {
                "method":"GET",
                "summary":"Get total incoming bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_incoming_bytes",
                "produces":[
                   "application/json"
@@ -72,7 +72,7 @@
             {
                "method":"GET",
                "summary":"Get all total incoming bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_total_incoming_bytes",
                "produces":[
                   "application/json"
@@ -88,7 +88,7 @@
             {
                "method":"GET",
                "summary":"Get total outgoing bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_total_outgoing_bytes",
                "produces":[
                   "application/json"
@@ -112,7 +112,7 @@
             {
                "method":"GET",
                "summary":"Get all total outgoing bytes",
-               "type": "long",
+               "type":"int",
                "nickname":"get_all_total_outgoing_bytes",
                "produces":[
                   "application/json"
@@ -154,7 +154,7 @@
                "description":"The peer"
             },
             "session_index":{
-               "type": "long",
+               "type":"int",
                "description":"The session index"
             },
             "connecting":{
@@ -211,7 +211,7 @@
                "description":"The ID"
             },
             "files":{
-               "type": "long",
+               "type":"int",
                "description":"Number of files to transfer. Can be 0 if nothing to transfer for some streaming request."
             },
             "total_size":{
@@ -242,7 +242,7 @@
                "description":"The peer address"
             },
             "session_index":{
-               "type": "long",
+               "type":"int",
                "description":"The session index"
             },
             "file_name":{

api/api-doc/system.json

@@ -52,76 +52,6 @@
             }
          ]
       },
-      {
-         "path":"/system/log",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Write a message to the Scylla log",
-               "type":"void",
-               "nickname":"write_log_message",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"message",
-                     "description":"The message to write to the log",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"level",
-                     "description":"The logging level to use",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "error",
-                        "warn",
-                        "info",
-                        "debug",
-                        "trace"
-                     ],
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/system/drop_sstable_caches",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Drop in-memory caches for data which is in sstables",
-               "type":"void",
-               "nickname":"drop_sstable_caches",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/system/uptime_ms",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Get system uptime, in milliseconds",
-               "type":"long",
-               "nickname":"get_system_uptime",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      },
       {
          "path":"/system/logger/{name}",
          "operations":[

api/api-doc/task_manager.json

@@ -1,251 +0,0 @@
-{
-    "apiVersion":"0.0.1",
-    "swaggerVersion":"1.2",
-    "basePath":"{{Protocol}}://{{Host}}",
-    "resourcePath":"/task_manager",
-    "produces":[
-       "application/json"
-    ],
-    "apis":[
-       {
-          "path":"/task_manager/list_modules",
-          "operations":[
-             {
-                "method":"GET",
-                "summary":"Get all modules names",
-                "type":"array",
-                "items":{
-                   "type":"string"
-                },
-                "nickname":"get_modules",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                ]
-             }
-          ]
-       },
-       {
-          "path":"/task_manager/list_module_tasks/{module}",
-          "operations":[
-             {
-                "method":"GET",
-                "summary":"Get a list of tasks",
-                "type":"array",
-                "items":{
-                    "type":"task_stats"
-                },
-                "nickname":"get_tasks",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                    {
-                        "name":"module",
-                        "description":"The module to query about",
-                        "required":true,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"path"
-                    },
-                    {
-                        "name":"internal",
-                        "description":"Boolean flag indicating whether internal tasks should be shown (false by default)",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"boolean",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"keyspace",
-                        "description":"The keyspace to query about",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"table",
-                        "description":"The table to query about",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    }
-                ]
-             }
-          ]
-       },
-       {
-          "path":"/task_manager/task_status/{task_id}",
-          "operations":[
-             {
-                "method":"GET",
-                "summary":"Get task status",
-                "type":"task_status",
-                "nickname":"get_task_status",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                    {
-                        "name":"task_id",
-                        "description":"The uuid of a task to query about",
-                        "required":true,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"path"
-                    }
-                ]
-             }
-          ]
-       },
-       {
-          "path":"/task_manager/abort_task/{task_id}",
-          "operations":[
-             {
-                "method":"POST",
-                "summary":"Abort running task and its descendants",
-                "type":"void",
-                "nickname":"abort_task",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                   {
-                      "name":"task_id",
-                      "description":"The uuid of a task to abort",
-                      "required":true,
-                      "allowMultiple":false,
-                      "type":"string",
-                      "paramType":"path"
-                   }
-                ]
-             }
-          ]
-       },
-       {
-        "path":"/task_manager/wait_task/{task_id}",
-        "operations":[
-           {
-              "method":"GET",
-              "summary":"Wait for a task to complete",
-              "type":"task_status",
-              "nickname":"wait_task",
-              "produces":[
-                 "application/json"
-              ],
-              "parameters":[
-                 {
-                    "name":"task_id",
-                    "description":"The uuid of a task to wait for",
-                    "required":true,
-                    "allowMultiple":false,
-                    "type":"string",
-                    "paramType":"path"
-                 }
-              ]
-           }
-        ]
-     }
-    ],
-    "models":{
-       "task_stats" :{
-           "id": "task_stats",
-           "description":"A task statistics object",
-           "properties":{
-             "task_id":{
-                "type":"string",
-                "description":"The uuid of a task"
-             },
-             "state":{
-                "type":"string",
-                "enum":[
-                  "created",
-                  "running",
-                  "done",
-                  "failed"
-                ],
-                "description":"The state of a task"
-             }
-           }
-       },
-       "task_status":{
-          "id":"task_status",
-          "description":"A task status object",
-          "properties":{
-             "id":{
-                "type":"string",
-                "description":"The uuid of the task"
-             },
-             "type":{
-                "type":"string",
-                "description":"The description of the task"
-             },
-             "state":{
-               "type":"string",
-               "enum":[
-                 "created",
-                 "running",
-                 "done",
-                 "failed"
-               ],
-                "description":"The state of the task"
-             },
-             "is_abortable":{
-                "type":"boolean",
-                "description":"Boolean flag indicating whether the task can be aborted"
-             },
-             "start_time":{
-                "type":"datetime",
-                "description":"The start time of the task"
-             },
-             "end_time":{
-                "type":"datetime",
-                "description":"The end time of the task (unspecified when the task is not completed)"
-             },
-             "error":{
-                "type":"string",
-                "description":"Error string, if the task failed"
-             },
-             "parent_id":{
-               "type":"string",
-               "description":"The uuid of the parent task"
-            },
-            "sequence_number":{
-               "type":"long",
-               "description":"The running sequence number of the task"
-            },
-            "shard":{
-               "type":"long",
-               "description":"The number of a shard the task is running on"
-            },
-            "keyspace":{
-               "type":"string",
-               "description":"The keyspace the task is working on (if applicable)"
-            },
-            "table":{
-               "type":"string",
-               "description":"The table the task is working on (if applicable)"
-            },
-            "entity":{
-               "type":"string",
-               "description":"Task-specific entity description"
-            },
-            "progress_units":{
-               "type":"string",
-               "description":"A description of the progress units"
-            },
-            "progress_total":{
-               "type":"double",
-               "description":"The total number of units to complete for the task"
-            },
-            "progress_completed":{
-               "type":"double",
-               "description":"The number of units completed so far"
-            }
-          }
-       }
-    }
- }

api/api-doc/task_manager_test.json

@@ -1,185 +0,0 @@
-{
-    "apiVersion":"0.0.1",
-    "swaggerVersion":"1.2",
-    "basePath":"{{Protocol}}://{{Host}}",
-    "resourcePath":"/task_manager_test",
-    "produces":[
-       "application/json"
-    ],
-    "apis":[
-       {
-          "path":"/task_manager_test/test_module",
-          "operations":[
-             {
-                "method":"POST",
-                "summary":"Register test module in task manager",
-                "type":"void",
-                "nickname":"register_test_module",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                ]
-             },
-             {
-                "method":"DELETE",
-                "summary":"Unregister test module in task manager",
-                "type":"void",
-                "nickname":"unregister_test_module",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                ]
-             }
-          ]
-       },
-       {
-          "path":"/task_manager_test/test_task",
-          "operations":[
-             {
-                "method":"POST",
-                "summary":"Register test task",
-                "type":"string",
-                "nickname":"register_test_task",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                    {
-                        "name":"task_id",
-                        "description":"The uuid of a task to register",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"shard",
-                        "description":"The shard of the task",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"long",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"parent_id",
-                        "description":"The uuid of a parent task",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"keyspace",
-                        "description":"The keyspace the task is working on",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"table",
-                        "description":"The table the task is working on",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"type",
-                        "description":"The type of the task",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    },
-                    {
-                        "name":"entity",
-                        "description":"Task-specific entity description",
-                        "required":false,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    }
-                ]
-             },
-             {
-                "method":"DELETE",
-                "summary":"Unregister test task",
-                "type":"void",
-                "nickname":"unregister_test_task",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                    {
-                        "name":"task_id",
-                        "description":"The uuid of a task to register",
-                        "required":true,
-                        "allowMultiple":false,
-                        "type":"string",
-                        "paramType":"query"
-                    }
-                ]
-             }
-          ]
-       },
-       {
-          "path":"/task_manager_test/finish_test_task/{task_id}",
-          "operations":[
-             {
-                "method":"POST",
-                "summary":"Finish test task",
-                "type":"void",
-                "nickname":"finish_test_task",
-                "produces":[
-                   "application/json"
-                ],
-                "parameters":[
-                   {
-                      "name":"task_id",
-                      "description":"The uuid of a task to finish",
-                      "required":true,
-                      "allowMultiple":false,
-                      "type":"string",
-                      "paramType":"path"
-                   },
-                   {
-                      "name":"error",
-                      "description":"The error with which task fails (if it does)",
-                      "required":false,
-                      "allowMultiple":false,
-                      "type":"string",
-                      "paramType":"query"
-                   }
-                ]
-             }
-          ]
-       },
-       {
-         "path":"/task_manager_test/ttl",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Set ttl in seconds and get last value",
-               "type":"long",
-               "nickname":"get_and_update_ttl",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"ttl",
-                     "description":"The number of seconds for which the tasks will be kept in memory after it finishes",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      }
-    ]
- }

