sstables: Fix sstable reshaping for STCS

The heuristic of STCS reshape is correct, and it built the compaction
descriptor correctly, but forgot to return it to the caller, so no
reshape was ever done on behalf of STCS even when the strategy
needed it.

Fixes #7774.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20201209175044.1609102-1-raphaelsc@scylladb.com>
(cherry picked from commit e4b55f40f3)

.github/CODEOWNERS

@@ -4,7 +4,7 @@ auth/* @elcallio @vladzcloudius
 # CACHE
 row_cache* @tgrabiec @haaawk
 *mutation* @tgrabiec @haaawk
-test/boost/mvcc* @tgrabiec @haaawk
+tests/mvcc* @tgrabiec @haaawk
 
 # CDC
 cdc/* @haaawk @kbr- @elcallio @piodul @jul-stas
@@ -19,13 +19,13 @@ db/batch* @elcallio
 service/storage_proxy* @gleb-cloudius
 
 # COMPACTION
-compaction/* @raphaelsc @nyh
+sstables/compaction* @raphaelsc @nyh
 
 # CQL TRANSPORT LAYER
-transport/*
+transport/* @penberg
 
 # CQL QUERY LANGUAGE
-cql3/* @tgrabiec @psarna @cvybhu
+cql3/* @tgrabiec @penberg @psarna
 
 # COUNTERS
 counters* @haaawk @jul-stas
@@ -35,7 +35,7 @@ tests/counter_test* @haaawk @jul-stas
 gms/* @tgrabiec @asias
 
 # DOCKER
-dist/docker/*
+dist/docker/* @penberg
 
 # LSA
 utils/logalloc* @tgrabiec
@@ -58,9 +58,9 @@ service/migration* @tgrabiec @nyh
 schema* @tgrabiec @nyh
 
 # SECONDARY INDEXES
-db/index/* @nyh @psarna
-cql3/statements/*index* @nyh @psarna
-test/boost/*index* @nyh @psarna
+db/index/* @nyh @penberg @psarna
+cql3/statements/*index* @nyh @penberg @psarna
+test/boost/*index* @nyh @penberg @psarna
 
 # SSTABLES
 sstables/* @tgrabiec @raphaelsc @nyh
@@ -78,20 +78,4 @@ db/hints/* @haaawk @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
+redis-test/* @nyh @syuu1228

.github/workflows/docs-pages@v2.yaml

@@ -1,29 +0,0 @@
-name: "Docs / Publish"
-
-on:
-  push:
-    branches:
-    - master
-    paths:
-    - "docs/**"
-  workflow_dispatch:
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        persist-credentials: false
-        fetch-depth: 0
-    - name: Set up Python
-      uses: actions/setup-python@v1
-      with:
-        python-version: 3.7
-    - name: Build docs
-      run: make -C docs multiversion
-    - name: Deploy
-      run: ./docs/_utils/deploy.sh
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pr@v1.yaml

@@ -1,25 +0,0 @@
-name: "Docs / Build PR"
-
-on:
-  pull_request:
-    branches:
-    - master
-    paths:
-    - "docs/**"
-
-jobs:
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        persist-credentials: false
-        fetch-depth: 0
-    - name: Set up Python
-      uses: actions/setup-python@v1
-      with:
-        python-version: 3.7
-    - name: Build docs
-      run: make -C docs test

.gitignore

@@ -25,7 +25,3 @@ tags
 testlog
 test/*/*.reject
 .vscode
-docs/_build
-docs/poetry.lock
-compile_commands.json
-.ccls-cache/

CMakeLists.txt

@@ -1,5 +1,8 @@
-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)
@@ -17,779 +20,138 @@ else()
     set(BUILD_TYPE "release")
 endif()
 
-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)
+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()
+
+# 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} "${CMAKE_SOURCE_DIR}/build/${BUILD_TYPE}/seastar:$ENV{PKG_CONFIG_PATH}")
+pkg_check_modules(SEASTAR seastar)
+
+if(NOT SEASTAR_INCLUDE_DIRS)
+    # Default value. A more accurate list is populated through `pkg-config` below if `seastar.pc` is available.
+    set(SEASTAR_INCLUDE_DIRS "seastar/include")
+endif()
+
+find_package(Boost COMPONENTS filesystem program_options system thread)
+
+##
+## Populate the names of all source and header files in the indicated paths in a designated variable.
+##
+## When RECURSIVE is specified, directories are traversed recursively.
+##
+## Use: scan_scylla_source_directories(VAR my_result_var [RECURSIVE] PATHS [path1 path2 ...])
+##
+function (scan_scylla_source_directories)
+    set(options RECURSIVE)
+    set(oneValueArgs VAR)
+    set(multiValueArgs PATHS)
+    cmake_parse_arguments(args "${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/testing
+          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
+          raft
+          repair
+          service
+          sstables
+          streaming
+          test
+          thrift
+          tracing
+          transport
+          utils)
 
-    add_custom_target(${args_TARGET}
-        DEPENDS ${outputs})
+scan_scylla_source_directories(
+        VAR SCYLLA_GEN_SOURCE_FILES
+        RECURSIVE
+        PATHS build/${BUILD_TYPE}/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/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
-    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
-    connection_notifier.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/term_expr.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/relation.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/single_column_relation.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/use_statement.cc
-    cql3/token_relation.cc
-    cql3/tuples.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
-    database.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/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
-    distributed_loader.cc
-    duration.cc
-    exceptions/exceptions.cc
-    flat_mutation_reader.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
-    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
-    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
-    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-result-set.cc
-    raft/fsm.cc
-    raft/log.cc
-    raft/raft.cc
-    raft/server.cc
-    raft/tracker.cc
-    range_tombstone.cc
-    range_tombstone_list.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
-    row_cache.cc
-    schema.cc
-    schema_mutations.cc
-    schema_registry.cc
-    serializer.cc
-    service/client_state.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_gossip_failure_detector.cc
-    service/raft/raft_group_registry.cc
-    service/raft/raft_rpc.cc
-    service/raft/raft_sys_table_storage.cc
-    service/raft/schema_raft_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.cc
-    table_helper.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
-    ${LUA_LIBRARIES}
-    thrift
-    crypt)
+# If the Seastar pkg-config information is available, append to the default flags.
+#
+# For ease of browsing the source code, we always pretend that DPDK is enabled.
+target_compile_options(scylla PUBLIC
+        -std=gnu++20
+        -DHAVE_DPDK
+        -DHAVE_HWLOC
+        "${SEASTAR_CFLAGS}")
 
-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
-
-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}
+        ${Boost_INCLUDE_DIRS}
+        xxhash
+        libdeflate
+        abseil
+        build/${BUILD_TYPE}/gen)

CONTRIBUTING.md

@@ -1,20 +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.
+To contribute code to Scylla, you need to sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) 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

@@ -172,8 +172,12 @@ 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
@@ -362,27 +366,7 @@ $ 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`.
-
 ### Core dump debugging
 
-See [debugging.md](debugging.md).
+Slides:
+2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

NOTICE.txt

@@ -5,7 +5,3 @@ It includes files from https://github.com/antonblanchard/crc32-vpmsum (author An
 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

@@ -42,8 +42,8 @@ For further information, please see:
 * [Docker image build documentation] for information on how to build Docker images.
 
 [developer documentation]: HACKING.md
-[build documentation]: docs/guides/building.md
-[docker image build documentation]: dist/docker/debian/README.md
+[build documentation]: docs/building.md
+[docker image build documentation]: dist/docker/redhat/README.md
 
 ## Running Scylla
 
@@ -65,7 +65,7 @@ $ ./tools/toolchain/dbuild ./build/release/scylla --help
 
 ## Testing
 
-See [test.py manual](docs/guides/testing.md).
+See [test.py manual](docs/testing.md).
 
 ## Scylla APIs and compatibility
 By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
@@ -78,7 +78,10 @@ and the current compatibility of this feature as well as Scylla-specific extensi
 
 ## Documentation
 
-Documentation can be found [here](https://scylla.docs.scylladb.com).
+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/).
 

SCYLLA-VERSION-GEN

@@ -1,66 +1,7 @@
 #!/bin/sh
 
-USAGE=$(cat <<-END
-Usage: $(basename "$0") [-h|--help] [-o|--output-dir PATH] -- 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.
-
-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
-)
-
-while [[ $# -gt 0 ]]; do
-	opt="$1"
-	case $opt in
-		-h|--help)
-			echo "$USAGE"
-			exit 0
-			;;
-		-o|--output-dir)
-			OUTPUT_DIR="$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
-
-# Default scylla product/version tags
 PRODUCT=scylla
-VERSION=4.6.11
+VERSION=4.3.7
 
 if test -f version
 then
@@ -68,7 +9,7 @@ then
 	SCYLLA_RELEASE=$(cat version | awk -F'-' '{print $2}')
 else
 	DATE=$(date +%Y%m%d)
-	GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1)
+	GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
 	SCYLLA_VERSION=$VERSION
 	# For custom package builds, replace "0" with "counter.your_name",
 	# where counter starts at 1 and increments for successive versions.
@@ -78,15 +19,16 @@ else
 	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi
 
-if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" |cut -d . -f 3)
+if [ -f build/SCYLLA-RELEASE-FILE ]; then
+	RELEASE_FILE=$(cat build/SCYLLA-RELEASE-FILE)
+	GIT_COMMIT_FILE=$(cat build/SCYLLA-RELEASE-FILE |cut -d . -f 3)
 	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
 		exit 0
 	fi
 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

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
  */
 
 /*

absl-flat_hash_map.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
  */
 
 /*

alternator/auth.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -24,6 +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"
@@ -31,13 +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 "database.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 {
 
@@ -66,14 +62,6 @@ 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;
@@ -103,7 +91,7 @@ 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");
@@ -136,36 +124,24 @@ 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.get_db().local().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_return coroutine::make_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));
+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_return coroutine::make_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_return coroutine::make_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.execute_internal(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::unrecognized_client(fmt::format("User not found: {}", username));
+        }
+        salted_hash = res->one().get_opt<sstring>("salted_hash");
+        if (!salted_hash) {
+            throw api_error::unrecognized_client(fmt::format("No password found for user: {}", username));
+        }
+        return make_ready_future<std::string>(*salted_hash);
+    });
 }
 
 }

alternator/auth.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -27,8 +27,8 @@
 #include "gc_clock.hh"
 #include "utils/loading_cache.hh"
 
-namespace service {
-class storage_proxy;
+namespace cql3 {
+class query_processor;
 }
 
 namespace alternator {
@@ -39,8 +39,8 @@ 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

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -19,6 +19,10 @@
  * 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>

alternator/base64.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -23,11 +23,16 @@
 
 #include <string_view>
 #include "bytes.hh"
+#include "utils/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()));
+}
+
 size_t base64_decoded_len(std::string_view str);
 
 bool base64_begins_with(std::string_view base, std::string_view operand);

alternator/conditions.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -28,8 +28,7 @@
 #include <unordered_map>
 #include "utils/rjson.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
+#include "base64.hh"
 #include <stdexcept>
 #include <boost/algorithm/cxx11/all_of.hpp>
 #include <boost/algorithm/cxx11/any_of.hpp>
@@ -263,7 +262,7 @@ bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
     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;
+        return base64_decode(kv1.value).find(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) {
@@ -387,7 +386,7 @@ bool check_compare(const rjson::value* v1, const rjson::value& v2, const Compara
                    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.
@@ -477,7 +476,7 @@ static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const r
                              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);
+        return check_BETWEEN(base64_decode(kv_v.value), base64_decode(kv_lb.value), base64_decode(kv_ub.value), bounds_from_query);
     }
     if (v_from_query) {
         throw api_error::validation(

alternator/conditions.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*

alternator/controller.cc

@@ -1,128 +0,0 @@
-/*
- * Copyright (C) 2021-present 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 General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#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"
-
-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,
-        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)
-    , _config(config)
-{
-}
-
-future<> controller::start() {
-    return seastar::async([this] {
-        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;
-        try {
-            addr = net::dns::get_host_by_name(_config.alternator_address(), family).get0().addr_list.front();
-        } catch (...) {
-            std::throw_with_nested(std::runtime_error(fmt::format("Unable to resolve alternator_address {}", _config.alternator_address())));
-        }
-
-        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)).get();
-        std::optional<uint16_t> alternator_port;
-        if (_config.alternator_port()) {
-            alternator_port = _config.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();
-            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");
-            utils::configure_tls_creds_builder(creds.value(), std::move(opts)).get();
-        }
-        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);
-        }).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() {
-    return seastar::async([this] {
-        _server.stop().get();
-        _executor.stop().get();
-        destroy_smp_service_group(_ssg.value()).get();
-    });
-}
-
-}

alternator/controller.hh

@@ -1,82 +0,0 @@
-/*
- * Copyright (C) 2021-present 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 General Public License
- * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#pragma once
-
-#include <seastar/core/sharded.hh>
-#include <seastar/core/smp.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 alternator {
-
-using namespace seastar;
-
-class executor;
-class server;
-
-class 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;
-    const db::config& _config;
-
-    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,
-        const db::config& config);
-
-    future<> start();
-    future<> stop();
-};
-
-}

alternator/error.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -34,7 +34,7 @@ namespace alternator {
 // "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 {
+class api_error final {
 public:
     using status_type = httpd::reply::status_type;
     status_type _http_code;
@@ -59,9 +59,6 @@ public:
     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));
     }
@@ -80,20 +77,9 @@ public:
     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 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;
 };
 
 }

alternator/executor.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -27,9 +27,9 @@
 #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"
@@ -50,17 +50,7 @@ namespace cql3::selection {
 }
 
 namespace service {
-    class storage_proxy;
-}
-
-namespace cdc {
-    class metadata;
-}
-
-namespace gms {
-
-class gossiper;
-
+    class storage_service;
 }
 
 namespace alternator {
@@ -80,81 +70,11 @@ public:
     std::string to_json() const override;
 };
 
-namespace parsed {
-class path;
-};
-
-const std::map<sstring, sstring>& get_tags_of_table(schema_ptr schema);
-future<> update_tags(service::migration_manager& mm, schema_ptr schema, std::map<sstring, sstring>&& tags_map);
-schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
-
-// 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>;
-using attrs_to_get = attribute_path_map<std::monostate>;
-
-
 class executor : public peering_sharded_service<executor> {
-    gms::gossiper& _gossiper;
     service::storage_proxy& _proxy;
     service::migration_manager& _mm;
     db::system_distributed_keyspace& _sdks;
-    cdc::metadata& _cdc_metadata;
+    service::storage_service& _ss;
     // 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;
@@ -167,8 +87,8 @@ public:
     static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
     static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.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, db::system_distributed_keyspace& sdks, service::storage_service& ss, smp_service_group ssg)
+        : _proxy(proxy), _mm(mm), _sdks(sdks), _ss(ss), _ssg(ssg) {}
 
     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);
@@ -187,8 +107,6 @@ public:
     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);
@@ -199,12 +117,10 @@ public:
 
     future<> create_keyspace(std::string_view keyspace_name);
 
+    static tracing::trace_state_ptr maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
+
     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);
 
 private:
@@ -220,14 +136,16 @@ public:
         const query::partition_slice&,
         const cql3::selection::selection&,
         const query::result&,
-        const attrs_to_get&);
+        const std::unordered_set<std::string>&);
 
     static void describe_single_item(const cql3::selection::selection&,
         const std::vector<bytes_opt>&,
-        const attrs_to_get&,
+        const std::unordered_set<std::string>&,
         rjson::value&,
         bool = false);
 
+
+
     void add_stream_options(const rjson::value& stream_spec, schema_builder&) const;
     void supplement_table_info(rjson::value& descr, const schema& schema) const;
     void supplement_table_stream_info(rjson::value& descr, const schema& schema) const;

alternator/expressions.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -21,7 +21,7 @@
 
 #include "expressions.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
+#include "base64.hh"
 #include "conditions.hh"
 #include "alternator/expressionsLexer.hpp"
 #include "alternator/expressionsParser.hpp"
@@ -130,27 +130,6 @@ void condition_expression::append(condition_expression&& a, char op) {
     }, _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
@@ -172,9 +151,10 @@ std::ostream& operator<<(std::ostream& os, const path& p) {
 // 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,
+static void resolve_path(parsed::path& p,
         const rjson::value* expression_attribute_names,
         std::unordered_set<std::string>& used_attribute_names) {
+    const std::string& column_name = p.root();
     if (column_name.size() > 0 && column_name.front() == '#') {
         if (!expression_attribute_names) {
             throw api_error::validation(
@@ -186,30 +166,7 @@ static std::optional<std::string> resolve_path_component(const std::string& colu
                     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);
+        p.set_root(std::string(rjson::to_string_view(*value)));
     }
 }
 
@@ -428,6 +385,24 @@ void for_condition_expression_on(const parsed::condition_expression& ce, const n
 // expression. The parsed expression is assumed to have been "resolved", with
 // the matching resolve_* function.
 
