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)

.gitattributes

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

.github/CODEOWNERS

@@ -2,52 +2,48 @@
 auth/* @elcallio @vladzcloudius
 
 # CACHE
-row_cache* @tgrabiec
-*mutation* @tgrabiec
-test/boost/mvcc* @tgrabiec
+row_cache* @tgrabiec @haaawk
+*mutation* @tgrabiec @haaawk
+tests/mvcc* @tgrabiec @haaawk
 
 # CDC
-cdc/* @kbr- @elcallio @piodul @jul-stas
-test/cql/cdc_* @kbr- @elcallio @piodul @jul-stas
-test/boost/cdc_* @kbr- @elcallio @piodul @jul-stas
+cdc/* @haaawk @kbr- @elcallio @piodul @jul-stas
+test/cql/cdc_* @haaawk @kbr- @elcallio @piodul @jul-stas
+test/boost/cdc_* @haaawk @kbr- @elcallio @piodul @jul-stas
 
 # COMMITLOG / BATCHLOG
-db/commitlog/* @elcallio @eliransin
+db/commitlog/* @elcallio
 db/batch* @elcallio
 
 # COORDINATOR
 service/storage_proxy* @gleb-cloudius
 
 # COMPACTION
-compaction/* @raphaelsc @nyh
+sstables/compaction* @raphaelsc @nyh
 
 # CQL TRANSPORT LAYER
-transport/*
+transport/* @penberg
 
 # CQL QUERY LANGUAGE
-cql3/* @tgrabiec @cvybhu @nyh
+cql3/* @tgrabiec @penberg @psarna
 
 # COUNTERS
-counters* @jul-stas
-tests/counter_test* @jul-stas
-
-# DOCS
-docs/* @annastuchlik @tzach
-docs/alternator @annastuchlik @tzach @nyh @havaker @nuivall
+counters* @haaawk @jul-stas
+tests/counter_test* @haaawk @jul-stas
 
 # GOSSIP
 gms/* @tgrabiec @asias
 
 # DOCKER
-dist/docker/*
+dist/docker/* @penberg
 
 # LSA
 utils/logalloc* @tgrabiec
 
 # MATERIALIZED VIEWS
-db/view/* @nyh @cvybhu @piodul
-cql3/statements/*view* @nyh @cvybhu @piodul
-test/boost/view_* @nyh @cvybhu @piodul
+db/view/* @nyh @psarna
+cql3/statements/*view* @nyh @psarna
+test/boost/view_* @nyh @psarna
 
 # PACKAGING
 dist/* @syuu1228
@@ -62,9 +58,9 @@ service/migration* @tgrabiec @nyh
 schema* @tgrabiec @nyh
 
 # SECONDARY INDEXES
-index/* @nyh @cvybhu @piodul
-cql3/statements/*index* @nyh @cvybhu @piodul
-test/boost/*index* @nyh @cvybhu @piodul
+db/index/* @nyh @penberg @psarna
+cql3/statements/*index* @nyh @penberg @psarna
+test/boost/*index* @nyh @penberg @psarna
 
 # SSTABLES
 sstables/* @tgrabiec @raphaelsc @nyh
@@ -74,28 +70,12 @@ streaming/* @tgrabiec @asias
 service/storage_service.* @tgrabiec @asias
 
 # ALTERNATOR
-alternator/* @nyh @havaker @nuivall
-test/alternator/* @nyh @havaker @nuivall
+alternator/* @nyh @psarna
+test/alternator/* @nyh @psarna
 
 # HINTED HANDOFF
-db/hints/* @piodul @vladzcloudius @eliransin
+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/scripts/label_promoted_commits.py

@@ -1,87 +0,0 @@
-from github import Github
-import argparse
-import re
-import sys
-import os
-
-try:
-    github_token = os.environ["GITHUB_TOKEN"]
-except KeyError:
-    print("Please set the 'GITHUB_TOKEN' environment variable")
-    sys.exit(1)
-
-
-def parser():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--repository', type=str, required=True,
-                        help='Github repository name (e.g., scylladb/scylladb)')
-    parser.add_argument('--commit_before_merge', type=str, required=True, help='Git commit ID to start labeling from ('
-                                                                               'newest commit).')
-    parser.add_argument('--commit_after_merge', type=str, required=True,
-                        help='Git commit ID to end labeling at (oldest '
-                             'commit, exclusive).')
-    parser.add_argument('--update_issue', type=bool, default=False, help='Set True to update issues when backport was '
-                                                                         'done')
-    parser.add_argument('--ref', type=str, required=True, help='PR target branch')
-    return parser.parse_args()
-
-
-def add_comment_and_close_pr(pr, comment):
-    if pr.state == 'open':
-        pr.create_issue_comment(comment)
-        pr.edit(state="closed")
-
-
-def mark_backport_done(repo, ref_pr_number, branch):
-    pr = repo.get_pull(int(ref_pr_number))
-    label_to_remove = f'backport/{branch}'
-    label_to_add = f'{label_to_remove}-done'
-    current_labels = [label.name for label in pr.get_labels()]
-    if label_to_remove in current_labels:
-        pr.remove_from_labels(label_to_remove)
-    if label_to_add not in current_labels:
-        pr.add_to_labels(label_to_add)
-
-
-def main():
-    # This script is triggered by a push event to either the master branch or a branch named branch-x.y (where x and y represent version numbers). Based on the pushed branch, the script performs the following actions:
-    # - When ref branch is `master`, it will add the `promoted-to-master` label, which we need later for the auto backport process
-    # - When ref branch is `branch-x.y` (which means we backported a patch), it will replace in the original PR the `backport/x.y` label with `backport/x.y-done` and will close the backport PR (Since GitHub close only the one referring to default branch)
-    args = parser()
-    pr_pattern = re.compile(r'Closes .*#([0-9]+)')
-    target_branch = re.search(r'branch-(\d+\.\d+)', args.ref)
-    g = Github(github_token)
-    repo = g.get_repo(args.repository, lazy=False)
-    commits = repo.compare(head=args.commit_after_merge, base=args.commit_before_merge)
-    processed_prs = set()
-    # Print commit information
-    for commit in commits.commits:
-        print(f'Commit sha is: {commit.sha}')
-        match = pr_pattern.search(commit.commit.message)
-        if match:
-            pr_number = int(match.group(1))
-            if pr_number in processed_prs:
-                continue
-            if target_branch:
-                pr = repo.get_pull(pr_number)
-                branch_name = target_branch[1]
-                refs_pr = re.findall(r'Refs (?:#|https.*?)(\d+)', pr.body)
-                if refs_pr:
-                    print(f'branch-{target_branch.group(1)}, pr number is: {pr_number}')
-                    # 1. change the backport label of the parent PR to note that
-                    #    we've merge the corresponding backport PR
-                    # 2. close the backport PR and leave a comment on it to note
-                    #    that it has been merged with a certain git commit,
-                    ref_pr_number = refs_pr[0]
-                    mark_backport_done(repo, ref_pr_number, branch_name)
-                    comment = f'Closed via {commit.sha}'
-                    add_comment_and_close_pr(pr, comment)
-            else:
-                print(f'master branch, pr number is: {pr_number}')
-                pr = repo.get_pull(pr_number)
-                pr.add_to_labels('promoted-to-master')
-            processed_prs.add(pr_number)
-
-
-if __name__ == "__main__":
-    main()

.github/workflows/add-label-when-promoted.yaml

@@ -1,36 +0,0 @@
-name: Check if commits are promoted
-
-on:
-  push:
-    branches:
-      - master
-      - branch-*.*
-
-env:
-  DEFAULT_BRANCH: 'master'
-
-jobs:
-  check-commit:
-    runs-on: ubuntu-latest
-    permissions:
-      pull-requests: write
-      issues: write
-    steps:
-      - name: Dump GitHub context
-        env:
-          GITHUB_CONTEXT: ${{ toJson(github) }}
-        run: echo "$GITHUB_CONTEXT"
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          repository: ${{ github.repository }}
-          ref: ${{ env.DEFAULT_BRANCH }}
-          fetch-depth: 0  # Fetch all history for all tags and branches
-
-      - name: Install dependencies
-        run: sudo apt-get install -y python3-github
-
-      - name: Run python script
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python .github/scripts/label_promoted_commits.py --commit_before_merge ${{ github.event.before }} --commit_after_merge ${{ github.event.after }} --repository ${{ github.repository }} --ref ${{ github.ref }}

.github/workflows/docs-amplify-enhanced.yaml

@@ -1,17 +0,0 @@
-name: "Docs / Amplify enhanced"
-
-on: issue_comment
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    if: ${{ github.event.issue.pull_request }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-      - name: Amplify enhanced
-        env:
-          TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        uses: scylladb/sphinx-scylladb-theme/.github/actions/amplify-enhanced@master

.github/workflows/docs-pages.yaml

@@ -1,40 +0,0 @@
-name: "Docs / Publish"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-
-on:
-  push:
-    branches:
-      - 'master'
-      - 'enterprise'
-    paths:
-      - "docs/**"
-  workflow_dispatch:
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v3
-        with:
-          python-version: 3.7
-      - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
-      - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" multiversion
-      - name: Build redirects
-        run: make -C docs FLAG="${{ env.FLAG }}" redirects
-      - name: Deploy docs to GitHub Pages
-        run: ./docs/_utils/deploy.sh
-        if: (github.ref_name == 'master' && env.FLAG == 'opensource') || (github.ref_name == 'enterprise' && env.FLAG == 'enterprise')
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/docs-pr.yaml

@@ -1,32 +0,0 @@
-name: "Docs / Build PR"
-# For more information,
-# see https://sphinx-theme.scylladb.com/stable/deployment/production.html#available-workflows
-
-env:
-  FLAG: ${{ github.repository == 'scylladb/scylla-enterprise' && 'enterprise' || 'opensource' }}
-
-on:
-  pull_request:
-    branches:
-      - master
-      - enterprise
-    paths:
-      - "docs/**"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - name: Set up Python
-        uses: actions/setup-python@v3
-        with:
-          python-version: 3.7
-      - name: Set up env
-        run: make -C docs FLAG="${{ env.FLAG }}" setupenv
-      - name: Build docs
-        run: make -C docs FLAG="${{ env.FLAG }}" test

.gitignore

@@ -22,11 +22,6 @@ resources
 .pytest_cache
 /expressions.tokens
 tags
-!db/tags/
 testlog
 test/*/*.reject
 .vscode
-compile_commands.json
-.ccls-cache/
-.mypy_cache
-.envrc

.gitmodules

@@ -6,6 +6,12 @@
 	path = swagger-ui
 	url = ../scylla-swagger-ui
 	ignore = dirty
+[submodule "libdeflate"]
+	path = libdeflate
+	url = ../libdeflate
+[submodule "abseil"]
+	path = abseil
+	url = ../abseil-cpp
 [submodule "scylla-jmx"]
 	path = tools/jmx
 	url = ../scylla-jmx
@@ -15,6 +21,3 @@
 [submodule "scylla-python3"]
 	path = tools/python3
 	url = ../scylla-python3
-[submodule "tools/cqlsh"]
-	path = tools/cqlsh
-	url = ../scylla-cqlsh

.mailmap

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

CMakeLists.txt

@@ -1,229 +1,157 @@
-cmake_minimum_required(VERSION 3.27)
+##
+## For best results, first compile the project using the Ninja build-system.
+##
 
+cmake_minimum_required(VERSION 3.7)
 project(scylla)
 
-include(CTest)
-
-list(APPEND CMAKE_MODULE_PATH
-  ${CMAKE_CURRENT_SOURCE_DIR}/cmake
-  ${CMAKE_CURRENT_SOURCE_DIR}/seastar/cmake)
-
-# Set the possible values of build type for cmake-gui
-set(scylla_build_types
-    "Debug" "Release" "Dev" "Sanitize" "Coverage")
-set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
-  ${scylla_build_types})
-if(NOT CMAKE_BUILD_TYPE)
-    set(CMAKE_BUILD_TYPE "Release" CACHE
-        STRING "Choose the type of build." FORCE)
-    message(WARNING "CMAKE_BUILD_TYPE not specified, Using 'Release'")
-elseif(NOT CMAKE_BUILD_TYPE IN_LIST scylla_build_types)
-    message(FATAL_ERROR "Unknown CMAKE_BUILD_TYPE: ${CMAKE_BUILD_TYPE}. "
-        "Following types are supported: ${scylla_build_types}")
+if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
+  message(STATUS "Setting build type to 'Release' as none was specified.")
+  set(CMAKE_BUILD_TYPE "Release" CACHE
+      STRING "Choose the type of build." FORCE)
+  # Set the possible values of build type for cmake-gui
+  set_property(CACHE CMAKE_BUILD_TYPE PROPERTY STRINGS
+    "Debug" "Release" "Dev" "Sanitize")
 endif()
-string(TOUPPER "${CMAKE_BUILD_TYPE}" build_mode)
-include(mode.${build_mode})
-include(mode.common)
-add_compile_definitions(
-    ${Seastar_DEFINITIONS_${build_mode}}
-    FMT_DEPRECATED_OSTREAM)
-include(limit_jobs)
-# Configure Seastar compile options to align with Scylla
-set(CMAKE_CXX_STANDARD "20" CACHE INTERNAL "")
-set(CMAKE_CXX_EXTENSIONS ON CACHE INTERNAL "")
-set(CMAKE_CXX_VISIBILITY_PRESET hidden)
 
-set(Seastar_TESTING ON CACHE BOOL "" FORCE)
-set(Seastar_API_LEVEL 7 CACHE STRING "" FORCE)
-set(Seastar_APPS ON CACHE BOOL "" FORCE)
-set(Seastar_EXCLUDE_APPS_FROM_ALL ON CACHE BOOL "" FORCE)
-add_subdirectory(seastar)
+if(CMAKE_BUILD_TYPE)
+    string(TOLOWER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
+else()
+    set(BUILD_TYPE "release")
+endif()
 
-# System libraries dependencies
-find_package(Boost REQUIRED
-    COMPONENTS filesystem program_options system thread regex unit_test_framework)
-find_package(Lua REQUIRED)
-find_package(ZLIB REQUIRED)
-find_package(ICU COMPONENTS uc i18n REQUIRED)
-find_package(absl COMPONENTS hash raw_hash_set REQUIRED)
-find_package(libdeflate REQUIRED)
-find_package(libxcrypt REQUIRED)
-find_package(Snappy REQUIRED)
-find_package(RapidJSON REQUIRED)
-find_package(Thrift REQUIRED)
-find_package(xxHash REQUIRED)
+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()
 
-set(scylla_gen_build_dir "${CMAKE_BINARY_DIR}/gen")
-file(MAKE_DIRECTORY "${scylla_gen_build_dir}")
+# 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)
 
-include(add_version_library)
-generate_scylla_version()
+find_package(PkgConfig REQUIRED)
 
-add_library(scylla-main STATIC)
-target_sources(scylla-main
-  PRIVATE
-    absl-flat_hash_map.cc
-    bytes.cc
-    client_data.cc
-    clocks-impl.cc
-    collection_mutation.cc
-    compress.cc
-    converting_mutation_partition_applier.cc
-    counters.cc
-    direct_failure_detector/failure_detector.cc
-    duration.cc
-    exceptions/exceptions.cc
-    frozen_schema.cc
-    generic_server.cc
-    debug.cc
-    init.cc
-    keys.cc
-    message/messaging_service.cc
-    multishard_mutation_query.cc
-    mutation_query.cc
-    partition_slice_builder.cc
-    querier.cc
-    query.cc
-    query_ranges_to_vnodes.cc
-    query-result-set.cc
-    tombstone_gc_options.cc
-    tombstone_gc.cc
-    reader_concurrency_semaphore.cc
-    row_cache.cc
-    schema_mutations.cc
-    serializer.cc
-    sstables_loader.cc
-    table_helper.cc
-    tasks/task_manager.cc
-    timeout_config.cc
-    unimplemented.cc
-    validation.cc
-    vint-serialization.cc
-    zstd.cc)
-target_link_libraries(scylla-main
-  PRIVATE
-    db
-    absl::hash
-    absl::raw_hash_set
-    Seastar::seastar
-    Snappy::snappy
-    systemd
-    ZLIB::ZLIB)
-add_subdirectory(api)
-add_subdirectory(alternator)
-add_subdirectory(db)
-add_subdirectory(auth)
-add_subdirectory(cdc)
-add_subdirectory(compaction)
-add_subdirectory(cql3)
-add_subdirectory(data_dictionary)
-add_subdirectory(dht)
-add_subdirectory(gms)
-add_subdirectory(idl)
-add_subdirectory(index)
-add_subdirectory(interface)
-add_subdirectory(lang)
-add_subdirectory(locator)
-add_subdirectory(mutation)
-add_subdirectory(mutation_writer)
-add_subdirectory(node_ops)
-add_subdirectory(readers)
-add_subdirectory(redis)
-add_subdirectory(replica)
-add_subdirectory(raft)
-add_subdirectory(repair)
-add_subdirectory(rust)
-add_subdirectory(schema)
-add_subdirectory(service)
-add_subdirectory(sstables)
-add_subdirectory(streaming)
-add_subdirectory(test)
-add_subdirectory(thrift)
-add_subdirectory(tools)
-add_subdirectory(tracing)
-add_subdirectory(transport)
-add_subdirectory(types)
-add_subdirectory(utils)
-add_version_library(scylla_version
-    release.cc)
+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" "${dir}/*.hh")
+    endforeach()
+
+    if (args_RECURSIVE)
+        set(glob_kind GLOB_RECURSE)
+    else()
+        set(glob_kind GLOB)
+    endif()
+
+    file(${glob_kind} var
+            ${globs})
+
+    set(${args_VAR} ${var} PARENT_SCOPE)
+endfunction()
+
+## Although Seastar is an external project, it is common enough to explore the sources while doing
+## Scylla development that we'll treat the Seastar sources as part of this project for easier navigation.
+scan_scylla_source_directories(
+        VAR SEASTAR_SOURCE_FILES
+        RECURSIVE
+
+        PATHS
+          seastar/core
+          seastar/http
+          seastar/json
+          seastar/net
+          seastar/rpc
+          seastar/testing
+          seastar/util)
+
+scan_scylla_source_directories(
+        VAR SCYLLA_ROOT_SOURCE_FILES
+        PATHS .)
+
+scan_scylla_source_directories(
+        VAR SCYLLA_SUB_SOURCE_FILES
+        RECURSIVE
+
+        PATHS
+          api
+          auth
+          cql3
+          db
+          dht
+          exceptions
+          gms
+          index
+          io
+          locator
+          message
+          raft
+          repair
+          service
+          sstables
+          streaming
+          test
+          thrift
+          tracing
+          transport
+          utils)
+
+scan_scylla_source_directories(
+        VAR SCYLLA_GEN_SOURCE_FILES
+        RECURSIVE
+        PATHS build/${BUILD_TYPE}/gen)
+
+set(SCYLLA_SOURCE_FILES
+        ${SCYLLA_ROOT_SOURCE_FILES}
+        ${SCYLLA_GEN_SOURCE_FILES}
+        ${SCYLLA_SUB_SOURCE_FILES})
 
 add_executable(scylla
-  main.cc)
-target_link_libraries(scylla PRIVATE
-    scylla-main
-    api
-    auth
-    alternator
-    db
-    cdc
-    compaction
-    cql3
-    data_dictionary
-    dht
-    gms
-    idl
-    index
-    lang
-    locator
-    mutation
-    mutation_writer
-    raft
-    readers
-    redis
-    repair
-    replica
-    schema
-    scylla_version
-    service
-    sstables
-    streaming
-    test-perf
-    thrift
-    tools
-    tracing
-    transport
-    types
-    utils)
-target_link_libraries(Boost::regex
-  INTERFACE
-    ICU::i18n
-    ICU::uc)
+        ${SEASTAR_SOURCE_FILES}
+        ${SCYLLA_SOURCE_FILES})
 
-target_link_libraries(scylla PRIVATE
-    seastar
-    Boost::program_options)
+# 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}")
 
-# Force SHA1 build-id generation
-set(default_linker_flags "-Wl,--build-id=sha1")
-include(CheckLinkerFlag)
-set(Scylla_USE_LINKER
-    ""
-    CACHE
-    STRING
-    "Use specified linker instead of the default one")
-if(Scylla_USE_LINKER)
-    set(linkers "${Scylla_USE_LINKER}")
-else()
-    set(linkers "lld" "gold")
-endif()
-
-foreach(linker ${linkers})
-    set(linker_flag "-fuse-ld=${linker}")
-    check_linker_flag(CXX ${linker_flag} "CXX_LINKER_HAVE_${linker}")
-    if(CXX_LINKER_HAVE_${linker})
-        string(APPEND default_linker_flags " ${linker_flag}")
-        break()
-    elseif(Scylla_USE_LINKER)
-        message(FATAL_ERROR "${Scylla_USE_LINKER} is not supported.")
-    endif()
-endforeach()
-
-set(CMAKE_EXE_LINKER_FLAGS "${default_linker_flags}" CACHE INTERNAL "")
-
-# TODO: patch dynamic linker to match configure.py behavior
-
-target_include_directories(scylla PRIVATE
-    "${CMAKE_CURRENT_SOURCE_DIR}"
-    "${scylla_gen_build_dir}")
-
-add_subdirectory(dist)
+# 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

@@ -1,22 +1,11 @@
-# Contributing to Scylla
+# Asking questions or requesting help
 
-## Asking questions or requesting help
+Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
 
-Use the [ScyllaDB Community Forum](https://forum.scylladb.com) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+# Reporting an issue
 
-Join the [Scylla Developers mailing list](https://groups.google.com/g/scylladb-dev) for deeper technical discussions and to discuss your ideas for contributions.
+Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to report issues.  Fill in as much information as you can in the issue template, especially for performance problems.
 
-## Reporting an issue
+# Contributing Code to Scylla
 
-Please use the [issue tracker](https://github.com/scylladb/scylla/issues/) to report issues or to suggest features. Fill in as much information as you can in the issue template, especially for performance problems.
-
-## Contributing code to Scylla
-
-Before you can contribute code to Scylla for the first time, you should sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send the signed form cla@scylladb.com. You can then submit your changes as patches to the to the [scylladb-dev mailing list](https://groups.google.com/forum/#!forum/scylladb-dev) or as a pull request to the [Scylla project on github](https://github.com/scylladb/scylla).
-If you need help formatting or sending patches, [check out these instructions](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches).
-
-The Scylla C++ source code uses the [Seastar coding style](https://github.com/scylladb/seastar/blob/master/coding-style.md) so please adhere to that in your patches. Note that Scylla code is written with `using namespace seastar`, so should not explicitly add the `seastar::` prefix to Seastar symbols. You will usually not need to add `using namespace seastar` to new source files, because most Scylla header files have `#include "seastarx.hh"`, which does this.
-
-Header files in Scylla must be self-contained, i.e., each can be included without having to include specific other headers first. To verify that your change did not break this property, run `ninja dev-headers`. If you added or removed header files, you must `touch configure.py` first - this will cause `configure.py` to be automatically re-run to generate a fresh list of header files.
-
-For more criteria on what reviewers consider good code, see the [review checklist](https://github.com/scylladb/scylla/blob/master/docs/dev/review-checklist.md).
+To contribute code to Scylla, you need to sign the [Contributor License Agreement](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
@@ -195,7 +199,7 @@ $ # Edit configuration options as appropriate
 $ SCYLLA_HOME=$HOME/scylla build/release/scylla
 ```
 
-The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories`, `commitlog_directory` and `schema_commitlog_directory` fields as appropriate.
+The `scylla.yaml` file in the repository by default writes all database data to `/var/lib/scylla`, which likely requires root access. Change the `data_file_directories` and `commitlog_directory` fields as appropriate.
 
 Scylla has a number of requirements for the file-system and operating system to operate ideally and at peak performance. However, during development, these requirements can be relaxed with the `--developer-mode` flag.
 
@@ -362,61 +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`.
-
-### Resolving stack backtraces
-
-Scylla may print stack backtraces to the log for several reasons.
-For example:
-- When aborting (e.g. due to assertion failure, internal error, or segfault)
-- When detecting seastar reactor stalls (where a seastar task runs for a long time without yielding the cpu to other tasks on that shard)
-
-The backtraces contain code pointers so they are not very helpful without resolving into code locations.
-To resolve the backtraces, one needs the scylla relocatable package that contains the scylla binary (with debug information),
-as well as the dynamic libraries it is linked against.
-
-Builds from our automated build system are uploaded to the cloud
-and can be searched on http://backtrace.scylladb.com/
-
-Make sure you have the scylla server exact `build-id` to locate
-its respective relocatable package, required for decoding backtraces it prints.
-
-The build-id is printed to the system log when scylla starts.
-It can also be found by executing `scylla --build-id`, or
-by using the `file` utility, for example:
-```
-$ scylla --build-id
-4cba12e6eb290a406bfa4930918db23941fd4be3
-
-$ file scylla
-scylla: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked, interpreter /////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////lib64/ld-linux-x86-64.so.2, for GNU/Linux 3.2.0, BuildID[sha1]=4cba12e6eb290a406bfa4930918db23941fd4be3, with debug_info, not stripped, too many notes (256)
-```
-
-To find the build-id of a coredump, use the `eu-unstrip` utility as follows:
-```
-$ eu-unstrip -n --core <coredump> | awk '/scylla$/ { s=$2; sub(/@.*$/, "", s); print s; exit(0); }'
-4cba12e6eb290a406bfa4930918db23941fd4be3
-```
-
 ### Core dump debugging
 
-See [debugging.md](docs/dev/debugging.md).
+Slides:
+2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

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

@@ -30,9 +30,9 @@ requirements - you just need to meet the frozen toolchain's prerequisites
 Building Scylla with the frozen toolchain `dbuild` is as easy as:
 
 ```bash
-$ git submodule update --init --force --recursive
-$ ./tools/toolchain/dbuild ./configure.py
-$ ./tools/toolchain/dbuild ninja build/release/scylla
+$ git submodule update --init --force --recursive
+$ ./tools/toolchain/dbuild ./configure.py
+$ ./tools/toolchain/dbuild ninja build/release/scylla
 ```
 
 For further information, please see:
@@ -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/dev/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
 
@@ -60,12 +60,12 @@ Please note that you need to run Scylla with `dbuild` if you built it with the f
 For more run options, run:
 