api/api.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "api.hh"
@@ -23,14 +36,10 @@
 #include "endpoint_snitch.hh"
 #include "compaction_manager.hh"
 #include "hinted_handoff.hh"
-#include "error_injection.hh"
-#include "authorization_cache.hh"
 #include <seastar/http/exception.hh>
 #include "stream_manager.hh"
 #include "system.hh"
 #include "api/config.hh"
-#include "task_manager.hh"
-#include "task_manager_test.hh"
 
 logging::logger apilog("api");
 
@@ -39,7 +48,7 @@ namespace api {
 static std::unique_ptr<reply> exception_reply(std::exception_ptr eptr) {
     try {
         std::rethrow_exception(eptr);
-    } catch (const replica::no_such_keyspace& ex) {
+    } catch (const no_such_keyspace& ex) {
         throw bad_param_exception(ex.what());
     }
     // We never going to get here
@@ -59,19 +68,13 @@ future<> set_server_init(http_context& ctx) {
         rb->set_api_doc(r);
         rb02->set_api_doc(r);
         rb02->register_api_file(r, "swagger20_header");
+        set_config(rb02, ctx, r);
         rb->register_function(r, "system",
                 "The system related API");
         set_system(ctx, r);
     });
 }
 
-future<> set_server_config(http_context& ctx, const db::config& cfg) {
-    auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
-    return ctx.http_server.set_routes([&ctx, &cfg, rb02](routes& r) {
-        set_config(rb02, ctx, r, cfg);
-    });
-}
-
 static future<> register_api(http_context& ctx, const sstring& api_name,
         const sstring api_desc,
         std::function<void(http_context& ctx, routes& r)> f) {
@@ -83,86 +86,17 @@ static future<> register_api(http_context& ctx, const sstring& api_name,
     });
 }
 
-future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl) {
-    return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_transport_controller(ctx, r, ctl); });
+future<> set_server_storage_service(http_context& ctx) {
+    return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
 }
 
-future<> unset_transport_controller(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_transport_controller(ctx, r); });
+future<> set_server_snitch(http_context& ctx) {
+    return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
 }
 
-future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl) {
-    return ctx.http_server.set_routes([&ctx, &ctl] (routes& r) { set_rpc_controller(ctx, r, ctl); });
-}
-
-future<> unset_rpc_controller(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_rpc_controller(ctx, r); });
-}
-
-future<> set_server_storage_service(http_context& ctx, sharded<service::storage_service>& ss, sharded<gms::gossiper>& g, sharded<cdc::generation_service>& cdc_gs, sharded<db::system_keyspace>& sys_ks) {
-    return register_api(ctx, "storage_service", "The storage service API", [&ss, &g, &cdc_gs, &sys_ks] (http_context& ctx, routes& r) {
-            set_storage_service(ctx, r, ss, g.local(), cdc_gs, sys_ks);
-        });
-}
-
-future<> set_server_sstables_loader(http_context& ctx, sharded<sstables_loader>& sst_loader) {
-    return ctx.http_server.set_routes([&ctx, &sst_loader] (routes& r) { set_sstables_loader(ctx, r, sst_loader); });
-}
-
-future<> unset_server_sstables_loader(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_sstables_loader(ctx, r); });
-}
-
-future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb) {
-    return ctx.http_server.set_routes([&ctx, &vb] (routes& r) { set_view_builder(ctx, r, vb); });
-}
-
-future<> unset_server_view_builder(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_view_builder(ctx, r); });
-}
-
-future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair) {
-    return ctx.http_server.set_routes([&ctx, &repair] (routes& r) { set_repair(ctx, r, repair); });
-}
-
-future<> unset_server_repair(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_repair(ctx, r); });
-}
-
-future<> set_server_authorization_cache(http_context &ctx, sharded<auth::service> &auth_service) {
-    return register_api(ctx, "authorization_cache",
-                "The authorization cache API", [&auth_service] (http_context &ctx, routes &r) {
-                     set_authorization_cache(ctx, r, auth_service);
-                 });
-}
-
-future<> unset_server_authorization_cache(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_authorization_cache(ctx, r); });
-}
-
-future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl) {
-    return ctx.http_server.set_routes([&ctx, &snap_ctl] (routes& r) { set_snapshot(ctx, r, snap_ctl); });
-}
-
-future<> unset_server_snapshot(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_snapshot(ctx, r); });
-}
-
-future<> set_server_snitch(http_context& ctx, sharded<locator::snitch_ptr>& snitch) {
-    return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", [&snitch] (http_context& ctx, routes& r) {
-        set_endpoint_snitch(ctx, r, snitch);
-    });
-}
-
-future<> unset_server_snitch(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_endpoint_snitch(ctx, r); });
-}
-
-future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g) {
+future<> set_server_gossip(http_context& ctx) {
     return register_api(ctx, "gossiper",
-                "The gossiper API", [&g] (http_context& ctx, routes& r) {
-                    set_gossiper(ctx, r, g.local());
-                });
+                "The gossiper API", set_gossiper);
 }
 
 future<> set_server_load_sstable(http_context& ctx) {
@@ -170,32 +104,19 @@ future<> set_server_load_sstable(http_context& ctx) {
                 "The column family API", set_column_family);
 }
 
-future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms) {
+future<> set_server_messaging_service(http_context& ctx) {
     return register_api(ctx, "messaging_service",
-                "The messaging service API", [&ms] (http_context& ctx, routes& r) {
-                    set_messaging_service(ctx, r, ms);
-                });
-}
-future<> unset_server_messaging_service(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_messaging_service(ctx, r); });
+                "The messaging service API", set_messaging_service);
 }
 
-future<> set_server_storage_proxy(http_context& ctx, sharded<service::storage_service>& ss) {
+future<> set_server_storage_proxy(http_context& ctx) {
     return register_api(ctx, "storage_proxy",
-                "The storage proxy API", [&ss] (http_context& ctx, routes& r) {
-                    set_storage_proxy(ctx, r, ss);
-                });
+                "The storage proxy API", set_storage_proxy);
 }
 
-future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm) {
+future<> set_server_stream_manager(http_context& ctx) {
     return register_api(ctx, "stream_manager",
-                "The stream manager API", [&sm] (http_context& ctx, routes& r) {
-                    set_stream_manager(ctx, r, sm);
-                });
-}
-
-future<> unset_server_stream_manager(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_stream_manager(ctx, r); });
+                "The stream manager API", set_stream_manager);
 }
 
 future<> set_server_cache(http_context& ctx) {
@@ -203,34 +124,13 @@ future<> set_server_cache(http_context& ctx) {
             "The cache service API", set_cache_service);
 }
 
-future<> set_hinted_handoff(http_context& ctx, sharded<gms::gossiper>& g) {
-    return register_api(ctx, "hinted_handoff",
-                "The hinted handoff API", [&g] (http_context& ctx, routes& r) {
-                    set_hinted_handoff(ctx, r, g.local());
-                });
-}
-
-future<> unset_hinted_handoff(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_hinted_handoff(ctx, r); });
-}
-
-future<> set_server_gossip_settle(http_context& ctx, sharded<gms::gossiper>& g) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx, &g](routes& r) {
-        rb->register_function(r, "failure_detector",
-                "The failure detector API");
-        set_failure_detector(ctx, r, g.local());
-    });
-}
-
-future<> set_server_compaction_manager(http_context& ctx) {
+future<> set_server_gossip_settle(http_context& ctx) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
 
     return ctx.http_server.set_routes([rb, &ctx](routes& r) {
-        rb->register_function(r, "compaction_manager",
-                "The Compaction manager API");
-        set_compaction_manager(ctx, r);
+        rb->register_function(r, "failure_detector",
+                "The failure detector API");
+        set_failure_detector(ctx,r);
     });
 }
 
@@ -238,71 +138,23 @@ future<> set_server_done(http_context& ctx) {
     auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
 
     return ctx.http_server.set_routes([rb, &ctx](routes& r) {
+        rb->register_function(r, "compaction_manager",
+                "The Compaction manager API");
+        set_compaction_manager(ctx, r);
         rb->register_function(r, "lsa", "Log-structured allocator API");
         set_lsa(ctx, r);
 
         rb->register_function(r, "commitlog",
                 "The commit log API");
         set_commitlog(ctx,r);
+        rb->register_function(r, "hinted_handoff",
+                "The hinted handoff API");
+        set_hinted_handoff(ctx, r);
         rb->register_function(r, "collectd",
                 "The collectd API");
         set_collectd(ctx, r);
-        rb->register_function(r, "error_injection",
-                "The error injection API");
-        set_error_injection(ctx, r);
     });
 }
 