+// 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.
+static 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) {
+        throw api_error::validation("UpdateExpression: list_append() given a non-list");
+    }
+    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::set(ret, "L", std::move(cat));
+    return ret;
+}
+
 // 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.
@@ -464,11 +439,11 @@ static rjson::value calculate_size(const rjson::value& 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));
+        rjson::set(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)));
+    rjson::set(json_ret, "N", rjson::from_string(std::to_string(ret)));
     return json_ret;
 }
 
@@ -487,7 +462,7 @@ static const rjson::value& calculate_value(const parsed::constant& c) {
 
 static rjson::value to_bool_json(bool b) {
     rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "BOOL", rjson::value(b));
+    rjson::set(json_ret, "BOOL", rjson::value(b));
     return json_ret;
 }
 
@@ -512,11 +487,7 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
             }
             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;
+            return list_concatenate(v1, v2);
         }
     },
     {"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
@@ -652,55 +623,6 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
     },
 };
 
-// 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.
@@ -718,12 +640,21 @@ rjson::value calculate_value(const parsed::value& v,
             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));
+                        format("UpdateExpression: unknown function '{}' called.", f._function_name));
             }
             return function_it->second(caller, previous_item, f);
         },
         [&] (const parsed::path& p) -> rjson::value {
-            return extract_path(previous_item, p, caller);
+            if (!previous_item) {
+                return rjson::null_value();
+            }
+            std::string update_path = p.root();
+            if (p.has_operators()) {
+                // FIXME: support this
+                throw api_error::validation("Reading attribute paths not yet implemented");
+            }
+            const rjson::value* previous_value = rjson::find(*previous_item, update_path);
+            return previous_value ? rjson::copy(*previous_value) : rjson::null_value();
         }
     }, v._value);
 }

alternator/expressions.g

@@ -1,5 +1,8 @@
 /*
- * 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.
  */
 
 /*

alternator/expressions.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*

alternator/expressions_types.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -49,23 +49,15 @@ 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;
@@ -73,13 +65,6 @@ 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

alternator/rmw_operation.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2020-present ScyllaDB
+ * Copyright 2020 ScyllaDB
  */
 
 /*
@@ -22,7 +22,8 @@
 #pragma once
 
 #include "seastarx.hh"
-#include "service/paxos/cas_request.hh"
+#include "service/storage_proxy.hh"
+#include "service/storage_proxy.hh"
 #include "utils/rjson.hh"
 #include "executor.hh"
 

alternator/serialization.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -19,8 +19,7 @@
  * 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"
@@ -69,7 +68,7 @@ struct from_json_visitor {
         bo.write(t.from_string(rjson::to_string_view(v)));
     }
     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()));
@@ -115,18 +114,18 @@ struct to_json_visitor {
     void operator()(const decimal_type_impl& t) const {
         auto s = to_json_string(*decimal_type, 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(to_json_string(t, bytes(bv))));
     }
 };
 
@@ -197,7 +196,7 @@ bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column
                 format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
     }
     if (column.type == bytes_type) {
-        return rjson::base64_decode(it->value);
+        return base64_decode(it->value);
     } else {
         return column.type->from_string(rjson::to_string_view(it->value));
     }
@@ -302,7 +301,7 @@ rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
     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));
+    rjson::set(ret, "N", rjson::from_string(str_ret));
     return ret;
 }
 
@@ -311,7 +310,7 @@ rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
     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));
+    rjson::set(ret, "N", rjson::from_string(str_ret));
     return ret;
 }
 
@@ -337,7 +336,7 @@ rjson::value set_sum(const rjson::value& v1, const rjson::value& v2) {
         }
     }
     rjson::value ret = rjson::empty_object();
-    rjson::add_with_string_name(ret, set1_type, std::move(sum));
+    rjson::set_with_string_name(ret, set1_type, std::move(sum));
     return ret;
 }
 
@@ -365,7 +364,7 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
         return std::nullopt;
     }
     rjson::value ret = rjson::empty_object();
-    rjson::add_with_string_name(ret, set1_type, rjson::empty_array());
+    rjson::set_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));
@@ -373,23 +372,4 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
     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;
-}
-
 }

alternator/serialization.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -85,11 +85,5 @@ rjson::value set_sum(const rjson::value& v1, const rjson::value& v2);
 // 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

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -22,20 +22,15 @@
 #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 "seastarx.hh"
 #include "error.hh"
 #include "utils/rjson.hh"
 #include "auth.hh"
 #include <cctype>
-#include "service/storage_proxy.hh"
-#include "locator/snitch_base.hh"
-#include "gms/gossiper.hh"
+#include "cql3/query_processor.hh"
+#include "service/storage_service.hh"
 #include "utils/overloaded_functor.hh"
-#include "utils/fb_utilities.hh"
 
 static logging::logger slogger("alternator-server");
 
@@ -64,40 +59,6 @@ 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
@@ -132,10 +93,6 @@ public:
                  [&] (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;
@@ -148,16 +105,14 @@ public:
 
              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));
                 });
     }
@@ -171,6 +126,7 @@ protected:
     }
 
     future_handler_function _f_handle;
+    sstring _type;
 };
 
 class gated_handler : public handler_base {
@@ -190,7 +146,6 @@ 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);
         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));
@@ -198,25 +153,21 @@ protected:
 };
 
 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) {}
+    local_nodelist_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 {
         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
+        // using gms::get_local_gossiper().get_live_members(). But getting
         // just the list of live nodes in this DC needs more elaborate code:
         sstring local_dc = locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(
                 utils::fb_utilities::get_broadcast_address());
         std::unordered_set<gms::inet_address> local_dc_nodes =
-                _proxy.get_token_metadata_ptr()->get_topology().get_datacenter_endpoints().at(local_dc);
+                service::get_local_storage_service().get_token_metadata().
+                get_topology().get_datacenter_endpoints().at(local_dc);
         for (auto& ip : local_dc_nodes) {
-            if (_gossiper.is_alive(ip)) {
+            if (gms::get_local_gossiper().is_alive(ip)) {
                 rjson::push_back(results, rjson::from_string(ip.to_sstring()));
             }
         }
@@ -227,26 +178,10 @@ protected:
     }
 };
 
-// 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>("<unauthenticated request>");
+        return make_ready_future<>();
     }
     auto host_it = req._headers.find("Host");
     if (host_it == req._headers.end()) {
@@ -254,34 +189,27 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
     }
     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");
+        throw api_error::invalid_signature("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::invalid_signature(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") {
@@ -291,8 +219,7 @@ 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));
@@ -316,10 +243,10 @@ 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),
@@ -329,102 +256,52 @@ 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.");
         }
-        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());
-        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) {
+future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
     _executor._stats.total_operations++;
     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 httpd::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{executor::client_state::internal_tag()};
-    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, req->_headers);
+    return verify_signature(*req).then([this, op, req = std::move(req)] () mutable {
+        auto callback_it = _callbacks.find(op);
+        if (callback_it == _callbacks.end()) {
+            _executor._stats.unsupported_operations++;
+            throw api_error::unknown_operation(format("Unsupported operation {}", op));
+        }
+        return with_gate(_pending_requests, [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] () mutable {
+            //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 {
+                tracing::trace_state_ptr trace_state = executor::maybe_trace_query(*client_state, op, req->content);
+                tracing::trace(trace_state, op);
+                // JSON parsing can allocate up to roughly 2x the size of the raw document, + a couple of bytes for maintenance.
+                // FIXME: by this time, the whole HTTP request was already read, so some memory is already occupied.
+                // Once HTTP allows working on streams, we should grab the permit *before* reading the HTTP payload.
+                size_t mem_estimate = req->content.size() * 3 + 8000;
+                auto units_fut = get_units(*_memory_limiter, mem_estimate);
+                if (_memory_limiter->waiters()) {
+                    ++_executor._stats.requests_blocked_memory;
+                }
+                return units_fut.then([this, callback_it = std::move(callback_it), &client_state, trace_state, req = std::move(req)] (semaphore_units<> units) mutable {
+                    return _json_parser.parse(req->content).then([this, callback_it = std::move(callback_it), &client_state, trace_state,
+                            units = std::move(units), req = std::move(req)] (rjson::value json_request) mutable {
+                        return callback_it->second(_executor, *client_state, trace_state, make_service_permit(std::move(units)), std::move(json_request), std::move(req)).finally([trace_state] {});
+                    });
+                });
+            });
+        });
+    });
 }
 
 void server::set_routes(routes& r) {
@@ -445,19 +322,16 @@ void server::set_routes(routes& r) {
     // 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.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests));
 }
 
 //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)
+server::server(executor& exec)
         : _http_server("http-alternator")
         , _https_server("https-alternator")
         , _executor(exec)
-        , _proxy(proxy)
-        , _gossiper(gossiper)
         , _key_cache(1024, 1min, slogger)
         , _enforce_authorization(false)
         , _enabled_servers{}
@@ -514,12 +388,6 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
         {"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));
         }},
@@ -536,10 +404,9 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
 }
 
 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) {
+        bool enforce_authorization, semaphore* memory_limiter) {
     _memory_limiter = memory_limiter;
     _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"));
@@ -551,14 +418,12 @@ future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std:
             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);
@@ -596,7 +461,7 @@ server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
                 return;
             }
             try {
-                _parsed_document = rjson::parse_yieldable(std::move(_raw_document));
+                _parsed_document = rjson::parse_yieldable(_raw_document);
                 _current_exception = nullptr;
             } catch (...) {
                 _current_exception = std::current_exception();
@@ -606,12 +471,12 @@ server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
     })) {
 }
 
-future<rjson::value> server::json_parser::parse(chunked_content&& content) {
+future<rjson::value> server::json_parser::parse(std::string_view content) {
     if (content.size() < yieldable_parsing_threshold) {
-        return make_ready_future<rjson::value>(rjson::parse(std::move(content)));
+        return make_ready_future<rjson::value>(rjson::parse(content));
     }
-    return with_semaphore(_parsing_sem, 1, [this, content = std::move(content)] () mutable {
-        _raw_document = std::move(content);
+    return with_semaphore(_parsing_sem, 1, [this, content] {
+        _raw_document = content;
         _document_waiting.signal();
         return _document_parsed.wait().then([this] {
             if (_current_exception) {
@@ -629,12 +494,5 @@ future<> server::json_parser::stop() {
     return std::move(_run_parse_json_thread);
 }
 
-const char* api_error::what() const noexcept {
-    if (_what_string.empty()) {
-        _what_string = format("{} {}: {}", _http_code, _type, _msg);
-    }
-    return _what_string.c_str();
-}
-
 }
 

alternator/server.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -23,19 +23,15 @@
 
 #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 "utils/small_vector.hh"
-#include "utils/updateable_value.hh"
 #include <seastar/core/units.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&,
@@ -45,8 +41,6 @@ class server {
     http_server _http_server;
     http_server _https_server;
     executor& _executor;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
 
     key_cache _key_cache;
     bool _enforce_authorization;
@@ -55,11 +49,10 @@ class server {
     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;
+        std::string_view _raw_document;
         rjson::value _parsed_document;
         std::exception_ptr _current_exception;
         semaphore _parsing_sem{1};
@@ -69,25 +62,21 @@ class server {
         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<rjson::value> parse(std::string_view content);
         future<> stop();
     };
     json_parser _json_parser;
 
 public:
-    server(executor& executor, service::storage_proxy& proxy, gms::gossiper& gossiper);
+    server(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);
+            bool enforce_authorization, semaphore* memory_limiter);
     future<> stop();
 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<executor::request_return_type> handle_api_request(std::unique_ptr<request>&& req);
 };
 
 }

alternator/stats.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -38,7 +38,6 @@ stats::stats() : api_operations{} {
 #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")
             OPERATION(batch_write_item, "BatchWriteItem")
             OPERATION(create_backup, "CreateBackup")
             OPERATION(create_global_table, "CreateGlobalTable")
@@ -97,8 +96,6 @@ stats::stats() : api_operations{} {
                     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

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
@@ -92,7 +92,6 @@ public:
     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/streams.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2020-present ScyllaDB
+ * Copyright 2020 ScyllaDB
  */
 
 /*
@@ -26,7 +26,7 @@
 
 #include <seastar/json/formatter.hh>
 
-#include "utils/base64.hh"
+#include "base64.hh"
 #include "log.hh"
 #include "database.hh"
 #include "db/config.hh"
@@ -34,15 +34,13 @@
 #include "cdc/log.hh"
 #include "cdc/generation.hh"
 #include "cdc/cdc_options.hh"
-#include "cdc/metadata.hh"
 #include "db/system_distributed_keyspace.hh"
 #include "utils/UUID_gen.hh"
 #include "cql3/selection/selection.hh"
 #include "cql3/result_set.hh"
 #include "cql3/type_json.hh"
-#include "cql3/column_identifier.hh"
 #include "schema_builder.hh"
-#include "service/storage_proxy.hh"
+#include "service/storage_service.hh"
 #include "gms/feature.hh"
 #include "gms/feature_service.hh"
 
@@ -90,7 +88,7 @@ struct rapidjson::internal::TypeHelper<ValueType, utils::UUID>
 {};
 
 static db_clock::time_point as_timepoint(const utils::UUID& uuid) {
-    return db_clock::time_point{utils::UUID_gen::unix_timestamp(uuid)};
+    return db_clock::time_point{std::chrono::milliseconds(utils::UUID_gen::get_adjusted_timestamp(uuid))};
 }
 
 /**
@@ -196,7 +194,7 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
         if (table && ks_name != table->ks_name()) {
             continue;
         }
-        if (cdc::is_log_for_some_table(db, ks_name, cf_name)) {
+        if (cdc::is_log_for_some_table(ks_name, cf_name)) {
             if (table && table != cdc::get_base_table(db, *s)) {
                 continue;
             }
@@ -204,19 +202,19 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
             rjson::value new_entry = rjson::empty_object();
 
             last = i->first;
-            rjson::add(new_entry, "StreamArn", *last);
-            rjson::add(new_entry, "StreamLabel", rjson::from_string(stream_label(*s)));
-            rjson::add(new_entry, "TableName", rjson::from_string(cdc::base_name(table_name(*s))));
+            rjson::set(new_entry, "StreamArn", *last);
+            rjson::set(new_entry, "StreamLabel", rjson::from_string(stream_label(*s)));
+            rjson::set(new_entry, "TableName", rjson::from_string(cdc::base_name(table_name(*s))));
             rjson::push_back(streams, std::move(new_entry));
 
             --limit;
         }
     }
 
-    rjson::add(ret, "Streams", std::move(streams));
+    rjson::set(ret, "Streams", std::move(streams));
 
     if (last) {
-        rjson::add(ret, "LastEvaluatedStreamArn", *last);
+        rjson::set(ret, "LastEvaluatedStreamArn", *last);
     }
 
     return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
@@ -292,12 +290,9 @@ struct sequence_number {
 sequence_number::sequence_number(std::string_view v) 
     : uuid([&] {
         using namespace boost::multiprecision;
-        // workaround for weird clang 10 bug when calling constructor with
-        // view directly.
-        uint128_t tmp{std::string(v)};
+        uint128_t tmp{v};
         // see above
-        return utils::UUID_gen::get_time_UUID_raw(utils::UUID_gen::decimicroseconds{uint64_t(tmp >> 64)},
-            uint64_t(tmp & std::numeric_limits<uint64_t>::max()));
+        return utils::UUID_gen::get_time_UUID_raw(uint64_t(tmp >> 64), uint64_t(tmp & std::numeric_limits<uint64_t>::max()));
     }())
 {}
 
@@ -473,39 +468,46 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
     auto status = "DISABLED";
 
     if (opts.enabled()) {
-        if (!_cdc_metadata.streams_available()) {
+        auto& metadata = _ss.get_cdc_metadata();
+        if (!metadata.streams_available()) {
             status = "ENABLING";
         } else {
             status = "ENABLED";
         }
     } 
-
-    auto ttl = std::chrono::seconds(opts.ttl());
     
-    rjson::add(stream_desc, "StreamStatus", rjson::from_string(status));
+    rjson::set(stream_desc, "StreamStatus", rjson::from_string(status));
 
     stream_view_type type = cdc_options_to_steam_view_type(opts);
 
-    rjson::add(stream_desc, "StreamArn", alternator::stream_arn(schema->id()));
-    rjson::add(stream_desc, "StreamViewType", type);
-    rjson::add(stream_desc, "TableName", rjson::from_string(table_name(*bs)));
+    rjson::set(stream_desc, "StreamArn", alternator::stream_arn(schema->id()));
+    rjson::set(stream_desc, "StreamViewType", type);
+    rjson::set(stream_desc, "TableName", rjson::from_string(table_name(*bs)));
 
     describe_key_schema(stream_desc, *bs);
 
     if (!opts.enabled()) {
-        rjson::add(ret, "StreamDescription", std::move(stream_desc));
+        rjson::set(ret, "StreamDescription", std::move(stream_desc));
         return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
     }
 
     // TODO: label
     // TODO: creation time
 
-    auto normal_token_owners = _proxy.get_token_metadata_ptr()->count_normal_token_owners();
+    const auto& tm = _proxy.get_token_metadata();
+    // cannot really "resume" query, must iterate all data. because we cannot query neither "time" (pk) > something,
+    // or on expired...
+    // TODO: maybe add secondary index to topology table to enable this?
+    return _sdks.cdc_get_versioned_streams({ tm.count_normal_token_owners() }).then([this, &db, schema, shard_start, limit, ret = std::move(ret), stream_desc = std::move(stream_desc)](std::map<db_clock::time_point, cdc::streams_version> topologies) mutable {
 
-    // filter out cdc generations older than the table or now() - cdc::ttl (typically dynamodb_streams_max_window - 24h)
-    auto low_ts = std::max(as_timepoint(schema->id()), db_clock::now() - ttl);
+        // filter out cdc generations older than the table or now() - dynamodb_streams_max_window (24h)
+        auto low_ts = std::max(as_timepoint(schema->id()), db_clock::now() - dynamodb_streams_max_window);
 
-    return _sdks.cdc_get_versioned_streams(low_ts, { normal_token_owners }).then([this, &db, shard_start, limit, ret = std::move(ret), stream_desc = std::move(stream_desc)] (std::map<db_clock::time_point, cdc::streams_version> topologies) mutable {
+        auto i = topologies.lower_bound(low_ts);
+        // need first gen _intersecting_ the timestamp.
+        if (i != topologies.begin()) {
+            i = std::prev(i);
+        }
 
         auto e = topologies.end();
         auto prev = e;
@@ -513,7 +515,9 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
 
         std::optional<shard_id> last;
 
-        auto i = topologies.begin();
+        // i is now at the youngest generation we include. make a mark of it.
+        auto first = i;
+
         // if we're a paged query, skip to the generation where we left of.
         if (shard_start) {
             i = topologies.find(shard_start->time);
@@ -539,7 +543,7 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
         };
 
         // need a prev even if we are skipping stuff
-        if (i != topologies.begin()) {
+        if (i != first) {
             prev = std::prev(i);
         }
 
@@ -590,19 +594,19 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
                         pid = std::prev(pid);
                     }
                     if (pid != pids.end()) {
-                        rjson::add(shard, "ParentShardId", shard_id(prev->first, *pid));
+                        rjson::set(shard, "ParentShardId", shard_id(prev->first, *pid));
                     }
                 }
 
                 last.emplace(ts, id);
-                rjson::add(shard, "ShardId", *last);
+                rjson::set(shard, "ShardId", *last);
                 auto range = rjson::empty_object();
-                rjson::add(range, "StartingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(ts.time_since_epoch())));
+                rjson::set(range, "StartingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(ts.time_since_epoch().count())));
                 if (expired) {
-                    rjson::add(range, "EndingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(expired->time_since_epoch())));
+                    rjson::set(range, "EndingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(expired->time_since_epoch().count())));
                 }
 
-                rjson::add(shard, "SequenceNumberRange", std::move(range));
+                rjson::set(shard, "SequenceNumberRange", std::move(range));
                 rjson::push_back(shards, std::move(shard));
                 
                 if (--limit == 0) {
@@ -614,11 +618,11 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
         }
 
         if (last) {
-            rjson::add(stream_desc, "LastEvaluatedShardId", *last);
+            rjson::set(stream_desc, "LastEvaluatedShardId", *last);
         }
 
-        rjson::add(stream_desc, "Shards", std::move(shards));
-        rjson::add(ret, "StreamDescription", std::move(stream_desc));
+        rjson::set(stream_desc, "Shards", std::move(shards));
+        rjson::set(ret, "StreamDescription", std::move(stream_desc));
             
         return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
     });
@@ -763,7 +767,7 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
             inclusive_of_threshold = true;
             break;
         case shard_iterator_type::LATEST:
-            threshold = utils::UUID_gen::min_time_UUID((db_clock::now() - confidence_interval(db)).time_since_epoch());
+            threshold = utils::UUID_gen::min_time_UUID((db_clock::now() - confidence_interval(db)).time_since_epoch().count());
             inclusive_of_threshold = true;
             break;
     }
@@ -771,7 +775,7 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
     shard_iterator iter(stream_arn, *sid, threshold, inclusive_of_threshold);
 
     auto ret = rjson::empty_object();
-    rjson::add(ret, "ShardIterator", iter);
+    rjson::set(ret, "ShardIterator", iter);
 
     return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
 }
@@ -835,7 +839,7 @@ future<executor::request_return_type> executor::get_records(client_state& client
     dht::partition_range_vector partition_ranges{ dht::partition_range::make_singular(dht::decorate_key(*schema, pk)) };
 
     auto high_ts = db_clock::now() - confidence_interval(db);
-    auto high_uuid = utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch());
+    auto high_uuid = utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch().count());
     auto lo = clustering_key_prefix::from_exploded(*schema, { iter.threshold.serialize() });
     auto hi = clustering_key_prefix::from_exploded(*schema, { high_uuid.serialize() });
 