 ```bash
-$ ./tools/toolchain/dbuild ./build/release/scylla --help
+$ ./tools/toolchain/dbuild ./build/release/scylla --help
 ```
 
 ## Testing
 
-See [test.py manual](docs/dev/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](docs/dev/README.md).
+Documentation can be found in [./docs](./docs) and on the
+[wiki](https://github.com/scylladb/scylla/wiki). There is currently no clear
+definition of what goes where, so when looking for something be sure to check
+both.
 Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
 User documentation can be found [here](https://docs.scylladb.com/).
 
@@ -100,10 +103,10 @@ If you are a developer working on Scylla, please read the [developer guidelines]
 
 ## Contact
 
-* The [community forum] and [Slack channel] are for users to discuss configuration, management, and operations of the ScyllaDB open source.
+* The [users mailing list] and [Slack channel] are for users to discuss configuration, management, and operations of the ScyllaDB open source.
 * The [developers mailing list] is for developers and people interested in following the development of ScyllaDB to discuss technical topics.
 
-[Community forum]: https://forum.scylladb.com/
+[Users mailing list]: https://groups.google.com/forum/#!forum/scylladb-users
 
 [Slack channel]: http://slack.scylladb.com/
 

SCYLLA-VERSION-GEN

@@ -1,117 +1,34 @@
 #!/bin/sh
 
-USAGE=$(cat <<-END
-Usage: $(basename "$0") [-h|--help] [-o|--output-dir PATH] [--date-stamp DATE] -- generate Scylla version and build information files.
-
-Options:
-  -h|--help show this help message.
-  -o|--output-dir PATH specify destination path at which the version files are to be created.
-  -d|--date-stamp DATE manually set date for release parameter
-  -v|--verbose also print out the version number
-
-By default, the script will attempt to parse 'version' file
-in the current directory, which should contain a string of
-'\$version-\$release' form.
-
-Otherwise, it will call 'git log' on the source tree (the
-directory, which contains the script) to obtain current
-commit hash and use it for building the version and release
-strings.
-
-The script assumes that it's called from the Scylla source
-tree.
-
-The files created are:
-  SCYLLA-VERSION-FILE
-  SCYLLA-RELEASE-FILE
-  SCYLLA-PRODUCT-FILE
-
-By default, these files are created in the 'build'
-subdirectory under the directory containing the script.
-The destination directory can be overriden by
-using '-o PATH' option.
-END
-)
-
-DATE=""
-PRINT_VERSION=false
-
-while [ $# -gt 0 ]; do
-	opt="$1"
-	case $opt in
-		-h|--help)
-			echo "$USAGE"
-			exit 0
-			;;
-		-o|--output-dir)
-			OUTPUT_DIR="$2"
-			shift
-			shift
-			;;
-		--date-stamp)
-			DATE="$2"
-			shift
-			shift
-			;;
-		-v|--verbose)
-			PRINT_VERSION=true
-			shift
-			;;
-		*)
-			echo "Unexpected argument found: $1"
-			echo
-			echo "$USAGE"
-			exit 1
-			;;
-	esac
-done
-
-SCRIPT_DIR="$(dirname "$0")"
-
-if [ -z "$OUTPUT_DIR" ]; then
-	OUTPUT_DIR="$SCRIPT_DIR/build"
-fi
-
-if [ -z "$DATE" ]; then
-  DATE=$(date --utc +%Y%m%d)
-fi
-
-# Default scylla product/version tags
 PRODUCT=scylla
-VERSION=5.4.10
+VERSION=4.3.7
 
 if test -f version
 then
 	SCYLLA_VERSION=$(cat version | awk -F'-' '{print $1}')
 	SCYLLA_RELEASE=$(cat version | awk -F'-' '{print $2}')
 else
+	DATE=$(date +%Y%m%d)
+	GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
 	SCYLLA_VERSION=$VERSION
-	if [ -z "$SCYLLA_RELEASE" ]; then
-		DATE=$(date --utc +%Y%m%d)
-		GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1 --abbrev=12)
-		# For custom package builds, replace "0" with "counter.your_name",
-		# where counter starts at 1 and increments for successive versions.
-		# This ensures that the package manager will select your custom
-		# package over the standard release.
-		SCYLLA_BUILD=0
-		SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
-	elif [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-		echo "setting SCYLLA_RELEASE only makes sense in clean builds" 1>&2
-		exit 1
-	fi
+	# For custom package builds, replace "0" with "counter.your_name",
+	# where counter starts at 1 and increments for successive versions.
+	# This ensures that the package manager will select your custom
+	# package over the standard release.
+	SCYLLA_BUILD=0
+	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi
 
-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
 
-if $PRINT_VERSION; then
-	echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
-fi
-mkdir -p "$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"
+echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
+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

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "absl-flat_hash_map.hh"

absl-flat_hash_map.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once

alternator/CMakeLists.txt

@@ -1,30 +0,0 @@
-include(generate_cql_grammar)
-generate_cql_grammar(
-  GRAMMAR expressions.g
-  SOURCES cql_grammar_srcs)
-
-add_library(alternator STATIC)
-target_sources(alternator
-  PRIVATE
-    controller.cc
-    server.cc
-    executor.cc
-    stats.cc
-    serialization.cc
-    expressions.cc
-    conditions.cc
-    auth.cc
-    streams.cc
-    ttl.cc
-    ${cql_grammar_srcs})
-target_include_directories(alternator
-  PUBLIC
-    ${CMAKE_SOURCE_DIR}
-    ${CMAKE_BINARY_DIR}
-  PRIVATE
-    ${RAPIDJSON_INCLUDE_DIRS})
-target_link_libraries(alternator
-  cql3
-  idl
-  Seastar::seastar
-  xxHash::xxhash)

alternator/auth.cc

@@ -1,63 +1,147 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "alternator/error.hh"
 #include "log.hh"
 #include <string>
 #include <string_view>
+#include <gnutls/crypto.h>
+#include <seastar/util/defer.hh>
+#include "hashers.hh"
 #include "bytes.hh"
 #include "alternator/auth.hh"
 #include <fmt/format.h>
 #include "auth/common.hh"
 #include "auth/password_authenticator.hh"
 #include "auth/roles-metadata.hh"
-#include "service/storage_proxy.hh"
-#include "alternator/executor.hh"
-#include "cql3/selection/selection.hh"
-#include "query-result-set.hh"
-#include "cql3/result_set.hh"
-#include <seastar/core/coroutine.hh>
+#include "cql3/query_processor.hh"
+#include "cql3/untyped_result_set.hh"
 
 namespace alternator {
 
 static logging::logger alogger("alternator-auth");
 
-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username) {
-    schema_ptr schema = proxy.data_dictionary().find_schema("system_auth", "roles");
-    partition_key pk = partition_key::from_single_value(*schema, utf8_type->decompose(username));
-    dht::partition_range_vector partition_ranges{dht::partition_range(dht::decorate_key(*schema, pk))};
-    std::vector<query::clustering_range> bounds{query::clustering_range::make_open_ended_both_sides()};
-    const column_definition* salted_hash_col = schema->get_column_definition(bytes("salted_hash"));
-    if (!salted_hash_col) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("Credentials cannot be fetched for: {}", username)));
+static hmac_sha256_digest hmac_sha256(std::string_view key, std::string_view msg) {
+    hmac_sha256_digest digest;
+    int ret = gnutls_hmac_fast(GNUTLS_MAC_SHA256, key.data(), key.size(), msg.data(), msg.size(), digest.data());
+    if (ret) {
+        throw std::runtime_error(fmt::format("Computing HMAC failed ({}): {}", ret, gnutls_strerror(ret)));
     }
-    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col});
-    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id}, selection->get_query_options());
-    auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice,
-            proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
+    return digest;
+}
+
+static hmac_sha256_digest get_signature_key(std::string_view key, std::string_view date_stamp, std::string_view region_name, std::string_view service_name) {
+    auto date = hmac_sha256("AWS4" + std::string(key), date_stamp);
+    auto region = hmac_sha256(std::string_view(date.data(), date.size()), region_name);
+    auto service = hmac_sha256(std::string_view(region.data(), region.size()), service_name);
+    auto signing = hmac_sha256(std::string_view(service.data(), service.size()), "aws4_request");
+    return signing;
+}
+
+static std::string apply_sha256(std::string_view msg) {
+    sha256_hasher hasher;
+    hasher.update(msg.data(), msg.size());
+    return to_hex(hasher.finalize());
+}
+
+static std::string format_time_point(db_clock::time_point tp) {
+    time_t time_point_repr = db_clock::to_time_t(tp);
+    std::string time_point_str;
+    time_point_str.resize(17);
+    ::tm time_buf;
+    // strftime prints the terminating null character as well
+    std::strftime(time_point_str.data(), time_point_str.size(), "%Y%m%dT%H%M%SZ", ::gmtime_r(&time_point_repr, &time_buf));
+    time_point_str.resize(16);
+    return time_point_str;
+}
+
+void check_expiry(std::string_view signature_date) {
+    //FIXME: The default 15min can be changed with X-Amz-Expires header - we should honor it
+    std::string expiration_str = format_time_point(db_clock::now() - 15min);
+    std::string validity_str = format_time_point(db_clock::now() + 15min);
+    if (signature_date < expiration_str) {
+        throw api_error::invalid_signature(
+                fmt::format("Signature expired: {} is now earlier than {} (current time - 15 min.)",
+                signature_date, expiration_str));
+    }
+    if (signature_date > validity_str) {
+        throw api_error::invalid_signature(
+                fmt::format("Signature not yet current: {} is still later than {} (current time + 15 min.)",
+                signature_date, validity_str));
+    }
+}
+
+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,
+        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");
+    }
+    std::string_view amz_date = amz_date_it->second;
+    check_expiry(amz_date);
+    std::string_view datestamp = amz_date.substr(0, 8);
+    if (datestamp != orig_datestamp) {
+        throw api_error::invalid_signature(
+                format("X-Amz-Date date does not match the provided datestamp. Expected {}, got {}",
+                        orig_datestamp, datestamp));
+    }
+    std::string_view canonical_uri = "/";
+
+    std::stringstream canonical_headers;
+    for (const auto& header : signed_headers_map) {
+        canonical_headers << fmt::format("{}:{}", header.first, header.second) << '\n';
+    }
+
+    std::string payload_hash = apply_sha256(body_content);
+    std::string canonical_request = fmt::format("{}\n{}\n{}\n{}\n{}\n{}", method, canonical_uri, query_string, canonical_headers.str(), signed_headers_str, payload_hash);
+
+    std::string_view algorithm = "AWS4-HMAC-SHA256";
+    std::string credential_scope = fmt::format("{}/{}/{}/aws4_request", datestamp, region, service);
+    std::string string_to_sign = fmt::format("{}\n{}\n{}\n{}", algorithm, amz_date, credential_scope,  apply_sha256(canonical_request));
+
+    hmac_sha256_digest signing_key = get_signature_key(secret_access_key, datestamp, region, service);
+    hmac_sha256_digest signature = hmac_sha256(std::string_view(signing_key.data(), signing_key.size()), string_to_sign);
+
+    return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
+}
+
+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());
-    query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
-
-    auto result_set = builder.build();
-    if (result_set->empty()) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("User not found: {}", username)));
-    }
-    const managed_bytes_opt& salted_hash = result_set->rows().front().front(); // We only asked for 1 row and 1 column
-    if (!salted_hash) {
-        co_await coroutine::return_exception(api_error::unrecognized_client(format("No password found for user: {}", username)));
-    }
-    co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
+    auto& timeout = auth::internal_distributed_timeout_config();
+    return qp.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

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

alternator/base64.cc

@@ -1,15 +1,32 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+// 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>
-#include <seastar/core/print.hh>
+
 
 // Arrays for quickly converting to and from an integer between 0 and 63,
 // and the character used in base64 encoding to represent it.
@@ -17,12 +34,11 @@ static class base64_chars {
 public:
     static constexpr const char to[] =
             "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
-    static constexpr uint8_t invalid_char = 255;
-    uint8_t from[255];
+    int8_t from[255];
     base64_chars() {
         static_assert(sizeof(to) == 64 + 1);
         for (int i = 0; i < 255; i++) {
-            from[i] = invalid_char; // signal invalid character
+            from[i] = -1; // signal invalid character
         }
         for (int i = 0; i < 64; i++) {
             from[(unsigned) to[i]] = i;
@@ -61,30 +77,17 @@ std::string base64_encode(bytes_view in) {
     return ret;
 }
 
-static size_t base64_padding_len(std::string_view str) {
-    size_t padding = 0;
-    padding += (!str.empty() && str.back() == '=');
-    padding += (str.size() > 1 && *(str.end() - 2) == '=');
-    return padding;
-}
-
-static void base64_trim_padding(std::string_view& str) {
-    if (str.size() % 4 != 0) {
-        throw std::invalid_argument(format("Base64 encoded length is expected a multiple of 4 bytes but found: {}", str.size()));
-    }
-    str.remove_suffix(base64_padding_len(str));
-}
-
 static std::string base64_decode_string(std::string_view in) {
-    base64_trim_padding(in);
     int i = 0;
     int8_t chunk4[4]; // chunk of input, each byte converted to 0..63;
     std::string ret;
     ret.reserve(in.size() * 3 / 4);
     for (unsigned char c : in) {
         uint8_t dc = base64_chars.from[c];
-        if (dc == base64_chars::invalid_char) {
-           throw std::invalid_argument(format("Invalid Base64 character: '{}'", char(c)));
+        if (dc == 255) {
+            // Any unexpected character, include the "=" character usually
+            // used for padding, signals the end of the decode.
+            break;
         }
         chunk4[i++] = dc;
         if (i == 4) {
@@ -112,6 +115,13 @@ bytes base64_decode(std::string_view in) {
     return bytes(ret.begin(), ret.end());
 }
 
+static size_t base64_padding_len(std::string_view str) {
+    size_t padding = 0;
+    padding += (!str.empty() && str.back() == '=');
+    padding += (str.size() > 1 && *(str.end() - 2) == '=');
+    return padding;
+}
+
 size_t base64_decoded_len(std::string_view str) {
     return str.size() / 4 * 3 - base64_padding_len(str);
 }

alternator/base64.hh

@@ -0,0 +1,38 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include <string_view>
+#include "bytes.hh"
+#include "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

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <list>
@@ -15,8 +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>
@@ -232,14 +244,7 @@ bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
     if (it2->name == "S") {
         return rjson::to_string_view(it1->value).starts_with(rjson::to_string_view(it2->value));
     } else /* it2->name == "B" */ {
-        try {
-            return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
-        } catch(std::invalid_argument&) {
-            // determine if any of the malformed values is from query and raise an exception if so
-            unwrap_bytes(it1->value, v1_from_query);
-            unwrap_bytes(it2->value, v2_from_query);
-            return false;
-        }
+        return base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
     }
 }
 
@@ -248,7 +253,7 @@ static bool is_set_of(const rjson::value& type1, const rjson::value& type2) {
 }
 
 // Check if two JSON-encoded values match with the CONTAINS relation
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query) {
+bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
     if (!v1) {
         return false;
     }
@@ -257,12 +262,7 @@ bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from
     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") {
-        auto d_kv1 = unwrap_bytes(kv1.value, v1_from_query);
-        auto d_kv2 = unwrap_bytes(kv2.value, v2_from_query);
-        if (!d_kv1 || !d_kv2) {
-            return false;
-        }
-        return d_kv1->find(*d_kv2) != 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) {
@@ -285,11 +285,11 @@ bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from
 }
 
 // Check if two JSON-encoded values match with the NOT_CONTAINS relation
-static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query) {
+static bool check_NOT_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
     if (!v1) {
         return false;
     }
-    return !check_CONTAINS(v1, v2, v1_from_query, v2_from_query);
+    return !check_CONTAINS(v1, v2);
 }
 
 // Check if a JSON-encoded value equals any element of an array, which must have at least one element.
@@ -386,12 +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") {
-        auto d_kv1 = unwrap_bytes(kv1.value, v1_from_query);
-        auto d_kv2 = unwrap_bytes(kv2.value, v2_from_query);
-        if(!d_kv1 || !d_kv2) {
-            return false;
-        }
-        return cmp(*d_kv1, *d_kv2);
+        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.
@@ -481,13 +476,7 @@ static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const r
                              bounds_from_query);
     }
     if (kv_v.name == "B") {
-        auto d_kv_v = unwrap_bytes(kv_v.value, v_from_query);
-        auto d_kv_lb = unwrap_bytes(kv_lb.value, lb_from_query);
-        auto d_kv_ub = unwrap_bytes(kv_ub.value, ub_from_query);
-        if(!d_kv_v || !d_kv_lb || !d_kv_ub) {
-            return false;
-        }
-        return check_BETWEEN(*d_kv_v, *d_kv_lb, *d_kv_ub, 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(
@@ -580,7 +569,7 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
                             format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
                                     "got {} instead", argtype));
                 }
-                return check_CONTAINS(got, arg, false, true);
+                return check_CONTAINS(got, arg);
             }
         case comparison_operator_type::NOT_CONTAINS:
             {
@@ -594,7 +583,7 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
                             format("CONTAINS operator requires a single AttributeValue of type String, Number, or Binary, "
                                     "got {} instead", argtype));
                 }
-                return check_NOT_CONTAINS(got, arg, false, true);
+                return check_NOT_CONTAINS(got, arg);
             }
         }
         throw std::logic_error(format("Internal error: corrupted operator enum: {}", int(op)));

alternator/conditions.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -38,7 +51,7 @@ conditional_operator_type get_conditional_operator(const rjson::value& req);
 bool verify_expected(const rjson::value& req, const rjson::value* previous_item);
 bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);
 
-bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
+bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2);
 bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);
 
 bool verify_condition_expression(

alternator/controller.cc

@@ -1,162 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <seastar/net/dns.hh>
-#include "controller.hh"
-#include "server.hh"
-#include "executor.hh"
-#include "rmw_operation.hh"
-#include "db/config.hh"
-#include "cdc/generation_service.hh"
-#include "service/memory_limiter.hh"
-#include "auth/service.hh"
-#include "service/qos/service_level_controller.hh"
-
-using namespace seastar;
-
-namespace alternator {
-
-static logging::logger logger("alternator_controller");
-
-controller::controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        sharded<auth::service>& auth_service,
-        sharded<qos::service_level_controller>& sl_controller,
-        const db::config& config)
-    : _gossiper(gossiper)
-    , _proxy(proxy)
-    , _mm(mm)
-    , _sys_dist_ks(sys_dist_ks)
-    , _cdc_gen_svc(cdc_gen_svc)
-    , _memory_limiter(memory_limiter)
-    , _auth_service(auth_service)
-    , _sl_controller(sl_controller)
-    , _config(config)
-{
-}
-
-sstring controller::name() const {
-    return "alternator";
-}
-
-sstring controller::protocol() const {
-    return "dynamodb";
-}
-
-sstring controller::protocol_version() const {
-    return version;
-}
-
-std::vector<socket_address> controller::listen_addresses() const {
-    return _listen_addresses;
-}
-
-future<> controller::start_server() {
-    return seastar::async([this] {
-        _listen_addresses.clear();
-
-        auto preferred = _config.listen_interface_prefer_ipv6() ? std::make_optional(net::inet_address::family::INET6) : std::nullopt;
-        auto family = _config.enable_ipv6_dns_lookup() || preferred ? std::nullopt : std::make_optional(net::inet_address::family::INET);
-
-        // Create an smp_service_group to be used for limiting the
-        // concurrency when forwarding Alternator request between
-        // shards - if necessary for LWT.
-        smp_service_group_config c;
-        c.max_nonlocal_requests = 5000;
-        _ssg = create_smp_service_group(c).get0();
-
-        rmw_operation::set_default_write_isolation(_config.alternator_write_isolation());
-
-        net::inet_address addr = utils::resolve(_config.alternator_address, family).get0();
-
-        auto get_cdc_metadata = [] (cdc::generation_service& svc) { return std::ref(svc.get_cdc_metadata()); };
-        auto get_timeout_in_ms = [] (const db::config& cfg) -> utils::updateable_value<uint32_t> {
-            return cfg.alternator_timeout_in_ms;
-        };
-        _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(),
-                        sharded_parameter(get_timeout_in_ms, std::ref(_config))).get();
-        _server.start(std::ref(_executor), std::ref(_proxy), std::ref(_gossiper), std::ref(_auth_service), std::ref(_sl_controller)).get();
-        // Note: from this point on, if start_server() throws for any reason,
-        // it must first call stop_server() to stop the executor and server
-        // services we just started - or Scylla will cause an assertion
-        // failure when the controller object is destroyed in the exception
-        // unwinding.
-        std::optional<uint16_t> alternator_port;
-        if (_config.alternator_port()) {
-            alternator_port = _config.alternator_port();
-            _listen_addresses.push_back({addr, *alternator_port});
-        }
-        std::optional<uint16_t> alternator_https_port;
-        std::optional<tls::credentials_builder> creds;
-        if (_config.alternator_https_port()) {
-            alternator_https_port = _config.alternator_https_port();
-            _listen_addresses.push_back({addr, *alternator_https_port});
-            creds.emplace();
-            auto opts = _config.alternator_encryption_options();
-            if (opts.empty()) {
-                // Earlier versions mistakenly configured Alternator's
-                // HTTPS parameters via the "server_encryption_option"
-                // configuration parameter. We *temporarily* continue
-                // to allow this, for backward compatibility.
-                opts = _config.server_encryption_options();
-                if (!opts.empty()) {
-                logger.warn("Setting server_encryption_options to configure "
-                        "Alternator's HTTPS encryption is deprecated. Please "
-                        "switch to setting alternator_encryption_options instead.");
-                }
-            }
-            opts.erase("require_client_auth");
-            opts.erase("truststore");
-            try {
-                utils::configure_tls_creds_builder(creds.value(), std::move(opts)).get();
-            } catch(...) {
-                logger.error("Failed to set up Alternator TLS credentials: {}", std::current_exception());
-                stop_server().get();
-                std::throw_with_nested(std::runtime_error("Failed to set up Alternator TLS credentials"));
-            }
-        }
-        bool alternator_enforce_authorization = _config.alternator_enforce_authorization();
-        _server.invoke_on_all(
-                [this, addr, alternator_port, alternator_https_port, creds = std::move(creds), alternator_enforce_authorization] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, creds, alternator_enforce_authorization,
-                    &_memory_limiter.local().get_semaphore(),
-                    _config.max_concurrent_requests_per_shard);
-        }).handle_exception([this, addr, alternator_port, alternator_https_port] (std::exception_ptr ep) {
-            logger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF", ep);
-            return stop_server().then([ep = std::move(ep)] { return make_exception_future<>(ep); });
-        }).then([addr, alternator_port, alternator_https_port] {
-            logger.info("Alternator server listening on {}, HTTP port {}, HTTPS port {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF");
-        }).get();
-    });
-}
-
-future<> controller::stop_server() {
-    return seastar::async([this] {
-        if (!_ssg) {
-            return;
-        }
-        _server.stop().get();
-        _executor.stop().get();
-        _listen_addresses.clear();
-        destroy_smp_service_group(_ssg.value()).get();
-    });
-}
-
-future<> controller::request_stop_server() {
-    return stop_server();
-}
-
-}

alternator/controller.hh

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

alternator/error.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -21,9 +34,9 @@ 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 = http::reply::status_type;
+    using status_type = httpd::reply::status_type;
     status_type _http_code;
     std::string _type;
     std::string _msg;
@@ -46,9 +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));
     }
@@ -67,26 +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 serialization(std::string msg) {
-        return api_error("SerializationException", std::move(msg));
-    }
-    static api_error table_not_found(std::string msg) {
-        return api_error("TableNotFoundException", std::move(msg));
-    }
     static api_error internal(std::string msg) {
-        return api_error("InternalServerError", std::move(msg), http::reply::status_type::internal_server_error);
+        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

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -14,15 +27,14 @@
 #include <seastar/json/json_elements.hh>
 #include <seastar/core/sharded.hh>
 
+#include "service/storage_proxy.hh"
 #include "service/migration_manager.hh"
 #include "service/client_state.hh"
-#include "service_permit.hh"
 #include "db/timeout_clock.hh"
 
 #include "alternator/error.hh"
 #include "stats.hh"
 #include "utils/rjson.hh"
-#include "utils/updateable_value.hh"
 
 namespace db {
     class system_distributed_keyspace;
@@ -38,17 +50,7 @@ namespace cql3::selection {
 }
 
 namespace service {
-    class storage_proxy;
-}
-
-namespace cdc {
-    class metadata;
-}
-
-namespace gms {
-
-class gossiper;
-
+    class storage_service;
 }
 
 namespace alternator {
@@ -61,16 +63,6 @@ public:
     explicit make_jsonable(rjson::value&& value);
     std::string to_json() const override;
 };
-
-/**
- * Make return type for serializing the object "streamed",
- * i.e. direct to HTTP output stream. Note: only useful for
- * (very) large objects as there are overhead issues with this
- * as well, but for massive lists of return objects this can
- * help avoid large allocations/many re-allocs
- */ 
-json::json_return_type make_streamed(rjson::value&&);
-
 struct json_string : public json::jsonable {
     std::string _value;
 public:
@@ -78,87 +70,11 @@ public:
     std::string to_json() const override;
 };
 
-namespace parsed {
-class path;
-};
-
-schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
-bool is_alternator_keyspace(const sstring& ks_name);
-// Wraps the db::get_tags_of_table and throws if the table is missing the tags extension.
-const std::map<sstring, sstring>& get_tags_of_table_or_throw(schema_ptr schema);
-
-// An attribute_path_map object is used to hold data for various attributes
-// paths (parsed::path) in a hierarchy of attribute paths. Each attribute path
-// has a root attribute, and then modified by member and index operators -
-// for example in "a.b[2].c" we have "a" as the root, then ".b" member, then
-// "[2]" index, and finally ".c" member.
-// Data can be added to an attribute_path_map using the add() function, but
-// requires that attributes with data not be *overlapping* or *conflicting*:
-//
-// 1. Two attribute paths which are identical or an ancestor of one another
-//    are considered *overlapping* and not allowed. If a.b.c has data,
-//    we can't add more data in a.b.c or any of its descendants like a.b.c.d.
-//
-// 2. Two attribute paths which need the same parent to have both a member and
-//    an index are considered *conflicting* and not allowed. E.g., if a.b has
-//    data, you can't add a[1]. The meaning of adding both would be that the
-//    attribute a is both a map and an array, which isn't sensible.
-//
-// These two requirements are common to the two places where Alternator uses
-// this abstraction to describe how a hierarchical item is to be transformed:
-//
-// 1. In ProjectExpression: for filtering from a full top-level attribute
-//    only the parts for which user asked in ProjectionExpression.
-//
-// 2. In UpdateExpression: for taking the previous value of a top-level
-//    attribute, and modifying it based on the instructions in the user
-//    wrote in UpdateExpression.
-
-template<typename T>
-class attribute_path_map_node {
-public:
-    using data_t = T;
-    // We need the extra unique_ptr<> here because libstdc++ unordered_map
-    // doesn't work with incomplete types :-(
-    using members_t =  std::unordered_map<std::string, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The indexes list is sorted because DynamoDB requires handling writes
-    // beyond the end of a list in index order.
-    using indexes_t = std::map<unsigned, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The prohibition on "overlap" and "conflict" explained above means
-    // That only one of data, members or indexes is non-empty.
-    std::optional<std::variant<data_t, members_t, indexes_t>> _content;
-
-    bool is_empty() const { return !_content; }
-    bool has_value() const { return _content && std::holds_alternative<data_t>(*_content); }
-    bool has_members() const { return _content && std::holds_alternative<members_t>(*_content); }
-    bool has_indexes() const { return _content && std::holds_alternative<indexes_t>(*_content); }
-    // get_members() assumes that has_members() is true
-    members_t& get_members() { return std::get<members_t>(*_content); }
-    const members_t& get_members() const { return std::get<members_t>(*_content); }
-    indexes_t& get_indexes() { return std::get<indexes_t>(*_content); }
-    const indexes_t& get_indexes() const { return std::get<indexes_t>(*_content); }
-    T& get_value() { return std::get<T>(*_content); }
-    const T& get_value() const { return std::get<T>(*_content); }
-};
-
-template<typename T>
-using attribute_path_map = std::unordered_map<std::string, attribute_path_map_node<T>>;
-
-using attrs_to_get_node = attribute_path_map_node<std::monostate>;
-// attrs_to_get lists which top-level attribute are needed, and possibly also
-// which part of the top-level attribute is really needed (when nested
-// attribute paths appeared in the query).
-// Most code actually uses optional<attrs_to_get>. There, a disengaged
-// optional means we should get all attributes, not specific ones.
-using attrs_to_get = attribute_path_map<std::monostate>;