-future<> set_server_task_manager(http_context& ctx) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx](routes& r) {
-        rb->register_function(r, "task_manager",
-                "The task manager API");
-        set_task_manager(ctx, r);
-    });
-}
-
-#ifndef SCYLLA_BUILD_MODE_RELEASE
-
-future<> set_server_task_manager_test(http_context& ctx, lw_shared_ptr<db::config> cfg) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx, &cfg = *cfg](routes& r) mutable {
-        rb->register_function(r, "task_manager_test",
-                "The task manager test API");
-        set_task_manager_test(ctx, r, cfg);
-    });
-}
-
-#endif
-
-void req_params::process(const request& req) {
-    // Process mandatory parameters
-    for (auto& [name, ent] : params) {
-        if (!ent.is_mandatory) {
-            continue;
-        }
-        try {
-            ent.value = req.param[name];
-        } catch (std::out_of_range&) {
-            throw httpd::bad_param_exception(fmt::format("Mandatory parameter '{}' was not provided", name));
-        }
-    }
-
-    // Process optional parameters
-    for (auto& [name, value] : req.query_parameters) {
-        try {
-            auto& ent = params.at(name);
-            if (ent.is_mandatory) {
-                throw httpd::bad_param_exception(fmt::format("Parameter '{}' is expected to be provided as part of the request url", name));
-            }
-            ent.value = value;
-        } catch (std::out_of_range&) {
-            throw httpd::bad_param_exception(fmt::format("Unsupported optional parameter '{}'", name));
-        }
-    }
-}
-
 }
 

api/api.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -16,7 +29,6 @@
 #include <boost/units/detail/utility.hpp>
 #include "api/api-doc/utils.json.hh"
 #include "utils/histogram.hh"
-#include "utils/estimated_histogram.hh"
 #include <seastar/http/exception.hh>
 #include "api_init.hh"
 #include "seastarx.hh"
@@ -58,7 +70,7 @@ T map_sum(T&& dest, const S& src) {
     for (auto i : src) {
         dest[i.first] += i.second;
     }
-    return std::move(dest);
+    return dest;
 }
 
 template <typename MAP>
@@ -81,6 +93,13 @@ inline std::vector<sstring> split(const sstring& text, const char* separator) {
     return boost::split(tokens, text, boost::is_any_of(separator));
 }
 
+/**
+ * Split a column family parameter
+ */
+inline std::vector<sstring> split_cf(const sstring& cf) {
+    return split(cf, ",");
+}
+
 /**
  * A helper function to sum values on an a distributed object that
  * has a get_stats method.
@@ -137,14 +156,6 @@ future<json::json_return_type>  sum_timer_stats(distributed<T>& d, utils::timed_
     });
 }
 
-template<class T, class F>
-future<json::json_return_type>  sum_timer_stats(distributed<T>& d, utils::timed_rate_moving_average_summary_and_histogram F::*f) {
-    return d.map_reduce0([f](const T& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average_and_histogram(),
-            std::plus<utils::rate_moving_average_and_histogram>()).then([](const utils::rate_moving_average_and_histogram& val) {
-        return make_ready_future<json::json_return_type>(timer_to_json(val));
-    });
-}
-
 inline int64_t min_int64(int64_t a, int64_t b) {
     return std::min(a,b);
 }
@@ -245,67 +256,4 @@ public:
     operator T() const { return value; }
 };
 
-using mandatory = bool_class<struct mandatory_tag>;
-
-class req_params {
-public:
-    struct def {
-        std::optional<sstring> value;
-        mandatory is_mandatory = mandatory::no;
-
-        def(std::optional<sstring> value_ = std::nullopt, mandatory is_mandatory_ = mandatory::no)
-            : value(std::move(value_))
-            , is_mandatory(is_mandatory_)
-        { }
-
-        def(mandatory is_mandatory_)
-            : is_mandatory(is_mandatory_)
-        { }
-    };
-
-private:
-    std::unordered_map<sstring, def> params;
-
-public:
-    req_params(std::initializer_list<std::pair<sstring, def>> l) {
-        for (const auto& [name, ent] : l) {
-            add(std::move(name), std::move(ent));
-        }
-    }
-
-    void add(sstring name, def ent) {
-        params.emplace(std::move(name), std::move(ent));
-    }
-
-    void process(const request& req);
-
-    const std::optional<sstring>& get(const char* name) const {
-        return params.at(name).value;
-    }
-
-    template <typename T = sstring>
-    const std::optional<T> get_as(const char* name) const {
-        return get(name);
-    }
-
-    template <typename T = sstring>
-    requires std::same_as<T, bool>
-    const std::optional<bool> get_as(const char* name) const {
-        auto value = get(name);
-        if (!value) {
-            return std::nullopt;
-        }
-        std::transform(value->begin(), value->end(), value->begin(), ::tolower);
-        if (value == "true" || value == "yes" || value == "1") {
-            return true;
-        }
-        if (value == "false" || value == "no" || value == "0") {
-            return false;
-        }
-        throw boost::bad_lexical_cast{};
-    }
-};
-
-utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val);
-
 }

api/api_init.hh

@@ -3,60 +3,25 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 #pragma once
-
+#include "database_fwd.hh"
+#include "service/storage_proxy.hh"
 #include <seastar/http/httpd.hh>
-#include <seastar/core/future.hh>
-
-#include "replica/database_fwd.hh"
-#include "tasks/task_manager.hh"
-#include "seastarx.hh"
-
-namespace service {
-
-class load_meter;
-class storage_proxy;
-class storage_service;
-
-} // namespace service
-
-class sstables_loader;
-
-namespace streaming {
-class stream_manager;
-}
-
-namespace locator {
-
-class token_metadata;
-class shared_token_metadata;
-class snitch_ptr;
-
-} // namespace locator
-
-namespace cql_transport { class controller; }
-class thrift_controller;
-namespace db {
-class snapshot_ctl;
-class config;
-namespace view {
-class view_builder;
-}
-class system_keyspace;
-}
-namespace netw { class messaging_service; }
-class repair_service;
-namespace cdc { class generation_service; }
-
-namespace gms {
-
-class gossiper;
-
-}
-
-namespace auth { class service; }
 
 namespace api {
 
@@ -64,54 +29,24 @@ struct http_context {
     sstring api_dir;
     sstring api_doc;
     httpd::http_server_control http_server;
-    distributed<replica::database>& db;
+    distributed<database>& db;
     distributed<service::storage_proxy>& sp;
-    service::load_meter& lmeter;
-    const sharded<locator::shared_token_metadata>& shared_token_metadata;
-    sharded<tasks::task_manager>& tm;
-
-    http_context(distributed<replica::database>& _db,
-            distributed<service::storage_proxy>& _sp,
-            service::load_meter& _lm, const sharded<locator::shared_token_metadata>& _stm, sharded<tasks::task_manager>& _tm)
-            : db(_db), sp(_sp), lmeter(_lm), shared_token_metadata(_stm), tm(_tm) {
+    http_context(distributed<database>& _db,
+            distributed<service::storage_proxy>& _sp)
+            : db(_db), sp(_sp) {
     }
-
-    const locator::token_metadata& get_token_metadata();
 };
 
 future<> set_server_init(http_context& ctx);
-future<> set_server_config(http_context& ctx, const db::config& cfg);
-future<> set_server_snitch(http_context& ctx, sharded<locator::snitch_ptr>& snitch);
-future<> unset_server_snitch(http_context& ctx);
-future<> set_server_storage_service(http_context& ctx, sharded<service::storage_service>& ss, sharded<gms::gossiper>& g, sharded<cdc::generation_service>& cdc_gs, sharded<db::system_keyspace>& sys_ks);
-future<> set_server_sstables_loader(http_context& ctx, sharded<sstables_loader>& sst_loader);
-future<> unset_server_sstables_loader(http_context& ctx);
-future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb);
-future<> unset_server_view_builder(http_context& ctx);
-future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair);
-future<> unset_server_repair(http_context& ctx);
-future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl);
-future<> unset_transport_controller(http_context& ctx);
-future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
-future<> unset_rpc_controller(http_context& ctx);
-future<> set_server_authorization_cache(http_context& ctx, sharded<auth::service> &auth_service);
-future<> unset_server_authorization_cache(http_context& ctx);
-future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl);
-future<> unset_server_snapshot(http_context& ctx);
-future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g);
+future<> set_server_snitch(http_context& ctx);
+future<> set_server_storage_service(http_context& ctx);
+future<> set_server_gossip(http_context& ctx);
 future<> set_server_load_sstable(http_context& ctx);
-future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms);
-future<> unset_server_messaging_service(http_context& ctx);
-future<> set_server_storage_proxy(http_context& ctx, sharded<service::storage_service>& ss);
-future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm);
-future<> unset_server_stream_manager(http_context& ctx);
-future<> set_hinted_handoff(http_context& ctx, sharded<gms::gossiper>& g);
-future<> unset_hinted_handoff(http_context& ctx);
-future<> set_server_gossip_settle(http_context& ctx, sharded<gms::gossiper>& g);
+future<> set_server_messaging_service(http_context& ctx);
+future<> set_server_storage_proxy(http_context& ctx);
+future<> set_server_stream_manager(http_context& ctx);
+future<> set_server_gossip_settle(http_context& ctx);
 future<> set_server_cache(http_context& ctx);
-future<> set_server_compaction_manager(http_context& ctx);
 future<> set_server_done(http_context& ctx);
-future<> set_server_task_manager(http_context& ctx);
-future<> set_server_task_manager_test(http_context& ctx, lw_shared_ptr<db::config> cfg);
 