@@ -847,18 +851,16 @@ future<executor::request_return_type> executor::get_records(client_state& client
     static const bytes op_column_name = cdc::log_meta_column_name_bytes("operation");
     static const bytes eor_column_name = cdc::log_meta_column_name_bytes("end_of_batch");
 
-    auto key_names = boost::copy_range<attrs_to_get>(
+    auto key_names = boost::copy_range<std::unordered_set<std::string>>(
         boost::range::join(std::move(base->partition_key_columns()), std::move(base->clustering_key_columns()))
-        | boost::adaptors::transformed([&] (const column_definition& cdef) {
-            return std::make_pair<std::string, attrs_to_get_node>(cdef.name_as_text(), {}); })
+        | boost::adaptors::transformed([&] (const column_definition& cdef) { return cdef.name_as_text(); })
     );
     // Include all base table columns as values (in case pre or post is enabled).
     // This will include attributes not stored in the frozen map column
-    auto attr_names = boost::copy_range<attrs_to_get>(base->regular_columns()
+    auto attr_names = boost::copy_range<std::unordered_set<std::string>>(base->regular_columns()
         // this will include the :attrs column, which we will also force evaluating. 
         // But not having this set empty forces out any cdc columns from actual result 
-        | boost::adaptors::transformed([] (const column_definition& cdef) {
-            return std::make_pair<std::string, attrs_to_get_node>(cdef.name_as_text(), {}); })
+        | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.name_as_text(); })
     );
 
     std::vector<const column_definition*> columns;
@@ -881,17 +883,8 @@ future<executor::request_return_type> executor::get_records(client_state& client
     auto partition_slice = query::partition_slice(
         std::move(bounds)
         , {}, std::move(regular_columns), selection->get_query_options());
-
-	auto& opts = base->cdc_options();
-	auto mul = 2; // key-only, allow for delete + insert
-    if (opts.preimage()) {
-        ++mul;
-    }
-    if (opts.postimage()) {
-        ++mul;
-    }
     auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice, _proxy.get_max_result_size(partition_slice),
-            query::row_limit(limit * mul));
+            query::row_limit(limit * 4));
 
     return _proxy.query(schema, std::move(command), std::move(partition_ranges), cl, service::storage_proxy::coordinator_query_options(default_timeout(), std::move(permit), client_state)).then(
             [this, schema, partition_slice = std::move(partition_slice), selection = std::move(selection), start_time = std::move(start_time), limit, key_names = std::move(key_names), attr_names = std::move(attr_names), type, iter, high_ts] (service::storage_proxy::coordinator_query_result qr) mutable {       
@@ -927,13 +920,13 @@ future<executor::request_return_type> executor::get_records(client_state& client
 
         auto maybe_add_record = [&] {
             if (!dynamodb.ObjectEmpty()) {
-                rjson::add(record, "dynamodb", std::move(dynamodb));
+                rjson::set(record, "dynamodb", std::move(dynamodb));
                 dynamodb = rjson::empty_object();
             }
             if (!record.ObjectEmpty()) {
                 // TODO: awsRegion?
-                rjson::add(record, "eventID", event_id(iter.shard.id, *timestamp));
-                rjson::add(record, "eventSource", "scylladb:alternator");
+                rjson::set(record, "eventID", event_id(iter.shard.id, *timestamp));
+                rjson::set(record, "eventSource", "scylladb:alternator");
                 rjson::push_back(records, std::move(record));
                 record = rjson::empty_object();
                 --limit;
@@ -948,10 +941,10 @@ future<executor::request_return_type> executor::get_records(client_state& client
             if (!dynamodb.HasMember("Keys")) {
                 auto keys = rjson::empty_object();
                 describe_single_item(*selection, row, key_names, keys);
-                rjson::add(dynamodb, "Keys", std::move(keys));
-                rjson::add(dynamodb, "ApproximateCreationDateTime", utils::UUID_gen::unix_timestamp_in_sec(ts).count());
-                rjson::add(dynamodb, "SequenceNumber", sequence_number(ts));
-                rjson::add(dynamodb, "StreamViewType", type);
+                rjson::set(dynamodb, "Keys", std::move(keys));
+                rjson::set(dynamodb, "ApproximateCreationDateTime", utils::UUID_gen::unix_timestamp_in_sec(ts).count());
+                rjson::set(dynamodb, "SequenceNumber", sequence_number(ts));
+                rjson::set(dynamodb, "StreamViewType", type);
                 //TODO: SizeInBytes
             }
 
@@ -983,17 +976,17 @@ future<executor::request_return_type> executor::get_records(client_state& client
                 auto item = rjson::empty_object();
                 describe_single_item(*selection, row, attr_names, item, true);
                 describe_single_item(*selection, row, key_names, item);
-                rjson::add(dynamodb, op == cdc::operation::pre_image ? "OldImage" : "NewImage", std::move(item));
+                rjson::set(dynamodb, op == cdc::operation::pre_image ? "OldImage" : "NewImage", std::move(item));
                 break;
             }
             case cdc::operation::update:
-                rjson::add(record, "eventName", "MODIFY");
+                rjson::set(record, "eventName", "MODIFY");
                 break;
             case cdc::operation::insert:
-                rjson::add(record, "eventName", "INSERT");
+                rjson::set(record, "eventName", "INSERT");
                 break;
             default:
-                rjson::add(record, "eventName", "REMOVE");
+                rjson::set(record, "eventName", "REMOVE");
                 break;
             }
             if (eor) {
@@ -1007,7 +1000,7 @@ future<executor::request_return_type> executor::get_records(client_state& client
 
         auto ret = rjson::empty_object();
         auto nrecords = records.Size();
-        rjson::add(ret, "Records", std::move(records));
+        rjson::set(ret, "Records", std::move(records));
 
         if (nrecords != 0) {
             // #9642. Set next iterators threshold to > last
@@ -1016,15 +1009,13 @@ future<executor::request_return_type> executor::get_records(client_state& client
             // without checking if maybe we reached the end-of-shard. If the
             // shard did end, then the next read will have nrecords == 0 and
             // will notice end end of shard and not return NextShardIterator.
-            rjson::add(ret, "NextShardIterator", next_iter);
+            rjson::set(ret, "NextShardIterator", next_iter);
             _stats.api_operations.get_records_latency.add(std::chrono::steady_clock::now() - start_time);
             return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
         }
 
         // ugh. figure out if we are and end-of-shard
-        auto normal_token_owners = _proxy.get_token_metadata_ptr()->count_normal_token_owners();
-        
-        return _sdks.cdc_current_generation_timestamp({ normal_token_owners }).then([this, iter, high_ts, start_time, ret = std::move(ret)](db_clock::time_point ts) mutable {
+        return cdc::get_local_streams_timestamp().then([this, iter, high_ts, start_time, ret = std::move(ret)](db_clock::time_point ts) mutable {
             auto& shard = iter.shard;            
 
             if (shard.time < ts && ts < high_ts) {
@@ -1037,8 +1028,8 @@ future<executor::request_return_type> executor::get_records(client_state& client
                 // a search from it until high_ts and found nothing, so we
                 // can also start the next search from high_ts.
                 // TODO: but why? It's simpler just to leave the iterator be.
-                shard_iterator next_iter(iter.table, iter.shard, utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch()), true);
-                rjson::add(ret, "NextShardIterator", iter);
+                shard_iterator next_iter(iter.table, iter.shard, utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch().count()), true);
+                rjson::set(ret, "NextShardIterator", iter);
             }
             _stats.api_operations.get_records_latency.add(std::chrono::steady_clock::now() - start_time);
             return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
@@ -1096,11 +1087,11 @@ void executor::supplement_table_stream_info(rjson::value& descr, const schema& s
         auto& db = _proxy.get_db().local();
         auto& cf = db.find_column_family(schema.ks_name(), cdc::log_name(schema.cf_name()));
         stream_arn arn(cf.schema()->id());
-        rjson::add(descr, "LatestStreamArn", arn);
-        rjson::add(descr, "LatestStreamLabel", rjson::from_string(stream_label(*cf.schema())));
+        rjson::set(descr, "LatestStreamArn", arn);
+        rjson::set(descr, "LatestStreamLabel", rjson::from_string(stream_label(*cf.schema())));
 
         auto stream_desc = rjson::empty_object();
-        rjson::add(stream_desc, "StreamEnabled", true);
+        rjson::set(stream_desc, "StreamEnabled", true);
 
         auto mode = stream_view_type::KEYS_ONLY;
         if (opts.preimage() && opts.postimage()) {
@@ -1110,8 +1101,8 @@ void executor::supplement_table_stream_info(rjson::value& descr, const schema& s
         } else if (opts.postimage()) {
             mode = stream_view_type::NEW_IMAGE;
         }
-        rjson::add(stream_desc, "StreamViewType", mode);
-        rjson::add(descr, "StreamSpecification", std::move(stream_desc));
+        rjson::set(stream_desc, "StreamViewType", mode);
+        rjson::set(descr, "StreamSpecification", std::move(stream_desc));
     }
 }
 

alternator/tags_extension.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*

alternator/ttl.cc

@@ -1,113 +0,0 @@
-/*
- * Copyright 2021-present 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 <seastar/core/sstring.hh>
-#include <seastar/core/coroutine.hh>
-
-#include "executor.hh"
-#include "service/storage_proxy.hh"
-#include "gms/feature_service.hh"
-#include "database.hh"
-#include "utils/rjson.hh"
-
-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.get_db().local().features().cluster_supports_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(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 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(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));
-}
-
-} // namespace alternator

api/api-doc/column_family.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"
                   }
                ]
@@ -2925,10 +2925,6 @@
          "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 +2932,6 @@
                },
                "description":"Read results"
             },
-            "write_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
             "write":{
                "type":"array",
                "items":{

api/api-doc/gossiper.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":[

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"
                ],
@@ -252,7 +252,7 @@
                  "UNUSED__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":[

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":[
@@ -637,14 +575,6 @@
                      "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"
                   }
                ]
             },
@@ -770,7 +700,7 @@
          "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.",
+               "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": "long",
                "nickname":"scrub",
                "produces":[
@@ -793,20 +723,6 @@
                      "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":"keyspace",
                      "description":"The keyspace to query about",
@@ -1054,14 +970,6 @@
                      "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.",
@@ -1197,14 +1105,6 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"ignore_nodes",
-                     "description":"List of dead nodes to ingore in removenode operation",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                   }
                ]
             }
@@ -1856,22 +1756,6 @@
                      "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"
                   }
                ]
             }
@@ -1982,14 +1866,6 @@
                      "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"
                   }
                ]
             },
@@ -2488,10 +2364,6 @@
             "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."
             }
          }
       },

api/api-doc/system.json

@@ -52,22 +52,6 @@
             }
          ]
       },
-      {
-         "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":[

api/api.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
  */
 
 /*
@@ -75,10 +75,10 @@ future<> set_server_init(http_context& ctx) {
     });
 }
 
-future<> set_server_config(http_context& ctx, const db::config& cfg) {
+future<> set_server_config(http_context& ctx) {
     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);
+    return ctx.http_server.set_routes([&ctx, rb02](routes& r) {
+        set_config(rb02, ctx, r);
     });
 }
 
@@ -109,30 +109,12 @@ 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) {
-    return register_api(ctx, "storage_service", "The storage service API", [&ss, &g, &cdc_gs] (http_context& ctx, routes& r) {
-            set_storage_service(ctx, r, ss, g.local(), cdc_gs);
-        });
+future<> set_server_storage_service(http_context& ctx) {
+    return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
 }
 
-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<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms) {
+    return ctx.http_server.set_routes([&ctx, &ms] (routes& r) { set_repair(ctx, r, ms); });
 }
 
 future<> unset_server_repair(http_context& ctx) {
@@ -151,11 +133,9 @@ future<> set_server_snitch(http_context& ctx) {
     return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
 }
 
-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) {
@@ -173,11 +153,9 @@ future<> unset_server_messaging_service(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_messaging_service(ctx, r); });
 }
 
-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) {
@@ -190,34 +168,13 @@ 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);
     });
 }
 
@@ -225,12 +182,18 @@ 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);

api/api.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
  */
 
 /*
@@ -29,7 +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"
@@ -71,7 +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>

api/api_init.hh

@@ -19,48 +19,16 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 #pragma once
-
-#include <seastar/http/httpd.hh>
-#include <seastar/core/future.hh>
-
 #include "database_fwd.hh"
-#include "seastarx.hh"
-
-namespace service {
-
-class load_meter;
-class storage_proxy;
-class storage_service;
-
-} // namespace service
-
-class sstables_loader;
-
-namespace locator {
-
-class token_metadata;
-class shared_token_metadata;
-
-} // namespace locator
+#include "service/storage_proxy.hh"
+#include <seastar/http/httpd.hh>
 
+namespace service { class load_meter; }
+namespace locator { class token_metadata; }
 namespace cql_transport { class controller; }
 class thrift_controller;
-namespace db {
-class snapshot_ctl;
-class config;
-namespace view {
-class view_builder;
-}
-}
+namespace db { class snapshot_ctl; }
 namespace netw { class messaging_service; }
-class repair_service;
-namespace cdc { class generation_service; }
-
-namespace gms {
-
-class gossiper;
-
-}
 
 namespace api {
 
@@ -71,26 +39,20 @@ struct http_context {
     distributed<database>& db;
     distributed<service::storage_proxy>& sp;
     service::load_meter& lmeter;
-    const sharded<locator::shared_token_metadata>& shared_token_metadata;
+    const sharded<locator::token_metadata>& token_metadata;
 
     http_context(distributed<database>& _db,
             distributed<service::storage_proxy>& _sp,
-            service::load_meter& _lm, const sharded<locator::shared_token_metadata>& _stm)
-            : db(_db), sp(_sp), lmeter(_lm), shared_token_metadata(_stm) {
+            service::load_meter& _lm, const sharded<locator::token_metadata>& _tm)
+            : db(_db), sp(_sp), lmeter(_lm), token_metadata(_tm) {
     }
-
-    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_config(http_context& ctx);
 future<> set_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);
-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<> set_server_storage_service(http_context& ctx);
+future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms);
 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);
@@ -98,17 +60,14 @@ future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
 future<> unset_rpc_controller(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_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_storage_proxy(http_context& ctx);
 future<> set_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_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);
 
 }

api/cache_service.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/cache_service.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/collectd.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/collectd.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/column_family.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -24,13 +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_view_types.hh"
 #include "db/data_listeners.hh"
-#include "storage_service.hh"
-#include "unimplemented.hh"
 
 extern logging::logger apilog;
 
@@ -183,7 +180,7 @@ static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ct
 
 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;
@@ -191,7 +188,7 @@ static int64_t min_partition_size(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;
@@ -199,7 +196,7 @@ static int64_t max_partition_size(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;
@@ -277,7 +274,7 @@ public:
 
 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);
@@ -313,8 +310,8 @@ 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;
@@ -322,7 +319,7 @@ 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){
@@ -427,7 +424,7 @@ void set_column_family(http_context& ctx, routes& r) {
     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), [](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;
@@ -439,7 +436,7 @@ void set_column_family(http_context& ctx, routes& r) {
     cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
         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;
@@ -450,7 +447,7 @@ 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), [](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;
@@ -602,8 +599,7 @@ 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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            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>());
@@ -611,8 +607,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     cf::get_all_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            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>());
@@ -620,8 +615,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            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>());
@@ -629,8 +623,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     cf::get_all_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            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>());
@@ -662,8 +655,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_size();
             });
         }, std::plus<uint64_t>());
@@ -671,8 +663,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     cf::get_all_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
         return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_size();
             });
         }, std::plus<uint64_t>());
@@ -680,8 +671,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_memory_size();
             });
         }, std::plus<uint64_t>());
@@ -689,8 +679,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->filter_memory_size();
             });
         }, std::plus<uint64_t>());
@@ -698,8 +687,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->get_summary().memory_footprint();
             });
         }, std::plus<uint64_t>());
@@ -707,8 +695,7 @@ void set_column_family(http_context& ctx, routes& r) {
 
     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), [] (column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                 return s + sst->get_summary().memory_footprint();
             });
         }, std::plus<uint64_t>());
@@ -862,24 +849,18 @@ void set_column_family(http_context& ctx, routes& r) {
     });
 
     cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return ctx.db.invoke_on(0, [&ctx, req = std::move(req)] (database& db) {
-            auto g = database::autocompaction_toggle_guard(db);
-            return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
-                cf.enable_auto_compaction();
-            }).then([g = std::move(g)] {
-                return make_ready_future<json::json_return_type>(json_void());
-            });
+        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
+            cf.enable_auto_compaction();
+        }).then([] {
+            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)] (database& db) {
-            auto g = database::autocompaction_toggle_guard(db);
-            return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
-                cf.disable_auto_compaction();
-            }).then([g = std::move(g)] {
-                return make_ready_future<json::json_return_type>(json_void());
-            });
+        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
+            cf.disable_auto_compaction();
+        }).then([] {
+            return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
@@ -887,7 +868,7 @@ void set_column_family(http_context& ctx, routes& r) {
         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 {
+        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) {
@@ -992,20 +973,42 @@ 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);
+                    });
+                });
+            });
         });
     });
 

api/column_family.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -77,7 +77,7 @@ struct map_reduce_column_families_locally {
     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<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
-            *res = reducer(std::move(*res), mapper(*i.second.get()));
+            *res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
         }).then([res] {
             return std::move(*res);
         });
@@ -116,7 +116,4 @@ future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& n
 future<json::json_return_type>  get_cf_stats(http_context& ctx,
         int64_t column_family_stats::*f);
 
-
-std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name);
-
 }

api/commitlog.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/commitlog.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/compaction_manager.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -20,11 +20,10 @@
  */
 
 #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 <utility>
 
 namespace api {
@@ -59,13 +58,12 @@ void set_compaction_manager(http_context& ctx, routes& r) {
 
             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;

api/compaction_manager.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/config.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright 2018-present ScyllaDB
+ * Copyright 2018 ScyllaDB
  */
 
 /*
@@ -22,6 +22,7 @@
 #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>
 
@@ -88,11 +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);
@@ -102,9 +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

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
  */
 
 /*
@@ -26,5 +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

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/endpoint_snitch.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/error_injection.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
  */
 
 /*

api/error_injection.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019-present ScyllaDB
+ * Copyright (C) 2019 ScyllaDB
  */
 