-
-
 class executor : public peering_sharded_service<executor> {
-    gms::gossiper& _gossiper;
     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;
@@ -171,16 +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,
-             utils::updateable_value<uint32_t> default_timeout_in_ms)
-        : _gossiper(gossiper), _proxy(proxy), _mm(mm), _sdks(sdks), _cdc_metadata(cdc_metadata), _ssg(ssg) {
-        s_default_timeout_in_ms = std::move(default_timeout_in_ms);
-    }
+    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);
@@ -199,68 +107,48 @@ 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);
     future<request_return_type> get_records(client_state& client_state, tracing::trace_state_ptr, service_permit permit, rjson::value request);
-    future<request_return_type> describe_continuous_backups(client_state& client_state, service_permit permit, rjson::value request);
 
     future<> start();
-    future<> stop() {
-        // disconnect from the value source, but keep the value unchanged.
-        s_default_timeout_in_ms = utils::updateable_value<uint32_t>{s_default_timeout_in_ms()};
-        return make_ready_future<>();
-    }
+    future<> stop() { return make_ready_future<>(); }
+
+    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();
-private:
-    static thread_local utils::updateable_value<uint32_t> s_default_timeout_in_ms;
-public:
     static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);
 
 private:
     friend class rmw_operation;
 
+    static bool is_alternator_keyspace(const sstring& ks_name);
+    static sstring make_keyspace_name(const sstring& table_name);
     static void describe_key_schema(rjson::value& parent, const schema&, std::unordered_map<std::string,std::string> * = nullptr);
-    
-public:
     static void describe_key_schema(rjson::value& parent, const schema& schema, std::unordered_map<std::string,std::string>&);
-
+    
+public:    
     static std::optional<rjson::value> describe_single_item(schema_ptr,
         const query::partition_slice&,
         const cql3::selection::selection&,
         const query::result&,
-        const std::optional<attrs_to_get>&);
-
-    static future<std::vector<rjson::value>> describe_multi_item(schema_ptr schema,
-        const query::partition_slice&& slice,
-        shared_ptr<cql3::selection::selection> selection,
-        foreign_ptr<lw_shared_ptr<query::result>> query_result,
-        shared_ptr<const std::optional<attrs_to_get>> attrs_to_get);
+        const std::unordered_set<std::string>&);
 
     static void describe_single_item(const cql3::selection::selection&,
-        const std::vector<managed_bytes_opt>&,
-        const std::optional<attrs_to_get>&,
+        const std::vector<bytes_opt>&,
+        const std::unordered_set<std::string>&,
         rjson::value&,
         bool = false);
 
-    static void add_stream_options(const rjson::value& stream_spec, schema_builder&, service::storage_proxy& sp);
-    static void supplement_table_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
-    static void supplement_table_stream_info(rjson::value& descr, const schema& schema, const service::storage_proxy& sp);
+
+
+    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;
 };
 
-// is_big() checks approximately if the given JSON value is "bigger" than
-// the given big_size number of bytes. The goal is to *quickly* detect
-// oversized JSON that, for example, is too large to be serialized to a
-// contiguous string - we don't need an accurate size for that. Moreover,
-// as soon as we detect that the JSON is indeed "big", we can return true
-// and don't need to continue calculating its exact size.
-// For simplicity, we use a recursive implementation. This is fine because
-// Alternator limits the depth of JSONs it reads from inputs, and doesn't
-// add more than a couple of levels in its own output construction.
-bool is_big(const rjson::value& val, int big_size = 100'000);
-
 }

alternator/expressions.cc

@@ -1,14 +1,27 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "expressions.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
+#include "base64.hh"
 #include "conditions.hh"
 #include "alternator/expressionsLexer.hpp"
 #include "alternator/expressionsParser.hpp"
@@ -29,7 +42,7 @@
 namespace alternator {
 
 template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
-static Result do_with_parser(std::string_view input, Func&& f) {
+Result do_with_parser(std::string input, Func&& f) {
     expressionsLexer::InputStreamType input_stream{
         reinterpret_cast<const ANTLR_UINT8*>(input.data()),
         ANTLR_ENC_UTF8,
@@ -43,41 +56,31 @@ static Result do_with_parser(std::string_view input, Func&& f) {
     return result;
 }
 
-template <typename Func, typename Result = std::result_of_t<Func(expressionsParser&)>>
-static Result parse(const char* input_name, std::string_view input, Func&& f) {
-    if (input.length() > 4096) {
-        throw expressions_syntax_error(format("{} expression size {} exceeds allowed maximum 4096.",
-            input_name, input.length()));
-    }
-    try {
-        return do_with_parser(input, f);
-    } catch (expressions_syntax_error& e) {
-        // If already an expressions_syntax_error, don't print the type's
-        // name (it's just ugly), just the message.
-        // TODO: displayRecognitionError could set a position inside the
-        // expressions_syntax_error in throws, and we could use it here to
-        // mark the broken position in 'input'.
-        throw expressions_syntax_error(format("Failed parsing {} '{}': {}",
-            input_name, input, e.what()));
-    } catch (...) {
-        throw expressions_syntax_error(format("Failed parsing {} '{}': {}",
-            input_name, input, std::current_exception()));
-    }
-}
-
 parsed::update_expression
-parse_update_expression(std::string_view query) {
-    return parse("UpdateExpression", query,  std::mem_fn(&expressionsParser::update_expression));
+parse_update_expression(std::string query) {
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::update_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing UpdateExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 std::vector<parsed::path>
-parse_projection_expression(std::string_view query) {
-    return parse ("ProjectionExpression", query,  std::mem_fn(&expressionsParser::projection_expression));
+parse_projection_expression(std::string query) {
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::projection_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing ProjectionExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 parsed::condition_expression
-parse_condition_expression(std::string_view query, const char* caller) {
-    return parse(caller, query,  std::mem_fn(&expressionsParser::condition_expression));
+parse_condition_expression(std::string query) {
+    try {
+        return do_with_parser(query,  std::mem_fn(&expressionsParser::condition_expression));
+    } catch (...) {
+        throw expressions_syntax_error(format("Failed parsing ConditionExpression '{}': {}", query, std::current_exception()));
+    }
 }
 
 namespace parsed {
@@ -127,27 +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
@@ -169,9 +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(
@@ -183,30 +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)));
     }
 }
 
@@ -425,17 +385,30 @@ 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.
-// If the value's type (e.g. number) has no size defined, there are two cases:
-// 1. If from_data (the value came directly from an attribute of the data),
-//    It returns a JSON-encoded "null" value. Comparisons against this
-//    non-numeric value will later fail, so eventually the application will
-//    get a ConditionalCheckFailedException.
-// 2. Otherwise (the value came from a constant in the query or some other
-//    calculation), throw a ValidationException.
-static rjson::value calculate_size(const rjson::value& v, bool from_data) {
+// It return a JSON-encoded "null" value if this value's type has no size
+// defined. Comparisons against this non-numeric value will later fail.
+static rjson::value calculate_size(const rjson::value& v) {
     // NOTE: If v is improperly formatted for our JSON value encoding, it
     // must come from the request itself, not from the database, so it makes
     // sense to throw a ValidationException if we see such a problem.
@@ -464,15 +437,13 @@ static rjson::value calculate_size(const rjson::value& v, bool from_data) {
             throw api_error::validation(format("invalid byte string: {}", v));
         }
         ret = base64_decoded_len(rjson::to_string_view(it->value));
-    } else if (from_data) {
-        rjson::value json_ret = rjson::empty_object();
-        rjson::add(json_ret, "null", rjson::value(true));
-        return json_ret;
     } else {
-        throw api_error::validation(format("Unsupported operand type {} for function size()", it->name));
+        rjson::value json_ret = rjson::empty_object();
+        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;
 }
 
@@ -491,7 +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;
 }
 
@@ -516,11 +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) {
@@ -551,7 +518,7 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
                         format("{}: size() accepts 1 parameter, got {}", caller, f._parameters.size()));
             }
             rjson::value v = calculate_value(f._parameters[0], caller, previous_item);
-            return calculate_size(v, f._parameters[0].is_path());
+            return calculate_size(v);
         }
     },
     {"attribute_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
@@ -651,61 +618,11 @@ 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);
-            return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1,  v2,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
+            return to_bool_json(check_CONTAINS(v1.IsNull() ? nullptr : &v1,  v2));
         }
     },
 };
 
-// Given a parsed::path and an item read from the table, extract the value
-// of a certain attribute path, such as "a" or "a.b.c[3]". Returns a null
-// value if the item or the requested attribute does not exist.
-// Note that the item is assumed to be encoded in JSON using DynamoDB
-// conventions - each level of a nested document is a map with one key -
-// a type (e.g., "M" for map) - and its value is the representation of
-// that value.
-static rjson::value extract_path(const rjson::value* item,
-        const parsed::path& p, calculate_value_caller caller) {
-    if (!item) {
-        return rjson::null_value();
-    }
-    const rjson::value* v = rjson::find(*item, p.root());
-    if (!v) {
-        return rjson::null_value();
-    }
-    for (const auto& op : p.operators()) {
-        if (!v->IsObject() || v->MemberCount() != 1) {
-            // This shouldn't happen. We shouldn't have stored malformed
-            // objects. But today Alternator does not validate the structure
-            // of nested documents before storing them, so this can happen on
-            // read.
-            throw api_error::validation(format("{}: malformed item read: {}", caller, *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.
@@ -723,12 +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

@@ -1,9 +1,25 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
+ *
+ * This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
+ * top-level directory for licensing information.
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
@@ -74,22 +90,7 @@ options {
  */
 @parser::context {
     void displayRecognitionError(ANTLR_UINT8** token_names, ExceptionBaseType* ex) {
-        const char* err;
-        switch (ex->getType()) {
-        case antlr3::ExceptionType::FAILED_PREDICATE_EXCEPTION:
-            err = "expression nested too deeply";
-            break;
-        default:
-            err = "syntax error";
-            break;
-        }
-        // Alternator expressions are always single line so ex->get_line()
-        // is always 1, no sense to print it.
-        // TODO: return the position as part of the exception, so the
-        // caller in expressions.cc that knows the expression string can
-        // mark the error position in the final error message.
-        throw expressions_syntax_error(format("{} at char {}", err,
-            ex->get_charPositionInLine()));
+        throw expressions_syntax_error("syntax error");
     }
 }
 @lexer::context {
@@ -98,23 +99,6 @@ options {
     }
 }
 
-/* Unfortunately, ANTLR uses recursion - not the heap - to parse recursive
- * expressions. To make things even worse, ANTLR has no way to limit the
- * depth of this recursion (unlike Yacc which has YYMAXDEPTH). So deeply-
- * nested expression like "(((((((((((((..." can easily crash Scylla on a
- * stack overflow (see issue #14477).
- *
- * We are lucky that in the grammar for DynamoDB expressions (below),
- * only a few specific rules can recurse, so it was fairly easy to add a
- * "depth" counter to a few specific rules, and then use a predicate
- * "{depth<MAX_DEPTH}?" to avoid parsing if the depth exceeds this limit,
- * and throw a FAILED_PREDICATE_EXCEPTION in that case, which we will
- * report to the user as a "expression nested too deeply" error.
- */
-@parser::members {
-    static constexpr int MAX_DEPTH = 400;
-}
-
 /*
  * Lexical analysis phase, i.e., splitting the input up to tokens.
  * Lexical analyzer rules have names starting in capital letters.
@@ -187,20 +171,19 @@ path returns [parsed::path p]:
       | '[' INTEGER ']'           { $p.add_index(std::stoi($INTEGER.text)); }
     )*;
 
-/* See comment above why the "depth" counter was needed here */
-value[int depth] returns [parsed::value v]:
+value returns [parsed::value v]:
       VALREF       { $v.set_valref($VALREF.text); }
     | path         { $v.set_path($path.p); }
-    | {depth<MAX_DEPTH}? NAME { $v.set_func_name($NAME.text); }
-     '(' x=value[depth+1]    { $v.add_func_parameter($x.v); }
-     (',' x=value[depth+1]   { $v.add_func_parameter($x.v); })*
+    | NAME         { $v.set_func_name($NAME.text); }
+     '(' x=value   { $v.add_func_parameter($x.v); }
+     (',' x=value  { $v.add_func_parameter($x.v); })*
      ')'
     ;
 
 update_expression_set_rhs returns [parsed::set_rhs rhs]:
-    v=value[0]  { $rhs.set_value(std::move($v.v)); }
-    (   '+' v=value[0]  { $rhs.set_plus(std::move($v.v)); }
-      | '-' v=value[0]  { $rhs.set_minus(std::move($v.v)); }
+    v=value  { $rhs.set_value(std::move($v.v)); }
+    (   '+' v=value  { $rhs.set_plus(std::move($v.v)); }
+      | '-' v=value  { $rhs.set_minus(std::move($v.v)); }
     )?
     ;
 
@@ -238,7 +221,7 @@ projection_expression returns [std::vector<parsed::path> v]:
 
 
 primitive_condition returns [parsed::primitive_condition c]:
-      v=value[0]      { $c.add_value(std::move($v.v));
+      v=value         { $c.add_value(std::move($v.v));
                         $c.set_operator(parsed::primitive_condition::type::VALUE); }
       (  (  '='       { $c.set_operator(parsed::primitive_condition::type::EQ); }
           | '<' '>'   { $c.set_operator(parsed::primitive_condition::type::NE); }
@@ -247,14 +230,14 @@ primitive_condition returns [parsed::primitive_condition c]:
           | '>'       { $c.set_operator(parsed::primitive_condition::type::GT); }
           | '>' '='   { $c.set_operator(parsed::primitive_condition::type::GE); }
          )
-         v=value[0]   { $c.add_value(std::move($v.v)); }
+         v=value      { $c.add_value(std::move($v.v)); }
        | BETWEEN      { $c.set_operator(parsed::primitive_condition::type::BETWEEN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
+         v=value      { $c.add_value(std::move($v.v)); }
          AND
-         v=value[0]   { $c.add_value(std::move($v.v)); }
+         v=value      { $c.add_value(std::move($v.v)); }
        | IN '('       { $c.set_operator(parsed::primitive_condition::type::IN); }
-         v=value[0]   { $c.add_value(std::move($v.v)); }
-         (',' v=value[0] { $c.add_value(std::move($v.v)); })*
+         v=value      { $c.add_value(std::move($v.v)); }
+         (',' v=value { $c.add_value(std::move($v.v)); })*
          ')'
       )?
     ;
@@ -264,20 +247,19 @@ primitive_condition returns [parsed::primitive_condition c]:
 // common rule prefixes, and (lack of) support for operator precedence.
 // These rules could have been written more clearly using a more powerful
 // parser generator - such as Yacc.
-// See comment above why the "depth" counter was needed here.
-boolean_expression[int depth] returns [parsed::condition_expression e]:
-	  b=boolean_expression_1[depth]       { $e.append(std::move($b.e), '|'); }
-	  (OR b=boolean_expression_1[depth]   { $e.append(std::move($b.e), '|'); } )*
+boolean_expression returns [parsed::condition_expression e]:
+	  b=boolean_expression_1       { $e.append(std::move($b.e), '|'); }
+	  (OR b=boolean_expression_1   { $e.append(std::move($b.e), '|'); } )*
 	;
-boolean_expression_1[int depth] returns [parsed::condition_expression e]:
-	  b=boolean_expression_2[depth]       { $e.append(std::move($b.e), '&'); }
-	  (AND b=boolean_expression_2[depth]  { $e.append(std::move($b.e), '&'); } )*
+boolean_expression_1 returns [parsed::condition_expression e]:
+	  b=boolean_expression_2       { $e.append(std::move($b.e), '&'); }
+	  (AND b=boolean_expression_2  { $e.append(std::move($b.e), '&'); } )*
 	;
-boolean_expression_2[int depth] returns [parsed::condition_expression e]:
+boolean_expression_2 returns [parsed::condition_expression e]:
 	  p=primitive_condition        { $e.set_primitive(std::move($p.c)); }
-	| {depth<MAX_DEPTH}? NOT b=boolean_expression_2[depth+1]   { $e = std::move($b.e); $e.apply_not(); }
-	| {depth<MAX_DEPTH}? '(' b=boolean_expression[depth+1] ')' { $e = std::move($b.e); }
+	| NOT b=boolean_expression_2   { $e = std::move($b.e); $e.apply_not(); }
+	| '(' b=boolean_expression ')' { $e = std::move($b.e); }
     ;
 
 condition_expression returns [parsed::condition_expression e]:
-    boolean_expression[0] { e=std::move($boolean_expression.e); } EOF;
+    boolean_expression { e=std::move($boolean_expression.e); } EOF;

alternator/expressions.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -26,9 +39,9 @@ public:
     using runtime_error::runtime_error;
 };
 
-parsed::update_expression parse_update_expression(std::string_view query);
-std::vector<parsed::path> parse_projection_expression(std::string_view query);
-parsed::condition_expression parse_condition_expression(std::string_view query, const char* caller);
+parsed::update_expression parse_update_expression(std::string query);
+std::vector<parsed::path> parse_projection_expression(std::string query);
+parsed::condition_expression parse_condition_expression(std::string query);
 
 void resolve_update_expression(parsed::update_expression& ue,
         const rjson::value* expression_attribute_names,

alternator/expressions_types.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -19,7 +32,7 @@
 /*
  * Parsed representation of expressions and their components.
  *
- * Types in alternator::parsed namespace are used for holding the parse
+ * Types in alternator::parse namespace are used for holding the parse
  * tree - objects generated by the Antlr rules after parsing an expression.
  * Because of the way Antlr works, all these objects are default-constructed
  * first, and then assigned when the rule is completed, so all these types
@@ -36,23 +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;
@@ -60,13 +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

@@ -1,15 +1,29 @@
 /*
- * Copyright 2020-present ScyllaDB
+ * Copyright 2020 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "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

@@ -1,27 +1,36 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
+#include "base64.hh"
 #include "log.hh"
 #include "serialization.hh"
 #include "error.hh"
 #include "rapidjson/writer.h"
 #include "concrete_types.hh"
 #include "cql3/type_json.hh"
-#include "mutation/position_in_partition.hh"
 
 static logging::logger slogger("alternator-serialization");
 
 namespace alternator {
 
-bool is_alternator_keyspace(const sstring& ks_name);
-
 type_info type_info_from_string(std::string_view type) {
     static thread_local const std::unordered_map<std::string_view, type_info> type_infos = {
         {"S", {alternator_type::S, utf8_type}},
@@ -50,115 +59,6 @@ type_representation represent_type(alternator_type atype) {
     return it->second;
 }
 
-// Get the magnitude and precision of a big_decimal - as these concepts are
-// defined by DynamoDB - to allow us to enforce limits on those as explained
-// in ssue #6794. The "magnitude" of 9e123 is 123 and of -9e-123 is -123,
-// the "precision" of 12.34e56 is the number of significant digits - 4.
-//
-// Unfortunately it turned out to be quite difficult to take a big_decimal and
-// calculate its magnitude and precision from its scale() and unscaled_value().
-// So in the following ugly implementation we calculate them from the string
-// representation instead. We assume the number was already parsed
-// sucessfully to a big_decimal to it follows its syntax rules.
-//
-// FIXME: rewrite this function to take a big_decimal, not a string.
-// Maybe a snippet like this can help:
-// boost::multiprecision::cpp_int digits = boost::multiprecision::log10(num.unscaled_value().convert_to<boost::multiprecision::mpf_float_50>()).convert_to<boost::multiprecision::cpp_int>() + 1;
-
-
-internal::magnitude_and_precision internal::get_magnitude_and_precision(std::string_view s) {
-    size_t e_or_end = s.find_first_of("eE");
-    std::string_view base = s.substr(0, e_or_end);
-    if (s[0]=='-' || s[0]=='+') {
-        base = base.substr(1);
-    }
-    int magnitude = 0;
-    int precision = 0;
-    size_t dot_or_end = base.find_first_of(".");
-    size_t nonzero = base.find_first_not_of("0");
-    if (dot_or_end != std::string_view::npos) {
-        if (nonzero == dot_or_end) {
-            // 0.000031 => magnitude = -5 (like 3.1e-5), precision = 2.
-            std::string_view fraction = base.substr(dot_or_end + 1);
-            size_t nonzero2 = fraction.find_first_not_of("0");
-            if (nonzero2 != std::string_view::npos) {
-                magnitude = -nonzero2 - 1;
-                precision = fraction.size() - nonzero2;
-            }
-        } else {
-            // 000123.45678 => magnitude = 2, precision = 8.
-            magnitude = dot_or_end - nonzero - 1;
-            precision = base.size() - nonzero - 1;
-        }
-        // trailing zeros don't count to precision, e.g., precision
-        // of 1000.0, 1.0 or 1.0000 are just 1.
-        size_t last_significant = base.find_last_not_of(".0");
-        if (last_significant == std::string_view::npos) {
-            precision = 0;
-        } else if (last_significant < dot_or_end) {
-            // e.g., 1000.00 reduce 5 = 7 - (0+1) - 1 from precision
-            precision -= base.size() - last_significant - 2;
-        } else {
-            // e.g., 1235.60 reduce 5 = 7 - (5+1) from precision
-            precision -= base.size() - last_significant - 1;
-        }
-    } else if (nonzero == std::string_view::npos) {
-        // all-zero integer 000000
-        magnitude = 0;
-        precision = 0;
-    } else {
-        magnitude = base.size() - 1 - nonzero;
-        precision = base.size() - nonzero;
-        // trailing zeros don't count to precision, e.g., precision
-        // of 1000 is just 1.
-        size_t last_significant = base.find_last_not_of("0");
-        if (last_significant == std::string_view::npos) {
-            precision = 0;
-        } else {
-            // e.g., 1000 reduce 3 = 4 - (0+1)
-            precision -= base.size() - last_significant - 1;
-        }
-    }
-    if (precision && e_or_end != std::string_view::npos) {
-        std::string_view exponent = s.substr(e_or_end + 1);
-        if (exponent.size() > 4) {
-            // don't even bother atoi(), exponent is too large
-            magnitude = exponent[0]=='-' ? -9999 : 9999;
-        } else {
-            try {
-                magnitude += boost::lexical_cast<int32_t>(exponent);
-            } catch (...) {
-                magnitude = 9999;
-            }
-        }
-    }
-    return magnitude_and_precision {magnitude, precision};
-}
-
-// Parse a number read from user input, validating that it has a valid
-// numeric format and also in the allowed magnitude and precision ranges
-// (see issue #6794). Throws an api_error::validation if the validation
-// failed.
-static big_decimal parse_and_validate_number(std::string_view s) {
-    try {
-        big_decimal ret(s);
-        auto [magnitude, precision] = internal::get_magnitude_and_precision(s);
-        if (magnitude > 125) {
-            throw api_error::validation(format("Number overflow: {}. Attempting to store a number with magnitude larger than supported range.", s));
-        }
-        if (magnitude < -130) {
-            throw api_error::validation(format("Number underflow: {}. Attempting to store a number with magnitude lower than supported range.", s));
-        }
-        if (precision > 38) {
-            throw api_error::validation(format("Number too precise: {}. Attempting to store a number with more significant digits than supported.", s));
-        }
-        return ret;
-    } catch (const marshal_exception& e) {
-        throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", s));
-    }
-
-}
-
 struct from_json_visitor {
     const rjson::value& v;
     bytes_ostream& bo;
@@ -168,19 +68,21 @@ struct from_json_visitor {
         bo.write(t.from_string(rjson::to_string_view(v)));
     }
     void operator()(const bytes_type_impl& t) const {
-        // FIXME: it's difficult at this point to get information if value was provided
-        // in request or comes from the storage, for now we assume it's user's fault.
-        bo.write(*unwrap_bytes(v, true));
+        bo.write(base64_decode(v));
     }
     void operator()(const boolean_type_impl& t) const {
         bo.write(boolean_type->decompose(v.GetBool()));
     }
     void operator()(const decimal_type_impl& t) const {
-        bo.write(decimal_type->decompose(parse_and_validate_number(rjson::to_string_view(v))));
+        try {
+            bo.write(t.from_string(rjson::to_string_view(v)));
+        } catch (const marshal_exception& e) {
+            throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", v));
+        }
     }
     // default
     void operator()(const abstract_type& t) const {
-        bo.write(from_json_object(t, v));
+        bo.write(from_json_object(t, v, cql_serialization_format::internal()));
     }
 };
 
@@ -212,18 +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))));
     }
 };
 
@@ -271,47 +173,32 @@ bytes get_key_column_value(const rjson::value& item, const column_definition& co
     return get_key_from_typed_value(*key_typed_value, column);
 }
 
-// Parses the JSON encoding for a key value, which is a map with a single
-// entry whose key is the type and the value is the encoded value.
-// If this type does not match the desired "type_str", an api_error::validation
-// error is thrown (the "name" parameter is the name of the column which will
-// mentioned in the exception message).
-// If the type does match, a reference to the encoded value is returned.
-static const rjson::value& get_typed_value(const rjson::value& key_typed_value, std::string_view type_str, std::string_view name, std::string_view value_name) {
-    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
-            !key_typed_value.MemberBegin()->value.IsString()) {
-        throw api_error::validation(
-                format("Malformed value object for {} {}: {}",
-                        value_name, name, key_typed_value));
-    }
-
-    auto it = key_typed_value.MemberBegin();
-    if (rjson::to_string_view(it->name) != type_str) {
-        throw api_error::validation(
-                format("Type mismatch: expected type {} for {} {}, got type {}",
-                        type_str, value_name, name, it->name));
-    }
-    return it->value;
-}
-
 // Parses the JSON encoding for a key value, which is a map with a single
 // entry, whose key is the type (expected to match the key column's type)
 // and the value is the encoded value.
 bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column_definition& column) {
-    auto& value = get_typed_value(key_typed_value, type_to_string(column.type), column.name_as_text(), "key column");
-    std::string_view value_view = rjson::to_string_view(value);
+    if (!key_typed_value.IsObject() || key_typed_value.MemberCount() != 1 ||
+            !key_typed_value.MemberBegin()->value.IsString()) {
+        throw api_error::validation(
+                format("Malformed value object for key column {}: {}",
+                        column.name_as_text(), key_typed_value));
+    }
+
+    auto it = key_typed_value.MemberBegin();
+    if (it->name != type_to_string(column.type)) {
+        throw api_error::validation(
+                format("Type mismatch: expected type {} for key column {}, got type {}",
+                        type_to_string(column.type), column.name_as_text(), it->name));
+    }
+    std::string_view value_view = rjson::to_string_view(it->value);
     if (value_view.empty()) {
         throw api_error::validation(
                 format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
     }
     if (column.type == bytes_type) {
-        // FIXME: it's difficult at this point to get information if value was provided
-        // in request or comes from the storage, for now we assume it's user's fault.
-        return *unwrap_bytes(value, true);
-    } else if (column.type == decimal_type) {
-        return decimal_type->decompose(parse_and_validate_number(rjson::to_string_view(value)));
+        return base64_decode(it->value);
     } else {
-        return column.type->from_string(value_view);
+        return column.type->from_string(rjson::to_string_view(it->value));
     }
 
 }
@@ -321,7 +208,7 @@ rjson::value json_key_column_value(bytes_view cell, const column_definition& col
         std::string b64 = base64_encode(cell);
         return rjson::from_string(b64);
     } if (column.type == utf8_type) {
-        return rjson::from_string(reinterpret_cast<const char*>(cell.data()), cell.size());
+        return rjson::from_string(std::string(reinterpret_cast<const char*>(cell.data()), cell.size()));
     } else if (column.type == decimal_type) {
         // FIXME: use specialized Alternator number type, not the more
         // general "decimal_type". A dedicated type can be more efficient
@@ -362,38 +249,6 @@ clustering_key ck_from_json(const rjson::value& item, schema_ptr schema) {
     return clustering_key::from_exploded(raw_ck);
 }
 
-position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema) {
-    auto ck = ck_from_json(item, schema);
-    if (is_alternator_keyspace(schema->ks_name())) {
-        return position_in_partition::for_key(std::move(ck));
-    }
-    const auto region_item = rjson::find(item, scylla_paging_region);
-    const auto weight_item = rjson::find(item, scylla_paging_weight);
-    if (bool(region_item) != bool(weight_item)) {
-        throw api_error::validation("Malformed value object: region and weight has to be either both missing or both present");
-    }
-    bound_weight weight;
-    if (region_item) {
-        auto region_view = rjson::to_string_view(get_typed_value(*region_item, "S", scylla_paging_region, "key region"));
-        auto weight_view = rjson::to_string_view(get_typed_value(*weight_item, "N", scylla_paging_weight, "key weight"));
-        auto region = parse_partition_region(region_view);
-        if (weight_view == "-1") {
-            weight = bound_weight::before_all_prefixed;
-        } else if (weight_view == "0") {
-            weight = bound_weight::equal;