 }

api/authorization_cache.cc

@@ -1,33 +0,0 @@
-/*
- * Copyright (C) 2022-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include "api/api-doc/authorization_cache.json.hh"
-
-#include "api/authorization_cache.hh"
-#include "api/api.hh"
-#include "auth/common.hh"
-
-namespace api {
-using namespace json;
-
-void set_authorization_cache(http_context& ctx, routes& r, sharded<auth::service> &auth_service) {
-    httpd::authorization_cache_json::authorization_cache_reset.set(r, [&auth_service] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        co_await auth_service.invoke_on_all([] (auth::service& auth) -> future<>  {
-            auth.reset_authorization_cache();
-            return make_ready_future<>();
-        });
-
-        co_return json_void();
-    });
-}
-
-void unset_authorization_cache(http_context& ctx, routes& r) {
-    httpd::authorization_cache_json::authorization_cache_reset.unset(r);
-}
-
-}

api/authorization_cache.hh

@@ -1,18 +0,0 @@
-/*
- * Copyright (C) 2022-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include "api.hh"
-
-namespace api {
-
-void set_authorization_cache(http_context& ctx, routes& r, sharded<auth::service> &auth_service);
-void unset_authorization_cache(http_context& ctx, routes& r);
-
-}

api/cache_service.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "cache_service.hh"
@@ -195,34 +208,32 @@ void set_cache_service(http_context& ctx, routes& r) {
     });
 
     cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
-            return db.row_cache_tracker().region().occupancy().used_space();
-        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
-            return make_ready_future<json::json_return_type>(res);
-        });
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
+            return cf.get_row_cache().get_cache_tracker().region().occupancy().used_space();
+        }, std::plus<uint64_t>());
     });
 
     cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [](const replica::column_family& cf) {
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.count();
         }, std::plus<uint64_t>());
     });
 
     cs::get_row_requests.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [](const replica::column_family& cf) {
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count();
         }, std::plus<uint64_t>());
     });
 
     cs::get_row_hit_rate.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [](const replica::column_family& cf) {
+        return map_reduce_cf(ctx, ratio_holder(), [](const column_family& cf) {
             return ratio_holder(cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count(),
                     cf.get_row_cache().stats().hits.count());
         }, std::plus<ratio_holder>());
     });
 
     cs::get_row_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -230,7 +241,7 @@ void set_cache_service(http_context& ctx, routes& r) {
     });
 
     cs::get_row_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.rate() + cf.get_row_cache().stats().misses.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -240,19 +251,15 @@ void set_cache_service(http_context& ctx, routes& r) {
     cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         // In origin row size is the weighted size.
         // We currently do not support weights, so we use num entries instead
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
-            return db.row_cache_tracker().partitions();
-        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
-            return make_ready_future<json::json_return_type>(res);
-        });
+        return map_reduce_cf(ctx, 0, [](const column_family& cf) {
+            return cf.get_row_cache().partitions();
+        }, std::plus<uint64_t>());
     });
 
     cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
-            return db.row_cache_tracker().partitions();
-        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
-            return make_ready_future<json::json_return_type>(res);
-        });
+        return map_reduce_cf(ctx, 0, [](const column_family& cf) {
+            return cf.get_row_cache().partitions();
+        }, std::plus<uint64_t>());
     });
 
     cs::get_counter_capacity.set(r, [] (std::unique_ptr<request> req) {

api/cache_service.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once

api/collectd.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "collectd.hh"
@@ -29,11 +42,8 @@ static auto transformer(const std::vector<collectd_value>& values) {
         case scollectd::data_type::GAUGE:
             collected_value.values.push(v.d());
             break;
-        case scollectd::data_type::COUNTER:
-            collected_value.values.push(v.ui());
-            break;
-        case scollectd::data_type::REAL_COUNTER:
-            collected_value.values.push(v.d());
+        case scollectd::data_type::DERIVE:
+            collected_value.values.push(v.i());
             break;
         default:
             collected_value.values.push(v.ui());
@@ -54,7 +64,7 @@ static const char* str_to_regex(const sstring& v) {
 void set_collectd(http_context& ctx, routes& r) {
     cd::get_collectd.set(r, [&ctx](std::unique_ptr<request> req) {
 
-        auto id = ::make_shared<scollectd::type_instance_id>(req->param["pluginid"],
+        auto id = make_shared<scollectd::type_instance_id>(req->param["pluginid"],
                 req->get_query_param("instance"), req->get_query_param("type"),
                 req->get_query_param("type_instance"));
 

api/collectd.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once

api/column_family.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "column_family.hh"
@@ -11,13 +24,10 @@
 #include <vector>
 #include <seastar/http/exception.hh>
 #include "sstables/sstables.hh"
-#include "sstables/metadata_collector.hh"
 #include "utils/estimated_histogram.hh"
 #include <algorithm>
-#include "db/system_keyspace.hh"
+#include "db/system_keyspace_view_types.hh"
 #include "db/data_listeners.hh"
-#include "storage_service.hh"
-#include "unimplemented.hh"
 
 extern logging::logger apilog;
 
@@ -43,57 +53,57 @@ std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
     return std::make_tuple(name.substr(0, pos), name.substr(end));
 }
 
-const table_id& get_uuid(const sstring& ks, const sstring& cf, const replica::database& db) {
+const utils::UUID& get_uuid(const sstring& ks, const sstring& cf, const database& db) {
     try {
         return db.find_uuid(ks, cf);
-    } catch (replica::no_such_column_family& e) {
-        throw bad_param_exception(e.what());
+    } catch (std::out_of_range& e) {
+        throw bad_param_exception(format("Column family '{}:{}' not found", ks, cf));
     }
 }
 
-const table_id& get_uuid(const sstring& name, const replica::database& db) {
+const utils::UUID& get_uuid(const sstring& name, const database& db) {
     auto [ks, cf] = parse_fully_qualified_cf_name(name);
     return get_uuid(ks, cf, db);
 }
 
-future<> foreach_column_family(http_context& ctx, const sstring& name, function<void(replica::column_family&)> f) {
+future<> foreach_column_family(http_context& ctx, const sstring& name, function<void(column_family&)> f) {
     auto uuid = get_uuid(name, ctx.db.local());
 
-    return ctx.db.invoke_on_all([f, uuid](replica::database& db) {
+    return ctx.db.invoke_on_all([f, uuid](database& db) {
         f(db.find_column_family(uuid));
     });
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, name, int64_t(0), [f](const replica::column_family& cf) {
+        int64_t column_family_stats::*f) {
+    return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
         return cf.get_stats().*f;
     }, std::plus<int64_t>());
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, int64_t(0), [f](const replica::column_family& cf) {
+        int64_t column_family_stats::*f) {
+    return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
         return cf.get_stats().*f;
     }, std::plus<int64_t>());
 }
 
 static future<json::json_return_type>  get_cf_stats_count(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, name, int64_t(0), [f](const replica::column_family& cf) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
         return (cf.get_stats().*f).hist.count;
     }, std::plus<int64_t>());
 }
 
 static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
     auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([uuid, f](replica::database& db) {
+    return ctx.db.map_reduce0([uuid, f](database& db) {
         // Histograms information is sample of the actual load
         // so to get an estimation of sum, we multiply the mean
         // with count. The information is gather in nano second,
         // but reported in micro
-        replica::column_family& cf = db.find_column_family(uuid);
+        column_family& cf = db.find_column_family(uuid);
         return ((cf.get_stats().*f).hist.count/1000.0) * (cf.get_stats().*f).hist.mean;
     }, 0.0, std::plus<double>()).then([](double res) {
         return make_ready_future<json::json_return_type>((int64_t)res);
@@ -102,16 +112,16 @@ static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const
 
 
 static future<json::json_return_type>  get_cf_stats_count(http_context& ctx,
-        utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, int64_t(0), [f](const replica::column_family& cf) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
         return (cf.get_stats().*f).hist.count;
     }, std::plus<int64_t>());
 }
 
 static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    utils::UUID uuid = get_uuid(name, ctx.db.local());
+    return ctx.db.map_reduce0([f, uuid](const database& p) {
         return (p.find_column_family(uuid).get_stats().*f).hist;},
             utils::ihistogram(),
             std::plus<utils::ihistogram>())
@@ -120,20 +130,8 @@ static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const
     });
 }
 