 /*

api/failure_detector.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -28,10 +28,10 @@ namespace api {
 
 namespace fd = httpd::failure_detector_json;
 
-void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
-    fd::get_all_endpoint_states.set(r, [&g](std::unique_ptr<request> req) {
+void set_failure_detector(http_context& ctx, routes& r) {
+    fd::get_all_endpoint_states.set(r, [](std::unique_ptr<request> req) {
         std::vector<fd::endpoint_state> res;
-        for (auto i : g.endpoint_state_map) {
+        for (auto i : gms::get_local_gossiper().endpoint_state_map) {
             fd::endpoint_state val;
             val.addrs = boost::lexical_cast<std::string>(i.first);
             val.is_alive = i.second.is_alive();
@@ -52,14 +52,14 @@ void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
         return make_ready_future<json::json_return_type>(res);
     });
 
-    fd::get_up_endpoint_count.set(r, [&g](std::unique_ptr<request> req) {
-        return gms::get_up_endpoint_count(g).then([](int res) {
+    fd::get_up_endpoint_count.set(r, [](std::unique_ptr<request> req) {
+        return gms::get_up_endpoint_count().then([](int res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    fd::get_down_endpoint_count.set(r, [&g](std::unique_ptr<request> req) {
-        return gms::get_down_endpoint_count(g).then([](int res) {
+    fd::get_down_endpoint_count.set(r, [](std::unique_ptr<request> req) {
+        return gms::get_down_endpoint_count().then([](int res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
@@ -70,8 +70,8 @@ void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
         });
     });
 
-    fd::get_simple_states.set(r, [&g] (std::unique_ptr<request> req) {
-        return gms::get_simple_states(g).then([](const std::map<sstring, sstring>& map) {
+    fd::get_simple_states.set(r, [] (std::unique_ptr<request> req) {
+        return gms::get_simple_states().then([](const std::map<sstring, sstring>& map) {
             return make_ready_future<json::json_return_type>(map_to_key_value<fd::mapper>(map));
         });
     });
@@ -83,8 +83,8 @@ void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
         });
     });
 
-    fd::get_endpoint_state.set(r, [&g] (std::unique_ptr<request> req) {
-        return get_endpoint_state(g, req->param["addr"]).then([](const sstring& state) {
+    fd::get_endpoint_state.set(r, [](std::unique_ptr<request> req) {
+        return gms::get_endpoint_state(req->param["addr"]).then([](const sstring& state) {
             return make_ready_future<json::json_return_type>(state);
         });
     });

api/failure_detector.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -23,14 +23,8 @@
 
 #include "api.hh"
 
-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {
 
-void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g);
+void set_failure_detector(http_context& ctx, routes& r);
 
 }

api/gossiper.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -26,50 +26,43 @@
 namespace api {
 using namespace json;
 
-void set_gossiper(http_context& ctx, routes& r, gms::gossiper& g) {
-    httpd::gossiper_json::get_down_endpoint.set(r, [&g] (const_req req) {
-        auto res = g.get_unreachable_members();
+void set_gossiper(http_context& ctx, routes& r) {
+    httpd::gossiper_json::get_down_endpoint.set(r, [] (const_req req) {
+        auto res = gms::get_local_gossiper().get_unreachable_members();
         return container_to_vec(res);
     });
 
-    httpd::gossiper_json::get_live_endpoint.set(r, [&g] (const_req req) {
-        auto res = g.get_live_members();
+    httpd::gossiper_json::get_live_endpoint.set(r, [] (const_req req) {
+        auto res = gms::get_local_gossiper().get_live_members();
         return container_to_vec(res);
     });
 
-    httpd::gossiper_json::get_endpoint_downtime.set(r, [&g] (const_req req) {
+    httpd::gossiper_json::get_endpoint_downtime.set(r, [] (const_req req) {
         gms::inet_address ep(req.param["addr"]);
-        return g.get_endpoint_downtime(ep);
+        return gms::get_local_gossiper().get_endpoint_downtime(ep);
     });
 
-    httpd::gossiper_json::get_current_generation_number.set(r, [&g] (std::unique_ptr<request> req) {
+    httpd::gossiper_json::get_current_generation_number.set(r, [] (std::unique_ptr<request> req) {
         gms::inet_address ep(req->param["addr"]);
-        return g.get_current_generation_number(ep).then([] (int res) {
+        return gms::get_local_gossiper().get_current_generation_number(ep).then([] (int res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    httpd::gossiper_json::get_current_heart_beat_version.set(r, [&g] (std::unique_ptr<request> req) {
+    httpd::gossiper_json::get_current_heart_beat_version.set(r, [] (std::unique_ptr<request> req) {
         gms::inet_address ep(req->param["addr"]);
-        return g.get_current_heart_beat_version(ep).then([] (int res) {
+        return gms::get_local_gossiper().get_current_heart_beat_version(ep).then([] (int res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    httpd::gossiper_json::assassinate_endpoint.set(r, [&g](std::unique_ptr<request> req) {
+    httpd::gossiper_json::assassinate_endpoint.set(r, [](std::unique_ptr<request> req) {
         if (req->get_query_param("unsafe") != "True") {
-            return g.assassinate_endpoint(req->param["addr"]).then([] {
+            return gms::get_local_gossiper().assassinate_endpoint(req->param["addr"]).then([] {
                 return make_ready_future<json::json_return_type>(json_void());
             });
         }
-        return g.unsafe_assassinate_endpoint(req->param["addr"]).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    httpd::gossiper_json::force_remove_endpoint.set(r, [&g](std::unique_ptr<request> req) {
-        gms::inet_address ep(req->param["addr"]);
-        return g.force_remove_endpoint(ep).then([] {
+        return gms::get_local_gossiper().unsafe_assassinate_endpoint(req->param["addr"]).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });

api/gossiper.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -23,14 +23,8 @@
 
 #include "api.hh"
 
-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {
 
-void set_gossiper(http_context& ctx, routes& r, gms::gossiper& g);
+void set_gossiper(http_context& ctx, routes& r);
 
 }

api/hinted_handoff.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -19,93 +19,15 @@
  * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <algorithm>
-#include <vector>
-
 #include "hinted_handoff.hh"
 #include "api/api-doc/hinted_handoff.json.hh"
 
-#include "gms/inet_address.hh"
-#include "gms/gossiper.hh"
-#include "service/storage_proxy.hh"
-
 namespace api {
 
 using namespace json;
 namespace hh = httpd::hinted_handoff_json;
 
-void set_hinted_handoff(http_context& ctx, routes& r, gms::gossiper& g) {
-    hh::create_hints_sync_point.set(r, [&ctx, &g] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        auto parse_hosts_list = [&g] (sstring arg) {
-            std::vector<sstring> hosts_str = split(arg, ",");
-            std::vector<gms::inet_address> hosts;
-            hosts.reserve(hosts_str.size());
-
-            if (hosts_str.empty()) {
-                // No target_hosts specified means that we should wait for hints for all nodes to be sent
-                const auto members_set = g.get_live_members();
-                std::copy(members_set.begin(), members_set.end(), std::back_inserter(hosts));
-            } else {
-                for (const auto& host_str : hosts_str) {
-                    try {
-                        gms::inet_address host;
-                        host = gms::inet_address(host_str);
-                        hosts.push_back(host);
-                    } catch (std::exception& e) {
-                        throw httpd::bad_param_exception(format("Failed to parse host address {}: {}", host_str, e.what()));
-                    }
-                }
-            }
-            return hosts;
-        };
-
-        std::vector<gms::inet_address> target_hosts = parse_hosts_list(req->get_query_param("target_hosts"));
-        return ctx.sp.local().create_hint_sync_point(std::move(target_hosts)).then([] (db::hints::sync_point sync_point) {
-            return json::json_return_type(sync_point.encode());
-        });
-    });
-
-    hh::get_hints_sync_point.set(r, [&ctx] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        db::hints::sync_point sync_point;
-        const sstring encoded = req->get_query_param("id");
-        try {
-            sync_point = db::hints::sync_point::decode(encoded);
-        } catch (std::exception& e) {
-            throw httpd::bad_param_exception(format("Failed to parse the sync point description {}: {}", encoded, e.what()));
-        }
-
-        lowres_clock::time_point deadline;
-        const sstring timeout_str = req->get_query_param("timeout");
-        try {
-            deadline = [&] {
-                if (timeout_str.empty()) {
-                    // Empty string - don't wait at all, just check the status
-                    return lowres_clock::time_point::min();
-                } else {
-                    const auto timeout = std::stoll(timeout_str);
-                    if (timeout >= 0) {
-                        // Wait until the point is reached, or until `timeout` seconds elapse
-                        return lowres_clock::now() + std::chrono::seconds(timeout);
-                    } else {
-                        // Negative value indicates infinite timeout
-                        return lowres_clock::time_point::max();
-                    }
-                }
-            } ();
-        } catch (std::exception& e) {
-            throw httpd::bad_param_exception(format("Failed to parse the timeout parameter {}: {}", timeout_str, e.what()));
-        }
-
-        using return_type = hh::ns_get_hints_sync_point::get_hints_sync_point_return_type;
-        using return_type_wrapper = hh::ns_get_hints_sync_point::return_type_wrapper;
-
-        return ctx.sp.local().wait_for_hint_sync_point(std::move(sync_point), deadline).then([] {
-            return json::json_return_type(return_type_wrapper(return_type::DONE));
-        }).handle_exception_type([] (const timed_out_error&) {
-            return json::json_return_type(return_type_wrapper(return_type::IN_PROGRESS));
-        });
-    });
-
+void set_hinted_handoff(http_context& ctx, routes& r) {
     hh::list_endpoints_pending_hints.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
@@ -149,16 +71,5 @@ void set_hinted_handoff(http_context& ctx, routes& r, gms::gossiper& g) {
     });
 }
 
-void unset_hinted_handoff(http_context& ctx, routes& r) {
-    hh::create_hints_sync_point.unset(r);
-    hh::get_hints_sync_point.unset(r);
-
-    hh::list_endpoints_pending_hints.unset(r);
-    hh::truncate_all_hints.unset(r);
-    hh::schedule_hint_delivery.unset(r);
-    hh::pause_hints_delivery.unset(r);
-    hh::get_create_hint_count.unset(r);
-    hh::get_not_stored_hints_count.unset(r);
 }
 
-}

api/hinted_handoff.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -23,15 +23,8 @@
 
 #include "api.hh"
 
-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {
 
-void set_hinted_handoff(http_context& ctx, routes& r, gms::gossiper& g);
-void unset_hinted_handoff(http_context& ctx, routes& r);
+void set_hinted_handoff(http_context& ctx, routes& r);
 
 }

api/lsa.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -26,7 +26,6 @@
 #include <seastar/http/exception.hh>
 #include "utils/logalloc.hh"
 #include "log.hh"
-#include "database.hh"
 
 namespace api {
 

api/lsa.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/messaging_service.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -96,10 +96,6 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
         return c.get_stats().sent_messages;
     }));
 
-    get_replied_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
-        return c.get_stats().replied;
-    }));
-
     get_dropped_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
         // We don't have the same drop message mechanism
         // as origin has.
@@ -159,7 +155,6 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
 void unset_messaging_service(http_context& ctx, routes& r) {
     get_timeout_messages.unset(r);
     get_sent_messages.unset(r);
-    get_replied_messages.unset(r);
     get_dropped_messages.unset(r);
     get_exception_messages.unset(r);
     get_pending_messages.unset(r);

api/messaging_service.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/storage_proxy.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -193,7 +193,7 @@ sum_timer_stats_storage_proxy(distributed<proxy>& d,
     });
 }
 
-void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_service>& ss) {
+void set_storage_proxy(http_context& ctx, routes& r) {
     sp::get_total_hints.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
@@ -201,39 +201,29 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_se
     });
 
     sp::get_hinted_handoff_enabled.set(r, [&ctx](std::unique_ptr<request> req)  {
-        const auto& filter = service::get_storage_proxy().local().get_hints_host_filter();
-        return make_ready_future<json::json_return_type>(!filter.is_disabled_for_all());
+        auto enabled = ctx.db.local().get_config().hinted_handoff_enabled();
+        return make_ready_future<json::json_return_type>(enabled);
     });
 
     sp::set_hinted_handoff_enabled.set(r, [](std::unique_ptr<request> req)  {
+        //TBD
+        unimplemented();
         auto enable = req->get_query_param("enable");
-        auto filter = (enable == "true" || enable == "1")
-                ? db::hints::host_filter(db::hints::host_filter::enabled_for_all_tag {})
-                : db::hints::host_filter(db::hints::host_filter::disabled_for_all_tag {});
-        return service::get_storage_proxy().invoke_on_all([filter = std::move(filter)] (service::storage_proxy& sp) {
-            return sp.change_hints_host_filter(filter);
-        }).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
+        return make_ready_future<json::json_return_type>(json_void());
     });
 
     sp::get_hinted_handoff_enabled_by_dc.set(r, [](std::unique_ptr<request> req)  {
-        std::vector<sstring> res;
-        const auto& filter = service::get_storage_proxy().local().get_hints_host_filter();
-        const auto& dcs = filter.get_dcs();
-        res.reserve(res.size());
-        std::copy(dcs.begin(), dcs.end(), std::back_inserter(res));
+        //TBD
+        unimplemented();
+        std::vector<sp::mapper_list> res;
         return make_ready_future<json::json_return_type>(res);
     });
 
     sp::set_hinted_handoff_enabled_by_dc_list.set(r, [](std::unique_ptr<request> req)  {
-        auto dcs = req->get_query_param("dcs");
-        auto filter = db::hints::host_filter::parse_from_dc_list(std::move(dcs));
-        return service::get_storage_proxy().invoke_on_all([filter = std::move(filter)] (service::storage_proxy& sp) {
-            return sp.change_hints_host_filter(filter);
-        }).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
+        //TBD
+        unimplemented();
+        auto enable = req->get_query_param("dcs");
+        return make_ready_future<json::json_return_type>(json_void());
     });
 
     sp::get_max_hint_window.set(r, [](std::unique_ptr<request> req)  {
@@ -363,8 +353,8 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_se
         return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_background);
     });
 
-    sp::get_schema_versions.set(r, [&ss](std::unique_ptr<request> req)  {
-        return ss.local().describe_schema_versions().then([] (auto result) {
+    sp::get_schema_versions.set(r, [](std::unique_ptr<request> req)  {
+        return service::get_local_storage_service().describe_schema_versions().then([] (auto result) {
             std::vector<sp::mapper_list> res;
             for (auto e : result) {
                 sp::mapper_list entry;

api/storage_proxy.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -21,13 +21,10 @@
 
 #pragma once
 
-#include <seastar/core/sharded.hh>
 #include "api.hh"
 
-namespace service { class storage_service; }
-
 namespace api {
 
-void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_service>& ss);
+void set_storage_proxy(http_context& ctx, routes& r);
 
 }

api/storage_service.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -22,50 +22,31 @@
 #include "storage_service.hh"
 #include "api/api-doc/storage_service.json.hh"
 #include "db/config.hh"
-#include "db/schema_tables.hh"
-#include "utils/hash.hh"
-#include <sstream>
+#include <optional>
 #include <time.h>
-#include <algorithm>
 #include <boost/range/adaptor/map.hpp>
 #include <boost/range/adaptor/filtered.hpp>
-#include <boost/algorithm/string/trim_all.hpp>
-#include <boost/algorithm/string/case_conv.hpp>
-#include <boost/functional/hash.hpp>
 #include "service/storage_service.hh"
 #include "service/load_meter.hh"
 #include "db/commitlog/commitlog.hh"
 #include "gms/gossiper.hh"
 #include "db/system_keyspace.hh"
 #include "seastar/http/exception.hh"
-#include <seastar/core/coroutine.hh>
 #include "repair/repair.hh"
 #include "locator/snitch_base.hh"
 #include "column_family.hh"
 #include "log.hh"
 #include "release.hh"
-#include "compaction/compaction_manager.hh"
+#include "sstables/compaction_manager.hh"
 #include "sstables/sstables.hh"
 #include "database.hh"
 #include "db/extensions.hh"
 #include "db/snapshot-ctl.hh"
 #include "transport/controller.hh"
 #include "thrift/controller.hh"
-#include "locator/token_metadata.hh"
-#include "cdc/generation_service.hh"
-#include "service/storage_proxy.hh"
-#include "locator/abstract_replication_strategy.hh"
-#include "sstables_loader.hh"
-#include "db/view/view_builder.hh"
-
-extern logging::logger apilog;
 
 namespace api {
 
-const locator::token_metadata& http_context::get_token_metadata() {
-        return *shared_token_metadata.local().get();
-}
-
 namespace ss = httpd::storage_service_json;
 using namespace json;
 
@@ -84,7 +65,7 @@ static ss::token_range token_range_endpoints_to_json(const dht::token_range_endp
     r.rpc_endpoints = d._rpc_endpoints;
     for (auto det : d._endpoint_details) {
         ss::endpoint_detail ed;
-        ed.host = boost::lexical_cast<std::string>(det._host);
+        ed.host = det._host;
         ed.datacenter = det._datacenter;
         if (det._rack != "") {
             ed.rack = det._rack;
@@ -107,59 +88,12 @@ static auto wrap_ks_cf(http_context &ctx, ks_cf_func f) {
     };
 }
 
-seastar::future<json::json_return_type> run_toppartitions_query(db::toppartitions_query& q, http_context &ctx, bool legacy_request) {
-    namespace cf = httpd::column_family_json;
-    return q.scatter().then([&q, legacy_request] {
-        return sleep(q.duration()).then([&q, legacy_request] {
-            return q.gather(q.capacity()).then([&q, legacy_request] (auto topk_results) {
-                apilog.debug("toppartitions query: processing results");
-                cf::toppartitions_query_results results;
-
-                results.read_cardinality = topk_results.read.size();
-                results.write_cardinality = topk_results.write.size();
-
-                for (auto& d: topk_results.read.top(q.list_size())) {
-                    cf::toppartitions_record r;
-                    r.partition = (legacy_request ? "" : "(" + d.item.schema->ks_name() + ":" + d.item.schema->cf_name() + ") ") + 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 = (legacy_request ? "" : "(" + d.item.schema->ks_name() + ":" + d.item.schema->cf_name() + ") ") + sstring(d.item);
-                    r.count = d.count;
-                    r.error = d.error;
-                    results.write.push(r);
-                }
-                return make_ready_future<json::json_return_type>(results);
-            });
-        });
-    });
-}
-
-future<json::json_return_type> set_tables_autocompaction(http_context& ctx, service::storage_service& ss, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
+future<json::json_return_type> set_tables_autocompaction(http_context& ctx, const sstring &keyspace, std::vector<sstring> tables, bool enabled) {
     if (tables.empty()) {
         tables = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
     }
 