-        } else if (weight_view == "1") {
-            weight = bound_weight::after_all_prefixed;
-        } else {
-            throw std::runtime_error(fmt::format("Invalid value for weight: {}", weight_view));
-        }
-        return position_in_partition(region, weight, region == partition_region::clustered ? std::optional(std::move(ck)) : std::nullopt);
-    }
-    if (ck.is_empty()) {
-        return position_in_partition::for_partition_start();
-    }
-    return position_in_partition::for_key(std::move(ck));
-}
-
 big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
     if (!v.IsObject() || v.MemberCount() != 1) {
         throw api_error::validation(format("{}: invalid number object", diagnostic));
@@ -402,38 +257,17 @@ big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
     if (it->name != "N") {
         throw api_error::validation(format("{}: expected number, found type '{}'", diagnostic, it->name));
     }
-    if (!it->value.IsString()) {
-        // We shouldn't reach here. Callers normally validate their input
-        // earlier with validate_value().
-        throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
-    }
-    big_decimal ret = parse_and_validate_number(rjson::to_string_view(it->value));
-    return ret;
-}
-
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return std::nullopt;
-    }
-    auto it = v.MemberBegin();
-    if (it->name != "N" || !it->value.IsString()) {
-        return std::nullopt;
-    }
     try {
-        return parse_and_validate_number(rjson::to_string_view(it->value));
-    } catch (api_error&) {
-        return std::nullopt;
-    }
-}
-
-std::optional<bytes> unwrap_bytes(const rjson::value& value, bool from_query) {
-    try {
-        return rjson::base64_decode(value);
-    } catch (...) {
-        if (from_query) {
-            throw api_error::serialization(format("Invalid base64 data"));
+        if (it->value.IsNumber()) {
+             // FIXME(sarna): should use big_decimal constructor with numeric values directly:
+            return big_decimal(rjson::print(it->value));
         }
-        return std::nullopt;
+        if (!it->value.IsString()) {
+            throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
+        }
+        return big_decimal(rjson::to_string_view(it->value));
+    } catch (const marshal_exception& e) {
+        throw api_error::validation(format("The parameter cannot be converted to a numeric value: {}", it->value));
     }
 }
 
@@ -444,7 +278,7 @@ const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value&
     auto it = v.MemberBegin();
     const std::string it_key = it->name.GetString();
     if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
-        return {std::move(it_key), nullptr};
+        return {"", nullptr};
     }
     return std::make_pair(it_key, &(it->value));
 }
@@ -466,8 +300,8 @@ rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
     auto n1 = unwrap_number(v1, "UpdateExpression");
     auto n2 = unwrap_number(v2, "UpdateExpression");
     rjson::value ret = rjson::empty_object();
-    sstring str_ret = (n1 + n2).to_string();
-    rjson::add(ret, "N", rjson::from_string(str_ret));
+    std::string str_ret = std::string((n1 + n2).to_string());
+    rjson::set(ret, "N", rjson::from_string(str_ret));
     return ret;
 }
 
@@ -475,8 +309,8 @@ rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
     auto n1 = unwrap_number(v1, "UpdateExpression");
     auto n2 = unwrap_number(v2, "UpdateExpression");
     rjson::value ret = rjson::empty_object();
-    sstring str_ret = (n1 - n2).to_string();
-    rjson::add(ret, "N", rjson::from_string(str_ret));
+    std::string str_ret = std::string((n1 - n2).to_string());
+    rjson::set(ret, "N", rjson::from_string(str_ret));
     return ret;
 }
 
@@ -502,7 +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;
 }
 
@@ -514,7 +348,7 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
     auto [set1_type, set1] = unwrap_set(v1);
     auto [set2_type, set2] = unwrap_set(v2);
     if (set1_type != set2_type) {
-        throw api_error::validation(format("Set DELETE type mismatch: {} and {}", set1_type, set2_type));
+        throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
     }
     if (!set1 || !set2) {
         throw api_error::validation("UpdateExpression: DELETE operation can only be performed on a set");
@@ -530,7 +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));
@@ -538,23 +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

@@ -1,24 +1,34 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include <string>
 #include <string_view>
-#include <optional>
-#include "types/types.hh"
-#include "schema/schema_fwd.hh"
+#include "types.hh"
+#include "schema_fwd.hh"
 #include "keys.hh"
 #include "utils/rjson.hh"
 #include "utils/big_decimal.hh"
 
-class position_in_partition;
-
 namespace alternator {
 
 enum class alternator_type : int8_t {
@@ -35,9 +45,6 @@ struct type_representation {
     data_type dtype;
 };
 
-inline constexpr std::string_view scylla_paging_region(":scylla:paging:region");
-inline constexpr std::string_view scylla_paging_weight(":scylla:paging:weight");
-
 type_info type_info_from_string(std::string_view type);
 type_representation represent_type(alternator_type atype);
 
@@ -52,21 +59,11 @@ rjson::value json_key_column_value(bytes_view cell, const column_definition& col
 
 partition_key pk_from_json(const rjson::value& item, schema_ptr schema);
 clustering_key ck_from_json(const rjson::value& item, schema_ptr schema);
-position_in_partition pos_from_json(const rjson::value& item, schema_ptr schema);
 
 // If v encodes a number (i.e., it is a {"N": [...]}, returns an object representing it.  Otherwise,
 // raises ValidationException with diagnostic.
 big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);
 
-// try_unwrap_number is like unwrap_number, but returns an unset optional
-// when the given v does not encode a number.
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v);
-
-// unwrap_bytes decodes byte value, on decoding failure it either raises api_error::serialization
-// iff from_query is true or returns unset optional iff from_query is false.
-// Therefore it's safe to dereference returned optional when called with from_query equal true.
-std::optional<bytes> unwrap_bytes(const rjson::value& value, bool from_query);
-
 // Check if a given JSON object encodes a set (i.e., it is a {"SS": [...]}, or "NS", "BS"
 // and returns set's type and a pointer to that set. If the object does not encode a set,
 // returned value is {"", nullptr}
@@ -88,18 +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);
-
-namespace internal {
-struct magnitude_and_precision {
-    int magnitude;
-    int precision;
-};
-magnitude_and_precision get_magnitude_and_precision(std::string_view);
-}
 
 }

alternator/server.cc

@@ -1,36 +1,40 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "alternator/server.hh"
 #include "log.hh"
 #include <seastar/http/function_handlers.hh>
-#include <seastar/http/short_streams.hh>
-#include <seastar/core/coroutine.hh>
 #include <seastar/json/json_elements.hh>
-#include <seastar/util/defer.hh>
-#include <seastar/util/short_streams.hh>
 #include "seastarx.hh"
 #include "error.hh"
-#include "service/qos/service_level_controller.hh"
 #include "utils/rjson.hh"
 #include "auth.hh"
 #include <cctype>
-#include "service/storage_proxy.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"
-#include "utils/aws_sigv4.hh"
 
 static logging::logger slogger("alternator-server");
 
 using namespace httpd;
-using request = http::request;
-using reply = http::reply;
 
 namespace alternator {
 
@@ -55,40 +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
@@ -123,10 +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;
@@ -139,31 +105,28 @@ 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(
-                [](std::unique_ptr<reply> rep) {
-                    rep->set_mime_type("application/x-amz-json-1.0");
-                    rep->done();
+                [this](std::unique_ptr<reply> rep) {
+                    rep->done(_type);
                     return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
                 });
     }
 
 protected:
     void generate_error_reply(reply& rep, const api_error& err) {
-        rjson::value results = rjson::empty_object();
-        rjson::add(results, "__type", rjson::from_string("com.amazonaws.dynamodb.v20120810#" + err._type));
-        rjson::add(results, "message", err._msg);
-        rep._content = rjson::print(std::move(results));
+        rep._content += "{\"__type\":\"com.amazonaws.dynamodb.v20120810#" + err._type + "\"," +
+                "\"message\":\"" + err._msg + "\"}";
         rep._status = err._http_code;
         slogger.trace("api_handler error case: {}", rep._content);
     }
 
     future_handler_function _f_handle;
+    sstring _type;
 };
 
 class gated_handler : public handler_base {
@@ -183,7 +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));
@@ -191,27 +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:
-        auto& topology = _proxy.get_token_metadata_ptr()->get_topology();
-        sstring local_dc = topology.get_datacenter();
-        std::unordered_set<gms::inet_address> local_dc_nodes = topology.get_datacenter_endpoints().at(local_dc);
+        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 =
+                service::get_local_storage_service().get_token_metadata().
+                get_topology().get_datacenter_endpoints().at(local_dc);
         for (auto& ip : local_dc_nodes) {
-            // Note that it's not enough for the node to be is_alive() - a
-            // node joining the cluster is also "alive" but not responsive to
-            // requests. We need the node to be in normal state. See #19694.
-            if (_gossiper.is_normal(ip)) {
+            if (gms::get_local_gossiper().is_alive(ip)) {
                 rjson::push_back(results, rjson::from_string(ip.to_sstring()));
             }
         }
@@ -222,26 +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>();
+        return make_ready_future<>();
     }
     auto host_it = req._headers.find("Host");
     if (host_it == req._headers.end()) {
@@ -249,34 +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") {
@@ -286,8 +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));
@@ -311,10 +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),
@@ -323,114 +255,53 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
                                                     region = std::move(region),
                                                     service = std::move(service),
                                                     user_signature = std::move(user_signature)] (key_cache::value_ptr key_ptr) {
-        std::string signature;
-        try {
-            signature = utils::aws::get_signature(user, *key_ptr, std::string_view(host), "/", req._method,
-                datestamp, signed_headers_str, signed_headers_map, &content, region, service, "");
-        } catch (const std::exception& e) {
-            throw api_error::invalid_signature(e.what());
-        }
+        std::string signature = get_signature(user, *key_ptr, std::string_view(host), req._method,
+                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());
-        if (!username.empty()) {
-            tracing::set_username(trace_state, auth::authenticated_user(username));
-        }
-    }
-    return trace_state;
-}
-
-future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request> req) {
+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 util::read_entire_stream(*req->content_stream);
-    auto username = co_await verify_signature(*req, content);
-
-    if (slogger.is_enabled(log_level::trace)) {
-        std::string buf;
-        slogger.trace("Request: {} {} {}", op, truncated_content_view(content, buf), req->_headers);
-    }
-    auto callback_it = _callbacks.find(op);
-    if (callback_it == _callbacks.end()) {
-        _executor._stats.unsupported_operations++;
-        co_return api_error::unknown_operation(format("Unsupported operation {}", op));
-    }
-    if (_pending_requests.get_count() >= _max_concurrent_requests) {
-        _executor._stats.requests_shed++;
-        co_return api_error::request_limit_exceeded(format("too many in-flight requests (configured via max_concurrent_requests_per_shard): {}", _pending_requests.get_count()));
-    }
-    _pending_requests.enter();
-    auto leave = defer([this] () noexcept { _pending_requests.leave(); });
-    //FIXME: Client state can provide more context, e.g. client's endpoint address
-    // We use unique_ptr because client_state cannot be moved or copied
-    executor::client_state client_state = username.empty()
-        ? service::client_state{service::client_state::internal_tag()}
-        : service::client_state{service::client_state::internal_tag(), _auth_service, _sl_controller, username};
-    co_await client_state.maybe_update_per_service_level_params();
-
-    tracing::trace_state_ptr trace_state = maybe_trace_query(client_state, username, op, content);
-    tracing::trace(trace_state, "{}", op);
-    rjson::value json_request = co_await _json_parser.parse(std::move(content));
-    co_return co_await callback_it->second(_executor, client_state, trace_state,
-            make_service_permit(std::move(units)), std::move(json_request), std::move(req));
+    slogger.trace("Request: {} {} {}", op, req->content, 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) {
@@ -451,21 +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, auth::service& auth_service, qos::service_level_controller& sl_controller)
+server::server(executor& exec)
         : _http_server("http-alternator")
         , _https_server("https-alternator")
         , _executor(exec)
-        , _proxy(proxy)
-        , _gossiper(gossiper)
-        , _auth_service(auth_service)
-        , _sl_controller(sl_controller)
         , _key_cache(1024, 1min, slogger)
         , _enforce_authorization(false)
         , _enabled_servers{}
@@ -522,12 +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));
         }},
@@ -540,44 +400,46 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
         {"GetRecords", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
             return e.get_records(client_state, std::move(trace_state), std::move(permit), std::move(json_request));
         }},
-        {"DescribeContinuousBackups", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_continuous_backups(client_state, std::move(permit), std::move(json_request));
-        }},
     } {
 }
 
 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"));
     }
     return seastar::async([this, addr, port, https_port, creds] {
-        _executor.start().get();
+        try {
+            _executor.start().get();
 
-        if (port) {
-            set_routes(_http_server._routes);
-            _http_server.set_content_length_limit(server::content_length_limit);
-            _http_server.set_content_streaming(true);
-            _http_server.listen(socket_address{addr, *port}).get();
-            _enabled_servers.push_back(std::ref(_http_server));
-        }
-        if (https_port) {
-            set_routes(_https_server._routes);
-            _https_server.set_content_length_limit(server::content_length_limit);
-            _https_server.set_content_streaming(true);
-            _https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
-                if (ep) {
-                    slogger.warn("Exception loading {}: {}", files, ep);
-                } else {
-                    slogger.info("Reloaded {}", files);
-                }
-            }).get0());
-            _https_server.listen(socket_address{addr, *https_port}).get();
-            _enabled_servers.push_back(std::ref(_https_server));
+            if (port) {
+                set_routes(_http_server._routes);
+                _http_server.set_content_length_limit(server::content_length_limit);
+                _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_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
+                    if (ep) {
+                        slogger.warn("Exception loading {}: {}", files, ep);
+                    } else {
+                        slogger.info("Reloaded {}", files);
+                    }
+                }).get0());
+                _https_server.listen(socket_address{addr, *https_port}).get();
+                _enabled_servers.push_back(std::ref(_https_server));
+            }
+        } catch (...) {
+            slogger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
+                    addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF", std::current_exception());
+            std::throw_with_nested(std::runtime_error(
+                    format("Failed to set up Alternator HTTP server on {} port {}, TLS port {}",
+                            addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF")));
         }
     });
 }
@@ -599,7 +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();
@@ -609,12 +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) {
@@ -632,12 +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("{} {}: {}", static_cast<int>(_http_code), _type, _msg);
-    }
-    return _what_string.c_str();
-}
-
 }
 

alternator/server.hh

@@ -1,42 +1,46 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "alternator/executor.hh"
 #include <seastar/core/future.hh>
-#include <seastar/core/condition-variable.hh>
 #include <seastar/http/httpd.hh>
 #include <seastar/net/tls.hh>
 #include <optional>
 #include "alternator/auth.hh"
-#include "service/qos/service_level_controller.hh"
 #include "utils/small_vector.hh"
-#include "utils/updateable_value.hh"
 #include <seastar/core/units.hh>
 
 namespace alternator {
 
-using chunked_content = rjson::chunked_content;
-
 class server {
     static constexpr size_t content_length_limit = 16*MB;
     using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
-            tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<http::request>)>;
+            tracing::trace_state_ptr, service_permit, rjson::value, std::unique_ptr<request>)>;
     using alternator_callbacks_map = std::unordered_map<std::string_view, alternator_callback>;
 
-    httpd::http_server _http_server;
-    httpd::http_server _https_server;
+    http_server _http_server;
+    http_server _https_server;
     executor& _executor;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
-    auth::service& _auth_service;
-    qos::service_level_controller& _sl_controller;
 
     key_cache _key_cache;
     bool _enforce_authorization;
@@ -45,11 +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};
@@ -59,25 +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, auth::service& service, qos::service_level_controller& sl_controller);
+    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::http::request&, const chunked_content&);
-    future<executor::request_return_type> handle_api_request(std::unique_ptr<http::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

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "stats.hh"
@@ -25,7 +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")
@@ -84,8 +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

@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -79,7 +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

@@ -1,9 +1,22 @@
 /*
- * Copyright 2020-present ScyllaDB
+ * Copyright 2020 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <type_traits>
@@ -13,28 +26,27 @@
 
 #include <seastar/json/formatter.hh>
 
-#include "utils/base64.hh"
+#include "base64.hh"
 #include "log.hh"
+#include "database.hh"
 #include "db/config.hh"
 
 #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/schema_builder.hh"
-#include "service/storage_proxy.hh"
+#include "schema_builder.hh"
+#include "service/storage_service.hh"
 #include "gms/feature.hh"
 #include "gms/feature_service.hh"
 
 #include "executor.hh"
+#include "tags_extension.hh"
 #include "rmw_operation.hh"
-#include "data_dictionary/data_dictionary.hh"
 
 /**
  * Base template type to implement  rapidjson::internal::TypeHelper<...>:s
@@ -75,8 +87,8 @@ struct rapidjson::internal::TypeHelper<ValueType, utils::UUID>
     : public from_string_helper<ValueType, utils::UUID>
 {};
 
-static db_clock::time_point as_timepoint(const table_id& tid) {
-    return db_clock::time_point{utils::UUID_gen::unix_timestamp(tid.uuid())};
+static db_clock::time_point as_timepoint(const utils::UUID& uuid) {
+    return db_clock::time_point{std::chrono::milliseconds(utils::UUID_gen::get_adjusted_timestamp(uuid))};
 }
 
 /**
@@ -107,9 +119,6 @@ public:
     stream_arn(const UUID& uuid)
         : UUID(uuid)
     {}
-    stream_arn(const table_id& tid)
-        : UUID(tid.uuid())
-    {}
     stream_arn(std::string_view v)
         : UUID(v.substr(1))
     {
@@ -141,46 +150,27 @@ namespace alternator {
 future<alternator::executor::request_return_type> alternator::executor::list_streams(client_state& client_state, service_permit permit, rjson::value request) {
     _stats.api_operations.list_streams++;
 
-    auto limit = rjson::get_opt<int>(request, "Limit").value_or(100);
+    auto limit = rjson::get_opt<int>(request, "Limit").value_or(std::numeric_limits<int>::max());
     auto streams_start = rjson::get_opt<stream_arn>(request, "ExclusiveStartStreamArn");
     auto table = find_table(_proxy, request);
-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();
+    auto& cfs = db.get_column_families();
+    auto i = cfs.begin();
+    auto e = cfs.end();
 
     if (limit < 1) {
         throw api_error::validation("Limit must be 1 or more");
     }
 
-    std::vector<data_dictionary::table> cfs;
-
-    if (table) {
-        auto log_name = cdc::log_name(table->cf_name());
-        try {
-            cfs.emplace_back(db.find_table(table->ks_name(), log_name));
-        } catch (data_dictionary::no_such_column_family&) {
-            cfs.clear();
-        }
-    } else {
-        cfs = db.get_tables();
-    }
-
-    // # 12601 (maybe?) - sort the set of tables on ID. This should ensure we never
-    // generate duplicates in a paged listing here. Can obviously miss things if they 
-    // are added between paged calls and end up with a "smaller" UUID/ARN, but that 
-    // is to be expected.
-    if (std::cmp_less(limit, cfs.size()) || streams_start) {
-        std::sort(cfs.begin(), cfs.end(), [](const data_dictionary::table& t1, const data_dictionary::table& t2) {
-            return t1.schema()->id().uuid() < t2.schema()->id().uuid();
-        });
-    }
-
-    auto i = cfs.begin();
-    auto e = cfs.end();
-
+    // TODO: the unordered_map here is not really well suited for partial
+    // querying - we're sorting on local hash order, and creating a table
+    // between queries may or may not miss info. But that should be rare,
+    // and we can probably expect this to be a single call.
     if (streams_start) {
-        i = std::find_if(i, e, [&](const data_dictionary::table& t) {
-            return t.schema()->id().uuid() == streams_start
-                && cdc::get_base_table(db.real_database(), *t.schema())
-                && is_alternator_keyspace(t.schema()->ks_name())
+        i = std::find_if(i, e, [&](const std::pair<utils::UUID, lw_shared_ptr<column_family>>& p) {
+            return p.first == streams_start 
+                && cdc::get_base_table(db, *p.second->schema())
+                && is_alternator_keyspace(p.second->schema()->ks_name())
                 ;
         });
         if (i != e) {
@@ -194,30 +184,37 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
     std::optional<stream_arn> last;
 
     for (;limit > 0 && i != e; ++i) {
-        auto s = i->schema();
+        auto s = i->second->schema();
         auto& ks_name = s->ks_name();
         auto& cf_name = s->cf_name();
 
         if (!is_alternator_keyspace(ks_name)) {
             continue;
         }
-        if (cdc::is_log_for_some_table(db.real_database(), ks_name, cf_name)) {
+        if (table && ks_name != table->ks_name()) {
+            continue;
+        }
+        if (cdc::is_log_for_some_table(ks_name, cf_name)) {
+            if (table && table != cdc::get_base_table(db, *s)) {
+                continue;
+            }
+
             rjson::value new_entry = rjson::empty_object();
 
-            last = i->schema()->id();
-            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))));
+            last = i->first;
+            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)));
@@ -293,12 +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()));
     }())
 {}
 
@@ -425,12 +419,10 @@ using namespace std::string_literals;
  * This will be a partial overlap, but it is the best we can do.
  */
 
-static std::chrono::seconds confidence_interval(data_dictionary::database db) {
+static std::chrono::seconds confidence_interval(const database& db) {
     return std::chrono::seconds(db.get_config().alternator_streams_time_window_s());
 }
 
-using namespace std::chrono_literals;
-
 // Dynamo docs says no data shall live longer than 24h.
 static constexpr auto dynamodb_streams_max_window = 24h;
 
@@ -445,12 +437,12 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
     auto stream_arn = rjson::get<alternator::stream_arn>(request, "StreamArn");
 
     schema_ptr schema, bs;
-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();
 
     try {
-        auto cf = db.find_column_family(table_id(stream_arn));
+        auto& cf = db.find_column_family(stream_arn);
         schema = cf.schema();
-        bs = cdc::get_base_table(db.real_database(), *schema);
+        bs = cdc::get_base_table(_proxy.get_db().local(), *schema);
     } catch (...) {        
     }
  
@@ -476,39 +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([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;
@@ -516,7 +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);
@@ -542,7 +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);
         }
 
@@ -593,19 +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) {
@@ -617,11 +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)));
     });
@@ -729,18 +730,18 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
     }
 
     auto stream_arn = rjson::get<alternator::stream_arn>(request, "StreamArn");
-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();
     
     schema_ptr schema = nullptr;
     std::optional<shard_id> sid;
 
     try {
-        auto cf = db.find_column_family(table_id(stream_arn));
+        auto& cf = db.find_column_family(stream_arn);
         schema = cf.schema();
         sid = rjson::get<shard_id>(request, "ShardId");
     } catch (...) {
     }
-    if (!schema || !cdc::get_base_table(db.real_database(), *schema) || !is_alternator_keyspace(schema->ks_name())) {
+    if (!schema || !cdc::get_base_table(db, *schema) || !is_alternator_keyspace(schema->ks_name())) {
         throw api_error::resource_not_found("Invalid StreamArn");
     }
     if (!sid) {
@@ -766,7 +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;
     }
@@ -774,7 +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)));
 }
@@ -817,17 +818,17 @@ future<executor::request_return_type> executor::get_records(client_state& client
         throw api_error::validation("Limit must be 1 or more");
     }
 
-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();
     schema_ptr schema, base;
     try {
-        auto log_table = db.find_column_family(table_id(iter.table));
+        auto& log_table = db.find_column_family(iter.table);
         schema = log_table.schema();
-        base = cdc::get_base_table(db.real_database(), *schema);
+        base = cdc::get_base_table(db, *schema);
     } catch (...) {        
     }
 
     if (!schema || !base || !is_alternator_keyspace(schema->ks_name())) {
-        throw api_error::resource_not_found(fmt::to_string(iter.table));
+        throw api_error::resource_not_found(boost::lexical_cast<std::string>(iter.table));
     }
 
     tracing::add_table_name(trace_state, schema->ks_name(), schema->cf_name());
@@ -838,7 +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() });
 
@@ -850,18 +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");
 
-    std::optional<attrs_to_get> 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
-    std::optional<attrs_to_get> 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;
@@ -884,21 +883,12 @@ 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::tombstone_limit(_proxy.get_tombstone_limit()), 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 {       
-        cql3::selection::result_set_builder builder(*selection, gc_clock::now());
+        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();
@@ -930,13 +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;
@@ -951,10 +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
             }
 
@@ -986,17 +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) {
@@ -1010,7 +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
@@ -1019,15 +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) {
@@ -1040,31 +1028,28 @@ 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);
-            if (is_big(ret)) {
-                return make_ready_future<executor::request_return_type>(make_streamed(std::move(ret)));
-            }
             return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
         });
     });
 }
 
-void executor::add_stream_options(const rjson::value& stream_specification, schema_builder& builder, service::storage_proxy& sp) {
+void executor::add_stream_options(const rjson::value& stream_specification, schema_builder& builder) const {
     auto stream_enabled = rjson::find(stream_specification, "StreamEnabled");
     if (!stream_enabled || !stream_enabled->IsBool()) {
         throw api_error::validation("StreamSpecification needs boolean StreamEnabled");
     }
 
     if (stream_enabled->GetBool()) {
-        auto db = sp.data_dictionary();
+        auto& db = _proxy.get_db().local();
 
-        if (!db.features().cdc) {
+        if (!db.features().cluster_supports_cdc()) {
             throw api_error::validation("StreamSpecification: streams (CDC) feature not enabled in cluster.");
         }
-        if (!db.features().alternator_streams) {
+        if (!db.features().cluster_supports_alternator_streams()) {
             throw api_error::validation("StreamSpecification: alternator streams feature not enabled in cluster.");
         }
 
@@ -1096,17 +1081,17 @@ void executor::add_stream_options(const rjson::value& stream_specification, sche
     }
 }
 
-void executor::supplement_table_stream_info(rjson::value& descr, const schema& schema, const service::storage_proxy& sp) {
+void executor::supplement_table_stream_info(rjson::value& descr, const schema& schema) const {
     auto& opts = schema.cdc_options();
     if (opts.enabled()) {
-        auto db = sp.data_dictionary();
-        auto cf = db.find_table(schema.ks_name(), cdc::log_name(schema.cf_name()));
+        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()) {
@@ -1116,8 +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

@@ -1,18 +1,31 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "serializer.hh"
-#include "schema/schema.hh"
+#include "schema.hh"
 #include "db/extensions.hh"
 
-namespace db {
+namespace alternator {
 
 class tags_extension : public schema_extension {
 public:
@@ -37,9 +50,4 @@ private:
     std::map<sstring, sstring> _tags;
 };
 
-// Information whether the view updates are synchronous is stored using the
-// SYNCHRONOUS_VIEW_UPDATES_TAG_KEY tag. Value of this tag is a stored as a
-// serialized boolean value ("true" or "false")
-static const sstring SYNCHRONOUS_VIEW_UPDATES_TAG_KEY("system:synchronous_view_updates");
-
 }

alternator/ttl.cc

@@ -1,851 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <chrono>
-#include <cstdint>
-#include <exception>
-#include <optional>
-#include <seastar/core/sstring.hh>
-#include <seastar/core/coroutine.hh>