-static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
-        return (p.find_column_family(uuid).get_stats().*f).hist;},
-            utils::ihistogram(),
-            std::plus<utils::ihistogram>())
-            .then([](const utils::ihistogram& val) {
-                return make_ready_future<json::json_return_type>(to_json(val));
-    });
-}
-
-static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    std::function<utils::ihistogram(const replica::database&)> fun = [f] (const replica::database& db)  {
+static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    std::function<utils::ihistogram(const database&)> fun = [f] (const database& db)  {
         utils::ihistogram res;
         for (auto i : db.get_column_families()) {
             res += (i.second->get_stats().*f).hist;
@@ -148,9 +146,9 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils:
 }
 
 static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    utils::UUID uuid = get_uuid(name, ctx.db.local());
+    return ctx.db.map_reduce0([f, uuid](const database& p) {
         return (p.find_column_family(uuid).get_stats().*f).rate();},
             utils::rate_moving_average_and_histogram(),
             std::plus<utils::rate_moving_average_and_histogram>())
@@ -159,8 +157,8 @@ static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& c
     });
 }
 
-static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_summary_and_histogram replica::column_family_stats::*f) {
-    std::function<utils::rate_moving_average_and_histogram(const replica::database&)> fun = [f] (const replica::database& db)  {
+static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    std::function<utils::rate_moving_average_and_histogram(const database&)> fun = [f] (const database& db)  {
         utils::rate_moving_average_and_histogram res;
         for (auto i : db.get_column_families()) {
             res += (i.second->get_stats().*f).rate();
@@ -175,30 +173,30 @@ static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ct
 }
 
 static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ctx, const sstring& name) {
-    return map_reduce_cf(ctx, name, int64_t(0), [](const replica::column_family& cf) {
+    return map_reduce_cf(ctx, name, int64_t(0), [](const column_family& cf) {
         return cf.get_unleveled_sstables();
     }, std::plus<int64_t>());
 }
 
-static int64_t min_partition_size(replica::column_family& cf) {
+static int64_t min_partition_size(column_family& cf) {
     int64_t res = INT64_MAX;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i: *cf.get_sstables() ) {
         res = std::min(res, i->get_stats_metadata().estimated_partition_size.min());
     }
     return (res == INT64_MAX) ? 0 : res;
 }
 
-static int64_t max_partition_size(replica::column_family& cf) {
+static int64_t max_partition_size(column_family& cf) {
     int64_t res = 0;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i: *cf.get_sstables() ) {
         res = std::max(i->get_stats_metadata().estimated_partition_size.max(), res);
     }
     return res;
 }
 
-static integral_ratio_holder mean_partition_size(replica::column_family& cf) {
+static integral_ratio_holder mean_partition_size(column_family& cf) {
     integral_ratio_holder res;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i: *cf.get_sstables() ) {
         auto c = i->get_stats_metadata().estimated_partition_size.count();
         res.sub += i->get_stats_metadata().estimated_partition_size.mean() * c;
         res.total += c;
@@ -222,7 +220,7 @@ static json::json_return_type sum_map(const std::unordered_map<sstring, uint64_t
 
 static future<json::json_return_type>  sum_sstable(http_context& ctx, const sstring name, bool total) {
     auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([uuid, total](replica::database& db) {
+    return ctx.db.map_reduce0([uuid, total](database& db) {
         std::unordered_map<sstring, uint64_t> m;
         auto sstables = (total) ? db.find_column_family(uuid).get_sstables_including_compacted_undeleted() :
                 db.find_column_family(uuid).get_sstables();
@@ -238,7 +236,7 @@ static future<json::json_return_type>  sum_sstable(http_context& ctx, const sstr
 
 
 static future<json::json_return_type> sum_sstable(http_context& ctx, bool total) {
-    return map_reduce_cf_raw(ctx, std::unordered_map<sstring, uint64_t>(), [total](replica::column_family& cf) {
+    return map_reduce_cf_raw(ctx, std::unordered_map<sstring, uint64_t>(), [total](column_family& cf) {
         std::unordered_map<sstring, uint64_t> m;
         auto sstables = (total) ? cf.get_sstables_including_compacted_undeleted() :
                 cf.get_sstables();
@@ -251,12 +249,6 @@ static future<json::json_return_type> sum_sstable(http_context& ctx, bool total)
     });
 }
 
-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const replica::column_family&)> f) {
-    return map_reduce_cf_raw(ctx, name, utils::time_estimated_histogram(), f, utils::time_estimated_histogram_merge).then([](const utils::time_estimated_histogram& res) {
-        return make_ready_future<json::json_return_type>(time_to_json_histogram(res));
-    });
-}
-
 template <typename T>
 class sum_ratio {
     uint64_t _n = 0;
@@ -274,9 +266,9 @@ public:
     }
 };
 
-static double get_compression_ratio(replica::column_family& cf) {
+static double get_compression_ratio(column_family& cf) {
     sum_ratio<double> result;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i : *cf.get_sstables()) {
         auto compression_ratio = i->get_compression_ratio();
         if (compression_ratio != sstables::metadata_collector::NO_COMPRESSION_RATIO) {
             result(compression_ratio);
@@ -312,8 +304,8 @@ void set_column_family(http_context& ctx, routes& r) {
         return res;
     });
 
-    cf::get_column_family.set(r, [&ctx] (std::unique_ptr<request> req){
-            std::list<cf::column_family_info> res;
+    cf::get_column_family.set(r, [&ctx] (const_req req){
+            vector<cf::column_family_info> res;
             for (auto i: ctx.db.local().get_column_families_mapping()) {
                 cf::column_family_info info;
                 info.ks = i.first.first;
@@ -321,7 +313,7 @@ void set_column_family(http_context& ctx, routes& r) {
                 info.type = "ColumnFamilies";
                 res.push_back(info);
             }
-            return make_ready_future<json::json_return_type>(json::stream_range_as_array(std::move(res), std::identity()));
+            return res;
         });
 
     cf::get_column_family_name_keyspace.set(r, [&ctx] (const_req req){
@@ -333,15 +325,15 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_memtable_columns_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t{0}, [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], 0, [](column_family& cf) {
             return cf.active_memtable().partition_count();
-        }, std::plus<>());
+        }, std::plus<int>());
     });
 
     cf::get_all_memtable_columns_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t{0}, [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, 0, [](column_family& cf) {
             return cf.active_memtable().partition_count();
-        }, std::plus<>());
+        }, std::plus<int>());
     });
 
     cf::get_memtable_on_heap_size.set(r, [] (const_req req) {
@@ -353,25 +345,25 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_memtable_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
             return cf.active_memtable().region().occupancy().total_space();
         }, std::plus<int64_t>());
     });
 
     cf::get_all_memtable_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
             return cf.active_memtable().region().occupancy().total_space();
         }, std::plus<int64_t>());
     });
 
     cf::get_memtable_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
             return cf.active_memtable().region().occupancy().used_space();
         }, std::plus<int64_t>());
     });
 
     cf::get_all_memtable_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
             return cf.active_memtable().region().occupancy().used_space();
         }, std::plus<int64_t>());
     });
@@ -386,15 +378,15 @@ void set_column_family(http_context& ctx, routes& r) {
 
     cf::get_cf_all_memtables_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         warn(unimplemented::cause::INDEXES);
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
             return cf.occupancy().total_space();
         }, std::plus<int64_t>());
     });
 
     cf::get_all_cf_all_memtables_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         warn(unimplemented::cause::INDEXES);
-        return ctx.db.map_reduce0([](const replica::database& db){
-            return db.dirty_memory_region_group().real_memory_used();
+        return ctx.db.map_reduce0([](const database& db){
+            return db.dirty_memory_region_group().memory_used();
         }, int64_t(0), std::plus<int64_t>()).then([](int res) {
             return make_ready_future<json::json_return_type>(res);
         });
@@ -402,31 +394,31 @@ void set_column_family(http_context& ctx, routes& r) {
 
     cf::get_cf_all_memtables_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         warn(unimplemented::cause::INDEXES);
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
             return cf.occupancy().used_space();
         }, std::plus<int64_t>());
     });
 
     cf::get_all_cf_all_memtables_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         warn(unimplemented::cause::INDEXES);
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
             return cf.active_memtable().region().occupancy().used_space();
         }, std::plus<int64_t>());
     });
 
     cf::get_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx,req->param["name"] ,&replica::column_family_stats::memtable_switch_count);
+        return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::memtable_switch_count);
     });
 
     cf::get_all_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &replica::column_family_stats::memtable_switch_count);
+        return get_cf_stats(ctx, &column_family_stats::memtable_switch_count);
     });
 
     // FIXME: this refers to partitions, not rows.
     cf::get_estimated_row_size_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             utils::estimated_histogram res(0);
-            for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+            for (auto i: *cf.get_sstables() ) {
                 res.merge(i->get_stats_metadata().estimated_partition_size);
             }
             return res;
@@ -436,9 +428,9 @@ void set_column_family(http_context& ctx, routes& r) {
 