-    apilog.info("set_tables_autocompaction: enabled={} keyspace={} tables={}", enabled, keyspace, tables);
-    return do_with(keyspace, std::move(tables), [&ctx, enabled] (const sstring &keyspace, const std::vector<sstring>& tables) {
-        return ctx.db.invoke_on(0, [&ctx, &keyspace, &tables, enabled] (database& db) {
-            auto g = database::autocompaction_toggle_guard(db);
-            return ctx.db.invoke_on_all([&keyspace, &tables, enabled] (database& db) {
-                return parallel_for_each(tables, [&db, &keyspace, enabled] (const sstring& table) {
-                    column_family& cf = db.find_column_family(keyspace, table);
-                    if (enabled) {
-                        cf.enable_auto_compaction();
-                    } else {
-                        cf.disable_auto_compaction();
-                    }
-                    return make_ready_future<>();
-                });
-            }).finally([g = std::move(g)] {});
-        });
-    }).then([] {
+    return service::get_local_storage_service().set_tables_autocompaction(keyspace, tables, enabled).then([]{
         return make_ready_future<json::json_return_type>(json_void());
     });
 }
@@ -216,10 +150,10 @@ void unset_rpc_controller(http_context& ctx, routes& r) {
     ss::is_rpc_server_running.unset(r);
 }
 
-void set_repair(http_context& ctx, routes& r, sharded<repair_service>& repair) {
-    ss::repair_async.set(r, [&ctx, &repair](std::unique_ptr<request> req) {
+void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms) {
+    ss::repair_async.set(r, [&ctx, &ms](std::unique_ptr<request> req) {
         static std::vector<sstring> options = {"primaryRange", "parallelism", "incremental",
-                "jobThreads", "ranges", "columnFamilies", "dataCenters", "hosts", "ignore_nodes", "trace",
+                "jobThreads", "ranges", "columnFamilies", "dataCenters", "hosts", "trace",
                 "startToken", "endToken" };
         std::unordered_map<sstring, sstring> options_map;
         for (auto o : options) {
@@ -233,7 +167,7 @@ void set_repair(http_context& ctx, routes& r, sharded<repair_service>& repair) {
         // returns immediately, not waiting for the repair to finish. The user
         // then has other mechanisms to track the ongoing repair's progress,
         // or stop it.
-        return repair_start(repair, validate_keyspace(ctx, req->param),
+        return repair_start(ctx.db, ms, validate_keyspace(ctx, req->param),
                 options_map).then([] (int i) {
                     return make_ready_future<json::json_return_type>(i);
                 });
@@ -285,20 +219,20 @@ void set_repair(http_context& ctx, routes& r, sharded<repair_service>& repair) {
             try {
                 res = fut.get0();
             } catch (std::exception& e) {
-                return make_exception_future<json::json_return_type>(httpd::bad_param_exception(e.what()));
+                return make_exception_future<json::json_return_type>(httpd::server_error_exception(e.what()));
             }
             return make_ready_future<json::json_return_type>(json::json_return_type(res));
         });
     });
 
-    ss::force_terminate_all_repair_sessions.set(r, [&ctx](std::unique_ptr<request> req) {
-        return repair_abort_all(ctx.db).then([] {
+    ss::force_terminate_all_repair_sessions.set(r, [](std::unique_ptr<request> req) {
+        return repair_abort_all(service::get_local_storage_service().db()).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::force_terminate_all_repair_sessions_new.set(r, [&ctx](std::unique_ptr<request> req) {
-        return repair_abort_all(ctx.db).then([] {
+    ss::force_terminate_all_repair_sessions_new.set(r, [](std::unique_ptr<request> req) {
+        return repair_abort_all(service::get_local_storage_service().db()).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
@@ -314,73 +248,22 @@ void unset_repair(http_context& ctx, routes& r) {
     ss::force_terminate_all_repair_sessions_new.unset(r);
 }
 
-void set_sstables_loader(http_context& ctx, routes& r, sharded<sstables_loader>& sst_loader) {
-    ss::load_new_ss_tables.set(r, [&ctx, &sst_loader](std::unique_ptr<request> req) {
-        auto ks = validate_keyspace(ctx, req->param);
-        auto cf = req->get_query_param("cf");
-        auto stream = req->get_query_param("load_and_stream");
-        auto primary_replica = req->get_query_param("primary_replica_only");
-        boost::algorithm::to_lower(stream);
-        boost::algorithm::to_lower(primary_replica);
-        bool load_and_stream = stream == "true" || stream == "1";
-        bool primary_replica_only = primary_replica == "true" || primary_replica == "1";
-        // No need to add the keyspace, since all we want is to avoid always sending this to the same
-        // CPU. Even then I am being overzealous here. This is not something that happens all the time.
-        auto coordinator = std::hash<sstring>()(cf) % smp::count;
-        return sst_loader.invoke_on(coordinator,
-                [ks = std::move(ks), cf = std::move(cf),
-                load_and_stream, primary_replica_only] (sstables_loader& loader) {
-            return loader.load_new_sstables(ks, cf, load_and_stream, primary_replica_only);
-        }).then_wrapped([] (auto&& f) {
-            if (f.failed()) {
-                auto msg = fmt::format("Failed to load new sstables: {}", f.get_exception());
-                return make_exception_future<json::json_return_type>(httpd::server_error_exception(msg));
-            }
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-}
-
-void unset_sstables_loader(http_context& ctx, routes& r) {
-    ss::load_new_ss_tables.unset(r);
-}
-
-void set_view_builder(http_context& ctx, routes& r, sharded<db::view::view_builder>& vb) {
-    ss::view_build_statuses.set(r, [&ctx, &vb] (std::unique_ptr<request> req) {
-        auto keyspace = validate_keyspace(ctx, req->param);
-        auto view = req->param["view"];
-        return vb.local().view_build_statuses(std::move(keyspace), std::move(view)).then([] (std::unordered_map<sstring, sstring> status) {
-            std::vector<storage_service_json::mapper> res;
-            return make_ready_future<json::json_return_type>(map_to_key_value(std::move(status), res));
-        });
-    });
-
-}
-
-void unset_view_builder(http_context& ctx, routes& r) {
-    ss::view_build_statuses.unset(r);
-}
-
-static future<json::json_return_type> describe_ring_as_json(sharded<service::storage_service>& ss, sstring keyspace) {
-    co_return json::json_return_type(stream_range_as_array(co_await ss.local().describe_ring(keyspace), token_range_endpoints_to_json));
-}
-
-void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_service>& ss, gms::gossiper& g, sharded<cdc::generation_service>& cdc_gs) {
+void set_storage_service(http_context& ctx, routes& r) {
     ss::local_hostid.set(r, [](std::unique_ptr<request> req) {
-        return db::system_keyspace::load_local_host_id().then([](const utils::UUID& id) {
+        return db::system_keyspace::get_local_host_id().then([](const utils::UUID& id) {
             return make_ready_future<json::json_return_type>(id.to_sstring());
         });
     });
 
     ss::get_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.get_token_metadata().sorted_tokens(), [](const dht::token& i) {
+        return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.token_metadata.local().sorted_tokens(), [](const dht::token& i) {
            return boost::lexical_cast<std::string>(i);
         }));
     });
 
     ss::get_node_tokens.set(r, [&ctx] (std::unique_ptr<request> req) {
         gms::inet_address addr(req->param["endpoint"]);
-        return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.get_token_metadata().get_tokens(addr), [](const dht::token& i) {
+        return make_ready_future<json::json_return_type>(stream_range_as_array(ctx.token_metadata.local().get_tokens(addr), [](const dht::token& i) {
            return boost::lexical_cast<std::string>(i);
        }));
     });
@@ -389,8 +272,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return ctx.db.local().commitlog()->active_config().commit_log_location;
     });
 
-    ss::get_token_endpoint.set(r, [&ss] (std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(stream_range_as_array(ss.local().get_token_to_endpoint_map(), [](const auto& i) {
+    ss::get_token_endpoint.set(r, [] (std::unique_ptr<request> req) {
+        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_to_endpoint_map(), [](const auto& i) {
             storage_service_json::mapper val;
             val.key = boost::lexical_cast<std::string>(i.first);
             val.value = boost::lexical_cast<std::string>(i.second);
@@ -398,58 +281,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         }));
     });
 
-    ss::toppartitions_generic.set(r, [&ctx] (std::unique_ptr<request> req) {
-        bool filters_provided = false;
-
-        std::unordered_set<std::tuple<sstring, sstring>, utils::tuple_hash> table_filters {};
-        if (req->query_parameters.contains("table_filters")) {
-            filters_provided = true;
-            auto filters = req->get_query_param("table_filters");
-            std::stringstream ss { filters };
-            std::string filter;
-            while (!filters.empty() && ss.good()) {
-                std::getline(ss, filter, ',');
-                table_filters.emplace(parse_fully_qualified_cf_name(filter));
-            }
-        }
-
-        std::unordered_set<sstring> keyspace_filters {};
-        if (req->query_parameters.contains("keyspace_filters")) {
-            filters_provided = true;
-            auto filters = req->get_query_param("keyspace_filters");
-            std::stringstream ss { filters };
-            std::string filter;
-            while (!filters.empty() && ss.good()) {
-                std::getline(ss, filter, ',');
-                keyspace_filters.emplace(std::move(filter));
-            }
-        }
-
-        // when the query is empty return immediately
-        if (filters_provided && table_filters.empty() && keyspace_filters.empty()) {
-            apilog.debug("toppartitions query: processing results");
-            httpd::column_family_json::toppartitions_query_results results;
-
-            results.read_cardinality = 0;
-            results.write_cardinality = 0;
-
-            return make_ready_future<json::json_return_type>(results);
-        }
-
-        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: #table_filters={} #keyspace_filters={} duration={} list_size={} capacity={}",
-            !table_filters.empty() ? std::to_string(table_filters.size()) : "all", !keyspace_filters.empty() ? std::to_string(keyspace_filters.size()) : "all", duration.param, list_size.param, capacity.param);
-
-        return seastar::do_with(db::toppartitions_query(ctx.db, std::move(table_filters), std::move(keyspace_filters), duration.value, list_size, capacity), [&ctx] (db::toppartitions_query& q) {
-            return run_toppartitions_query(q, ctx);
-        });
-    });
-
     ss::get_leaving_nodes.set(r, [&ctx](const_req req) {
-        return container_to_vec(ctx.get_token_metadata().get_leaving_endpoints());
+        return container_to_vec(ctx.token_metadata.local().get_leaving_endpoints());
     });
 
     ss::get_moving_nodes.set(r, [](const_req req) {
@@ -458,7 +291,7 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
     });
 
     ss::get_joining_nodes.set(r, [&ctx](const_req req) {
-        auto points = ctx.get_token_metadata().get_bootstrap_tokens();
+        auto points = ctx.token_metadata.local().get_bootstrap_tokens();
         std::unordered_set<sstring> addr;
         for (auto i: points) {
             addr.insert(boost::lexical_cast<std::string>(i.second));
@@ -466,15 +299,15 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return container_to_vec(addr);
     });
 
-    ss::get_release_version.set(r, [&ss](const_req req) {
-        return ss.local().get_release_version();
+    ss::get_release_version.set(r, [](const_req req) {
+        return service::get_local_storage_service().get_release_version();
     });
 
     ss::get_scylla_release_version.set(r, [](const_req req) {
         return scylla_version();
     });
-    ss::get_schema_version.set(r, [&ss](const_req req) {
-        return ss.local().get_schema_version();
+    ss::get_schema_version.set(r, [](const_req req) {
+        return service::get_local_storage_service().get_schema_version();
     });
 
     ss::get_all_data_file_locations.set(r, [&ctx](const_req req) {
@@ -485,11 +318,11 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return ctx.db.local().get_config().saved_caches_directory();
     });
 
-    ss::get_range_to_endpoint_map.set(r, [&ctx, &ss](std::unique_ptr<request> req) {
+    ss::get_range_to_endpoint_map.set(r, [&ctx](std::unique_ptr<request> req) {
         auto keyspace = validate_keyspace(ctx, req->param);
         std::vector<ss::maplist_mapper> res;
-        return make_ready_future<json::json_return_type>(stream_range_as_array(ss.local().get_range_to_address_map(keyspace),
-                [](const std::pair<dht::token_range, inet_address_vector_replica_set>& entry){
+        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_range_to_address_map(keyspace),
+                [](const std::pair<dht::token_range, std::vector<gms::inet_address>>& entry){
             ss::maplist_mapper m;
             if (entry.first.start()) {
                 m.key.push(entry.first.start().value().value().to_sstring());
@@ -516,17 +349,18 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(res);
     });
 
-    ss::describe_any_ring.set(r, [&ctx, &ss](std::unique_ptr<request> req) {
-        return describe_ring_as_json(ss, "");
+    ss::describe_any_ring.set(r, [&ctx](std::unique_ptr<request> req) {
+        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(""), token_range_endpoints_to_json));
     });
 
-    ss::describe_ring.set(r, [&ctx, &ss](std::unique_ptr<request> req) {
-        return describe_ring_as_json(ss, validate_keyspace(ctx, req->param));
+    ss::describe_ring.set(r, [&ctx](std::unique_ptr<request> req) {
+        auto keyspace = validate_keyspace(ctx, req->param);
+        return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().describe_ring(keyspace), token_range_endpoints_to_json));
     });
 
     ss::get_host_id_map.set(r, [&ctx](const_req req) {
         std::vector<ss::mapper> res;
-        return map_to_key_value(ctx.get_token_metadata().get_endpoint_to_host_id_map_for_reading(), res);
+        return map_to_key_value(ctx.token_metadata.local().get_endpoint_to_host_id_map_for_reading(), res);
     });
 
     ss::get_load.set(r, [&ctx](std::unique_ptr<request> req) {
@@ -546,24 +380,21 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         });
     });
 
-    ss::get_current_generation_number.set(r, [&g](std::unique_ptr<request> req) {
+    ss::get_current_generation_number.set(r, [](std::unique_ptr<request> req) {
         gms::inet_address ep(utils::fb_utilities::get_broadcast_address());
-        return g.get_current_generation_number(ep).then([](int res) {
+        return gms::get_local_gossiper().get_current_generation_number(ep).then([](int res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    ss::get_natural_endpoints.set(r, [&ctx, &ss](const_req req) {
+    ss::get_natural_endpoints.set(r, [&ctx](const_req req) {
         auto keyspace = validate_keyspace(ctx, req.param);
-        return container_to_vec(ss.local().get_natural_endpoints(keyspace, req.get_query_param("cf"),
+        return container_to_vec(service::get_local_storage_service().get_natural_endpoints(keyspace, req.get_query_param("cf"),
                 req.get_query_param("key")));
     });
 
-    ss::cdc_streams_check_and_repair.set(r, [&ctx, &cdc_gs] (std::unique_ptr<request> req) {
-        if (!cdc_gs.local_is_initialized()) {
-            throw std::runtime_error("get_cdc_generation_service: not initialized yet");
-        }
-        return cdc_gs.local().check_and_repair_cdc_streams().then([] {
+    ss::cdc_streams_check_and_repair.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return service::get_local_storage_service().check_and_repair_cdc_streams().then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
@@ -574,51 +405,40 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         if (column_families.empty()) {
             column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
         }
-        return ctx.db.invoke_on_all([keyspace, column_families] (database& db) -> future<> {
-            auto table_ids = boost::copy_range<std::vector<utils::UUID>>(column_families | boost::adaptors::transformed([&] (auto& cf_name) {
-                return db.find_uuid(keyspace, cf_name);
-            }));
-            // major compact smaller tables first, to increase chances of success if low on space.
-            std::ranges::sort(table_ids, std::less<>(), [&] (const utils::UUID& id) {
-                return db.find_column_family(id).get_stats().live_disk_space_used;
-            });
-            // as a table can be dropped during loop below, let's find it before issuing major compaction request.
-            for (auto& id : table_ids) {
-                co_await db.find_column_family(id).compact_all_sstables();
+        return ctx.db.invoke_on_all([keyspace, column_families] (database& db) {
+            std::vector<column_family*> column_families_vec;
+            for (auto cf : column_families) {
+                column_families_vec.push_back(&db.find_column_family(keyspace, cf));
             }
-            co_return;
+            return parallel_for_each(column_families_vec, [] (column_family* cf) {
+                    return cf->compact_all_sstables();
+            });
         }).then([]{
                 return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::force_keyspace_cleanup.set(r, [&ctx, &ss](std::unique_ptr<request> req) {
+    ss::force_keyspace_cleanup.set(r, [&ctx](std::unique_ptr<request> req) {
         auto keyspace = validate_keyspace(ctx, req->param);
         auto column_families = split_cf(req->get_query_param("cf"));
         if (column_families.empty()) {
             column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
         }
-        return ss.local().is_cleanup_allowed(keyspace).then([&ctx, keyspace,
+        return service::get_local_storage_service().is_cleanup_allowed(keyspace).then([&ctx, keyspace,
                 column_families = std::move(column_families)] (bool is_cleanup_allowed) mutable {
             if (!is_cleanup_allowed) {
                 return make_exception_future<json::json_return_type>(
                         std::runtime_error("Can not perform cleanup operation when topology changes"));
             }
-            return ctx.db.invoke_on_all([keyspace, column_families] (database& db) -> future<> {
-                auto table_ids = boost::copy_range<std::vector<utils::UUID>>(column_families | boost::adaptors::transformed([&] (auto& table_name) {
-                    return db.find_uuid(keyspace, table_name);
-                }));
-                // cleanup smaller tables first, to increase chances of success if low on space.
-                std::ranges::sort(table_ids, std::less<>(), [&] (const utils::UUID& id) {
-                    return db.find_column_family(id).get_stats().live_disk_space_used;
-                });
+            return ctx.db.invoke_on_all([keyspace, column_families] (database& db) {
+                std::vector<column_family*> column_families_vec;
                 auto& cm = db.get_compaction_manager();
-                // as a table can be dropped during loop below, let's find it before issuing the cleanup request.
-                for (auto& id : table_ids) {
-                    table& t = db.find_column_family(id);
-                    co_await cm.perform_cleanup(db, &t);
+                for (auto cf : column_families) {
+                    column_families_vec.push_back(&db.find_column_family(keyspace, cf));
                 }
-                co_return;
+                return parallel_for_each(column_families_vec, [&cm, &db] (column_family* cf) {
+                    return cm.perform_cleanup(db, cf);
+                });
             }).then([]{
                 return make_ready_future<json::json_return_type>(0);
             });
@@ -655,49 +475,34 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
     });
 