-#include <seastar/core/sleep.hh>
-#include <seastar/core/future.hh>
-#include <seastar/core/lowres_clock.hh>
-#include <seastar/coroutine/maybe_yield.hh>
-#include <boost/multiprecision/cpp_int.hpp>
-
-#include "exceptions/exceptions.hh"
-#include "gms/gossiper.hh"
-#include "gms/inet_address.hh"
-#include "inet_address_vectors.hh"
-#include "locator/abstract_replication_strategy.hh"
-#include "log.hh"
-#include "gc_clock.hh"
-#include "replica/database.hh"
-#include "service_permit.hh"
-#include "timestamp.hh"
-#include "service/storage_proxy.hh"
-#include "service/pager/paging_state.hh"
-#include "service/pager/query_pagers.hh"
-#include "gms/feature_service.hh"
-#include "sstables/types.hh"
-#include "mutation/mutation.hh"
-#include "types/types.hh"
-#include "types/map.hh"
-#include "utils/rjson.hh"
-#include "utils/big_decimal.hh"
-#include "utils/fb_utilities.hh"
-#include "cql3/selection/selection.hh"
-#include "cql3/values.hh"
-#include "cql3/query_options.hh"
-#include "cql3/column_identifier.hh"
-#include "alternator/executor.hh"
-#include "alternator/controller.hh"
-#include "alternator/serialization.hh"
-#include "dht/sharder.hh"
-#include "db/config.hh"
-#include "db/tags/utils.hh"
-
-#include "ttl.hh"
-
-static logging::logger tlogger("alternator_ttl");
-
-namespace alternator {
-
-// We write the expiration-time attribute enabled on a table using a
-// tag TTL_TAG_KEY.
-// Currently, the *value* of this tag is simply the name of the attribute,
-// and the expiration scanner interprets it as an Alternator attribute name -
-// It can refer to a real column or if that doesn't exist, to a member of
-// the ":attrs" map column. Although this is designed for Alternator, it may
-// be good enough for CQL as well (there, the ":attrs" column won't exist).
-static const sstring TTL_TAG_KEY("system:ttl_attribute");
-
-future<executor::request_return_type> executor::update_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.update_time_to_live++;
-    if (!_proxy.data_dictionary().features().alternator_ttl) {
-        co_return api_error::unknown_operation("UpdateTimeToLive not yet supported. Experimental support is available if the 'alternator-ttl' experimental feature is enabled on all nodes.");
-    }
-
-    schema_ptr schema = get_table(_proxy, request);
-    rjson::value* spec = rjson::find(request, "TimeToLiveSpecification");
-    if (!spec || !spec->IsObject()) {
-        co_return api_error::validation("UpdateTimeToLive missing mandatory TimeToLiveSpecification");
-    }
-    const rjson::value* v = rjson::find(*spec, "Enabled");
-    if (!v || !v->IsBool()) {
-        co_return api_error::validation("UpdateTimeToLive requires boolean Enabled");
-    }
-    bool enabled = v->GetBool();
-    v = rjson::find(*spec, "AttributeName");
-    if (!v || !v->IsString()) {
-        co_return api_error::validation("UpdateTimeToLive requires string AttributeName");
-    }
-    // Although the DynamoDB documentation specifies that attribute names
-    // should be between 1 and 64K bytes, in practice, it only allows
-    // between 1 and 255 bytes. There are no other limitations on which
-    // characters are allowed in the name.
-    if (v->GetStringLength() < 1 || v->GetStringLength() > 255) {
-        co_return api_error::validation("The length of AttributeName must be between 1 and 255");
-    }
-    sstring attribute_name(v->GetString(), v->GetStringLength());
-
-    co_await db::modify_tags(_mm, schema->ks_name(), schema->cf_name(), [&](std::map<sstring, sstring>& tags_map) {
-        if (enabled) {
-            if (tags_map.contains(TTL_TAG_KEY)) {
-                throw 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()) {
-                throw api_error::validation("TTL is already disabled");
-            } else if (i->second != attribute_name) {
-                throw 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);
-        }
-    });
-
-    // Prepare the response, which contains a TimeToLiveSpecification
-    // basically identical to the request's
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveSpecification", std::move(*spec));
-    co_return make_jsonable(std::move(response));
-}
-
-future<executor::request_return_type> executor::describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.describe_time_to_live++;
-    schema_ptr schema = get_table(_proxy, request);
-    std::map<sstring, sstring> tags_map = get_tags_of_table_or_throw(schema);
-    rjson::value desc = rjson::empty_object();
-    auto i = tags_map.find(TTL_TAG_KEY);
-    if (i == tags_map.end()) {
-        rjson::add(desc, "TimeToLiveStatus", "DISABLED");
-    } else {
-        rjson::add(desc, "TimeToLiveStatus", "ENABLED");
-        rjson::add(desc, "AttributeName", rjson::from_string(i->second));
-    }
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveDescription", std::move(desc));
-    co_return make_jsonable(std::move(response));
-}
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLive request.
-//
-// Here is a brief overview of how the expiration service works:
-//
-// An expiration thread on each shard periodically scans the items (i.e.,
-// rows) owned by this shard, looking for items whose chosen expiration-time
-// attribute indicates they are expired, and deletes those items.
-// The expiration-time "attribute" can be either an actual Scylla column
-// (must be numeric) or an Alternator "attribute" - i.e., an element in
-// the ATTRS_COLUMN_NAME map<utf8,bytes> column where the numeric expiration
-// time is encoded in DynamoDB's JSON encoding inside the bytes value.
-// To avoid scanning the same items RF times in RF replicas, only one node is
-// responsible for scanning a token range at a time. Normally, this is the
-// node owning this range as a "primary range" (the first node in the ring
-// with this range), but when this node is down, the secondary owner (the
-// second in the ring) may take over.
-// An expiration thread is reponsible for all tables which need expiration
-// scans. Currently, the different tables are scanned sequentially (not in
-// parallel).
-// The expiration thread scans item using CL=QUORUM to ensures that it reads
-// a consistent expiration-time attribute. This means that the items are read
-// locally and in addition QUORUM-1 additional nodes (one additional node
-// when RF=3) need to read the data and send digests.
-// When the expiration thread decides that an item has expired and wants
-// to delete it, it does it using a CL=QUORUM write. This allows this
-// deletion to be visible for consistent (quorum) reads. The deletion,
-// like user deletions, will also appear on the CDC log and therefore
-// Alternator Streams if enabled - currently as ordinary deletes (the
-// userIdentity flag is currently missing this is issue #11523).
-expiration_service::expiration_service(data_dictionary::database db, service::storage_proxy& proxy, gms::gossiper& g)
-        : _db(db)
-        , _proxy(proxy)
-        , _gossiper(g)
-{
-}
-
-// Convert the big_decimal used to represent expiration time to an integer.
-// Any fractional part is dropped. If the number is negative or invalid,
-// 0 is returned, and if it's too high, the maximum unsigned long is returned.
-static unsigned long bigdecimal_to_ul(const big_decimal& bd) {
-    // The big_decimal format has an integer mantissa of arbitrary length
-    // "unscaled_value" and then a (power of 10) exponent "scale".
-    if (bd.unscaled_value() <= 0) {
-        return 0;
-    }
-    if (bd.scale() == 0) {
-        // The fast path, when the expiration time is an integer, scale==0.
-        return static_cast<unsigned long>(bd.unscaled_value());
-    }
-    // Because the mantissa can be of arbitrary length, we work on it
-    // as a string. TODO: find a less ugly algorithm.
-    auto str = bd.unscaled_value().str();
-    if (bd.scale() > 0) {
-        int len = str.length();
-        if (len < bd.scale()) {
-            return 0;
-        }
-        str = str.substr(0, len-bd.scale());
-    } else {
-        if (bd.scale() < -20) {
-            return std::numeric_limits<unsigned long>::max();
-        }
-        for (int i = 0; i < -bd.scale(); i++) {
-            str.push_back('0');
-        }
-    }
-    // strtoul() returns ULONG_MAX if the number is too large, or 0 if not
-    // a number.
-    return strtoul(str.c_str(), nullptr, 10);
-}
-
-// The following is_expired() functions all check if an item with the given
-// expiration time has expired, according to the DynamoDB API rules.
-// The rules are:
-// 1. If the expiration time attribute's value is not a number type,
-//    the item is not expired.
-// 2. The expiration time is measured in seconds since the UNIX epoch.
-// 3. If the expiration time is more than 5 years in the past, it is assumed
-//    to be malformed and ignored - and the item does not expire.
-static bool is_expired(gc_clock::time_point expiration_time, gc_clock::time_point now) {
-    return expiration_time <= now &&
-           expiration_time > now - std::chrono::years(5);
-}
-
-static bool is_expired(const big_decimal& expiration_time, gc_clock::time_point now) {
-    unsigned long t = bigdecimal_to_ul(expiration_time);
-    // We assume - and the assumption turns out to be correct - that the
-    // epoch of gc_clock::time_point and the one used by the DynamoDB protocol
-    // are the same (the UNIX epoch in UTC). The resolution (seconds) is also
-    // the same.
-    return is_expired(gc_clock::time_point(gc_clock::duration(std::chrono::seconds(t))), now);
-}
-static bool is_expired(const rjson::value& expiration_time, gc_clock::time_point now) {
-    std::optional<big_decimal> n = try_unwrap_number(expiration_time);
-    return n && is_expired(*n, now);
-}
-
-// expire_item() expires an item - i.e., deletes it as appropriate for
-// expiration - with CL=QUORUM and (FIXME!) in a way Alternator Streams
-// understands it is an expiration event - not a user-initiated deletion.
-static future<> expire_item(service::storage_proxy& proxy,
-                            const service::query_state& qs,
-                            const std::vector<managed_bytes_opt>& row,
-                            schema_ptr schema,
-                            api::timestamp_type ts) {
-    // Prepare the row key to delete
-    // NOTICE: the order of columns is guaranteed by the fact that selection::wildcard
-    // is used, which indicates that columns appear in the order defined by
-    // schema::all_columns_in_select_order() - partition key columns goes first,
-    // immediately followed by clustering key columns
-    std::vector<bytes> exploded_pk;
-    const unsigned pk_size = schema->partition_key_size();
-    const unsigned ck_size = schema->clustering_key_size();
-    for (unsigned c = 0; c < pk_size; ++c) {
-        const auto& row_c = row[c];
-        if (!row_c) {
-            // This shouldn't happen - all key columns must have values.
-            // But if it ever happens, let's just *not* expire the item.
-            // FIXME: log or increment a metric if this happens.
-            return make_ready_future<>();
-        }
-        exploded_pk.push_back(to_bytes(*row_c));
-    }
-    auto pk = partition_key::from_exploded(exploded_pk);
-    mutation m(schema, pk);
-    // If there's no clustering key, a tombstone should be created directly
-    // on a partition, not on a clustering row - otherwise it will look like
-    // an open-ended range tombstone, which will crash on KA/LA sstable format.
-    // See issue #6035
-    if (ck_size == 0) {
-        m.partition().apply(tombstone(ts, gc_clock::now()));
-    } else {
-        std::vector<bytes> exploded_ck;
-        for (unsigned c = pk_size; c < pk_size + ck_size; ++c) {
-            const auto& row_c = row[c];
-            if (!row_c) {
-                // This shouldn't happen - all key columns must have values.
-                // But if it ever happens, let's just *not* expire the item.
-                // FIXME: log or increment a metric if this happens.
-                return make_ready_future<>();
-            }
-            exploded_ck.push_back(to_bytes(*row_c));
-        }
-        auto ck = clustering_key::from_exploded(exploded_ck);
-        m.partition().clustered_row(*schema, ck).apply(tombstone(ts, gc_clock::now()));
-    }
-    std::vector<mutation> mutations;
-    mutations.push_back(std::move(m));
-    return proxy.mutate(std::move(mutations),
-        db::consistency_level::LOCAL_QUORUM,
-        executor::default_timeout(), // FIXME - which timeout?
-        qs.get_trace_state(), qs.get_permit(),
-        db::allow_per_partition_rate_limit::no);
-}
-
-static size_t random_offset(size_t min, size_t max) {
-    static thread_local std::default_random_engine re{std::random_device{}()};
-    std::uniform_int_distribution<size_t> dist(min, max);
-    return dist(re);
-}
-
-// Get a list of secondary token ranges for the given node, and the primary
-// node responsible for each of these token ranges.
-// A "secondary range" is a range of tokens where for each token, the second
-// node (in ring order) out of the RF replicas that hold this token is the
-// given node.
-// In the expiration scanner, we want to scan a secondary range but only if
-// this range's primary node is down. For this we need to return not just
-// a list of this node's secondary ranges - but also the primary owner of
-// each of those ranges.
-static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary_ranges(
-        const locator::effective_replication_map_ptr& erm,
-        gms::inet_address ep) {
-    const auto& tm = *erm->get_token_metadata_ptr();
-    const auto& sorted_tokens = tm.sorted_tokens();
-    std::vector<std::pair<dht::token_range, gms::inet_address>> ret;
-    if (sorted_tokens.empty()) {
-        on_internal_error(tlogger, "Token metadata is empty");
-    }
-    auto prev_tok = sorted_tokens.back();
-    for (const auto& tok : sorted_tokens) {
-        inet_address_vector_replica_set eps = erm->get_natural_endpoints(tok);
-        if (eps.size() <= 1 || eps[1] != ep) {
-            prev_tok = tok;
-            continue;
-        }
-        // Add the range (prev_tok, tok] to ret. However, if the range wraps
-        // around, split it to two non-wrapping ranges.
-        if (prev_tok < tok) {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        } else {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    std::nullopt},
-                eps[0]);
-            ret.emplace_back(
-                dht::token_range{
-                    std::nullopt,
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        }
-        prev_tok = tok;
-    }
-    return ret;
-}
-
-
-// A class for iterating over all the token ranges *owned* by this shard.
-// To avoid code duplication, it is a template with two distinct cases -
-// <primary> and <secondary>:
-//
-// In the <primary> case, we consider a token *owned* by this shard if:
-// 1. This node is a replica for this token.
-// 2. Moreover, this node is the *primary* replica of the token (i.e., the
-//    first replica in the ring).
-// 3. In this node, this shard is responsible for this token.
-// We will use this definition of which shard in the cluster owns which tokens
-// to split the expiration scanner's work between all the shards of the
-// system.
-//
-// In the <secondary> case, we consider a token *owned* by this shard if:
-// 1. This node is the *secondary* replica for this token (i.e., the second
-//    replica in the ring).
-// 2. The primary replica for this token is currently marked down.
-// 3. In this node, this shard is responsible for this token.
-// We use the <secondary> case to handle the possibility that some of the
-// nodes in the system are down. A dead node will not be expiring
-// the tokens owned by it, so we want the secondary owner to take over its
-// primary ranges.
-//
-// FIXME: need to decide how to choose primary ranges in multi-DC setup!
-// We could call get_primary_ranges_within_dc() below instead of get_primary_ranges().
-// NOTICE: Iteration currently starts from a random token range in order to improve
-// the chances of covering all ranges during a scan when restarts occur.
-// A more deterministic way would be to regularly persist the scanning state,
-// but that incurs overhead that we want to avoid if not needed.
-enum primary_or_secondary_t {primary, secondary};
-template<primary_or_secondary_t primary_or_secondary>
-class token_ranges_owned_by_this_shard {
-    // ranges_holder_primary holds just the primary ranges themselves
-    class ranges_holder_primary {
-        const dht::token_range_vector _token_ranges;
-     public:
-        ranges_holder_primary(const locator::vnode_effective_replication_map_ptr& erm, gms::gossiper& g, gms::inet_address ep)
-            : _token_ranges(erm->get_primary_ranges(ep)) {}
-        std::size_t size() const { return _token_ranges.size(); }
-        const dht::token_range& operator[](std::size_t i) const {
-            return _token_ranges[i];
-        }
-        bool should_skip(std::size_t i) const {
-            return false;
-        }
-    };
-    // ranges_holder<secondary> holds the secondary token ranges plus each
-    // range's primary owner, needed to implement should_skip().
-    class ranges_holder_secondary {
-        std::vector<std::pair<dht::token_range, gms::inet_address>> _token_ranges;
-        gms::gossiper& _gossiper;
-     public:
-        ranges_holder_secondary(const locator::effective_replication_map_ptr& erm, gms::gossiper& g, gms::inet_address ep)
-            : _token_ranges(get_secondary_ranges(erm, ep))
-            , _gossiper(g) {}
-        std::size_t size() const { return _token_ranges.size(); }
-        const dht::token_range& operator[](std::size_t i) const {
-            return _token_ranges[i].first;
-        }
-        // range i should be skipped if its primary owner is alive.
-        bool should_skip(std::size_t i) const {
-            return _gossiper.is_alive(_token_ranges[i].second);
-        }
-    };
-
-    schema_ptr _s;
-    // _token_ranges will contain a list of token ranges owned by this node.
-    // We'll further need to split each such range to the pieces owned by
-    // the current shard, using _intersecter.
-    using ranges_holder = std::conditional_t<
-            primary_or_secondary == primary_or_secondary_t::primary,
-            ranges_holder_primary,
-            ranges_holder_secondary>;
-    const ranges_holder _token_ranges;
-    // NOTICE: _range_idx is used modulo _token_ranges size when accessing
-    // the data to ensure that it doesn't go out of bounds
-    size_t _range_idx;
-    size_t _end_idx;
-    std::optional<dht::selective_token_range_sharder> _intersecter;
-    locator::effective_replication_map_ptr _erm;
-public:
-    token_ranges_owned_by_this_shard(replica::database& db, gms::gossiper& g, schema_ptr s)
-        :  _s(s)
-        , _token_ranges(db.find_keyspace(s->ks_name()).get_effective_replication_map(),
-                g, utils::fb_utilities::get_broadcast_address())
-        , _range_idx(random_offset(0, _token_ranges.size() - 1))
-        , _end_idx(_range_idx + _token_ranges.size())
-        , _erm(s->table().get_effective_replication_map())
-    {
-        tlogger.debug("Generating token ranges starting from base range {} of {}", _range_idx, _token_ranges.size());
-    }
-
-    // Return the next token_range owned by this shard, or nullopt when the
-    // iteration ends.
-    std::optional<dht::token_range> next() {
-        // We may need three or more iterations in the following loop if a
-        // vnode doesn't intersect with the given shard at all (such a small
-        // vnode is unlikely, but possible). The loop cannot be infinite
-        // because each iteration of the loop advances _range_idx.
-        for (;;) {
-            if (_intersecter) {
-                std::optional<dht::token_range> ret = _intersecter->next();
-                if (ret) {
-                    return ret;
-                }
-                // done with this range, go to next one
-                ++_range_idx;
-                _intersecter = std::nullopt;
-            }
-            if (_range_idx == _end_idx) {
-                return std::nullopt;
-            }
-            // If should_skip(), the range should be skipped. This happens for
-            // a secondary range whose primary owning node is still alive.
-            while (_token_ranges.should_skip(_range_idx % _token_ranges.size())) {
-                ++_range_idx;
-                if (_range_idx == _end_idx) {
-                    return std::nullopt;
-                }
-            }
-            _intersecter.emplace(_erm->get_sharder(*_s), _token_ranges[_range_idx % _token_ranges.size()], this_shard_id());
-        }
-    }
-
-    // Same as next(), just return a partition_range instead of token_range
-    std::optional<dht::partition_range> next_partition_range() {
-        std::optional<dht::token_range> ret = next();
-        if (ret) {
-            return dht::to_partition_range(*ret);
-        } else {
-            return std::nullopt;
-        }
-    }
-};
-
-// Precomputed information needed to perform a scan on partition ranges
-struct scan_ranges_context {
-    schema_ptr s;
-    bytes column_name;
-    std::optional<std::string> member;
-
-    ::shared_ptr<cql3::selection::selection> selection;
-    std::unique_ptr<service::query_state> query_state_ptr;
-    std::unique_ptr<cql3::query_options> query_options;
-    ::lw_shared_ptr<query::read_command> command;
-
-    scan_ranges_context(schema_ptr s, service::storage_proxy& proxy, bytes column_name, std::optional<std::string> member)
-        : s(s)
-        , column_name(column_name)
-        , member(member)
-    {
-        // FIXME: don't read the entire items - read only parts of it.
-        // We must read the key columns (to be able to delete) and also
-        // the requested attribute. If the requested attribute is a map's
-        // member we may be forced to read the entire map - but it would
-        // be good if we can read only the single item of the map - it
-        // should be possible (and a must for issue #7751!).
-        lw_shared_ptr<service::pager::paging_state> paging_state = nullptr;
-        auto regular_columns = boost::copy_range<query::column_id_vector>(
-            s->regular_columns() | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.id; }));
-        selection = cql3::selection::selection::wildcard(s);
-        query::partition_slice::option_set opts = selection->get_query_options();
-        opts.set<query::partition_slice::option::allow_short_read>();
-        // It is important that the scan bypass cache to avoid polluting it:
-        opts.set<query::partition_slice::option::bypass_cache>();
-        std::vector<query::clustering_range> ck_bounds{query::clustering_range::make_open_ended_both_sides()};
-        auto partition_slice = query::partition_slice(std::move(ck_bounds), {}, std::move(regular_columns), opts);
-        command = ::make_lw_shared<query::read_command>(s->id(), s->version(), partition_slice, proxy.get_max_result_size(partition_slice), query::tombstone_limit(proxy.get_tombstone_limit()));
-        executor::client_state client_state{executor::client_state::internal_tag()};
-        tracing::trace_state_ptr trace_state;
-        // NOTICE: empty_service_permit is used because the TTL service has fixed parallelism
-        query_state_ptr = std::make_unique<service::query_state>(client_state, trace_state, empty_service_permit());
-        // FIXME: What should we do on multi-DC? Will we run the expiration on the same ranges on all
-        // DCs or only once for each range? If the latter, we need to change the CLs in the
-        // scanner and deleter.
-        db::consistency_level cl = db::consistency_level::LOCAL_QUORUM;
-        query_options = std::make_unique<cql3::query_options>(cl, std::vector<cql3::raw_value>{});
-        query_options = std::make_unique<cql3::query_options>(std::move(query_options), std::move(paging_state));
-    }
-};
-
-// Scan data in a list of token ranges in one table, looking for expired
-// items and deleting them.
-// Because of issue #9167, partition_ranges must have a single partition
-// range for this code to work correctly.
-static future<> scan_table_ranges(
-        service::storage_proxy& proxy,
-        const scan_ranges_context& scan_ctx,
-        dht::partition_range_vector&& partition_ranges,
-        abort_source& abort_source,
-        named_semaphore& page_sem,
-        expiration_service::stats& expiration_stats)
-{
-    const schema_ptr& s = scan_ctx.s;
-    assert (partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
-    auto p = service::pager::query_pagers::pager(proxy, s, scan_ctx.selection, *scan_ctx.query_state_ptr,
-            *scan_ctx.query_options, scan_ctx.command, std::move(partition_ranges), nullptr);
-    while (!p->is_exhausted()) {
-        if (abort_source.abort_requested()) {
-            co_return;
-        }
-        auto units = co_await get_units(page_sem, 1);
-        // We don't need to limit page size in number of rows because there is
-        // a builtin limit of the page's size in bytes. Setting this limit to
-        // 1 is useful for debugging the paging code with moderate-size data.
-        uint32_t limit = std::numeric_limits<uint32_t>::max();
-        // Read a page, and if that times out, try again after a small sleep.
-        // If we didn't catch the timeout exception, it would cause the scan
-        // be aborted and only be restarted at the next scanning period.
-        // If we retry too many times, give up and restart the scan later.
-        std::unique_ptr<cql3::result_set> rs;
-        for (int retries=0; ; retries++) {
-            try {
-                // FIXME: which timeout?
-                rs = co_await p->fetch_page(limit, gc_clock::now(), executor::default_timeout());
-                break;
-            } catch(exceptions::read_timeout_exception&) {
-                tlogger.warn("expiration scanner read timed out, will retry: {}",
-                    std::current_exception());
-            }
-            // If we didn't break out of this loop, add a minimal sleep
-            if (retries >= 10) {
-                // Don't get stuck forever asking the same page, maybe there's
-                // a bug or a real problem in several replicas. Give up on
-                // this scan an retry the scan from a random position later,
-                // in the next scan period.
-                throw runtime_exception("scanner thread failed after too many timeouts for the same page");
-            }
-            co_await sleep_abortable(std::chrono::seconds(1), abort_source);
-        }
-        auto rows = rs->rows();
-        auto meta = rs->get_metadata().get_names();
-        std::optional<unsigned> expiration_column;
-        for (unsigned i = 0; i < meta.size(); i++) {
-            const cql3::column_specification& col = *meta[i];
-            if (col.name->name() == scan_ctx.column_name) {
-                expiration_column = i;
-                break;
-            }
-        }
-        if (!expiration_column) {
-            continue;
-        }
-        for (const auto& row : rows) {
-            const managed_bytes_opt& cell = row[*expiration_column];
-            if (!cell) {
-                continue;
-            }
-            auto v = meta[*expiration_column]->type->deserialize(*cell);
-            bool expired = false;
-            // FIXME: don't recalculate "now" all the time
-            auto now = gc_clock::now();
-            if (scan_ctx.member) {
-                // In this case, the expiration-time attribute we're
-                // looking for is a member in a map, saved serialized
-                // into bytes using Alternator's serialization (basically
-                // a JSON serialized into bytes)
-                // FIXME: is it possible to find a specific member of a map
-                // without iterating through it like we do here and compare
-                // the key?
-                for (const auto& entry : value_cast<map_type_impl::native_type>(v)) {
-                    std::string attr_name = value_cast<sstring>(entry.first);
-                    if (value_cast<sstring>(entry.first) == *scan_ctx.member) {
-                        bytes value = value_cast<bytes>(entry.second);
-                        rjson::value json = deserialize_item(value);
-                        expired = is_expired(json, now);
-                        break;
-                    }
-                }
-            } else {
-                // For a real column to contain an expiration time, it
-                // must be a numeric type.
-                // FIXME: Currently we only support decimal_type (which is
-                // what Alternator uses), but other numeric types can be
-                // supported as well to make this feature more useful in CQL.
-                // Note that kind::decimal is also checked above.
-                big_decimal n = value_cast<big_decimal>(v);
-                expired = is_expired(n, now);
-            }
-            if (expired) {
-                expiration_stats.items_deleted++;
-                // FIXME: maybe don't recalculate new_timestamp() all the time
-                // FIXME: if expire_item() throws on timeout, we need to retry it.
-                auto ts = api::new_timestamp();
-                co_await expire_item(proxy, *scan_ctx.query_state_ptr, row, s, ts);
-            }
-        }
-        // FIXME: once in a while, persist p->state(), so on reboot
-        // we don't start from scratch.
-    }
-}
-
-// scan_table() scans, in one table, data "owned" by this shard, looking for
-// expired items and deleting them.
-// We consider each node to "own" its primary token ranges, i.e., the tokens
-// that this node is their first replica in the ring. Inside the node, each
-// shard "owns" subranges of the node's token ranges - according to the node's
-// sharding algorithm.
-// When a node goes down, the token ranges owned by it will not be scanned
-// and items in those token ranges will not expire, so in the future (FIXME)
-// this function should additionally work on token ranges whose primary owner
-// is down and this node is the range's secondary owner.
-// If the TTL (expiration-time scanning) feature is not enabled for this
-// table, scan_table() returns false without doing anything. Remember that the
-// TTL feature may be enabled later so this function will need to be called
-// again when the feature is enabled.
-// Currently this function scans the entire table (or, rather the parts owned
-// by this shard) at full rate, once. In the future (FIXME) we should consider
-// how to pace this scan, how and when to repeat it, how to interleave or
-// parallelize scanning of multiple tables, and how to continue scans after a
-// reboot.
-static future<bool> scan_table(
-    service::storage_proxy& proxy,
-    data_dictionary::database db,
-    gms::gossiper& gossiper,
-    schema_ptr s,
-    abort_source& abort_source,
-    named_semaphore& page_sem,
-    expiration_service::stats& expiration_stats)
-{
-    // Check if an expiration-time attribute is enabled for this table.
-    // If not, just return false immediately.
-    // FIXME: the setting of the TTL may change in the middle of a long scan!
-    std::optional<std::string> attribute_name = db::find_tag(*s, TTL_TAG_KEY);
-    if (!attribute_name) {
-        co_return false;
-    }
-    // attribute_name may be one of the schema's columns (in Alternator, this
-    // means it's a key column), or an element in Alternator's attrs map
-    // encoded in Alternator's JSON encoding.
-    // FIXME: To make this less Alternators-specific, we should encode in the
-    // single key's value three things:
-    // 1. The name of a column
-    // 2. Optionally if column is a map, a member in the map