     // FIXME: this refers to partitions, not rows.
     cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
             uint64_t res = 0;
-            for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+            for (auto i: *cf.get_sstables() ) {
                 res += i->get_stats_metadata().estimated_partition_size.count();
             }
             return res;
@@ -447,9 +439,9 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_estimated_column_count_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             utils::estimated_histogram res(0);
-            for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+            for (auto i: *cf.get_sstables() ) {
                 res.merge(i->get_stats_metadata().estimated_cells_count);
             }
             return res;
@@ -464,87 +456,87 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx,req->param["name"] ,&replica::column_family_stats::pending_flushes);
+        return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::pending_flushes);
     });
 
     cf::get_all_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &replica::column_family_stats::pending_flushes);
+        return get_cf_stats(ctx, &column_family_stats::pending_flushes);
     });
 
     cf::get_read.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx,req->param["name"] ,&replica::column_family_stats::reads);
+        return get_cf_stats_count(ctx,req->param["name"] ,&column_family_stats::reads);
     });
 
     cf::get_all_read.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, &replica::column_family_stats::reads);
+        return get_cf_stats_count(ctx, &column_family_stats::reads);
     });
 
     cf::get_write.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, req->param["name"] ,&replica::column_family_stats::writes);
+        return get_cf_stats_count(ctx, req->param["name"] ,&column_family_stats::writes);
     });
 
     cf::get_all_write.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, &replica::column_family_stats::writes);
+        return get_cf_stats_count(ctx, &column_family_stats::writes);
     });
 
     cf::get_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::reads);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::reads);
     });
 
     cf::get_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, req->param["name"], &replica::column_family_stats::reads);
+        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::reads);
     });
 
     cf::get_read_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_sum(ctx,req->param["name"] ,&replica::column_family_stats::reads);
+        return get_cf_stats_sum(ctx,req->param["name"] ,&column_family_stats::reads);
     });
 
     cf::get_write_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_sum(ctx, req->param["name"] ,&replica::column_family_stats::writes);
+        return get_cf_stats_sum(ctx, req->param["name"] ,&column_family_stats::writes);
     });
 
     cf::get_all_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_histogram(ctx, &column_family_stats::writes);
     });
 
     cf::get_all_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
     });
 
     cf::get_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::writes);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::writes);
     });
 
     cf::get_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, req->param["name"], &replica::column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::writes);
     });
 
     cf::get_all_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_histogram(ctx, &column_family_stats::writes);
     });
 
     cf::get_all_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
     });
 
     cf::get_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
-            return cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
         }, std::plus<int64_t>());
     });
 
     cf::get_all_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
-            return cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
         }, std::plus<int64_t>());
     });
 
     cf::get_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, req->param["name"], &replica::column_family_stats::live_sstable_count);
+        return get_cf_stats(ctx, req->param["name"], &column_family_stats::live_sstable_count);
     });
 
     cf::get_all_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &replica::column_family_stats::live_sstable_count);
+        return get_cf_stats(ctx, &column_family_stats::live_sstable_count);
     });
 
     cf::get_unleveled_sstables.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -600,115 +592,105 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_get_false_positive();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_all_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_get_false_positive();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_get_recent_false_positive();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_all_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_get_recent_false_positive();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (column_family& cf) {
             return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
         }, std::plus<>());
     });
 
     cf::get_all_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, ratio_holder(), [] (column_family& cf) {
             return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
         }, std::plus<>());
     });
 
     cf::get_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (column_family& cf) {
             return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
         }, std::plus<>());
     });
 
     cf::get_all_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, ratio_holder(), [] (column_family& cf) {
             return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
         }, std::plus<>());
     });
 
     cf::get_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_size();
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_size();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_all_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_size();
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_size();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_memory_size();
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_memory_size();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_all_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_memory_size();
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_memory_size();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->get_summary().memory_footprint();
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->get_summary().memory_footprint();
             });
         }, std::plus<uint64_t>());
     });
 
     cf::get_all_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->get_summary().memory_footprint();
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->get_summary().memory_footprint();
             });
         }, std::plus<uint64_t>());
     });
@@ -752,7 +734,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_true_snapshots_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         auto uuid = get_uuid(req->param["name"], ctx.db.local());
         return ctx.db.local().find_column_family(uuid).get_snapshot_details().then([](
-                const std::unordered_map<sstring, replica::column_family::snapshot_details>& sd) {
+                const std::unordered_map<sstring, column_family::snapshot_details>& sd) {
             int64_t res = 0;
             for (auto i : sd) {
                 res += i.second.total;
@@ -781,7 +763,7 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_row_cache_hit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -789,7 +771,7 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_all_row_cache_hit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -797,7 +779,7 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_row_cache_miss.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().misses.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -805,7 +787,7 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_all_row_cache_miss.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().misses.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -814,36 +796,39 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_cas_prepare.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
-            return cf.get_stats().cas_prepare.histogram();
-        });
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
+            return cf.get_stats().estimated_cas_prepare;
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::get_cas_propose.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
-            return cf.get_stats().cas_accept.histogram();
-        });
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
+            return cf.get_stats().estimated_cas_propose;
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::get_cas_commit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
-            return cf.get_stats().cas_learn.histogram();
-        });
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
+            return cf.get_stats().estimated_cas_commit;
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::get_sstables_per_read_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
             return cf.get_stats().estimated_sstable_per_read;
         },
         utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::get_tombstone_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::tombstone_scanned);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::tombstone_scanned);
     });
 
     cf::get_live_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::live_scanned);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::live_scanned);
     });
 
     cf::get_col_update_time_delta_histogram.set(r, [] (std::unique_ptr<request> req) {
@@ -854,39 +839,16 @@ void set_column_family(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(res);
     });
 
-    cf::get_auto_compaction.set(r, [&ctx] (const_req req) {
-        auto uuid = get_uuid(req.param["name"], ctx.db.local());
-        replica::column_family& cf = ctx.db.local().find_column_family(uuid);
-        return !cf.is_auto_compaction_disabled_by_user();
-    });
-
-    cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return ctx.db.invoke_on(0, [&ctx, req = std::move(req)] (replica::database& db) {
-            auto g = replica::database::autocompaction_toggle_guard(db);
-            return foreach_column_family(ctx, req->param["name"], [](replica::column_family &cf) {
-                cf.enable_auto_compaction();
-            }).then([g = std::move(g)] {
-                return make_ready_future<json::json_return_type>(json_void());
-            });
-        });
-    });
-
-    cf::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return ctx.db.invoke_on(0, [&ctx, req = std::move(req)] (replica::database& db) {
-            auto g = replica::database::autocompaction_toggle_guard(db);
-            return foreach_column_family(ctx, req->param["name"], [](replica::column_family &cf) {
-                return cf.disable_auto_compaction();
-            }).then([g = std::move(g)] {
-                return make_ready_future<json::json_return_type>(json_void());
-            });
-        });
+    cf::is_auto_compaction_disabled.set(r, [] (const_req req) {
+        // FIXME
+        // currently auto compaction is disable
+        // it should be changed when it would have an API
+        return true;
     });
 
     cf::get_built_indexes.set(r, [&ctx](std::unique_ptr<request> req) {
-        auto ks_cf = parse_fully_qualified_cf_name(req->param["name"]);
-        auto&& ks = std::get<0>(ks_cf);
-        auto&& cf_name = std::get<1>(ks_cf);
-        return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace_view_build_progress>& vb) mutable {
+        auto [ks, cf_name] = parse_fully_qualified_cf_name(req->param["name"]);
+        return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace::view_build_progress>& vb) mutable {
             std::set<sstring> vp;
             for (auto b : vb) {
                 if (b.view.first == ks) {
@@ -895,10 +857,10 @@ void set_column_family(http_context& ctx, routes& r) {
             }
             std::vector<sstring> res;
             auto uuid = get_uuid(ks, cf_name, ctx.db.local());
-            replica::column_family& cf = ctx.db.local().find_column_family(uuid);
+            column_family& cf = ctx.db.local().find_column_family(uuid);
             res.reserve(cf.get_index_manager().list_indexes().size());
             for (auto&& i : cf.get_index_manager().list_indexes()) {
-                if (!vp.contains(secondary_index::index_table_name(i.metadata().name()))) {
+                if (vp.find(secondary_index::index_table_name(i.metadata().name())) == vp.end()) {
                     res.emplace_back(i.metadata().name());
                 }
             }
@@ -923,8 +885,8 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_compression_ratio.set(r, [&ctx](std::unique_ptr<request> req) {
         auto uuid = get_uuid(req->param["name"], ctx.db.local());
 
-        return ctx.db.map_reduce(sum_ratio<double>(), [uuid](replica::database& db) {
-            replica::column_family& cf = db.find_column_family(uuid);
+        return ctx.db.map_reduce(sum_ratio<double>(), [uuid](database& db) {
+            column_family& cf = db.find_column_family(uuid);
             return make_ready_future<double>(get_compression_ratio(cf));
         }).then([] (const double& result) {
             return make_ready_future<json::json_return_type>(result);
@@ -932,20 +894,22 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_read_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
-            return cf.get_stats().reads.histogram();
-        });
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
+            return cf.get_stats().estimated_read;
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::get_write_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
-            return cf.get_stats().writes.histogram();
-        });
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
+            return cf.get_stats().estimated_write;
+        },
+        utils::estimated_histogram_merge, utils_json::estimated_histogram());
     });
 
     cf::set_compaction_strategy_class.set(r, [&ctx](std::unique_ptr<request> req) {
         sstring strategy = req->get_query_param("class_name");
-        return foreach_column_family(ctx, req->param["name"], [strategy](replica::column_family& cf) {
+        return foreach_column_family(ctx, req->param["name"], [strategy](column_family& cf) {
             cf.set_compaction_strategy(sstables::compaction_strategy::type(strategy));
         }).then([] {
                 return make_ready_future<json::json_return_type>(json_void());
@@ -969,7 +933,7 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::get_sstable_count_per_level.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, req->param["name"], std::vector<uint64_t>(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, req->param["name"], std::vector<uint64_t>(), [](const column_family& cf) {
             return cf.sstable_count_per_level();
         }, concat_sstable_count_per_level).then([](const std::vector<uint64_t>& res) {
             return make_ready_future<json::json_return_type>(res);
@@ -980,7 +944,7 @@ void set_column_family(http_context& ctx, routes& r) {
         auto key = req->get_query_param("key");
         auto uuid = get_uuid(req->param["name"], ctx.db.local());
 