 
-    ss::decommission.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().decommission().then([] {
+    ss::decommission.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().decommission().then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::move.set(r, [&ss] (std::unique_ptr<request> req) {
+    ss::move.set(r, [] (std::unique_ptr<request> req) {
         auto new_token = req->get_query_param("new_token");
-        return ss.local().move(new_token).then([] {
+        return service::get_local_storage_service().move(new_token).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::remove_node.set(r, [&ss](std::unique_ptr<request> req) {
+    ss::remove_node.set(r, [](std::unique_ptr<request> req) {
         auto host_id = req->get_query_param("host_id");
-        std::vector<sstring> ignore_nodes_strs= split(req->get_query_param("ignore_nodes"), ",");
-        auto ignore_nodes = std::list<gms::inet_address>();
-        for (std::string n : ignore_nodes_strs) {
-            try {
-                std::replace(n.begin(), n.end(), '\"', ' ');
-                std::replace(n.begin(), n.end(), '\'', ' ');
-                boost::trim_all(n);
-                if (!n.empty()) {
-                    auto node = gms::inet_address(n);
-                    ignore_nodes.push_back(node);
-                }
-            } catch (...) {
-                throw std::runtime_error(format("Failed to parse ignore_nodes parameter: ignore_nodes={}, node={}", ignore_nodes_strs, n));
-            }
-        }
-        return ss.local().removenode(host_id, std::move(ignore_nodes)).then([] {
+        return service::get_local_storage_service().removenode(host_id).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::get_removal_status.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().get_removal_status().then([] (auto status) {
+    ss::get_removal_status.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().get_removal_status().then([] (auto status) {
             return make_ready_future<json::json_return_type>(status);
         });
     });
 
-    ss::force_remove_completion.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().force_remove_completion().then([] {
+    ss::force_remove_completion.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().force_remove_completion().then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
@@ -721,20 +526,20 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(res);
     });
 
-    ss::get_operation_mode.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().get_operation_mode().then([] (auto mode) {
+    ss::get_operation_mode.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().get_operation_mode().then([] (auto mode) {
             return make_ready_future<json::json_return_type>(mode);
         });
     });
 
-    ss::is_starting.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().is_starting().then([] (auto starting) {
+    ss::is_starting.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().is_starting().then([] (auto starting) {
             return make_ready_future<json::json_return_type>(starting);
         });
     });
 
-    ss::get_drain_progress.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.map_reduce(adder<service::storage_service::drain_progress>(), [] (auto& ss) {
+    ss::get_drain_progress.set(r, [](std::unique_ptr<request> req) {
+        return service::get_storage_service().map_reduce(adder<service::storage_service::drain_progress>(), [] (auto& ss) {
             return ss.get_drain_progress();
         }).then([] (auto&& progress) {
             auto progress_str = format("Drained {}/{} ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
@@ -742,8 +547,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         });
     });
 
-    ss::drain.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().drain().then([] {
+    ss::drain.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().drain().then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
@@ -774,20 +579,20 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         });
     });
 
-    ss::stop_gossiping.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().stop_gossiping().then([] {
+    ss::stop_gossiping.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().stop_gossiping().then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::start_gossiping.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().start_gossiping().then([] {
+    ss::start_gossiping.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().start_gossiping().then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    ss::is_gossip_running.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().is_gossip_running().then([] (bool running){
+    ss::is_gossip_running.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().is_gossip_running().then([] (bool running){
             return make_ready_future<json::json_return_type>(running);
         });
     });
@@ -799,8 +604,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    ss::is_initialized.set(r, [&ss](std::unique_ptr<request> req) {
-        return ss.local().is_initialized().then([] (bool initialized) {
+    ss::is_initialized.set(r, [](std::unique_ptr<request> req) {
+        return service::get_local_storage_service().is_initialized().then([] (bool initialized) {
             return make_ready_future<json::json_return_type>(initialized);
         });
     });
@@ -809,8 +614,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    ss::is_joined.set(r, [&ss] (std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(ss.local().is_joined());
+    ss::is_joined.set(r, [] (std::unique_ptr<request> req) {
+        return make_ready_future<json::json_return_type>(service::get_local_storage_service().is_joined());
     });
 
     ss::set_stream_throughput_mb_per_sec.set(r, [](std::unique_ptr<request> req) {
@@ -838,10 +643,10 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    ss::is_incremental_backups_enabled.set(r, [&ctx](std::unique_ptr<request> req) {
+    ss::is_incremental_backups_enabled.set(r, [](std::unique_ptr<request> req) {
         // If this is issued in parallel with an ongoing change, we may see values not agreeing.
         // Reissuing is asking for trouble, so we will just return true upon seeing any true value.
-        return ctx.db.map_reduce(adder<bool>(), [] (database& db) {
+        return service::get_local_storage_service().db().map_reduce(adder<bool>(), [] (database& db) {
             for (auto& pair: db.get_keyspaces()) {
                 auto& ks = pair.second;
                 if (ks.incremental_backups_enabled()) {
@@ -854,10 +659,10 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         });
     });
 
-    ss::set_incremental_backups_enabled.set(r, [&ctx](std::unique_ptr<request> req) {
+    ss::set_incremental_backups_enabled.set(r, [](std::unique_ptr<request> req) {
         auto val_str = req->get_query_param("value");
         bool value = (val_str == "True") || (val_str == "true") || (val_str == "1");
-        return ctx.db.invoke_on_all([value] (database& db) {
+        return service::get_local_storage_service().db().invoke_on_all([value] (database& db) {
             db.set_enable_incremental_backups(value);
 
             // Change both KS and CF, so they are in sync
@@ -875,9 +680,9 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         });
     });
 
-    ss::rebuild.set(r, [&ss](std::unique_ptr<request> req) {
+    ss::rebuild.set(r, [](std::unique_ptr<request> req) {
         auto source_dc = req->get_query_param("source_dc");
-        return ss.local().rebuild(std::move(source_dc)).then([] {
+        return service::get_local_storage_service().rebuild(std::move(source_dc)).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
@@ -902,6 +707,23 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(json_void());
     });
 
+    ss::load_new_ss_tables.set(r, [&ctx](std::unique_ptr<request> req) {
+        auto ks = validate_keyspace(ctx, req->param);
+        auto cf = req->get_query_param("cf");
+        // No need to add the keyspace, since all we want is to avoid always sending this to the same
+        // CPU. Even then I am being overzealous here. This is not something that happens all the time.
+        auto coordinator = std::hash<sstring>()(cf) % smp::count;
+        return service::get_storage_service().invoke_on(coordinator, [ks = std::move(ks), cf = std::move(cf)] (service::storage_service& s) {
+            return s.load_new_sstables(ks, cf);
+        }).then_wrapped([] (auto&& f) {
+            if (f.failed()) {
+                auto msg = fmt::format("Failed to load new sstables: {}", f.get_exception());
+                return make_exception_future<json::json_return_type>(httpd::server_error_exception(msg));
+            }
+            return make_ready_future<json::json_return_type>(json_void());
+        });
+    });
+
     ss::sample_key_range.set(r, [](std::unique_ptr<request> req) {
         //TBD
         unimplemented();
@@ -910,12 +732,9 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
     });
 
     ss::reset_local_schema.set(r, [](std::unique_ptr<request> req) {
-        // FIXME: We should truncate schema tables if more than one node in the cluster.
-        auto& sp = service::get_storage_proxy();
-        auto& fs = sp.local().features();
-        return db::schema_tables::recalculate_schema_version(sp, fs).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
+        //TBD
+        unimplemented();
+        return make_ready_future<json::json_return_type>(json_void());
     });
 
     ss::set_trace_probability.set(r, [](std::unique_ptr<request> req) {
@@ -948,7 +767,6 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         res.enable = tracing::tracing::get_local_tracing_instance().slow_query_tracing_enabled();
         res.ttl = tracing::tracing::get_local_tracing_instance().slow_query_record_ttl().count() ;
         res.threshold = tracing::tracing::get_local_tracing_instance().slow_query_threshold().count();
-        res.fast = tracing::tracing::get_local_tracing_instance().ignore_trace_events_enabled();
         return res;
     });
 
@@ -956,9 +774,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         auto enable = req->get_query_param("enable");
         auto ttl = req->get_query_param("ttl");
         auto threshold = req->get_query_param("threshold");
-        auto fast = req->get_query_param("fast");
         try {
-            return tracing::tracing::tracing_instance().invoke_on_all([enable, ttl, threshold, fast] (auto& local_tracing) {
+            return tracing::tracing::tracing_instance().invoke_on_all([enable, ttl, threshold] (auto& local_tracing) {
                 if (threshold != "") {
                     local_tracing.set_slow_query_threshold(std::chrono::microseconds(std::stol(threshold.c_str())));
                 }
@@ -968,9 +785,6 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
                 if (enable != "") {
                     local_tracing.set_slow_query_enabled(strcasecmp(enable.c_str(), "true") == 0);
                 }
-                if (fast != "") {
-                    local_tracing.set_ignore_trace_events(strcasecmp(fast.c_str(), "true") == 0);
-                }
             }).then([] {
                 return make_ready_future<json::json_return_type>(json_void());
             });
@@ -979,18 +793,18 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         }
     });
 
-    ss::enable_auto_compaction.set(r, [&ctx, &ss](std::unique_ptr<request> req) {
+    ss::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
         auto keyspace = validate_keyspace(ctx, req->param);
         auto tables = split_cf(req->get_query_param("cf"));
 
-        return set_tables_autocompaction(ctx, ss.local(), keyspace, tables, true);
+        return set_tables_autocompaction(ctx, keyspace, tables, true);
     });
 
-    ss::disable_auto_compaction.set(r, [&ctx, &ss](std::unique_ptr<request> req) {
+    ss::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
         auto keyspace = validate_keyspace(ctx, req->param);
         auto tables = split_cf(req->get_query_param("cf"));
 
-        return set_tables_autocompaction(ctx, ss.local(), keyspace, tables, false);
+        return set_tables_autocompaction(ctx, keyspace, tables, false);
     });
 
     ss::deliver_hints.set(r, [](std::unique_ptr<request> req) {
@@ -1000,12 +814,12 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(json_void());
       });
 
-    ss::get_cluster_name.set(r, [&g](const_req req) {
-        return g.get_cluster_name();
+    ss::get_cluster_name.set(r, [](const_req req) {
+        return gms::get_local_gossiper().get_cluster_name();
     });
 
-    ss::get_partitioner_name.set(r, [&g](const_req req) {
-        return g.get_partitioner_name();
+    ss::get_partitioner_name.set(r, [](const_req req) {
+        return gms::get_local_gossiper().get_partitioner_name();
     });
 
     ss::get_tombstone_warn_threshold.set(r, [](std::unique_ptr<request> req) {
@@ -1058,8 +872,8 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return get_cf_stats(ctx, &column_family_stats::live_disk_space_used);
     });
 
-    ss::get_exceptions.set(r, [&ss](const_req req) {
-        return ss.local().get_exception_count();
+    ss::get_exceptions.set(r, [](const_req req) {
+        return service::get_local_storage_service().get_exception_count();
     });
 
     ss::get_total_hints_in_progress.set(r, [](std::unique_ptr<request> req) {
@@ -1074,21 +888,30 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         return make_ready_future<json::json_return_type>(0);
     });
 
-    ss::get_ownership.set(r, [&ss] (std::unique_ptr<request> req) {
-        return ss.local().get_ownership().then([] (auto&& ownership) {
+    ss::get_ownership.set(r, [] (std::unique_ptr<request> req) {
+        return service::get_local_storage_service().get_ownership().then([] (auto&& ownership) {
             std::vector<storage_service_json::mapper> res;
             return make_ready_future<json::json_return_type>(map_to_key_value(ownership, res));
         });
     });
 
-    ss::get_effective_ownership.set(r, [&ctx, &ss] (std::unique_ptr<request> req) {
+    ss::get_effective_ownership.set(r, [&ctx] (std::unique_ptr<request> req) {
         auto keyspace_name = req->param["keyspace"] == "null" ? "" : validate_keyspace(ctx, req->param);
-        return ss.local().effective_ownership(keyspace_name).then([] (auto&& ownership) {
+        return service::get_local_storage_service().effective_ownership(keyspace_name).then([] (auto&& ownership) {
             std::vector<storage_service_json::mapper> res;
             return make_ready_future<json::json_return_type>(map_to_key_value(ownership, res));
         });
     });
 
+    ss::view_build_statuses.set(r, [&ctx] (std::unique_ptr<request> req) {
+        auto keyspace = validate_keyspace(ctx, req->param);
+        auto view = req->param["view"];
+        return service::get_local_storage_service().view_build_statuses(std::move(keyspace), std::move(view)).then([] (std::unordered_map<sstring, sstring> status) {
+            std::vector<storage_service_json::mapper> res;
+            return make_ready_future<json::json_return_type>(map_to_key_value(std::move(status), res));
+        });
+    });
+
     ss::sstable_info.set(r, [&ctx] (std::unique_ptr<request> req) {
         auto ks = api::req_param<sstring>(*req, "keyspace", {}).value;
         auto cf = api::req_param<sstring>(*req, "cf", {}).value;
@@ -1098,7 +921,7 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
         using table_sstables_list = std::vector<ss::table_sstables>;
 
         return do_with(table_sstables_list{}, [ks, cf, &ctx](table_sstables_list& dst) {
-            return ctx.db.map_reduce([&dst](table_sstables_list&& res) {
+            return service::get_local_storage_service().db().map_reduce([&dst](table_sstables_list&& res) {
                 for (auto&& t : res) {
                     auto i = std::find_if(dst.begin(), dst.end(), [&t](const ss::table_sstables& t2) {
                         return t.keyspace() == t2.keyspace() && t.table() == t2.table();
@@ -1131,7 +954,7 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
                         tst.keyspace = schema->ks_name();
                         tst.table = schema->cf_name();
 
-                        for (auto sstables = t->get_sstables_including_compacted_undeleted(); auto sstable : *sstables) {
+                        for (auto sstable : *t->get_sstables_including_compacted_undeleted()) {
                             auto ts = db_clock::to_time_t(sstable->data_file_write_time());
                             ::tm t;
                             ::gmtime_r(&ts, &t);
@@ -1214,6 +1037,7 @@ void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_
             });
         });
     });
+
 }
 
 void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl) {
@@ -1255,17 +1079,14 @@ void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_
     });
 
     ss::take_snapshot.set(r, [&snap_ctl](std::unique_ptr<request> req) {
-        apilog.debug("take_snapshot: {}", req->query_parameters);
         auto tag = req->get_query_param("tag");
         auto column_families = split(req->get_query_param("cf"), ",");
-        auto sfopt = req->get_query_param("sf");
-        auto sf = db::snapshot_ctl::skip_flush(strcasecmp(sfopt.c_str(), "true") == 0);
 
         std::vector<sstring> keynames = split(req->get_query_param("kn"), ",");
 
         auto resp = make_ready_future<>();
         if (column_families.empty()) {
-            resp = snap_ctl.local().take_snapshot(tag, keynames, sf);
+            resp = snap_ctl.local().take_snapshot(tag, keynames);
         } else {
             if (keynames.empty()) {
                 throw httpd::bad_param_exception("The keyspace of column families must be specified");
@@ -1273,7 +1094,7 @@ void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_
             if (keynames.size() > 1) {
                 throw httpd::bad_param_exception("Only one keyspace allowed when specifying a column family");
             }
-            resp = snap_ctl.local().take_column_family_snapshot(keynames[0], column_families, tag, sf);
+            resp = snap_ctl.local().take_column_family_snapshot(keynames[0], column_families, tag);
         }
         return resp.then([] {
             return make_ready_future<json::json_return_type>(json_void());
@@ -1297,28 +1118,7 @@ void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_
     });
 
     ss::scrub.set(r, wrap_ks_cf(ctx, [&snap_ctl] (http_context& ctx, std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
-        auto scrub_mode = sstables::compaction_type_options::scrub::mode::abort;
-
-        const sstring scrub_mode_str = req_param<sstring>(*req, "scrub_mode", "");
-        if (scrub_mode_str == "") {
-            const auto skip_corrupted = req_param<bool>(*req, "skip_corrupted", false);
-
-            if (skip_corrupted) {
-                scrub_mode = sstables::compaction_type_options::scrub::mode::skip;
-            }
-        } else {
-            if (scrub_mode_str == "ABORT") {
-                scrub_mode = sstables::compaction_type_options::scrub::mode::abort;
-            } else if (scrub_mode_str == "SKIP") {
-                scrub_mode = sstables::compaction_type_options::scrub::mode::skip;
-            } else if (scrub_mode_str == "SEGREGATE") {
-                scrub_mode = sstables::compaction_type_options::scrub::mode::segregate;
-            } else if (scrub_mode_str == "VALIDATE") {
-                scrub_mode = sstables::compaction_type_options::scrub::mode::validate;
-            } else {
-                throw std::invalid_argument(fmt::format("Unknown argument for 'scrub_mode' parameter: {}", scrub_mode_str));
-            }
-        }
+        const auto skip_corrupted = req_param<bool>(*req, "skip_corrupted", false);
 
         auto f = make_ready_future<>();
         if (!req_param<bool>(*req, "disable_snapshot", false)) {
@@ -1328,12 +1128,12 @@ void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_
             });
         }
 
-        return f.then([&ctx, keyspace, column_families, scrub_mode] {
+        return f.then([&ctx, keyspace, column_families, skip_corrupted] {
             return ctx.db.invoke_on_all([=] (database& db) {
                 return do_for_each(column_families, [=, &db](sstring cfname) {
                     auto& cm = db.get_compaction_manager();
                     auto& cf = db.find_column_family(keyspace, cfname);
-                    return cm.perform_sstable_scrub(&cf, scrub_mode);
+                    return cm.perform_sstable_scrub(&cf, skip_corrupted);
                 });
             });
         }).then([]{

api/storage_service.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -23,35 +23,16 @@
 
 #include <seastar/core/sharded.hh>
 #include "api.hh"
-#include "db/data_listeners.hh"
 
 namespace cql_transport { class controller; }
 class thrift_controller;
-namespace db {
-class snapshot_ctl;
-namespace view {
-class view_builder;
-}
-}
+namespace db { class snapshot_ctl; }
 namespace netw { class messaging_service; }
-class repair_service;
-namespace cdc { class generation_service; }
-class sstables_loader;
-
-namespace gms {
-
-class gossiper;
-
-}
 
 namespace api {
 
-void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_service>& ss, gms::gossiper& g, sharded<cdc::generation_service>& cdc_gs);
-void set_sstables_loader(http_context& ctx, routes& r, sharded<sstables_loader>& sst_loader);
-void unset_sstables_loader(http_context& ctx, routes& r);
-void set_view_builder(http_context& ctx, routes& r, sharded<db::view::view_builder>& vb);
-void unset_view_builder(http_context& ctx, routes& r);
-void set_repair(http_context& ctx, routes& r, sharded<repair_service>& repair);
+void set_storage_service(http_context& ctx, routes& r);
+void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
 void unset_repair(http_context& ctx, routes& r);
 void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl);
 void unset_transport_controller(http_context& ctx, routes& r);
@@ -59,6 +40,5 @@ void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl);
 void unset_rpc_controller(http_context& ctx, routes& r);
 void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl);
 void unset_snapshot(http_context& ctx, routes& r);
-seastar::future<json::json_return_type> run_toppartitions_query(db::toppartitions_query& q, http_context &ctx, bool legacy_request = false);
 