-    // 3. The deserializer for the value: CQL or Alternator (JSON).
-    // The deserializer can be guessed: If the given column or map item is
-    // numeric, it can be used directly. If it is a "bytes" type, it needs to
-    // be deserialized using Alternator's deserializer.
-    bytes column_name = to_bytes(*attribute_name);
-    const column_definition *cd = s->get_column_definition(column_name);
-    std::optional<std::string> member;
-    if (!cd) {
-        member = std::move(attribute_name);
-        column_name = bytes(executor::ATTRS_COLUMN_NAME);
-        cd = s->get_column_definition(column_name);
-        tlogger.info("table {} TTL enabled with attribute {} in {}", s->cf_name(), *member, executor::ATTRS_COLUMN_NAME);
-    } else {
-        tlogger.info("table {} TTL enabled with attribute {}", s->cf_name(), *attribute_name);
-    }
-    if (!cd) {
-        tlogger.info("table {} TTL column is missing, not scanning", s->cf_name());
-        co_return false;
-    }
-    data_type column_type = cd->type;
-    // Verify that the column has the right type: If "member" exists
-    // the column must be a map, and if it doesn't, the column must
-    // (currently) be a decimal_type. If the column has the wrong type
-    // nothing can get expired in this table, and it's pointless to
-    // scan it.
-    if ((member && column_type->get_kind() != abstract_type::kind::map) ||
-        (!member && column_type->get_kind() != abstract_type::kind::decimal)) {
-        tlogger.info("table {} TTL column has unsupported type, not scanning", s->cf_name());
-        co_return false;
-    }
-    expiration_stats.scan_table++;
-    // FIXME: need to pace the scan, not do it all at once.
-    scan_ranges_context scan_ctx{s, proxy, std::move(column_name), std::move(member)};
-    token_ranges_owned_by_this_shard<primary> my_ranges(db.real_database(), gossiper, s);
-    while (std::optional<dht::partition_range> range = my_ranges.next_partition_range()) {
-        // Note that because of issue #9167 we need to run a separate
-        // query on each partition range, and can't pass several of
-        // them into one partition_range_vector.
-        dht::partition_range_vector partition_ranges;
-        partition_ranges.push_back(std::move(*range));
-        // FIXME: if scanning a single range fails, including network errors,
-        // we fail the entire scan (and rescan from the beginning). Need to
-        // reconsider this. Saving the scan position might be a good enough
-        // solution for this problem.
-        co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem, expiration_stats);
-    }
-    // If each node only scans its own primary ranges, then when any node is
-    // down part of the token range will not get scanned. This can be viewed
-    // as acceptable (when the comes back online, it will resume its scan),
-    // but as noted in issue #9787, we can allow more prompt expiration
-    // by tasking another node to take over scanning of the dead node's primary
-    // ranges. What we do here is that this node will also check expiration
-    // on its *secondary* ranges - but only those whose primary owner is down.
-    token_ranges_owned_by_this_shard<secondary> my_secondary_ranges(db.real_database(), gossiper, s);
-    while (std::optional<dht::partition_range> range = my_secondary_ranges.next_partition_range()) {
-        expiration_stats.secondary_ranges_scanned++;
-        dht::partition_range_vector partition_ranges;
-        partition_ranges.push_back(std::move(*range));
-        co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem, expiration_stats);
-    }
-    co_return true;
-}
-
-
-future<> expiration_service::run() {
-    // FIXME: don't just tight-loop, think about timing, pace, and
-    // store position in durable storage, etc.
-    // FIXME: think about working on different tables in parallel.
-    // also need to notice when a new table is added, a table is
-    // deleted or when ttl is enabled or disabled for a table!
-    for (;;) {
-        auto start = lowres_clock::now();
-        // _db.tables() may change under our feet during a
-        // long-living loop, so we must keep our own copy of the list of
-        // schemas.
-        std::vector<schema_ptr> schemas;
-        for (auto cf : _db.get_tables()) {
-            schemas.push_back(cf.schema());
-        }
-        for (schema_ptr s : schemas) {
-            co_await coroutine::maybe_yield();
-            if (shutting_down()) {
-                co_return;
-            }
-            try {
-                co_await scan_table(_proxy, _db, _gossiper, s, _abort_source, _page_sem, _expiration_stats);
-            } catch (...) {
-                // The scan of a table may fail in the middle for many
-                // reasons, including network failure and even the table
-                // being removed. We'll continue scanning this table later
-                // (if it still exists). In any case it's important to catch
-                // the exception and not let the scanning service die for
-                // good.
-                // If the table has been deleted, it is expected that the scan
-                // will fail at some point, and even a warning is excessive.
-                if (_db.has_schema(s->ks_name(), s->cf_name())) {
-                    tlogger.warn("table {}.{} expiration scan failed: {}",
-                        s->ks_name(), s->cf_name(), std::current_exception());
-                } else {
-                    tlogger.info("expiration scan failed when table {}.{} was deleted",
-                        s->ks_name(), s->cf_name());
-                }
-            }
-        }
-        _expiration_stats.scan_passes++;
-        // The TTL scanner runs above once over all tables, at full steam.
-        // After completing such a scan, we sleep until it's time start
-        // another scan. TODO: If the scan went too fast, we can slow it down
-        // in the next iteration by reducing the scanner's scheduling-group
-        // share (if using a separate scheduling group), or introduce
-        // finer-grain sleeps into the scanning code.
-        std::chrono::milliseconds scan_duration(std::chrono::duration_cast<std::chrono::milliseconds>(lowres_clock::now() - start));
-        std::chrono::milliseconds period(long(_db.get_config().alternator_ttl_period_in_seconds() * 1000));
-        if (scan_duration < period) {
-            try {
-                tlogger.info("sleeping {} seconds until next period", (period - scan_duration).count()/1000.0);
-                co_await seastar::sleep_abortable(period - scan_duration, _abort_source);
-            } catch(seastar::sleep_aborted&) {}
-        } else {
-                tlogger.warn("scan took {} seconds, longer than period - not sleeping", scan_duration.count()/1000.0);
-        }
-    }
-}
-
-future<> expiration_service::start() {
-    // Called by main() on each shard to start the expiration-service
-    // thread. Just runs run() in the background and allows stop().
-    if (_db.features().alternator_ttl) {
-        if (!shutting_down()) {
-            _end = run().handle_exception([] (std::exception_ptr ep) {
-                tlogger.error("expiration_service failed: {}", ep);
-            });
-        }
-    }
-    return make_ready_future<>();
-}
-
-future<> expiration_service::stop() {
-    if (_abort_source.abort_requested()) {
-        throw std::logic_error("expiration_service::stop() called a second time");
-    }
-    _abort_source.request_abort();
-    if (!_end) {
-        // if _end is was not set, start() was never called
-        return make_ready_future<>();
-    }
-    return std::move(*_end);
-}
-
-expiration_service::stats::stats() {
-    _metrics.add_group("expiration", {
-        seastar::metrics::make_total_operations("scan_passes", scan_passes,
-            seastar::metrics::description("number of passes over the database")),
-        seastar::metrics::make_total_operations("scan_table", scan_table,
-            seastar::metrics::description("number of table scans (counting each scan of each table that enabled expiration)")),
-        seastar::metrics::make_total_operations("items_deleted", items_deleted,
-            seastar::metrics::description("number of items deleted after expiration")),
-        seastar::metrics::make_total_operations("secondary_ranges_scanned", secondary_ranges_scanned,
-            seastar::metrics::description("number of token ranges scanned by this node while their primary owner was down")),
-    });
-}
-
-
-} // namespace alternator

alternator/ttl.hh

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

amplify.yml

@@ -1,15 +0,0 @@
-version: 1
-applications:
-  - frontend:
-      phases:
-        build:
-          commands:
-            - make setupenv
-            - make dirhtml
-      artifacts:
-        baseDirectory: _build/dirhtml
-        files:
-          - '**/*'
-      cache:
-        paths: []
-    appRoot: docs

api/CMakeLists.txt

@@ -1,71 +0,0 @@
-# Generate C++ sources from Swagger definitions
-set(swagger_files
-  api-doc/authorization_cache.json
-  api-doc/cache_service.json
-  api-doc/collectd.json
-  api-doc/column_family.json
-  api-doc/commitlog.json
-  api-doc/compaction_manager.json
-  api-doc/config.json
-  api-doc/endpoint_snitch_info.json
-  api-doc/error_injection.json
-  api-doc/failure_detector.json
-  api-doc/gossiper.json
-  api-doc/hinted_handoff.json
-  api-doc/lsa.json
-  api-doc/messaging_service.json
-  api-doc/metrics.json
-  api-doc/storage_proxy.json
-  api-doc/storage_service.json
-  api-doc/stream_manager.json
-  api-doc/system.json
-  api-doc/task_manager.json
-  api-doc/task_manager_test.json
-  api-doc/utils.json)
-
-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_CURRENT_SOURCE_DIR}/${f}"
-    OUT_DIR "${scylla_gen_build_dir}/api/${dir}")
-  list(APPEND swagger_gen_files "${scylla_swagger_gen_${fname}_files}")
-endforeach()
-
-add_library(api)
-target_sources(api
-  PRIVATE
-    api.cc
-    cache_service.cc
-    collectd.cc
-    column_family.cc
-    commitlog.cc
-    compaction_manager.cc
-    config.cc
-    endpoint_snitch.cc
-    error_injection.cc
-    authorization_cache.cc
-    failure_detector.cc
-    gossiper.cc
-    hinted_handoff.cc
-    lsa.cc
-    messaging_service.cc
-    storage_proxy.cc
-    storage_service.cc
-    stream_manager.cc
-    system.cc
-    task_manager.cc
-    task_manager_test.cc
-    ${swagger_gen_files})
-target_include_directories(api
-  PUBLIC
-    ${CMAKE_SOURCE_DIR}
-    ${scylla_gen_build_dir})
-target_link_libraries(api
-  idl
-  wasmtime_bindings
-
-  Seastar::seastar
-  xxHash::xxhash)

api/api-doc/authorization_cache.json

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

api/api-doc/column_family.json

@@ -84,20 +84,12 @@
                      "type":"string",
                      "paramType":"path"
                   },
-                  {
-                     "name":"flush_memtables",
-                     "description":"Controls flushing of memtables before compaction (true by default). Set to \"false\" to skip automatic flushing of memtables before compaction, e.g. when the table is flushed explicitly before invoking the compaction api.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  },
                   {
                      "name":"split_output",
                      "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"
                   }
                ]
@@ -445,68 +437,6 @@
             }
          ]
       },
-      {
-         "path":"/column_family/tombstone_gc/{name}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Check if tombstone GC is enabled for a given table",
-               "type":"boolean",
-               "nickname":"get_tombstone_gc",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            },
-            {
-               "method":"POST",
-               "summary":"Enable tombstone GC for a given table",
-               "type":"void",
-               "nickname":"enable_tombstone_gc",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Disable tombstone GC for a given table",
-               "type":"void",
-               "nickname":"disable_tombstone_gc",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"name",
-                     "description":"The table name in keyspace:name format",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/column_family/estimate_keys/{name}",
          "operations":[
@@ -2995,10 +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":{
@@ -3006,10 +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/compaction_manager.json

@@ -102,47 +102,7 @@
                "parameters":[
                   {
                      "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/compaction_manager/stop_keyspace_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Stop all running compaction-like tasks in the given keyspace and tables having the provided type.",
-               "type":"void",
-               "nickname":"stop_keyspace_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to stop compaction in",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"tables",
-                     "description":"Comma-separated tables to stop compaction in",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
+                     "description":"the type of compaction to stop. Can be one of: - COMPACTION - VALIDATION - CLEANUP - SCRUB - INDEX_BUILD",
                      "required":true,
                      "allowMultiple":false,
                      "type":"string",

api/api-doc/error_injection.json

@@ -34,14 +34,6 @@
                      "allowMultiple":false,
                      "type":"boolean",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"parameters",
-                     "description":"dict of parameters to pass to the injection (json format)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"dict",
-                     "paramType":"body"
                   }
                ]
             },
@@ -66,30 +58,6 @@
             }
          ]
       },
-      {
-         "path":"/v2/error_injection/injection/{injection}/message",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Send message to trigger an event in injection's code",
-               "type":"void",
-               "nickname":"message_injection",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"injection",
-                     "description":"injection name, should correspond to an injection added in code",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/v2/error_injection/injection",
          "operations":[
@@ -118,15 +86,5 @@
             }
          ]
       }
-   ],
-   "components":{
-      "schemas": {
-         "dict": {
-            "type": "object",
-            "additionalProperties": {
-               "type": "string"
-            }
-         }
-      }
-   }
+   ]
 }

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"
                ],
@@ -245,14 +245,14 @@
                  "GOSSIP_SHUTDOWN",
                  "DEFINITIONS_UPDATE",
                  "TRUNCATE",
-                 "UNUSED__REPLICATION_FINISHED",
+                 "REPLICATION_FINISHED",
                  "MIGRATION_REQUEST",
                  "PREPARE_MESSAGE",
                  "PREPARE_DONE_MESSAGE",
                  "UNUSED__STREAM_MUTATION",
                  "STREAM_MUTATION_DONE",
                  "COMPLETE_MESSAGE",
-                 "UNUSED__REPAIR_CHECKSUM_RANGE",
+                 "REPAIR_CHECKSUM_RANGE",
                  "GET_SCHEMA_VERSION"
                ]
             }

api/api-doc/metrics.def.json

@@ -1,34 +0,0 @@
-    "metrics_config": {
-        "id": "metrics_config",
-        "summary": "An entry in the metrics configuration",
-        "properties": {
-            "source_labels": {
-                "type": "array",
-                "items": {
-                    "type": "string"
-                },
-                "description": "The source labels, a match is based on concatination of the labels"
-            },
-            "action": {
-                "type": "string",
-                "description": "The action to perfrom on match",
-                "enum": ["skip_when_empty", "report_when_empty", "replace", "keep", "drop", "drop_label"]
-            },
-            "target_label": {
-                "type": "string",
-                "description": "The application state version"
-            },
-            "replacement": {
-                "type": "string",
-                "description": "The replacement string to use when replacing a value"
-            },
-            "regex": {
-                "type": "string",
-                "description": "The regex string to use when replacing a value"
-            },
-            "separator": {
-                "type": "string",
-                "description": "The separator string to use when concatinating the labels"
-            }
-        }
-    }

api/api-doc/metrics.json

@@ -1,66 +0,0 @@
-    "/v2/metrics-config/":{
-        "get":{
-            "description":"Return the metrics layer configuration",
-            "operationId":"get_metrics_config",
-            "produces":[
-                "application/json"
-            ],
-            "tags":[
-                "metrics"
-            ],
-            "parameters":[
-            ],
-            "responses":{
-                "200":{
-                "schema": {
-                    "type":"array",
-                    "items":{
-                        "$ref":"#/definitions/metrics_config",
-                        "description":"metrics Config value"
-                    }
-                    }
-                },
-                "default":{
-                    "description":"unexpected error",
-                    "schema":{
-                        "$ref":"#/definitions/ErrorModel"
-                    }
-                }
-            }
-        },
-        "post": {
-             "description":"Set the metrics layer relabel configuration",
-            "operationId":"set_metrics_config",
-            "produces":[
-                "application/json"
-            ],
-            "tags":[
-                "metrics"
-            ],
-            "parameters":[
-               {
-                "in":"body",
-                "name":"conf",
-                "description":"An array of relabel_config objects",
-                "schema": {
-                    "type":"array",
-                    "items":{
-                        "$ref":"#/definitions/metrics_config",
-                        "description":"metrics Config value"
-                    }
-                }
-               }
-            ],
-            "responses":{
-                "200":{
-                    "description": "OK"
-                },
-                "default":{
-                    "description":"unexpected error",
-                    "schema":{
-                        "$ref":"#/definitions/ErrorModel"
-                    }
-                }
-            }
-        }
-    }

api/api-doc/raft.json

@@ -1,43 +0,0 @@
-{
-   "apiVersion":"0.0.1",
-   "swaggerVersion":"1.2",
-   "basePath":"{{Protocol}}://{{Host}}",
-   "resourcePath":"/raft",
-   "produces":[
-      "application/json"
-   ],
-   "apis":[
-      {
-         "path":"/raft/trigger_snapshot/{group_id}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Triggers snapshot creation and log truncation for the given Raft group",
-               "type":"string",
-               "nickname":"trigger_snapshot",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"group_id",
-                     "description":"The ID of the group which should get snapshotted",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"timeout",
-                     "description":"Timeout in seconds after which the endpoint returns a failure. If not provided, 60s is used.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      }
-   ]
-}

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":[
@@ -465,7 +403,7 @@
          "operations":[
             {
                "method":"GET",
-               "summary":"Retrieve the mapping of endpoint to host ID of all nodes that own tokens",
+               "summary":"Retrieve the mapping of endpoint to host ID",
                "type":"array",
                "items":{
                   "type":"mapper"
@@ -624,7 +562,7 @@
                   },
                   {
                      "name":"kn",
-                     "description":"Keyspace(s) to snapshot. Multiple keyspaces can be provided using a comma-separated list. If omitted, snapshot all keyspaces.",
+                     "description":"Comma seperated keyspaces name to snapshot",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -632,19 +570,11 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Table(s) to snapshot. Multiple tables (in a single keyspace) can be provided using a comma-separated list. If omitted, snapshot all tables in the given keyspace(s).",
+                     "description":"the column family to snapshot",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"sf",
-                     "description":"Skip flush. When set to \"true\", do not flush memtables before snapshotting (snapshot will not contain unflushed data)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
                   }
                ]
             },
@@ -667,7 +597,7 @@
                   },
                   {
                      "name":"kn",
-                     "description":"Comma-separated keyspaces name that their snapshot will be deleted",
+                     "description":"Comma seperated keyspaces name that their snapshot will be deleted",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -701,30 +631,6 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/compact",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Forces major compaction in all keyspaces",
-               "type":"void",
-               "nickname":"force_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"flush_memtables",
-                     "description":"Controls flushing of memtables before compaction (true by default). Set to \"false\" to skip automatic flushing of memtables before compaction, e.g. when tables were flushed explicitly before invoking the compaction api.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
       {
          "path":"/storage_service/keyspace_compaction/{keyspace}",
          "operations":[
@@ -747,19 +653,11 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"flush_memtables",
-                     "description":"Controls flushing of memtables before compaction (true by default). Set to \"false\" to skip automatic flushing of memtables before compaction, e.g. when tables were flushed explicitly before invoking the compaction api.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
                   }
                ]
             }
@@ -787,39 +685,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/storage_service/keyspace_offstrategy_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Perform offstrategy compaction, if needed, in a single keyspace",
-               "type":"boolean",
-               "nickname":"perform_keyspace_offstrategy_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to operate on",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"Comma-separated table names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -834,7 +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":[
@@ -857,33 +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":"quarantine_mode",
-                     "description":"Controls whether to scrub quarantined sstables (default INCLUDE)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "INCLUDE",
-                        "EXCLUDE",
-                        "ONLY"
-                     ],
-                     "paramType":"query"
-                  },
                   {
                      "name":"keyspace",
                      "description":"The keyspace to query about",
@@ -894,7 +733,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -934,7 +773,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -944,21 +783,6 @@
             }
          ]
       },
-      {
-         "path":"/storage_service/flush",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Flush all memtables in all keyspaces.",
-               "type":"void",
-               "nickname":"force_flush",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[]
-            }
-         ]
-      },
       {
          "path":"/storage_service/keyspace_flush/{keyspace}",
          "operations":[
@@ -981,7 +805,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -1146,14 +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.",
@@ -1161,14 +977,6 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"ranges_parallelism",
-                     "description":"An integer specifying the number of ranges to repair in parallel by user request. If this number is bigger than the max_repair_ranges_in_parallel calculated by Scylla core, the smaller one will be used.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                   }
                ]
             },
@@ -1283,7 +1091,7 @@
          "operations":[
             {
                "method":"POST",
-               "summary":"Removes a node from the cluster. Replicated data that logically belonged to this node is redistributed among the remaining nodes.",
+               "summary":"Removes token (and all data associated with enpoint that had it) from the ring",
                "type":"void",
                "nickname":"remove_node",
                "produces":[
@@ -1297,14 +1105,6 @@
                      "allowMultiple":false,
                      "type":"string",
                      "paramType":"query"
-                  },
-                  {
-                     "name":"ignore_nodes",
-                     "description":"Comma-separated list of dead nodes to ignore in removenode operation. Use the same method for all nodes to ignore: either Host IDs or ip addresses.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                   }
                ]
             }
@@ -1956,22 +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"
                   }
                ]
             }
@@ -2001,7 +1785,7 @@
          "operations":[
             {
                "method":"POST",
-               "summary":"Forces this node to recalculate versions of schema objects.",
+               "summary":"Reset local schema",
                "type":"void",
                "nickname":"reset_local_schema",
                "produces":[
@@ -2082,14 +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"
                   }
                ]
             },
@@ -2128,7 +1904,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -2155,66 +1931,7 @@
                   },
                   {
                      "name":"cf",
-                     "description":"Comma-separated column family names",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/storage_service/tombstone_gc/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Enable tombstone GC",
-               "type":"void",
-               "nickname":"enable_tombstone_gc",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"Comma-separated column family names",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Disable tombstone GC",
-               "type":"void",
-               "nickname":"disable_tombstone_gc",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"Comma-separated column family names",
+                     "description":"Comma seperated column family names",
                      "required":false,
                      "allowMultiple":false,
                      "type":"string",
@@ -2542,23 +2259,7 @@
                ]
             }
          ]
-      },
-      {
-         "path":"/storage_service/raft_topology/reload",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Reload Raft topology state from disk.",
-               "type":"void",
-               "nickname":"reload_raft_topology_state",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            }
-         ]
-      }
+      }      
    ],
    "models":{
       "mapper":{
@@ -2663,10 +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."
             }
          }
       },
@@ -2761,7 +2458,7 @@
                 "description":"File creation time"
             },
             "generation":{
-                "type":"string",
+                "type":"long",
                 "description":"SSTable generation"
             },
             "level":{
@@ -2771,7 +2468,7 @@
             "version":{
                "type":"string",
                "enum":[
-                  "ka", "la", "mc", "md", "me"
+                  "ka", "la", "mc", "md"
                ],
                "description":"SSTable version"
             },

api/api-doc/swagger20_header.json

@@ -16,7 +16,7 @@
     }
   },
   "host": "{{Host}}",
-  "basePath": "/",
+  "basePath": "/v2",
   "schemes": [
     "http"
   ],

api/api-doc/system.json

@@ -52,61 +52,6 @@
             }
          ]
       },
-      {
-         "path":"/system/log",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Write a message to the Scylla log",
-               "type":"void",
-               "nickname":"write_log_message",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"message",
-                     "description":"The message to write to the log",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"level",
-                     "description":"The logging level to use",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "error",
-                        "warn",
-                        "info",
-                        "debug",
-                        "trace"
-                     ],
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/system/drop_sstable_caches",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Drop in-memory caches for data which is in sstables",
-               "type":"void",
-               "nickname":"drop_sstable_caches",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            }
-         ]
-      },
       {
          "path":"/system/uptime_ms",
          "operations":[

api/api-doc/task_manager.json

@@ -1,337 +0,0 @@
-{
-   "apiVersion":"0.0.1",
-   "swaggerVersion":"1.2",
-   "basePath":"{{Protocol}}://{{Host}}",
-   "resourcePath":"/task_manager",
-   "produces":[
-      "application/json"
-   ],
-   "apis":[
-      {
-         "path":"/task_manager/list_modules",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Get all modules names",
-               "type":"array",
-               "items":{
-                  "type":"string"
-               },
-               "nickname":"get_modules",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager/list_module_tasks/{module}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Get a list of tasks",
-               "type":"array",
-               "items":{
-                  "type":"task_stats"
-               },
-               "nickname":"get_tasks",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"module",
-                     "description":"The module to query about",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"internal",
-                     "description":"Boolean flag indicating whether internal tasks should be shown (false by default)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to query about",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"table",
-                     "description":"The table to query about",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager/task_status/{task_id}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Get task status",
-               "type":"task_status",
-               "nickname":"get_task_status",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to query about",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager/abort_task/{task_id}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Abort running task and its descendants",