-        return ctx.db.map_reduce0([key, uuid] (replica::database& db) {
+        return ctx.db.map_reduce0([key, uuid] (database& db) {
             return db.find_column_family(uuid).get_sstables_by_partition_key(key);
         }, std::unordered_set<sstring>(),
             [](std::unordered_set<sstring> a, std::unordered_set<sstring>&& b) mutable {
@@ -991,32 +955,44 @@ void set_column_family(http_context& ctx, routes& r) {
         });
     });
 
-
     cf::toppartitions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        auto name = req->param["name"];
-        auto [ks, cf] = parse_fully_qualified_cf_name(name);
+        auto name_param = req->param["name"];
+        auto [ks, cf] = parse_fully_qualified_cf_name(name_param);
 
         api::req_param<std::chrono::milliseconds, unsigned> duration{*req, "duration", 1000ms};
         api::req_param<unsigned> capacity(*req, "capacity", 256);
         api::req_param<unsigned> list_size(*req, "list_size", 10);
 
         apilog.info("toppartitions query: name={} duration={} list_size={} capacity={}",
-            name, duration.param, list_size.param, capacity.param);
+            name_param, duration.param, list_size.param, capacity.param);
 
-        return seastar::do_with(db::toppartitions_query(ctx.db, {{ks, cf}}, {}, duration.value, list_size, capacity), [&ctx] (db::toppartitions_query& q) {
-            return run_toppartitions_query(q, ctx, true);
+        return seastar::do_with(db::toppartitions_query(ctx.db, ks, cf, duration.value, list_size, capacity), [&ctx](auto& q) {
+            return q.scatter().then([&q] {
+                return sleep(q.duration()).then([&q] {
+                    return q.gather(q.capacity()).then([&q] (auto topk_results) {
+                        apilog.debug("toppartitions query: processing results");
+                        cf::toppartitions_query_results results;
+
+                        for (auto& d: topk_results.read.top(q.list_size())) {
+                            cf::toppartitions_record r;
+                            r.partition = sstring(d.item);
+                            r.count = d.count;
+                            r.error = d.error;
+                            results.read.push(r);
+                        }
+                        for (auto& d: topk_results.write.top(q.list_size())) {
+                            cf::toppartitions_record r;
+                            r.partition = sstring(d.item);
+                            r.count = d.count;
+                            r.error = d.error;
+                            results.write.push(r);
+                        }
+                        return make_ready_future<json::json_return_type>(results);
+                    });
+                });
+            });
         });
     });
 
-    cf::force_major_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        if (req->get_query_param("split_output") != "") {
-            fail(unimplemented::cause::API);
-        }
-        return foreach_column_family(ctx, req->param["name"], [](replica::column_family &cf) {
-            return cf.compact_all_sstables();
-        }).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
 }
 }

api/column_family.hh

@@ -1,16 +1,29 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "api.hh"
 #include "api/api-doc/column_family.json.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include <seastar/core/future-util.hh>
 #include <any>
 
@@ -18,17 +31,17 @@ namespace api {
 
 void set_column_family(http_context& ctx, routes& r);
 
-const table_id& get_uuid(const sstring& name, const replica::database& db);
-future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(replica::column_family&)> f);
+const utils::UUID& get_uuid(const sstring& name, const database& db);
+future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(column_family&)> f);
 
 
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
         Mapper mapper, Reducer reducer) {
     auto uuid = get_uuid(name, ctx.db.local());
-    using mapper_type = std::function<std::unique_ptr<std::any>(replica::database&)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(database&)>;
     using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    return ctx.db.map_reduce0(mapper_type([mapper, uuid](replica::database& db) {
+    return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
         return std::make_unique<std::any>(I(mapper(db.find_column_family(uuid))));
     }), std::make_unique<std::any>(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
         return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
@@ -55,16 +68,14 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
     });
 }
 
-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const replica::column_family&)> f);
-
 struct map_reduce_column_families_locally {
     std::any init;
-    std::function<std::unique_ptr<std::any>(replica::column_family&)> mapper;
+    std::function<std::unique_ptr<std::any>(column_family&)> mapper;
     std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)> reducer;
-    future<std::unique_ptr<std::any>> operator()(replica::database& db) const {
+    future<std::unique_ptr<std::any>> operator()(database& db) const {
         auto res = seastar::make_lw_shared<std::unique_ptr<std::any>>(std::make_unique<std::any>(init));
-        return do_for_each(db.get_column_families(), [res, this](const std::pair<table_id, seastar::lw_shared_ptr<replica::table>>& i) {
-            *res = reducer(std::move(*res), mapper(*i.second.get()));
+        return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+            *res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
         }).then([res] {
             return std::move(*res);
         });
@@ -74,9 +85,9 @@ struct map_reduce_column_families_locally {
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, I init,
         Mapper mapper, Reducer reducer) {
-    using mapper_type = std::function<std::unique_ptr<std::any>(replica::column_family&)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(column_family&)>;
     using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (replica::column_family& cf) mutable {
+    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
         return std::make_unique<std::any>(I(mapper(cf)));
     });
     auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
@@ -98,12 +109,9 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t replica::column_family_stats::*f);
+        int64_t column_family_stats::*f);
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t replica::column_family_stats::*f);
-
-
-std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name);
+        int64_t column_family_stats::*f);
 
 }

api/commitlog.cc

@@ -1,15 +1,28 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "commitlog.hh"
-#include "db/commitlog/commitlog.hh"
+#include <db/commitlog/commitlog.hh>
 #include "api/api-doc/commitlog.json.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include <vector>
 
 namespace api {
@@ -18,7 +31,7 @@ template<typename T>
 static auto acquire_cl_metric(http_context& ctx, std::function<T (db::commitlog*)> func) {
     typedef T ret_type;
 
-    return ctx.db.map_reduce0([func = std::move(func)](replica::database& db) {
+    return ctx.db.map_reduce0([func = std::move(func)](database& db) {
         if (db.commitlog() == nullptr) {
             return make_ready_future<ret_type>();
         }
@@ -34,7 +47,7 @@ void set_commitlog(http_context& ctx, routes& r) {
         auto res = make_shared<std::vector<sstring>>();
         return ctx.db.map_reduce([res](std::vector<sstring> names) {
             res->insert(res->end(), names.begin(), names.end());
-        }, [](replica::database& db) {
+        }, [](database& db) {
             if (db.commitlog() == nullptr) {
                 return make_ready_future<std::vector<sstring>>(std::vector<sstring>());
             }

api/commitlog.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once

api/compaction_manager.cc

@@ -1,21 +1,29 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <seastar/core/coroutine.hh>
-
 #include "compaction_manager.hh"
-#include "compaction/compaction_manager.hh"
+#include "sstables/compaction_manager.hh"
 #include "api/api-doc/compaction_manager.json.hh"
 #include "db/system_keyspace.hh"
 #include "column_family.hh"
-#include "unimplemented.hh"
-#include "storage_service.hh"
-
 #include <utility>
 
 namespace api {
@@ -25,7 +33,7 @@ using namespace json;
 
 static future<json::json_return_type> get_cm_stats(http_context& ctx,
         int64_t compaction_manager::stats::*f) {
-    return ctx.db.map_reduce0([f](replica::database& db) {
+    return ctx.db.map_reduce0([f](database& db) {
         return db.get_compaction_manager().get_stats().*f;
     }, int64_t(0), std::plus<int64_t>()).then([](const int64_t& res) {
         return make_ready_future<json::json_return_type>(res);
@@ -44,19 +52,18 @@ static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_ha
 
 void set_compaction_manager(http_context& ctx, routes& r) {
     cm::get_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) {
+        return ctx.db.map_reduce0([](database& db) {
             std::vector<cm::summary> summaries;
             const compaction_manager& cm = db.get_compaction_manager();
 
             for (const auto& c : cm.get_compactions()) {
                 cm::summary s;
-                s.id = c.compaction_uuid.to_sstring();
-                s.ks = c.ks_name;
-                s.cf = c.cf_name;
+                s.ks = c->ks_name;
+                s.cf = c->cf_name;
                 s.unit = "keys";
-                s.task_type = sstables::compaction_name(c.type);
-                s.completed = c.total_keys_written;
-                s.total = c.total_partitions;
+                s.task_type = sstables::compaction_name(c->type);
+                s.completed = c->total_keys_written;
+                s.total = c->total_partitions;
                 summaries.push_back(std::move(s));
             }
             return summaries;
@@ -66,11 +73,11 @@ void set_compaction_manager(http_context& ctx, routes& r) {
     });
 
     cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([&ctx](replica::database& db) {
+        return ctx.db.map_reduce0([&ctx](database& db) {
             return do_with(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), [&ctx, &db](std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& tasks) {
-                return do_for_each(db.get_column_families(), [&tasks](const std::pair<table_id, seastar::lw_shared_ptr<replica::table>>& i) {
-                    replica::table& cf = *i.second.get();
-                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+                return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+                    table& cf = *i.second.get();
+                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf);
                     return make_ready_future<>();
                 }).then([&tasks] {
                     return std::move(tasks);
@@ -100,34 +107,17 @@ void set_compaction_manager(http_context& ctx, routes& r) {
 
     cm::stop_compaction.set(r, [&ctx] (std::unique_ptr<request> req) {
         auto type = req->get_query_param("type");
-        return ctx.db.invoke_on_all([type] (replica::database& db) {
+        return ctx.db.invoke_on_all([type] (database& db) {
             auto& cm = db.get_compaction_manager();
-            return cm.stop_compaction(type);
+            cm.stop_compaction(type);
         }).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    cm::stop_keyspace_compaction.set(r, [&ctx] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        auto ks_name = validate_keyspace(ctx, req->param);
-        auto table_names = parse_tables(ks_name, ctx, req->query_parameters, "tables");
-        if (table_names.empty()) {
-            table_names = map_keys(ctx.db.local().find_keyspace(ks_name).metadata().get()->cf_meta_data());
-        }
-        auto type = req->get_query_param("type");
-        co_await ctx.db.invoke_on_all([&ks_name, &table_names, type] (replica::database& db) {
-            auto& cm = db.get_compaction_manager();
-            return parallel_for_each(table_names, [&db, &cm, &ks_name, type] (sstring& table_name) {
-                auto& t = db.find_column_family(ks_name, table_name);
-                return cm.stop_compaction(type, &t.as_table_state());
-            });
-        });
-        co_return json_void();
-    });
-
     cm::get_pending_tasks.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
-            return cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
         }, std::plus<int64_t>());
     });
 

api/compaction_manager.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once

api/config.cc

@@ -1,14 +1,28 @@
 /*
- * Copyright 2018-present ScyllaDB
+ * Copyright 2018 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "api/config.hh"
 #include "api/api-doc/config.json.hh"
 #include "db/config.hh"
+#include "database.hh"
 #include <sstream>
 #include <boost/algorithm/string/replace.hpp>
 
@@ -75,11 +89,11 @@ future<> get_config_swagger_entry(std::string_view name, const std::string& desc
 
 namespace cs = httpd::config_json;
 
-void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r, const db::config& cfg) {
-    rb->register_function(r, [&cfg] (output_stream<char>& os) {
-        return do_with(true, [&os, &cfg] (bool& first) {
+void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
+    rb->register_function(r, [&ctx] (output_stream<char>& os) {
+        return do_with(true, [&os, &ctx] (bool& first) {
             auto f = make_ready_future();
-            for (auto&& cfg_ref : cfg.values()) {
+            for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
                 auto&& cfg = cfg_ref.get();
                 f = f.then([&os, &first, &cfg] {
                     return get_config_swagger_entry(cfg.name(), std::string(cfg.desc()), cfg.type_name(), first, os);
@@ -89,9 +103,9 @@ void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx
         });
     });
 
-    cs::find_config_id.set(r, [&cfg] (const_req r) {
+    cs::find_config_id.set(r, [&ctx] (const_req r) {
         auto id = r.param["id"];
-        for (auto&& cfg_ref : cfg.values()) {
+        for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
             auto&& cfg = cfg_ref.get();
             if (id == cfg.name()) {
                 return cfg.value_as_json();

api/config.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -13,5 +26,5 @@
 
 namespace api {
 
-void set_config(std::shared_ptr<api_registry_builder20> rb, http_context& ctx, routes& r, const db::config& cfg);
+void set_config(std::shared_ptr<api_registry_builder20> rb, http_context& ctx, routes& r);
 }

api/endpoint_snitch.cc

@@ -1,68 +1,48 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "locator/token_metadata.hh"
 #include "locator/snitch_base.hh"
-#include "locator/production_snitch_base.hh"
 #include "endpoint_snitch.hh"
 #include "api/api-doc/endpoint_snitch_info.json.hh"
-#include "api/api-doc/storage_service.json.hh"
 #include "utils/fb_utilities.hh"
 
 namespace api {
 
-void set_endpoint_snitch(http_context& ctx, routes& r, sharded<locator::snitch_ptr>& snitch) {
+void set_endpoint_snitch(http_context& ctx, routes& r) {
     static auto host_or_broadcast = [](const_req req) {
         auto host = req.get_query_param("host");
         return host.empty() ? gms::inet_address(utils::fb_utilities::get_broadcast_address()) : gms::inet_address(host);
     };
 
-    httpd::endpoint_snitch_info_json::get_datacenter.set(r, [&ctx](const_req req) {
-        auto& topology = ctx.shared_token_metadata.local().get()->get_topology();
-        auto ep = host_or_broadcast(req);
-        if (!topology.has_endpoint(ep, locator::topology::pending::yes)) {
-            // Cannot return error here, nodetool status can race, request
-            // info about just-left node and not handle it nicely
-            return sstring(locator::production_snitch_base::default_dc);
-        }
-        return topology.get_datacenter(ep);
+    httpd::endpoint_snitch_info_json::get_datacenter.set(r, [](const_req req) {
+        return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(host_or_broadcast(req));
     });
 
-    httpd::endpoint_snitch_info_json::get_rack.set(r, [&ctx](const_req req) {
-        auto& topology = ctx.shared_token_metadata.local().get()->get_topology();
-        auto ep = host_or_broadcast(req);
-        if (!topology.has_endpoint(ep, locator::topology::pending::yes)) {
-            // Cannot return error here, nodetool status can race, request
-            // info about just-left node and not handle it nicely
-            return sstring(locator::production_snitch_base::default_rack);
-        }
-        return topology.get_rack(ep);
+    httpd::endpoint_snitch_info_json::get_rack.set(r, [](const_req req) {
+        return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_rack(host_or_broadcast(req));
     });
 
-    httpd::endpoint_snitch_info_json::get_snitch_name.set(r, [&snitch] (const_req req) {
-        return snitch.local()->get_name();
+    httpd::endpoint_snitch_info_json::get_snitch_name.set(r, [] (const_req req) {
+        return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_name();
     });
-
-    httpd::storage_service_json::update_snitch.set(r, [&snitch](std::unique_ptr<request> req) {
-        locator::snitch_config cfg;
-        cfg.name = req->get_query_param("ep_snitch_class_name");
-        return locator::i_endpoint_snitch::reset_snitch(snitch, cfg).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-}
-
-void unset_endpoint_snitch(http_context& ctx, routes& r) {
-    httpd::endpoint_snitch_info_json::get_datacenter.unset(r);
-    httpd::endpoint_snitch_info_json::get_rack.unset(r);
-    httpd::endpoint_snitch_info_json::get_snitch_name.unset(r);
-    httpd::storage_service_json::update_snitch.unset(r);
 }
 
 }

api/endpoint_snitch.hh

@@ -1,22 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "api.hh"
 
-namespace locator {
-class snitch_ptr;
-}
-
 namespace api {
 
-void set_endpoint_snitch(http_context& ctx, routes& r, sharded<locator::snitch_ptr>&);
-void unset_endpoint_snitch(http_context& ctx, routes& r);
+void set_endpoint_snitch(http_context& ctx, routes& r);
 
 }

api/error_injection.cc

@@ -1,56 +0,0 @@
-/*
- * Copyright (C) 2020-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include "api/api-doc/error_injection.json.hh"
-#include "api/api.hh"
-
-#include <seastar/http/exception.hh>
-#include "log.hh"
-#include "utils/error_injection.hh"
-#include <seastar/core/future-util.hh>
-
-namespace api {
-
-namespace hf = httpd::error_injection_json;
-
-void set_error_injection(http_context& ctx, routes& r) {
-
-    hf::enable_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->param["injection"];
-        bool one_shot = req->get_query_param("one_shot") == "True";
-        auto& errinj = utils::get_local_injector();
-        return errinj.enable_on_all(injection, one_shot).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-    hf::get_enabled_injections_on_all.set(r, [](std::unique_ptr<request> req) {
-        auto& errinj = utils::get_local_injector();
-        auto ret = errinj.enabled_injections_on_all();
-        return make_ready_future<json::json_return_type>(ret);
-    });
-
-    hf::disable_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->param["injection"];
-
-        auto& errinj = utils::get_local_injector();
-        return errinj.disable_on_all(injection).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-    hf::disable_on_all.set(r, [](std::unique_ptr<request> req) {
-        auto& errinj = utils::get_local_injector();
-        return errinj.disable_on_all().then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-}
-
-} // namespace api

api/error_injection.hh

@@ -1,17 +0,0 @@
-/*
- * Copyright (C) 2019-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include "api.hh"
-
-namespace api {
-
-void set_error_injection(http_context& ctx, routes& r);
-
-}