 }

api/stream_manager.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/stream_manager.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

api/system.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -25,9 +25,6 @@
 #include <seastar/core/reactor.hh>
 #include <seastar/http/exception.hh>
 #include "log.hh"
-#include "database.hh"
-
-extern logging::logger apilog;
 
 namespace api {
 
@@ -73,16 +70,6 @@ void set_system(http_context& ctx, routes& r) {
         }
         return json::json_void();
     });
-
-    hs::drop_sstable_caches.set(r, [&ctx](std::unique_ptr<request> req) {
-        apilog.info("Dropping sstable caches");
-        return ctx.db.invoke_on_all([] (database& db) {
-            return db.drop_caches();
-        }).then([] {
-            apilog.info("Caches dropped");
-            return json::json_return_type(json::json_void());
-        });
-    });
 }
 
 }

api/system.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*

atomic_cell.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
  */
 
 /*
@@ -24,125 +24,142 @@
 #include "counters.hh"
 #include "types.hh"
 
+/// LSA mirator for cells with irrelevant type
+///
+///
+const data::type_imr_descriptor& no_type_imr_descriptor() {
+    static thread_local data::type_imr_descriptor state(data::type_info::make_variable_size());
+    return state;
+}
+
 atomic_cell atomic_cell::make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
-    return atomic_cell_type::make_dead(timestamp, deletion_time);
+    auto& imr_data = no_type_imr_descriptor();
+    return atomic_cell(
+            imr_data.type_info(),
+            imr_object_type::make(data::cell::make_dead(timestamp, deletion_time), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, single_fragment_range(value));
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, managed_bytes_view value, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, fragment_range(value));
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, value);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value, collection_member cm)
 {
-    return atomic_cell_type::make_live(timestamp, value);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
                              gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, single_fragment_range(value), expiry, ttl);
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, managed_bytes_view value,
-                             gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, fragment_range(value), expiry, ttl);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
                              gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
                                    gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm)
 {
-    return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
-    return atomic_cell_type::make_live_counter_update(timestamp, value);
+    auto& imr_data = no_type_imr_descriptor();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live_counter_update(timestamp, value), &imr_data.lsa_migrator())
+    );
 }
 
 atomic_cell atomic_cell::make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size) {
-    return atomic_cell_type::make_live_uninitialized(timestamp, size);
+    auto& imr_data = no_type_imr_descriptor();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live_uninitialized(imr_data.type_info(), timestamp, size), &imr_data.lsa_migrator())
+    );
+}
+
+static imr::utils::object<data::cell::structure> copy_cell(const data::type_imr_descriptor& imr_data, const uint8_t* ptr)
+{
+    using imr_object_type = imr::utils::object<data::cell::structure>;
+
+    // If the cell doesn't own any memory it is trivial and can be copied with
+    // memcpy.
+    auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
+    if (!f.template get<data::cell::tags::external_data>()) {
+        data::cell::context ctx(f, imr_data.type_info());
+        // XXX: We may be better off storing the total cell size in memory. Measure!
+        auto size = data::cell::structure::serialized_object_size(ptr, ctx);
+        return imr_object_type::make_raw(size, [&] (uint8_t* dst) noexcept {
+            std::copy_n(ptr, size, dst);
+        }, &imr_data.lsa_migrator());
+    }
+
+    return imr_object_type::make(data::cell::copy_fn(imr_data.type_info(), ptr), &imr_data.lsa_migrator());
 }
 
 atomic_cell::atomic_cell(const abstract_type& type, atomic_cell_view other)
-    : _data(other._view) {
-    set_view(_data);
-}
-
-// Based on:
-//  - org.apache.cassandra.db.AbstractCell#reconcile()
-//  - org.apache.cassandra.db.BufferExpiringCell#reconcile()
-//  - org.apache.cassandra.db.BufferDeletedCell#reconcile()
-std::strong_ordering
-compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right) {
-    if (left.timestamp() != right.timestamp()) {
-        return left.timestamp() <=> right.timestamp();
-    }
-    if (left.is_live() != right.is_live()) {
-        return left.is_live() ? std::strong_ordering::less : std::strong_ordering::greater;
-    }
-    if (left.is_live()) {
-        auto c = compare_unsigned(left.value(), right.value()) <=> 0;
-        if (c != 0) {
-            return c;
-        }
-        if (left.is_live_and_has_ttl() != right.is_live_and_has_ttl()) {
-            // prefer expiring cells.
-            return left.is_live_and_has_ttl() ? std::strong_ordering::greater : std::strong_ordering::less;
-        }
-        if (left.is_live_and_has_ttl()) {
-            if (left.expiry() != right.expiry()) {
-                return left.expiry() <=> right.expiry();
-            } else {
-                // prefer the cell that was written later,
-                // so it survives longer after it expires, until purged.
-                return right.ttl() <=> left.ttl();
-            }
-        }
-    } else {
-        // Both are deleted
-
-        // Origin compares big-endian serialized deletion time. That's because it
-        // delegates to AbstractCell.reconcile() which compares values after
-        // comparing timestamps, which in case of deleted cells will hold
-        // serialized expiry.
-        return (uint64_t) left.deletion_time().time_since_epoch().count()
-                <=> (uint64_t) right.deletion_time().time_since_epoch().count();
-    }
-    return std::strong_ordering::equal;
-}
+    : atomic_cell(type.imr_state().type_info(),
+                  copy_cell(type.imr_state(), other._view.raw_pointer()))
+{ }
 
 atomic_cell_or_collection atomic_cell_or_collection::copy(const abstract_type& type) const {
-    if (_data.empty()) {
+    if (!_data.get()) {
         return atomic_cell_or_collection();
     }
-    return atomic_cell_or_collection(managed_bytes(_data));
+    auto& imr_data = type.imr_state();
+    return atomic_cell_or_collection(
+        copy_cell(imr_data, _data.get())
+    );
 }
 
 atomic_cell_or_collection::atomic_cell_or_collection(const abstract_type& type, atomic_cell_view acv)
-    : _data(acv._view)
+    : _data(copy_cell(type.imr_state(), acv._view.raw_pointer()))
 {
 }
 
 bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_cell_or_collection& other) const
 {
-    if (_data.empty() || other._data.empty()) {
-        return _data.empty() && other._data.empty();
+    auto ptr_a = _data.get();
+    auto ptr_b = other._data.get();
+
+    if (!ptr_a || !ptr_b) {
+        return !ptr_a && !ptr_b;
     }
 
     if (type.is_atomic()) {
-        auto a = atomic_cell_view::from_bytes(type, _data);
-        auto b = atomic_cell_view::from_bytes(type, other._data);
+        auto a = atomic_cell_view::from_bytes(type.imr_state().type_info(), _data);
+        auto b = atomic_cell_view::from_bytes(type.imr_state().type_info(), other._data);
         if (a.timestamp() != b.timestamp()) {
             return false;
         }
@@ -174,24 +191,44 @@ bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_c
 
 size_t atomic_cell_or_collection::external_memory_usage(const abstract_type& t) const
 {
-    return _data.external_memory_usage();
+    if (!_data.get()) {
+        return 0;
+    }
+    auto ctx = data::cell::context(_data.get(), t.imr_state().type_info());
+
+    auto view = data::cell::structure::make_view(_data.get(), ctx);
+    auto flags = view.get<data::cell::tags::flags>();
+
+    size_t external_value_size = 0;
+    if (flags.get<data::cell::tags::external_data>()) {
+        if (flags.get<data::cell::tags::collection>()) {
+            external_value_size = as_collection_mutation().data.size_bytes();
+        } else {
+            auto cell_view = data::cell::atomic_cell_view(t.imr_state().type_info(), view);
+            external_value_size = cell_view.value_size();
+        }
+        // Add overhead of chunk headers. The last one is a special case.
+        external_value_size += (external_value_size - 1) / data::cell::effective_external_chunk_length * data::cell::external_chunk_overhead;
+        external_value_size += data::cell::external_last_chunk_overhead;
+    }
+    return data::cell::structure::serialized_object_size(_data.get(), ctx)
+        + imr_object_type::size_overhead + external_value_size;
 }
 
 std::ostream&
 operator<<(std::ostream& os, const atomic_cell_view& acv) {
     if (acv.is_live()) {
-        fmt::print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
+        return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
             acv.is_counter_update()
                     ? "counter_update_value=" + to_sstring(acv.counter_update_value())
-                    : to_hex(to_bytes(acv.value())),
+                    : to_hex(acv.value().linearize()),
             acv.timestamp(),
             acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
             acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
     } else {
-        fmt::print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
+        return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
             acv.timestamp(), acv.deletion_time().time_since_epoch().count());
     }
-    return os;
 }
 
 std::ostream&
@@ -210,22 +247,22 @@ operator<<(std::ostream& os, const atomic_cell_view::printer& acvp) {
                 cell_value_string_builder << "counter_update_value=" << acv.counter_update_value();
             } else {
                 cell_value_string_builder << "shards: ";
-                auto ccv = counter_cell_view(acv);
-                cell_value_string_builder << ::join(", ", ccv.shards());
+                counter_cell_view::with_linearized(acv, [&cell_value_string_builder] (counter_cell_view& ccv) {
+                    cell_value_string_builder << ::join(", ", ccv.shards());
+                });
             }
         } else {
-            cell_value_string_builder << type.to_string(to_bytes(acv.value()));
+            cell_value_string_builder << type.to_string(acv.value().linearize());
         }
-        fmt::print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
+        return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
             cell_value_string_builder.str(),
             acv.timestamp(),
             acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
             acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
     } else {
-        fmt::print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
+        return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
             acv.timestamp(), acv.deletion_time().time_since_epoch().count());
     }
-    return os;
 }
 
 std::ostream&
@@ -234,11 +271,12 @@ operator<<(std::ostream& os, const atomic_cell::printer& acp) {
 }
 
 std::ostream& operator<<(std::ostream& os, const atomic_cell_or_collection::printer& p) {
-    if (p._cell._data.empty()) {
+    if (!p._cell._data.get()) {
         return os << "{ null atomic_cell_or_collection }";
     }
+    using dc = data::cell;
     os << "{ ";
-    if (p._cdef.type->is_multi_cell()) {
+    if (dc::structure::get_member<dc::tags::flags>(p._cell._data.get()).get<dc::tags::collection>()) {
         os << "collection ";
         auto cmv = p._cell.as_collection_mutation();
         os << collection_mutation_view::printer(*p._cdef.type, cmv);

atomic_cell.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -27,10 +27,11 @@
 #include "gc_clock.hh"
 #include "utils/managed_bytes.hh"
 #include <seastar/net//byteorder.hh>
-#include <seastar/util/bool_class.hh>
 #include <cstdint>
 #include <iosfwd>
-#include <concepts>
+#include "data/cell.hh"
+#include "data/schema_info.hh"
+#include "imr/utils.hh"
 #include "utils/fragmented_temporary_buffer.hh"
 
 #include "serializer.hh"
@@ -39,191 +40,41 @@ class abstract_type;
 class collection_type_impl;
 class atomic_cell_or_collection;
 
-using atomic_cell_value = managed_bytes;
-template <mutable_view is_mutable>
-using atomic_cell_value_basic_view = managed_bytes_basic_view<is_mutable>;
-using atomic_cell_value_view = atomic_cell_value_basic_view<mutable_view::no>;
-using atomic_cell_value_mutable_view = atomic_cell_value_basic_view<mutable_view::yes>;
-
-template <typename T>
-requires std::is_trivial_v<T>
-static void set_field(atomic_cell_value_mutable_view& out, unsigned offset, T val) {
-    auto out_view = managed_bytes_mutable_view(out);
-    out_view.remove_prefix(offset);
-    write<T>(out_view, val);
-}
-
-template <typename T>
-requires std::is_trivial_v<T>
-static void set_field(atomic_cell_value& out, unsigned offset, T val) {
-    auto out_view = atomic_cell_value_mutable_view(out);
-    set_field(out_view, offset, val);
-}
-
-template <FragmentRange Buffer>
-static void set_value(managed_bytes& b, unsigned value_offset, const Buffer& value) {
-    auto v = managed_bytes_mutable_view(b).substr(value_offset, value.size_bytes());
-    for (auto frag : value) {
-        write_fragmented(v, single_fragmented_view(frag));
-    }
-}
-
-template <typename T, FragmentedView Input>
-requires std::is_trivial_v<T>
-static T get_field(Input in, unsigned offset = 0) {
-    in.remove_prefix(offset);
-    return read_simple<T>(in);
-}
-
-/*
- * Represents atomic cell layout. Works on serialized form.
- *
- * Layout:
- *
- *  <live>  := <int8_t:flags><int64_t:timestamp>(<int64_t:expiry><int32_t:ttl>)?<value>
- *  <dead>  := <int8_t:    0><int64_t:timestamp><int64_t:deletion_time>
- */
-class atomic_cell_type final {
-private:
-    static constexpr int8_t LIVE_FLAG = 0x01;
-    static constexpr int8_t EXPIRY_FLAG = 0x02; // When present, expiry field is present. Set only for live cells
-    static constexpr int8_t COUNTER_UPDATE_FLAG = 0x08; // Cell is a counter update.
-    static constexpr unsigned flags_size = 1;
-    static constexpr unsigned timestamp_offset = flags_size;
-    static constexpr unsigned timestamp_size = 8;
-    static constexpr unsigned expiry_offset = timestamp_offset + timestamp_size;
-    static constexpr unsigned expiry_size = 8;
-    static constexpr unsigned deletion_time_offset = timestamp_offset + timestamp_size;
-    static constexpr unsigned deletion_time_size = 8;
-    static constexpr unsigned ttl_offset = expiry_offset + expiry_size;
-    static constexpr unsigned ttl_size = 4;
-    friend class counter_cell_builder;
-private:
-    static bool is_counter_update(atomic_cell_value_view cell) {
-        return cell.front() & COUNTER_UPDATE_FLAG;
-    }
-    static bool is_live(atomic_cell_value_view cell) {
-        return cell.front() & LIVE_FLAG;
-    }
-    static bool is_live_and_has_ttl(atomic_cell_value_view cell) {
-        return cell.front() & EXPIRY_FLAG;
-    }
-    static bool is_dead(atomic_cell_value_view cell) {
-        return !is_live(cell);
-    }
-    // Can be called on live and dead cells
-    static api::timestamp_type timestamp(atomic_cell_value_view cell) {
-        return get_field<api::timestamp_type>(cell, timestamp_offset);
-    }
-    static void set_timestamp(atomic_cell_value_mutable_view& cell, api::timestamp_type ts) {
-        set_field(cell, timestamp_offset, ts);
-    }
-    // Can be called on live cells only
-private:
-    template <mutable_view is_mutable>
-    static managed_bytes_basic_view<is_mutable> do_get_value(managed_bytes_basic_view<is_mutable> cell) {
-        auto expiry_field_size = bool(cell.front() & EXPIRY_FLAG) * (expiry_size + ttl_size);
-        auto value_offset = flags_size + timestamp_size + expiry_field_size;
-        cell.remove_prefix(value_offset);
-        return cell;
-    }
-public:
-    static atomic_cell_value_view value(managed_bytes_view cell) {
-        return do_get_value(cell);
-    }
-    static atomic_cell_value_mutable_view value(managed_bytes_mutable_view cell) {
-        return do_get_value(cell);
-    }
-    // Can be called on live counter update cells only
-    static int64_t counter_update_value(atomic_cell_value_view cell) {
-        return get_field<int64_t>(cell, flags_size + timestamp_size);
-    }
-    // Can be called only when is_dead() is true.
-    static gc_clock::time_point deletion_time(atomic_cell_value_view cell) {
-        assert(is_dead(cell));
-        return gc_clock::time_point(gc_clock::duration(get_field<int64_t>(cell, deletion_time_offset)));
-    }
-    // Can be called only when is_live_and_has_ttl() is true.
-    static gc_clock::time_point expiry(atomic_cell_value_view cell) {
-        assert(is_live_and_has_ttl(cell));
-        auto expiry = get_field<int64_t>(cell, expiry_offset);
-        return gc_clock::time_point(gc_clock::duration(expiry));
-    }
-    // Can be called only when is_live_and_has_ttl() is true.
-    static gc_clock::duration ttl(atomic_cell_value_view cell) {
-        assert(is_live_and_has_ttl(cell));
-        return gc_clock::duration(get_field<int32_t>(cell, ttl_offset));
-    }
-    static managed_bytes make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
-        managed_bytes b(managed_bytes::initialized_later(), flags_size + timestamp_size + deletion_time_size);
-        b[0] = 0;
-        set_field(b, timestamp_offset, timestamp);
-        set_field(b, deletion_time_offset, static_cast<int64_t>(deletion_time.time_since_epoch().count()));
-        return b;
-    }
-    template <FragmentRange Buffer>
-    static managed_bytes make_live(api::timestamp_type timestamp, const Buffer& value) {
-        auto value_offset = flags_size + timestamp_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size_bytes());
-        b[0] = LIVE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        set_value(b, value_offset, value);
-        return b;
-    }
-    static managed_bytes make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
-        auto value_offset = flags_size + timestamp_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + sizeof(value));
-        b[0] = LIVE_FLAG | COUNTER_UPDATE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        set_field(b, value_offset, value);
-        return b;
-    }
-    template <FragmentRange Buffer>
-    static managed_bytes make_live(api::timestamp_type timestamp, const Buffer& value, gc_clock::time_point expiry, gc_clock::duration ttl) {
-        auto value_offset = flags_size + timestamp_size + expiry_size + ttl_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size_bytes());
-        b[0] = EXPIRY_FLAG | LIVE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        set_field(b, expiry_offset, static_cast<int64_t>(expiry.time_since_epoch().count()));
-        set_field(b, ttl_offset, static_cast<int32_t>(ttl.count()));
-        set_value(b, value_offset, value);
-        return b;
-    }
-    static managed_bytes make_live_uninitialized(api::timestamp_type timestamp, size_t size) {
-        auto value_offset = flags_size + timestamp_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + size);
-        b[0] = LIVE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        return b;
-    }
-    template <mutable_view is_mutable>
-    friend class basic_atomic_cell_view;
-    friend class atomic_cell;
-};
+using atomic_cell_value_view = data::value_view;
+using atomic_cell_value_mutable_view = data::value_mutable_view;
 
 /// View of an atomic cell
 template<mutable_view is_mutable>
 class basic_atomic_cell_view {
 protected:
-    managed_bytes_basic_view<is_mutable> _view;
-	friend class atomic_cell;
+    data::cell::basic_atomic_cell_view<is_mutable> _view;
+    friend class atomic_cell;
+public:
+    using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const uint8_t*, uint8_t*>;
 protected:
-    void set_view(managed_bytes_basic_view<is_mutable> v) {
-        _view = v;
-    }
-    basic_atomic_cell_view() = default;
-    explicit basic_atomic_cell_view(managed_bytes_basic_view<is_mutable> v) : _view(std::move(v)) { }
+    explicit basic_atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> v)
+        : _view(std::move(v)) { }
+
+    basic_atomic_cell_view(const data::type_info& ti, pointer_type ptr)
+        : _view(data::cell::make_atomic_cell_view(ti, ptr))
+    { }
+
     friend class atomic_cell_or_collection;
 public:
     operator basic_atomic_cell_view<mutable_view::no>() const noexcept {
         return basic_atomic_cell_view<mutable_view::no>(_view);
     }
 