-               "type":"void",
-               "nickname":"abort_task",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to abort",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager/wait_task/{task_id}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Wait for a task to complete",
-               "type":"task_status",
-               "nickname":"wait_task",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to wait for",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager/task_status_recursive/{task_id}",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Get statuses of the task and all its descendants",
-               "type":"array",
-               "items":{
-                  "type":"task_status"
-               },
-               "nickname":"get_task_status_recursively",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to query about",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager/ttl",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Set ttl in seconds and get last value",
-               "type":"long",
-               "nickname":"get_and_update_ttl",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"ttl",
-                     "description":"The number of seconds for which the tasks will be kept in memory after it finishes",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      }
-   ],
-   "models":{
-      "task_stats" :{
-         "id": "task_stats",
-         "description":"A task statistics object",
-         "properties":{
-            "task_id":{
-               "type":"string",
-               "description":"The uuid of a task"
-            },
-            "state":{
-               "type":"string",
-               "enum":[
-                  "created",
-                  "running",
-                  "done",
-                  "failed"
-               ],
-               "description":"The state of a task"
-            },
-            "type":{
-               "type":"string",
-               "description":"The description of the task"
-            },
-            "scope":{
-               "type":"string",
-               "description":"The scope of the task"
-            },
-            "keyspace":{
-               "type":"string",
-               "description":"The keyspace the task is working on (if applicable)"
-            },
-            "table":{
-               "type":"string",
-               "description":"The table the task is working on (if applicable)"
-            },
-            "entity":{
-               "type":"string",
-               "description":"Task-specific entity description"
-            },
-            "sequence_number":{
-               "type":"long",
-               "description":"The running sequence number of the task"
-            }
-         }
-      },
-      "task_status":{
-         "id":"task_status",
-         "description":"A task status object",
-         "properties":{
-            "id":{
-               "type":"string",
-               "description":"The uuid of the task"
-            },
-            "type":{
-               "type":"string",
-               "description":"The description of the task"
-            },
-            "scope":{
-               "type":"string",
-               "description":"The scope of the task"
-            },
-            "state":{
-               "type":"string",
-               "enum":[
-                  "created",
-                  "running",
-                  "done",
-                  "failed"
-               ],
-               "description":"The state of the task"
-            },
-            "is_abortable":{
-               "type":"boolean",
-               "description":"Boolean flag indicating whether the task can be aborted"
-            },
-            "start_time":{
-               "type":"datetime",
-               "description":"The start time of the task"
-            },
-            "end_time":{
-               "type":"datetime",
-               "description":"The end time of the task (unspecified when the task is not completed)"
-            },
-            "error":{
-               "type":"string",
-               "description":"Error string, if the task failed"
-            },
-            "parent_id":{
-               "type":"string",
-               "description":"The uuid of the parent task"
-            },
-            "sequence_number":{
-               "type":"long",
-               "description":"The running sequence number of the task"
-            },
-            "shard":{
-               "type":"long",
-               "description":"The number of a shard the task is running on"
-            },
-            "keyspace":{
-               "type":"string",
-               "description":"The keyspace the task is working on (if applicable)"
-            },
-            "table":{
-               "type":"string",
-               "description":"The table the task is working on (if applicable)"
-            },
-            "entity":{
-               "type":"string",
-               "description":"Task-specific entity description"
-            },
-            "progress_units":{
-               "type":"string",
-               "description":"A description of the progress units"
-            },
-            "progress_total":{
-               "type":"double",
-               "description":"The total number of units to complete for the task"
-            },
-            "progress_completed":{
-               "type":"double",
-               "description":"The number of units completed so far"
-            },
-            "children_ids":{
-               "type":"array",
-               "items":{
-                  "type":"string"
-               },
-               "description":"Task IDs of children of this task"
-            }
-         }
-      }
-   }
-}

api/api-doc/task_manager_test.json

@@ -1,153 +0,0 @@
-{
-   "apiVersion":"0.0.1",
-   "swaggerVersion":"1.2",
-   "basePath":"{{Protocol}}://{{Host}}",
-   "resourcePath":"/task_manager_test",
-   "produces":[
-      "application/json"
-   ],
-   "apis":[
-      {
-         "path":"/task_manager_test/test_module",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Register test module in task manager",
-               "type":"void",
-               "nickname":"register_test_module",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Unregister test module in task manager",
-               "type":"void",
-               "nickname":"unregister_test_module",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager_test/test_task",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Register test task",
-               "type":"string",
-               "nickname":"register_test_task",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to register",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"shard",
-                     "description":"The shard of the task",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"long",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"parent_id",
-                     "description":"The uuid of a parent task",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace the task is working on",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"table",
-                     "description":"The table the task is working on",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"entity",
-                     "description":"Task-specific entity description",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            },
-            {
-               "method":"DELETE",
-               "summary":"Unregister test task",
-               "type":"void",
-               "nickname":"unregister_test_task",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to register",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/task_manager_test/finish_test_task/{task_id}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Finish test task",
-               "type":"void",
-               "nickname":"finish_test_task",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"task_id",
-                     "description":"The uuid of a task to finish",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"error",
-                     "description":"The error with which task fails (if it does)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      }
-   ]
-}

api/api.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "api.hh"
@@ -24,24 +37,19 @@
 #include "compaction_manager.hh"
 #include "hinted_handoff.hh"
 #include "error_injection.hh"
-#include "authorization_cache.hh"
 #include <seastar/http/exception.hh>
 #include "stream_manager.hh"
 #include "system.hh"
 #include "api/config.hh"
-#include "task_manager.hh"
-#include "task_manager_test.hh"
-#include "raft.hh"
 
 logging::logger apilog("api");
 
 namespace api {
-using namespace seastar::httpd;
 
 static std::unique_ptr<reply> exception_reply(std::exception_ptr eptr) {
     try {
         std::rethrow_exception(eptr);
-    } catch (const replica::no_such_keyspace& ex) {
+    } catch (const no_such_keyspace& ex) {
         throw bad_param_exception(ex.what());
     }
     // We never going to get here
@@ -61,18 +69,16 @@ future<> set_server_init(http_context& ctx) {
         rb->set_api_doc(r);
         rb02->set_api_doc(r);
         rb02->register_api_file(r, "swagger20_header");
-        rb02->register_api_file(r, "metrics");
         rb->register_function(r, "system",
                 "The system related API");
-        rb02->add_definitions_file(r, "metrics");
         set_system(ctx, r);
     });
 }
 
-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, false);
+    return ctx.http_server.set_routes([&ctx, rb02](routes& r) {
+        set_config(rb02, ctx, r);
     });
 }
 
@@ -103,51 +109,18 @@ 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, service::raft_group0_client& group0_client) {
-    return register_api(ctx, "storage_service", "The storage service API", [&ss, &group0_client] (http_context& ctx, routes& r) {
-            set_storage_service(ctx, r, ss, group0_client);
-        });
+future<> set_server_storage_service(http_context& ctx) {
+    return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
 }
 
-future<> unset_server_storage_service(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_storage_service(ctx, r); });
-}
-
-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) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_repair(ctx, r); });
 }
 
-future<> set_server_authorization_cache(http_context &ctx, sharded<auth::service> &auth_service) {
-    return register_api(ctx, "authorization_cache",
-                "The authorization cache API", [&auth_service] (http_context &ctx, routes &r) {
-                     set_authorization_cache(ctx, r, auth_service);
-                 });
-}
-
-future<> unset_server_authorization_cache(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_authorization_cache(ctx, r); });
-}
-
 future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl) {
     return ctx.http_server.set_routes([&ctx, &snap_ctl] (routes& r) { set_snapshot(ctx, r, snap_ctl); });
 }
@@ -156,32 +129,18 @@ future<> unset_server_snapshot(http_context& ctx) {
     return ctx.http_server.set_routes([&ctx] (routes& r) { unset_snapshot(ctx, r); });
 }
 
-future<> set_server_snitch(http_context& ctx, sharded<locator::snitch_ptr>& snitch) {
-    return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", [&snitch] (http_context& ctx, routes& r) {
-        set_endpoint_snitch(ctx, r, snitch);
-    });
+future<> set_server_snitch(http_context& ctx) {
+    return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
 }
 
-future<> unset_server_snitch(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_endpoint_snitch(ctx, r); });
-}
-
-future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g) {
+future<> set_server_gossip(http_context& ctx) {
     return register_api(ctx, "gossiper",
-                "The gossiper API", [&g] (http_context& ctx, routes& r) {
-                    set_gossiper(ctx, r, g.local());
-                });
+                "The gossiper API", set_gossiper);
 }
 
-future<> set_server_load_sstable(http_context& ctx, sharded<db::system_keyspace>& sys_ks) {
+future<> set_server_load_sstable(http_context& ctx) {
     return register_api(ctx, "column_family",
-                "The column family API", [&sys_ks] (http_context& ctx, routes& r) {
-                    set_column_family(ctx, r, sys_ks);
-                });
-}
-
-future<> unset_server_load_sstable(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_column_family(ctx, r); });
+                "The column family API", set_column_family);
 }
 
 future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms) {
@@ -194,26 +153,14 @@ 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_proxy>& proxy) {
+future<> set_server_storage_proxy(http_context& ctx) {
     return register_api(ctx, "storage_proxy",
-                "The storage proxy API", [&proxy] (http_context& ctx, routes& r) {
-                    set_storage_proxy(ctx, r, proxy);
-                });
+                "The storage proxy API", set_storage_proxy);
 }
 
-future<> unset_server_storage_proxy(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_storage_proxy(ctx, r); });
-}
-
-future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm) {
+future<> set_server_stream_manager(http_context& ctx) {
     return register_api(ctx, "stream_manager",
-                "The stream manager API", [&sm] (http_context& ctx, routes& r) {
-                    set_stream_manager(ctx, r, sm);
-                });
-}
-
-future<> unset_server_stream_manager(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_stream_manager(ctx, r); });
+                "The stream manager API", set_stream_manager);
 }
 
 future<> set_server_cache(http_context& ctx) {
@@ -221,34 +168,13 @@ future<> set_server_cache(http_context& ctx) {
             "The cache service API", set_cache_service);
 }
 
-future<> set_hinted_handoff(http_context& ctx, sharded<service::storage_proxy>& proxy) {
-    return register_api(ctx, "hinted_handoff",
-                "The hinted handoff API", [&proxy] (http_context& ctx, routes& r) {
-                    set_hinted_handoff(ctx, r, proxy);
-                });
-}
-
-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);
     });
 }
 
@@ -256,12 +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);
@@ -271,68 +203,5 @@ future<> set_server_done(http_context& ctx) {
     });
 }
 
-future<> set_server_task_manager(http_context& ctx, lw_shared_ptr<db::config> cfg) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx, &cfg = *cfg](routes& r) {
-        rb->register_function(r, "task_manager",
-                "The task manager API");
-        set_task_manager(ctx, r, cfg);
-    });
-}
-
-#ifndef SCYLLA_BUILD_MODE_RELEASE
-
-future<> set_server_task_manager_test(http_context& ctx) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx](routes& r) mutable {
-        rb->register_function(r, "task_manager_test",
-                "The task manager test API");
-        set_task_manager_test(ctx, r);
-    });
-}
-
-#endif
-
-future<> set_server_raft(http_context& ctx, sharded<service::raft_group_registry>& raft_gr) {
-    auto rb = std::make_shared<api_registry_builder>(ctx.api_doc);
-    return ctx.http_server.set_routes([rb, &ctx, &raft_gr] (routes& r) {
-        rb->register_function(r, "raft", "The Raft API");
-        set_raft(ctx, r, raft_gr);
-    });
-}
-
-future<> unset_server_raft(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_raft(ctx, r); });
-}
-
-void req_params::process(const request& req) {
-    // Process mandatory parameters
-    for (auto& [name, ent] : params) {
-        if (!ent.is_mandatory) {
-            continue;
-        }
-        try {
-            ent.value = req.get_path_param(name);
-        } catch (std::out_of_range&) {
-            throw httpd::bad_param_exception(fmt::format("Mandatory parameter '{}' was not provided", name));
-        }
-    }
-
-    // Process optional parameters
-    for (auto& [name, value] : req.query_parameters) {
-        try {
-            auto& ent = params.at(name);
-            if (ent.is_mandatory) {
-                throw httpd::bad_param_exception(fmt::format("Parameter '{}' is expected to be provided as part of the request url", name));
-            }
-            ent.value = value;
-        } catch (std::out_of_range&) {
-            throw httpd::bad_param_exception(fmt::format("Unsupported optional parameter '{}'", name));
-        }
-    }
-}
-
 }
 

api/api.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -16,7 +29,6 @@
 #include <boost/units/detail/utility.hpp>
 #include "api/api-doc/utils.json.hh"
 #include "utils/histogram.hh"
-#include "utils/estimated_histogram.hh"
 #include <seastar/http/exception.hh>
 #include "api_init.hh"
 #include "seastarx.hh"
@@ -27,7 +39,7 @@ template<class T>
 std::vector<sstring> container_to_vec(const T& container) {
     std::vector<sstring> res;
     for (auto i : container) {
-        res.push_back(fmt::to_string(i));
+        res.push_back(boost::lexical_cast<std::string>(i));
     }
     return res;
 }
@@ -47,8 +59,8 @@ template<class T, class MAP>
 std::vector<T>& map_to_key_value(const MAP& map, std::vector<T>& res) {
     for (auto i : map) {
         T val;
-        val.key = fmt::to_string(i.first);
-        val.value = fmt::to_string(i.second);
+        val.key = boost::lexical_cast<std::string>(i.first);
+        val.value = boost::lexical_cast<std::string>(i.second);
         res.push_back(val);
     }
     return res;
@@ -58,14 +70,14 @@ 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>
 std::vector<sstring> map_keys(const MAP& map) {
     std::vector<sstring> res;
     for (const auto& i : map) {
-        res.push_back(fmt::to_string(i.first));
+        res.push_back(boost::lexical_cast<std::string>(i.first));
     }
     return res;
 }
@@ -81,6 +93,13 @@ inline std::vector<sstring> split(const sstring& text, const char* separator) {
     return boost::split(tokens, text, boost::is_any_of(separator));
 }
 
+/**
+ * Split a column family parameter
+ */
+inline std::vector<sstring> split_cf(const sstring& cf) {
+    return split(cf, ",");
+}
+
 /**
  * A helper function to sum values on an a distributed object that
  * has a get_stats method.
@@ -137,14 +156,6 @@ future<json::json_return_type>  sum_timer_stats(distributed<T>& d, utils::timed_
     });
 }
 
-template<class T, class F>
-future<json::json_return_type>  sum_timer_stats(distributed<T>& d, utils::timed_rate_moving_average_summary_and_histogram F::*f) {
-    return d.map_reduce0([f](const T& p) {return (p.get_stats().*f).rate();}, utils::rate_moving_average_and_histogram(),
-            std::plus<utils::rate_moving_average_and_histogram>()).then([](const utils::rate_moving_average_and_histogram& val) {
-        return make_ready_future<json::json_return_type>(timer_to_json(val));
-    });
-}
-
 inline int64_t min_int64(int64_t a, int64_t b) {
     return std::min(a,b);
 }
@@ -189,7 +200,7 @@ struct basic_ratio_holder : public json::jsonable {
 typedef basic_ratio_holder<double>  ratio_holder;
 typedef basic_ratio_holder<int64_t> integral_ratio_holder;
 
-class unimplemented_exception : public httpd::base_exception {
+class unimplemented_exception : public base_exception {
 public:
     unimplemented_exception()
             : base_exception("API call is not supported yet", reply::status_type::internal_server_error) {
@@ -238,74 +249,13 @@ public:
                 value = T{boost::lexical_cast<Base>(param)};
             }
         } catch (boost::bad_lexical_cast&) {
-            throw httpd::bad_param_exception(format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
+            throw bad_param_exception(format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
         }
     }
 
     operator T() const { return value; }
 };
 
-using mandatory = bool_class<struct mandatory_tag>;
-
-class req_params {
-public:
-    struct def {
-        std::optional<sstring> value;
-        mandatory is_mandatory = mandatory::no;
-
-        def(std::optional<sstring> value_ = std::nullopt, mandatory is_mandatory_ = mandatory::no)
-            : value(std::move(value_))
-            , is_mandatory(is_mandatory_)
-        { }
-
-        def(mandatory is_mandatory_)
-            : is_mandatory(is_mandatory_)
-        { }
-    };
-
-private:
-    std::unordered_map<sstring, def> params;
-
-public:
-    req_params(std::initializer_list<std::pair<sstring, def>> l) {
-        for (const auto& [name, ent] : l) {
-            add(std::move(name), std::move(ent));
-        }
-    }
-
-    void add(sstring name, def ent) {
-        params.emplace(std::move(name), std::move(ent));
-    }
-
-    void process(const request& req);
-
-    const std::optional<sstring>& get(const char* name) const {
-        return params.at(name).value;
-    }
-
-    template <typename T = sstring>
-    const std::optional<T> get_as(const char* name) const {
-        return get(name);
-    }
-
-    template <typename T = sstring>
-    requires std::same_as<T, bool>
-    const std::optional<bool> get_as(const char* name) const {
-        auto value = get(name);
-        if (!value) {
-            return std::nullopt;
-        }
-        std::transform(value->begin(), value->end(), value->begin(), ::tolower);
-        if (value == "true" || value == "yes" || value == "1") {
-            return true;
-        }
-        if (value == "false" || value == "no" || value == "0") {
-            return false;
-        }
-        throw boost::bad_lexical_cast{};
-    }
-};
-
-httpd::utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val);
+utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimated_histogram& val);
 
 }

api/api_init.hh

@@ -3,64 +3,32 @@
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 #pragma once
-
+#include "database_fwd.hh"
+#include "service/storage_proxy.hh"
 #include <seastar/http/httpd.hh>
-#include <seastar/core/future.hh>
-
-#include "replica/database_fwd.hh"
-#include "tasks/task_manager.hh"
-#include "seastarx.hh"
-
-using request = http::request;
-using reply = http::reply;
-
-namespace service {
-
-class load_meter;
-class storage_proxy;
-class storage_service;
-class raft_group0_client;
-class raft_group_registry;
-
-} // namespace service
-
-class sstables_loader;
-
-namespace streaming {
-class stream_manager;
-}
-
-namespace locator {
-
-class token_metadata;
-class shared_token_metadata;
-class snitch_ptr;
-
-} // namespace locator
 
+namespace 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;
-}
-class system_keyspace;
-}
+namespace db { class snapshot_ctl; }
 namespace netw { class messaging_service; }
-class repair_service;
-
-namespace gms {
-
-class gossiper;
-
-}
-
-namespace auth { class service; }
 
 namespace api {
 
@@ -68,57 +36,38 @@ struct http_context {
     sstring api_dir;
     sstring api_doc;
     httpd::http_server_control http_server;
-    distributed<replica::database>& db;
+    distributed<database>& db;
+    distributed<service::storage_proxy>& sp;
     service::load_meter& lmeter;
-    const sharded<locator::shared_token_metadata>& shared_token_metadata;
-    sharded<tasks::task_manager>& tm;
+    const sharded<locator::token_metadata>& token_metadata;
 
-    http_context(distributed<replica::database>& _db,
-            service::load_meter& _lm, const sharded<locator::shared_token_metadata>& _stm, sharded<tasks::task_manager>& _tm)
-            : db(_db), lmeter(_lm), shared_token_metadata(_stm), tm(_tm) {
+    http_context(distributed<database>& _db,
+            distributed<service::storage_proxy>& _sp,
+            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_snitch(http_context& ctx, sharded<locator::snitch_ptr>& snitch);
-future<> unset_server_snitch(http_context& ctx);
-future<> set_server_storage_service(http_context& ctx, sharded<service::storage_service>& ss, service::raft_group0_client&);
-future<> unset_server_storage_service(http_context& ctx);
-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_config(http_context& ctx);
+future<> set_server_snitch(http_context& ctx);
+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);
 future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
 future<> unset_rpc_controller(http_context& ctx);
-future<> set_server_authorization_cache(http_context& ctx, sharded<auth::service> &auth_service);
-future<> unset_server_authorization_cache(http_context& ctx);
 future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl);
 future<> unset_server_snapshot(http_context& ctx);
-future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g);
-future<> set_server_load_sstable(http_context& ctx, sharded<db::system_keyspace>& sys_ks);
-future<> unset_server_load_sstable(http_context& ctx);
+future<> set_server_gossip(http_context& ctx);
+future<> set_server_load_sstable(http_context& ctx);
 future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms);
 future<> unset_server_messaging_service(http_context& ctx);
-future<> set_server_storage_proxy(http_context& ctx, sharded<service::storage_proxy>& proxy);
-future<> unset_server_storage_proxy(http_context& ctx);
-future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm);
-future<> unset_server_stream_manager(http_context& ctx);
-future<> set_hinted_handoff(http_context& ctx, sharded<service::storage_proxy>& p);
-future<> unset_hinted_handoff(http_context& ctx);
-future<> set_server_gossip_settle(http_context& ctx, sharded<gms::gossiper>& g);
+future<> set_server_storage_proxy(http_context& ctx);
+future<> set_server_stream_manager(http_context& ctx);
+future<> set_server_gossip_settle(http_context& ctx);
 future<> set_server_cache(http_context& ctx);
-future<> set_server_compaction_manager(http_context& ctx);
 future<> set_server_done(http_context& ctx);
-future<> set_server_task_manager(http_context& ctx, lw_shared_ptr<db::config> cfg);
-future<> set_server_task_manager_test(http_context& ctx);
-future<> set_server_raft(http_context&, sharded<service::raft_group_registry>&);
-future<> unset_server_raft(http_context&);
 
 }

api/authorization_cache.cc

@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 2022-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include "api/api-doc/authorization_cache.json.hh"
-
-#include "api/authorization_cache.hh"
-#include "api/api.hh"
-#include "auth/common.hh"
-#include "auth/service.hh"
-
-namespace api {
-using namespace json;
-using namespace seastar::httpd;
-
-void set_authorization_cache(http_context& ctx, routes& r, sharded<auth::service> &auth_service) {
-    httpd::authorization_cache_json::authorization_cache_reset.set(r, [&auth_service] (std::unique_ptr<http::request> req) -> future<json::json_return_type> {
-        co_await auth_service.invoke_on_all([] (auth::service& auth) -> future<>  {
-            auth.reset_authorization_cache();
-            return make_ready_future<>();
-        });
-
-        co_return json_void();
-    });
-}
-
-void unset_authorization_cache(http_context& ctx, routes& r) {
-    httpd::authorization_cache_json::authorization_cache_reset.unset(r);
-}
-
-}

api/authorization_cache.hh

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

api/cache_service.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "cache_service.hh"
@@ -12,128 +25,127 @@
 
 namespace api {
 using namespace json;
-using namespace seastar::httpd;
 namespace cs = httpd::cache_service_json;
 
 void set_cache_service(http_context& ctx, routes& r) {
-    cs::get_row_cache_save_period_in_seconds.set(r, [](std::unique_ptr<http::request> req) {
+    cs::get_row_cache_save_period_in_seconds.set(r, [](std::unique_ptr<request> req) {
         // We never save the cache
         // Origin uses 0 for never
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::set_row_cache_save_period_in_seconds.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_row_cache_save_period_in_seconds.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto period = req->get_query_param("period");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::get_key_cache_save_period_in_seconds.set(r, [](std::unique_ptr<http::request> req) {
+    cs::get_key_cache_save_period_in_seconds.set(r, [](std::unique_ptr<request> req) {
         // We never save the cache
         // Origin uses 0 for never
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::set_key_cache_save_period_in_seconds.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_key_cache_save_period_in_seconds.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto period = req->get_query_param("period");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::get_counter_cache_save_period_in_seconds.set(r, [](std::unique_ptr<http::request> req) {
+    cs::get_counter_cache_save_period_in_seconds.set(r, [](std::unique_ptr<request> req) {
         // We never save the cache
         // Origin uses 0 for never
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::set_counter_cache_save_period_in_seconds.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_counter_cache_save_period_in_seconds.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto ccspis = req->get_query_param("ccspis");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::get_row_cache_keys_to_save.set(r, [](std::unique_ptr<http::request> req) {
+    cs::get_row_cache_keys_to_save.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::set_row_cache_keys_to_save.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_row_cache_keys_to_save.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto rckts = req->get_query_param("rckts");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::get_key_cache_keys_to_save.set(r, [](std::unique_ptr<http::request> req) {
+    cs::get_key_cache_keys_to_save.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::set_key_cache_keys_to_save.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_key_cache_keys_to_save.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto kckts = req->get_query_param("kckts");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::get_counter_cache_keys_to_save.set(r, [](std::unique_ptr<http::request> req) {
+    cs::get_counter_cache_keys_to_save.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::set_counter_cache_keys_to_save.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_counter_cache_keys_to_save.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto cckts = req->get_query_param("cckts");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::invalidate_key_cache.set(r, [](std::unique_ptr<http::request> req) {
+    cs::invalidate_key_cache.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::invalidate_counter_cache.set(r, [](std::unique_ptr<http::request> req) {
+    cs::invalidate_counter_cache.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::set_row_cache_capacity_in_mb.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_row_cache_capacity_in_mb.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto capacity = req->get_query_param("capacity");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::set_key_cache_capacity_in_mb.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_key_cache_capacity_in_mb.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto period = req->get_query_param("period");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::set_counter_cache_capacity_in_mb.set(r, [](std::unique_ptr<http::request> req) {
+    cs::set_counter_cache_capacity_in_mb.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         auto capacity = req->get_query_param("capacity");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::save_caches.set(r, [](std::unique_ptr<http::request> req) {
+    cs::save_caches.set(r, [](std::unique_ptr<request> req) {
         // TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cs::get_key_capacity.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_capacity.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support keys cache,