+    void swap(basic_atomic_cell_view& other) noexcept {
+        using std::swap;
+        swap(_view, other._view);
+    }
+
     bool is_counter_update() const {
-        return atomic_cell_type::is_counter_update(_view);
+        return _view.is_counter_update();
     }
     bool is_live() const {
-        return atomic_cell_type::is_live(_view);
+        return _view.is_live();
     }
     bool is_live(tombstone t, bool is_counter) const {
         return is_live() && !is_covered_by(t, is_counter);
@@ -232,69 +83,73 @@ public:
         return is_live() && !is_covered_by(t, is_counter) && !has_expired(now);
     }
     bool is_live_and_has_ttl() const {
-        return atomic_cell_type::is_live_and_has_ttl(_view);
+        return _view.is_expiring();
     }
     bool is_dead(gc_clock::time_point now) const {
-        return atomic_cell_type::is_dead(_view) || has_expired(now);
+        return !is_live() || has_expired(now);
     }
     bool is_covered_by(tombstone t, bool is_counter) const {
         return timestamp() <= t.timestamp || (is_counter && t.timestamp != api::missing_timestamp);
     }
     // Can be called on live and dead cells
     api::timestamp_type timestamp() const {
-        return atomic_cell_type::timestamp(_view);
+        return _view.timestamp();
     }
     void set_timestamp(api::timestamp_type ts) {
-        atomic_cell_type::set_timestamp(_view, ts);
+        _view.set_timestamp(ts);
     }
     // Can be called on live cells only
-    atomic_cell_value_basic_view<is_mutable> value() const {
-        return atomic_cell_type::value(_view);
+    data::basic_value_view<is_mutable> value() const {
+        return _view.value();
     }
     // Can be called on live cells only
     size_t value_size() const {
-        return atomic_cell_type::value(_view).size();
+        return _view.value_size();
+    }
+    bool is_value_fragmented() const {
+        return _view.is_value_fragmented();
     }
     // Can be called on live counter update cells only
     int64_t counter_update_value() const {
-        return atomic_cell_type::counter_update_value(_view);
+        return _view.counter_update_value();
     }
     // Can be called only when is_dead(gc_clock::time_point)
     gc_clock::time_point deletion_time() const {
-        return !is_live() ? atomic_cell_type::deletion_time(_view) : expiry() - ttl();
+        return !is_live() ? _view.deletion_time() : expiry() - ttl();
     }
     // Can be called only when is_live_and_has_ttl()
     gc_clock::time_point expiry() const {
-        return atomic_cell_type::expiry(_view);
+        return _view.expiry();
     }
     // Can be called only when is_live_and_has_ttl()
     gc_clock::duration ttl() const {
-        return atomic_cell_type::ttl(_view);
+        return _view.ttl();
     }
     // Can be called on live and dead cells
     bool has_expired(gc_clock::time_point now) const {
         return is_live_and_has_ttl() && expiry() <= now;
     }
 
-    managed_bytes_view serialize() const {
-        return _view;
+    bytes_view serialize() const {
+        return _view.serialize();
     }
 };
 
 class atomic_cell_view final : public basic_atomic_cell_view<mutable_view::no> {
-    atomic_cell_view(managed_bytes_view v)
-        : basic_atomic_cell_view(v) {}
+    atomic_cell_view(const data::type_info& ti, const uint8_t* data)
+        : basic_atomic_cell_view<mutable_view::no>(ti, data) {}
 
     template<mutable_view is_mutable>
-    atomic_cell_view(basic_atomic_cell_view<is_mutable> view)
-        : basic_atomic_cell_view<mutable_view::no>(view) {}
+    atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> view)
+        : basic_atomic_cell_view<mutable_view::no>(view) { }
     friend class atomic_cell;
 public:
-    static atomic_cell_view from_bytes(const abstract_type& t, managed_bytes_view v) {
-        return atomic_cell_view(v);
+    static atomic_cell_view from_bytes(const data::type_info& ti, const imr::utils::object<data::cell::structure>& data) {
+        return atomic_cell_view(ti, data.get());
     }
-    static atomic_cell_view from_bytes(const abstract_type& t, bytes_view v) {
-        return atomic_cell_view(managed_bytes_view(v));
+
+    static atomic_cell_view from_bytes(const data::type_info& ti, bytes_view bv) {
+        return atomic_cell_view(ti, reinterpret_cast<const uint8_t*>(bv.begin()));
     }
 
     friend std::ostream& operator<<(std::ostream& os, const atomic_cell_view& acv);
@@ -309,11 +164,11 @@ public:
 };
 
 class atomic_cell_mutable_view final : public basic_atomic_cell_view<mutable_view::yes> {
-    atomic_cell_mutable_view(managed_bytes_mutable_view data)
-        : basic_atomic_cell_view(data) {}
+    atomic_cell_mutable_view(const data::type_info& ti, uint8_t* data)
+        : basic_atomic_cell_view<mutable_view::yes>(ti, data) {}
 public:
-    static atomic_cell_mutable_view from_bytes(const abstract_type& t, managed_bytes_mutable_view v) {
-        return atomic_cell_mutable_view(v);
+    static atomic_cell_mutable_view from_bytes(const data::type_info& ti, imr::utils::object<data::cell::structure>& data) {
+        return atomic_cell_mutable_view(ti, data.get());
     }
 
     friend class atomic_cell;
@@ -322,31 +177,26 @@ public:
 using atomic_cell_ref = atomic_cell_mutable_view;
 
 class atomic_cell final : public basic_atomic_cell_view<mutable_view::yes> {
-    managed_bytes _data;
-    atomic_cell(managed_bytes b) : _data(std::move(b))  {
-        set_view(_data);
-    }
-
+    using imr_object_type =  imr::utils::object<data::cell::structure>;
+    imr_object_type _data;
+    atomic_cell(const data::type_info& ti, imr::utils::object<data::cell::structure>&& data)
+        : basic_atomic_cell_view<mutable_view::yes>(ti, data.get()), _data(std::move(data)) {}
 public:
     class collection_member_tag;
     using collection_member = bool_class<collection_member_tag>;
 
-    atomic_cell(atomic_cell&& o) noexcept : _data(std::move(o._data)) {
-        set_view(_data);
-    }
+    atomic_cell(atomic_cell&&) = default;
     atomic_cell& operator=(const atomic_cell&) = delete;
-    atomic_cell& operator=(atomic_cell&& o) {
-        _data = std::move(o._data);
-        set_view(_data);
-        return *this;
+    atomic_cell& operator=(atomic_cell&&) = default;
+    void swap(atomic_cell& other) noexcept {
+        basic_atomic_cell_view<mutable_view::yes>::swap(other);
+        _data.swap(other._data);
     }
-    operator atomic_cell_view() const { return atomic_cell_view(managed_bytes_view(_data)); }
+    operator atomic_cell_view() const { return atomic_cell_view(_view); }
     atomic_cell(const abstract_type& t, atomic_cell_view other);
     static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time);
     static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
                                  collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, managed_bytes_view value,
-                                 collection_member = collection_member::no);
     static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
                                  collection_member = collection_member::no);
     static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
@@ -358,8 +208,6 @@ public:
     static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value);
     static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, bytes_view value,
         gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, managed_bytes_view value,
-        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
     static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
         gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
     static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
@@ -376,13 +224,6 @@ public:
             return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
         }
     }
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const managed_bytes_view& value, ttl_opt ttl, collection_member cm = collection_member::no) {
-        if (!ttl) {
-            return make_live(type, timestamp, value, cm);
-        } else {
-            return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
-        }
-    }
     static atomic_cell make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size);
     friend class atomic_cell_or_collection;
     friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
@@ -396,7 +237,7 @@ public:
 
 class column_definition;
 
-std::strong_ordering compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
+int compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
 void merge_column(const abstract_type& def,
         atomic_cell_or_collection& old,
         const atomic_cell_or_collection& neww);

atomic_cell_hash.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -52,7 +52,9 @@ struct appending_hash<atomic_cell_view> {
         feed_hash(h, cell.timestamp());
         if (cell.is_live()) {
             if (cdef.is_counter()) {
-                ::feed_hash(h, counter_cell_view(cell));
+                counter_cell_view::with_linearized(cell, [&] (counter_cell_view ccv) {
+                    ::feed_hash(h, ccv);
+                });
                 return;
             }
             if (cell.is_live_and_has_ttl()) {

atomic_cell_or_collection.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
@@ -24,15 +24,22 @@
 #include "atomic_cell.hh"
 #include "collection_mutation.hh"
 #include "schema.hh"
+#include "hashing.hh"
+
+#include "imr/utils.hh"
 
 // A variant type that can hold either an atomic_cell, or a serialized collection.
 // Which type is stored is determined by the schema.
-// Has an "empty" state.
-// Objects moved-from are left in an empty state.
 class atomic_cell_or_collection final {
-    managed_bytes _data;
+    // FIXME: This has made us lose small-buffer optimisation. Unfortunately,
+    // due to the changed cell format it would be less effective now, anyway.
+    // Measure the actual impact because any attempts to fix this will become
+    // irrelevant once rows are converted to the IMR as well, so maybe we can
+    // live with this like that.
+    using imr_object_type = imr::utils::object<data::cell::structure>;
+    imr_object_type _data;
 private:
-    atomic_cell_or_collection(managed_bytes&& data) : _data(std::move(data)) {}
+    atomic_cell_or_collection(imr::utils::object<data::cell::structure>&& data) : _data(std::move(data)) {}
 public:
     atomic_cell_or_collection() = default;
     atomic_cell_or_collection(atomic_cell_or_collection&&) = default;
@@ -42,16 +49,20 @@ public:
     atomic_cell_or_collection(atomic_cell ac) : _data(std::move(ac._data)) {}
     atomic_cell_or_collection(const abstract_type& at, atomic_cell_view acv);
     static atomic_cell_or_collection from_atomic_cell(atomic_cell data) { return { std::move(data._data) }; }
-    atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(*cdef.type, _data); }
-    atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(*cdef.type, _data); }
+    atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
+    atomic_cell_ref as_atomic_cell_ref(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
+    atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
     atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm._data)) { }
     atomic_cell_or_collection copy(const abstract_type&) const;
     explicit operator bool() const {
-        return !_data.empty();
+        return bool(_data);
     }
     static constexpr bool can_use_mutable_view() {
         return true;
     }
+    void swap(atomic_cell_or_collection& other) noexcept {
+        _data.swap(other._data);
+    }
     static atomic_cell_or_collection from_collection_mutation(collection_mutation data) { return std::move(data._data); }
     collection_mutation_view as_collection_mutation() const;
     bytes_view serialize() const;
@@ -71,3 +82,12 @@ public:
     };
     friend std::ostream& operator<<(std::ostream&, const printer&);
 };
+
+namespace std {
+
+inline void swap(atomic_cell_or_collection& a, atomic_cell_or_collection& b) noexcept
+{
+    a.swap(b);
+}
+
+}

auth/allow_all_authenticator.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
  */
 
 /*

auth/allow_all_authenticator.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
  */
 
 /*

auth/allow_all_authorizer.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
  */
 
 /*

auth/allow_all_authorizer.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
  */
 
 /*

auth/authenticated_user.cc

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
  *
  * Modified by ScyllaDB
  */

auth/authenticated_user.hh

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
  *
  * Modified by ScyllaDB
  */

auth/authentication_options.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
  */
 
 /*

auth/authentication_options.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
  */
 
 /*

auth/authenticator.cc

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
  *
  * Modified by ScyllaDB
  */

auth/authenticator.hh

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
  *
  * Modified by ScyllaDB
  */
@@ -47,6 +47,7 @@
 #include <stdexcept>
 #include <unordered_map>
 
+#include <boost/any.hpp>
 #include <seastar/core/enum.hh>
 #include <seastar/core/future.hh>
 #include <seastar/core/sstring.hh>
@@ -74,8 +75,6 @@ class authenticated_user;
 ///
 class authenticator {
 public:
-    using ptr_type = std::unique_ptr<authenticator>;
-
     ///
     /// The name of the key to be used for the user-name part of password authentication with \ref authenticate.
     ///

auth/authorizer.hh

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
  *
  * Modified by ScyllaDB
  */
@@ -91,8 +91,6 @@ public:
 ///
 class authorizer {
 public:
-    using ptr_type = std::unique_ptr<authorizer>;
-
     virtual ~authorizer() = default;
 
     virtual future<> start() = 0;

auth/common.cc

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
  */
 
 /*
@@ -45,13 +45,15 @@ static logging::logger auth_log("auth");
 // Func must support being invoked more than once.
 future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func) {
     struct empty_state { };
-    return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
-        return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
-            if (f.failed()) {
-                auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
-                return { };
-            }
-            return { empty_state() };
+    return delay_until_system_ready(as).then([&as, func = std::move(func)] () mutable {
+        return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
+            return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
+                if (f.failed()) {
+                    auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
+                    return { };
+                }
+                return { empty_state() };
+            });
         });
     }).discard_result();
 }
@@ -80,7 +82,7 @@ static future<> create_metadata_table_if_missing_impl(
     b.set_uuid(uuid);
     schema_ptr table = b.build();
     return ignore_existing([&mm, table = std::move(table)] () {
-        return mm.announce_new_column_family(table);
+        return mm.announce_new_column_family(table, false);
     });
 }
 
@@ -106,7 +108,7 @@ future<> wait_for_schema_agreement(::service::migration_manager& mm, const datab
     });
 }
 
-::service::query_state& internal_distributed_query_state() noexcept {
+const timeout_config& internal_distributed_timeout_config() noexcept {
 #ifdef DEBUG
     // Give the much slower debug tests more headroom for completing auth queries.
     static const auto t = 30s;
@@ -114,9 +116,7 @@ future<> wait_for_schema_agreement(::service::migration_manager& mm, const datab
     static const auto t = 5s;
 #endif
     static const timeout_config tc{t, t, t, t, t, t, t};
-    static thread_local ::service::client_state cs(::service::client_state::internal_tag{}, tc);
-    static thread_local ::service::query_state qs(cs, empty_service_permit());
-    return qs;
+    return tc;
 }
 
 }

auth/common.hh

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
  */
 
 /*
@@ -35,7 +35,6 @@
 #include "log.hh"
 #include "seastarx.hh"
 #include "utils/exponential_backoff_retry.hh"
-#include "service/query_state.hh"
 
 using namespace std::chrono_literals;
 
@@ -70,6 +69,10 @@ future<> once_among_shards(Task&& f) {
     return make_ready_future<>();
 }
 
+inline future<> delay_until_system_ready(seastar::abort_source& as) {
+    return sleep_abortable(15s, as);
+}
+
 // Func must support being invoked more than once.
 future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func);
 
@@ -84,6 +87,6 @@ future<> wait_for_schema_agreement(::service::migration_manager&, const database
 ///
 /// Time-outs for internal, non-local CQL queries.
 ///
-::service::query_state& internal_distributed_query_state() noexcept;
+const timeout_config& internal_distributed_timeout_config() noexcept;
 
 }

auth/default_authorizer.cc

@@ -17,7 +17,7 @@
  */
 
 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
  *
  * Modified by ScyllaDB
  */
@@ -62,7 +62,6 @@ extern "C" {
 #include "exceptions/exceptions.hh"
 #include "log.hh"
 #include "database.hh"
-#include "utils/class_registrator.hh"
 
 namespace auth {
 
@@ -104,6 +103,7 @@ future<bool> default_authorizer::any_granted() const {
     return _qp.execute_internal(
             query,
             db::consistency_level::LOCAL_ONE,
+            infinite_timeout_config,
             {},
             true).then([this](::shared_ptr<cql3::untyped_result_set> results) {
         return !results->empty();
@@ -116,7 +116,8 @@ future<> default_authorizer::migrate_legacy_metadata() const {
 
     return _qp.execute_internal(
             query,
-            db::consistency_level::LOCAL_ONE).then([this](::shared_ptr<cql3::untyped_result_set> results) {
+            db::consistency_level::LOCAL_ONE,
+            infinite_timeout_config).then([this](::shared_ptr<cql3::untyped_result_set> results) {
         return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
             return do_with(
                     row.get_as<sstring>("username"),
@@ -135,13 +136,13 @@ future<> default_authorizer::migrate_legacy_metadata() const {
 }
 
 future<> default_authorizer::start() {
-    static const sstring create_table = fmt::format(
-            "CREATE TABLE {}.{} ("
-            "{} text,"
-            "{} text,"
-            "{} set<text>,"
-            "PRIMARY KEY({}, {})"
-            ") WITH gc_grace_seconds={}",
+    static const sstring create_table = sprint(
+            "CREATE TABLE %s.%s ("
+            "%s text,"
+            "%s text,"
+            "%s set<text>,"
+            "PRIMARY KEY(%s, %s)"
+            ") WITH gc_grace_seconds=%d",
             meta::AUTH_KS,
             PERMISSIONS_CF,
             ROLE_NAME,
@@ -196,6 +197,7 @@ default_authorizer::authorize(const role_or_anonymous& maybe_role, const resourc
     return _qp.execute_internal(
             query,
             db::consistency_level::LOCAL_ONE,
+            infinite_timeout_config,
             {*maybe_role.name, r.name()}).then([](::shared_ptr<cql3::untyped_result_set> results) {
         if (results->empty()) {
             return permissions::NONE;
@@ -224,7 +226,7 @@ default_authorizer::modify(
         return _qp.execute_internal(
                 query,
                 db::consistency_level::ONE,
-                internal_distributed_query_state(),
+                internal_distributed_timeout_config(),
                 {permissions::to_strings(set), sstring(role_name), resource.name()}).discard_result();
     });
 }
@@ -249,7 +251,7 @@ future<std::vector<permission_details>> default_authorizer::list_all() const {
     return _qp.execute_internal(
             query,
             db::consistency_level::ONE,
-            internal_distributed_query_state(),
+            internal_distributed_timeout_config(),
             {},
             true).then([](::shared_ptr<cql3::untyped_result_set> results) {
         std::vector<permission_details> all_details;
@@ -276,7 +278,7 @@ future<> default_authorizer::revoke_all(std::string_view role_name) const {
     return _qp.execute_internal(
             query,
             db::consistency_level::ONE,
-            internal_distributed_query_state(),
+            internal_distributed_timeout_config(),
             {sstring(role_name)}).discard_result().handle_exception([role_name](auto ep) {
         try {
             std::rethrow_exception(ep);
@@ -296,6 +298,7 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
     return _qp.execute_internal(
             query,
             db::consistency_level::LOCAL_ONE,
+            infinite_timeout_config,
             {resource.name()}).then_wrapped([this, resource](future<::shared_ptr<cql3::untyped_result_set>> f) {
         try {
             auto res = f.get0();
@@ -312,6 +315,7 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
                 return _qp.execute_internal(
                         query,
                         db::consistency_level::LOCAL_ONE,
+                        infinite_timeout_config,
                         {r.get_as<sstring>(ROLE_NAME), resource.name()}).discard_result().handle_exception(
                                 [resource](auto ep) {
                     try {