@@ -141,7 +153,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_key_hits.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_hits.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support keys cache,
@@ -149,7 +161,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_key_requests.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_requests.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support keys cache,
@@ -157,7 +169,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_key_hit_rate.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_hit_rate.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support keys cache,
@@ -165,21 +177,21 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_key_hits_moving_avrage.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // See above
         return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
     });
 
-    cs::get_key_requests_moving_avrage.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // See above
         return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
     });
 
-    cs::get_key_size.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_size.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support keys cache,
@@ -187,7 +199,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_key_entries.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_key_entries.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support keys cache,
@@ -195,68 +207,68 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
+    cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return ctx.db.map_reduce0([](database& db) -> uint64_t {
             return db.row_cache_tracker().region().occupancy().used_space();
         }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [](const replica::column_family& cf) {
+    cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.count();
         }, std::plus<uint64_t>());
     });
 
-    cs::get_row_requests.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [](const replica::column_family& cf) {
+    cs::get_row_requests.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count();
         }, std::plus<uint64_t>());
     });
 
-    cs::get_row_hit_rate.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [](const replica::column_family& cf) {
+    cs::get_row_hit_rate.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return map_reduce_cf(ctx, ratio_holder(), [](const column_family& cf) {
             return ratio_holder(cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count(),
                     cf.get_row_cache().stats().hits.count());
         }, std::plus<ratio_holder>());
     });
 
-    cs::get_row_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+    cs::get_row_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
         });
     });
 
-    cs::get_row_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+    cs::get_row_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
             return cf.get_row_cache().stats().hits.rate() + cf.get_row_cache().stats().misses.rate();
         }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
             return make_ready_future<json::json_return_type>(meter_to_json(m));
         });
     });
 
-    cs::get_row_size.set(r, [&ctx] (std::unique_ptr<http::request> req) {
+    cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
         // In origin row size is the weighted size.
         // We currently do not support weights, so we use num entries instead
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
+        return ctx.db.map_reduce0([](database& db) -> uint64_t {
             return db.row_cache_tracker().partitions();
         }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
+    cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return ctx.db.map_reduce0([](database& db) -> uint64_t {
             return db.row_cache_tracker().partitions();
         }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
             return make_ready_future<json::json_return_type>(res);
         });
     });
 
-    cs::get_counter_capacity.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_capacity.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support counter cache,
@@ -264,7 +276,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_counter_hits.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_hits.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support counter cache,
@@ -272,7 +284,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_counter_requests.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_requests.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support counter cache,
@@ -280,7 +292,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_counter_hit_rate.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_hit_rate.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support counter cache,
@@ -288,21 +300,21 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_counter_hits_moving_avrage.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // See above
         return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
     });
 
-    cs::get_counter_requests_moving_avrage.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // See above
         return make_ready_future<json::json_return_type>(meter_to_json(utils::rate_moving_average()));
     });
 
-    cs::get_counter_size.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_size.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support counter cache,
@@ -310,7 +322,7 @@ void set_cache_service(http_context& ctx, routes& r) {
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cs::get_counter_entries.set(r, [] (std::unique_ptr<http::request> req) {
+    cs::get_counter_entries.set(r, [] (std::unique_ptr<request> req) {
         // TBD
         // FIXME
         // we don't support counter cache,

api/cache_service.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,6 +25,6 @@
 
 namespace api {
 
-void set_cache_service(http_context& ctx, httpd::routes& r);
+void set_cache_service(http_context& ctx, routes& r);
 
 }

api/collectd.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "collectd.hh"
@@ -29,11 +42,8 @@ static auto transformer(const std::vector<collectd_value>& values) {
         case scollectd::data_type::GAUGE:
             collected_value.values.push(v.d());
             break;
-        case scollectd::data_type::COUNTER:
-            collected_value.values.push(v.ui());
-            break;
-        case scollectd::data_type::REAL_COUNTER:
-            collected_value.values.push(v.d());
+        case scollectd::data_type::DERIVE:
+            collected_value.values.push(v.i());
             break;
         default:
             collected_value.values.push(v.ui());
@@ -52,9 +62,9 @@ static const char* str_to_regex(const sstring& v) {
 }
 
 void set_collectd(http_context& ctx, routes& r) {
-    cd::get_collectd.set(r, [](std::unique_ptr<request> req) {
+    cd::get_collectd.set(r, [&ctx](std::unique_ptr<request> req) {
 
-        auto id = ::make_shared<scollectd::type_instance_id>(req->get_path_param("pluginid"),
+        auto id = ::make_shared<scollectd::type_instance_id>(req->param["pluginid"],
                 req->get_query_param("instance"), req->get_query_param("type"),
                 req->get_query_param("type_instance"));
 
@@ -91,7 +101,7 @@ void set_collectd(http_context& ctx, routes& r) {
     });
 
     cd::enable_collectd.set(r, [](std::unique_ptr<request> req) -> future<json::json_return_type> {
-        std::regex plugin(req->get_path_param("pluginid").c_str());
+        std::regex plugin(req->param["pluginid"].c_str());
         std::regex instance(str_to_regex(req->get_query_param("instance")));
         std::regex type(str_to_regex(req->get_query_param("type")));
         std::regex type_instance(str_to_regex(req->get_query_param("type_instance")));

api/collectd.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,6 +25,6 @@
 
 namespace api {
 
-void set_collectd(http_context& ctx, httpd::routes& r);
+void set_collectd(http_context& ctx, routes& r);
 
 }

api/column_family.hh

@@ -1,39 +1,47 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "api.hh"
 #include "api/api-doc/column_family.json.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include <seastar/core/future-util.hh>
 #include <any>
 
-namespace db {
-class system_keyspace;
-}
-
 namespace api {
 
-void set_column_family(http_context& ctx, httpd::routes& r, sharded<db::system_keyspace>& sys_ks);
-void unset_column_family(http_context& ctx, httpd::routes& r);
+void set_column_family(http_context& ctx, routes& r);
 
-table_id get_uuid(const sstring& name, const replica::database& db);
-future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(replica::column_family&)> f);
+const utils::UUID& get_uuid(const sstring& name, const database& db);
+future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(column_family&)> f);
 
 
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
         Mapper mapper, Reducer reducer) {
     auto uuid = get_uuid(name, ctx.db.local());
-    using mapper_type = std::function<std::unique_ptr<std::any>(replica::database&)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(database&)>;
     using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    return ctx.db.map_reduce0(mapper_type([mapper, uuid](replica::database& db) {
+    return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
         return std::make_unique<std::any>(I(mapper(db.find_column_family(uuid))));
     }), std::make_unique<std::any>(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
         return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
@@ -60,18 +68,17 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
     });
 }
 
-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const replica::column_family&)> f);
+future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f);
 
 struct map_reduce_column_families_locally {
     std::any init;
-    std::function<std::unique_ptr<std::any>(replica::column_family&)> mapper;
+    std::function<std::unique_ptr<std::any>(column_family&)> mapper;
     std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)> reducer;
-    future<std::unique_ptr<std::any>> operator()(replica::database& db) const {
+    future<std::unique_ptr<std::any>> operator()(database& db) const {
         auto res = seastar::make_lw_shared<std::unique_ptr<std::any>>(std::make_unique<std::any>(init));
-        return db.get_tables_metadata().for_each_table_gently([res, this] (table_id, seastar::lw_shared_ptr<replica::table> table) {
-            *res = reducer(std::move(*res), mapper(*table.get()));
-            return make_ready_future();
-        }).then([res] () {
+        return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+            *res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
+        }).then([res] {
             return std::move(*res);
         });
     }
@@ -80,9 +87,9 @@ struct map_reduce_column_families_locally {
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, I init,
         Mapper mapper, Reducer reducer) {
-    using mapper_type = std::function<std::unique_ptr<std::any>(replica::column_family&)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(column_family&)>;
     using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (replica::column_family& cf) mutable {
+    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
         return std::make_unique<std::any>(I(mapper(cf)));
     });
     auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
@@ -104,12 +111,9 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
 }
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t replica::column_family_stats::*f);
+        int64_t column_family_stats::*f);
 
 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t replica::column_family_stats::*f);
-
-
-std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name);
+        int64_t column_family_stats::*f);
 
 }

api/commitlog.cc

@@ -1,25 +1,37 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "commitlog.hh"
 #include "db/commitlog/commitlog.hh"
 #include "api/api-doc/commitlog.json.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include <vector>
 
 namespace api {
-using namespace seastar::httpd;
 
 template<typename T>
 static auto acquire_cl_metric(http_context& ctx, std::function<T (db::commitlog*)> func) {
     typedef T ret_type;
 
-    return ctx.db.map_reduce0([func = std::move(func)](replica::database& db) {
+    return ctx.db.map_reduce0([func = std::move(func)](database& db) {
         if (db.commitlog() == nullptr) {
             return make_ready_future<ret_type>();
         }
@@ -35,7 +47,7 @@ void set_commitlog(http_context& ctx, routes& r) {
         auto res = make_shared<std::vector<sstring>>();
         return ctx.db.map_reduce([res](std::vector<sstring> names) {
             res->insert(res->end(), names.begin(), names.end());
-        }, [](replica::database& db) {
+        }, [](database& db) {
             if (db.commitlog() == nullptr) {
                 return make_ready_future<std::vector<sstring>>(std::vector<sstring>());
             }

api/commitlog.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,6 +25,6 @@
 
 namespace api {
 
-void set_commitlog(http_context& ctx, httpd::routes& r);
+void set_commitlog(http_context& ctx, routes& r);
 
 }

api/compaction_manager.cc

@@ -1,33 +1,39 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <seastar/core/coroutine.hh>
-#include <seastar/coroutine/exception.hh>
-
 #include "compaction_manager.hh"
-#include "compaction/compaction_manager.hh"
+#include "sstables/compaction_manager.hh"
 #include "api/api-doc/compaction_manager.json.hh"
 #include "db/system_keyspace.hh"
 #include "column_family.hh"
-#include "unimplemented.hh"
-#include "storage_service.hh"
-
 #include <utility>
 
 namespace api {
 
 namespace cm = httpd::compaction_manager_json;
 using namespace json;
-using namespace seastar::httpd;
 
 static future<json::json_return_type> get_cm_stats(http_context& ctx,
         int64_t compaction_manager::stats::*f) {
-    return ctx.db.map_reduce0([f](replica::database& db) {
+    return ctx.db.map_reduce0([f](database& db) {
         return db.get_compaction_manager().get_stats().*f;
     }, int64_t(0), std::plus<int64_t>()).then([](const int64_t& res) {
         return make_ready_future<json::json_return_type>(res);
@@ -43,21 +49,21 @@ static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_ha
     return std::move(a);
 }
 
+
 void set_compaction_manager(http_context& ctx, routes& r) {
-    cm::get_compactions.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) {
+    cm::get_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return ctx.db.map_reduce0([](database& db) {
             std::vector<cm::summary> summaries;
             const compaction_manager& cm = db.get_compaction_manager();
 
             for (const auto& c : cm.get_compactions()) {
                 cm::summary s;
-                s.id = c.compaction_uuid.to_sstring();
-                s.ks = c.ks_name;
-                s.cf = c.cf_name;
+                s.ks = c->ks_name;
+                s.cf = c->cf_name;
                 s.unit = "keys";
-                s.task_type = sstables::compaction_name(c.type);
-                s.completed = c.total_keys_written;
-                s.total = c.total_partitions;
+                s.task_type = sstables::compaction_name(c->type);
+                s.completed = c->total_keys_written;
+                s.total = c->total_partitions;
                 summaries.push_back(std::move(s));
             }
             return summaries;
@@ -66,12 +72,12 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         });
     });
 
-    cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) {
-            return do_with(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), [&db](std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& tasks) {
-                return db.get_tables_metadata().for_each_table_gently([&tasks] (table_id, lw_shared_ptr<replica::table> table) {
-                    replica::table& cf = *table.get();
-                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.estimate_pending_compactions();
+    cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return ctx.db.map_reduce0([&ctx](database& db) {
+            return do_with(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), [&ctx, &db](std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& tasks) {
+                return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+                    table& cf = *i.second.get();
+                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf);
                     return make_ready_future<>();
                 }).then([&tasks] {
                     return std::move(tasks);
@@ -92,74 +98,52 @@ void set_compaction_manager(http_context& ctx, routes& r) {
         });
     });
 
-    cm::force_user_defined_compaction.set(r, [] (std::unique_ptr<http::request> req) {
+    cm::force_user_defined_compaction.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         // FIXME
         warn(unimplemented::cause::API);
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    cm::stop_compaction.set(r, [&ctx] (std::unique_ptr<http::request> req) {
+    cm::stop_compaction.set(r, [&ctx] (std::unique_ptr<request> req) {
         auto type = req->get_query_param("type");
-        return ctx.db.invoke_on_all([type] (replica::database& db) {
+        return ctx.db.invoke_on_all([type] (database& db) {
             auto& cm = db.get_compaction_manager();
-            return cm.stop_compaction(type);
+            cm.stop_compaction(type);
         }).then([] {
             return make_ready_future<json::json_return_type>(json_void());
         });
     });
 
-    cm::stop_keyspace_compaction.set(r, [&ctx] (std::unique_ptr<http::request> req) -> future<json::json_return_type> {
-        auto ks_name = validate_keyspace(ctx, req);
-        auto table_names = parse_tables(ks_name, ctx, req->query_parameters, "tables");
-        if (table_names.empty()) {
-            table_names = map_keys(ctx.db.local().find_keyspace(ks_name).metadata().get()->cf_meta_data());
-        }
-        auto type = req->get_query_param("type");
-        co_await ctx.db.invoke_on_all([&ks_name, &table_names, type] (replica::database& db) {
-            auto& cm = db.get_compaction_manager();
-            return parallel_for_each(table_names, [&db, &cm, &ks_name, type] (sstring& table_name) {
-                auto& t = db.find_column_family(ks_name, table_name);
-                return t.parallel_foreach_table_state([&] (compaction::table_state& ts) {
-                    return cm.stop_compaction(type, &ts);
-                });
-            });
-        });
-        co_return json_void();
-    });
-
-    cm::get_pending_tasks.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
-            return cf.estimate_pending_compactions();
+    cm::get_pending_tasks.set(r, [&ctx] (std::unique_ptr<request> req) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
         }, std::plus<int64_t>());
     });
 
-    cm::get_completed_tasks.set(r, [&ctx] (std::unique_ptr<http::request> req) {
+    cm::get_completed_tasks.set(r, [&ctx] (std::unique_ptr<request> req) {
         return get_cm_stats(ctx, &compaction_manager::stats::completed_tasks);
     });
 
-    cm::get_total_compactions_completed.set(r, [] (std::unique_ptr<http::request> req) {
+    cm::get_total_compactions_completed.set(r, [] (std::unique_ptr<request> req) {
         // FIXME
         // We are currently dont have an API for compaction
         // so returning a 0 as the number of total compaction is ok
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cm::get_bytes_compacted.set(r, [] (std::unique_ptr<http::request> req) {
+    cm::get_bytes_compacted.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         // FIXME
         warn(unimplemented::cause::API);
         return make_ready_future<json::json_return_type>(0);
     });
 
-    cm::get_compaction_history.set(r, [&ctx] (std::unique_ptr<http::request> req) {
-        std::function<future<>(output_stream<char>&&)> f = [&ctx] (output_stream<char>&& out) -> future<> {
-            auto s = std::move(out);
-            bool first = true;
-            std::exception_ptr ex;
-            try {
-                co_await s.write("[");
-                co_await ctx.db.local().get_compaction_manager().get_compaction_history([&s, &first](const db::compaction_history_entry& entry) mutable -> future<> {
+    cm::get_compaction_history.set(r, [] (std::unique_ptr<request> req) {
+        std::function<future<>(output_stream<char>&&)> f = [](output_stream<char>&& s) {
+            return do_with(output_stream<char>(std::move(s)), true, [] (output_stream<char>& s, bool& first){
+                return s.write("[").then([&s, &first] {
+                    return db::system_keyspace::get_compaction_history([&s, &first](const db::system_keyspace::compaction_history_entry& entry) mutable {
                         cm::history h;
                         h.id = entry.id.to_sstring();
                         h.ks = std::move(entry.ks);
@@ -173,26 +157,23 @@ void set_compaction_manager(http_context& ctx, routes& r) {
                             e.value = it.second;
                             h.rows_merged.push(std::move(e));
                         }
-                        if (!first) {
-                            co_await s.write(", ");
-                        }
+                        auto fut = first ? make_ready_future<>() : s.write(", ");
                         first = false;
-                        co_await formatter::write(s, h);
+                        return fut.then([&s, h = std::move(h)] {
+                            return formatter::write(s, h);
+                        });
+                    }).then([&s] {
+                        return s.write("]").then([&s] {
+                            return s.close();
+                        });
                     });
-                co_await s.write("]");
-                co_await s.flush();
-            } catch (...) {
-                ex = std::current_exception();
-            }
-            co_await s.close();
-            if (ex) {
-                co_await coroutine::return_exception_ptr(std::move(ex));
-            }
+                });
+            });
         };
         return make_ready_future<json::json_return_type>(std::move(f));
     });
 
-    cm::get_compaction_info.set(r, [] (std::unique_ptr<http::request> req) {
+    cm::get_compaction_info.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         // FIXME
         warn(unimplemented::cause::API);

api/compaction_manager.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,6 +25,6 @@
 
 namespace api {
 
-void set_compaction_manager(http_context& ctx, httpd::routes& r);
+void set_compaction_manager(http_context& ctx, routes& r);
 
 }

api/config.cc

@@ -1,19 +1,32 @@
 /*
- * Copyright 2018-present ScyllaDB
+ * Copyright 2018 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "api/config.hh"
 #include "api/api-doc/config.json.hh"
 #include "db/config.hh"
+#include "database.hh"
 #include <sstream>
 #include <boost/algorithm/string/replace.hpp>
 
 namespace api {
-using namespace seastar::httpd;
 
 template<class T>
 json::json_return_type get_json_return_type(const T& val) {
@@ -45,7 +58,7 @@ future<> get_config_swagger_entry(std::string_view name, const std::string& desc
     } else {
         ss <<',';
     };
-    ss << "\"/v2/config/" << name <<"\": {"
+    ss << "\"/config/" << name <<"\": {"
       "\"get\": {"
         "\"description\": \"" << boost::replace_all_copy(boost::replace_all_copy(boost::replace_all_copy(description,"\n","\\n"),"\"", "''"), "\t", " ") <<"\","
         "\"operationId\": \"find_config_"<< name <<"\","
@@ -76,11 +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, bool first) {
-    rb->register_function(r, [&cfg, first] (output_stream<char>& os) {
-        return do_with(first, [&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);
@@ -90,9 +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) {
-        auto id = r.get_path_param("id");
-        for (auto&& cfg_ref : cfg.values()) {
+    cs::find_config_id.set(r, [&ctx] (const_req r) {
+        auto id = r.param["id"];
+        for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
             auto&& cfg = cfg_ref.get();
             if (id == cfg.name()) {
                 return cfg.value_as_json();

api/config.hh

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

api/endpoint_snitch.cc

@@ -1,69 +1,48 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "locator/token_metadata.hh"
 #include "locator/snitch_base.hh"
-#include "locator/production_snitch_base.hh"
 #include "endpoint_snitch.hh"
 #include "api/api-doc/endpoint_snitch_info.json.hh"
-#include "api/api-doc/storage_service.json.hh"
 #include "utils/fb_utilities.hh"
 
 namespace api {
-using namespace seastar::httpd;
 
-void set_endpoint_snitch(http_context& ctx, routes& r, sharded<locator::snitch_ptr>& snitch) {
+void set_endpoint_snitch(http_context& ctx, routes& r) {
     static auto host_or_broadcast = [](const_req req) {
         auto host = req.get_query_param("host");
         return host.empty() ? gms::inet_address(utils::fb_utilities::get_broadcast_address()) : gms::inet_address(host);
     };
 
-    httpd::endpoint_snitch_info_json::get_datacenter.set(r, [&ctx](const_req req) {
-        auto& topology = ctx.shared_token_metadata.local().get()->get_topology();
-        auto ep = host_or_broadcast(req);
-        if (!topology.has_endpoint(ep)) {
-            // Cannot return error here, nodetool status can race, request
-            // info about just-left node and not handle it nicely
-            return locator::endpoint_dc_rack::default_location.dc;
-        }
-        return topology.get_datacenter(ep);
+    httpd::endpoint_snitch_info_json::get_datacenter.set(r, [](const_req req) {
+        return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(host_or_broadcast(req));
     });
 
-    httpd::endpoint_snitch_info_json::get_rack.set(r, [&ctx](const_req req) {
-        auto& topology = ctx.shared_token_metadata.local().get()->get_topology();
-        auto ep = host_or_broadcast(req);
-        if (!topology.has_endpoint(ep)) {
-            // Cannot return error here, nodetool status can race, request
-            // info about just-left node and not handle it nicely
-            return locator::endpoint_dc_rack::default_location.rack;
-        }
-        return topology.get_rack(ep);
+    httpd::endpoint_snitch_info_json::get_rack.set(r, [](const_req req) {
+        return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_rack(host_or_broadcast(req));
     });
 
-    httpd::endpoint_snitch_info_json::get_snitch_name.set(r, [&snitch] (const_req req) {
-        return snitch.local()->get_name();
+    httpd::endpoint_snitch_info_json::get_snitch_name.set(r, [] (const_req req) {
+        return locator::i_endpoint_snitch::get_local_snitch_ptr()->get_name();
     });
-
-    httpd::storage_service_json::update_snitch.set(r, [&snitch](std::unique_ptr<request> req) {
-        locator::snitch_config cfg;
-        cfg.name = req->get_query_param("ep_snitch_class_name");
-        return locator::i_endpoint_snitch::reset_snitch(snitch, cfg).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
-
-}
-
-void unset_endpoint_snitch(http_context& ctx, routes& r) {
-    httpd::endpoint_snitch_info_json::get_datacenter.unset(r);
-    httpd::endpoint_snitch_info_json::get_rack.unset(r);
-    httpd::endpoint_snitch_info_json::get_snitch_name.unset(r);
-    httpd::storage_service_json::update_snitch.unset(r);
 }
 
 }

api/endpoint_snitch.hh

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

api/error_injection.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "api/api-doc/error_injection.json.hh"
@@ -12,41 +25,21 @@
 #include <seastar/http/exception.hh>
 #include "log.hh"
 #include "utils/error_injection.hh"
-#include "utils/rjson.hh"
-#include <seastar/core/future-util.hh>
-#include <seastar/util/short_streams.hh>
+#include "seastar/core/future-util.hh"
 
 namespace api {
-using namespace seastar::httpd;
 
 namespace hf = httpd::error_injection_json;
 
 void set_error_injection(http_context& ctx, routes& r) {
 
     hf::enable_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->get_path_param("injection");
+        sstring injection = req->param["injection"];
         bool one_shot = req->get_query_param("one_shot") == "True";
-        auto params = req->content;
-
-        const size_t max_params_size = 1024 * 1024;
-        if (params.size() > max_params_size) {
-            // This is a hard limit, because we don't want to allocate
-            // too much memory or block the thread for too long.
-            throw httpd::bad_param_exception(format("Injection parameters are too long, max length is {}", max_params_size));
-        }
-
-        try {
-            auto parameters = params.empty()
-                ? utils::error_injection_parameters{}
-                : rjson::parse_to_map<utils::error_injection_parameters>(params);
-
-            auto& errinj = utils::get_local_injector();
-            return errinj.enable_on_all(injection, one_shot, std::move(parameters)).then([] {
-                return make_ready_future<json::json_return_type>(json::json_void());
-            });
-        } catch (const rjson::error& e) {
-            throw httpd::bad_param_exception(format("Failed to parse injections parameters: {}", e.what()));
-        }
+        auto& errinj = utils::get_local_injector();
+        return errinj.enable_on_all(injection, one_shot).then([] {
+            return make_ready_future<json::json_return_type>(json::json_void());
+        });
     });
 
     hf::get_enabled_injections_on_all.set(r, [](std::unique_ptr<request> req) {
@@ -56,7 +49,7 @@ void set_error_injection(http_context& ctx, routes& r) {
     });
 
     hf::disable_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->get_path_param("injection");
+        sstring injection = req->param["injection"];
 
         auto& errinj = utils::get_local_injector();
         return errinj.disable_on_all(injection).then([] {
@@ -71,13 +64,6 @@ void set_error_injection(http_context& ctx, routes& r) {
         });
     });
 
-    hf::message_injection.set(r, [](std::unique_ptr<request> req) {
-        sstring injection = req->get_path_param("injection");
-        auto& errinj = utils::get_local_injector();
-        return errinj.receive_message_on_all(injection).then([] {
-            return make_ready_future<json::json_return_type>(json::json_void());
-        });
-    });
 }
 
 } // namespace api

api/error_injection.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2019-present ScyllaDB
+ * Copyright (C) 2019 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,6 +25,6 @@
 
 namespace api {
 
-void set_error_injection(http_context& ctx, httpd::routes& r);
+void set_error_injection(http_context& ctx, routes& r);
 
 }

api/failure_detector.cc

@@ -1,100 +1,106 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "failure_detector.hh"
 #include "api/api-doc/failure_detector.json.hh"
+#include "gms/failure_detector.hh"
 #include "gms/application_state.hh"
 #include "gms/gossiper.hh"
-
 namespace api {
-using namespace seastar::httpd;
 
 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) {
-        return g.container().invoke_on(0, [] (gms::gossiper& g) {
-            std::vector<fd::endpoint_state> res;
-            res.reserve(g.num_endpoints());
-            g.for_each_endpoint_state([&] (const gms::inet_address& addr, const gms::endpoint_state& eps) {
-                fd::endpoint_state val;
-                val.addrs = fmt::to_string(addr);
-                val.is_alive = g.is_alive(addr);
-                val.generation = eps.get_heart_beat_state().get_generation().value();
-                val.version = eps.get_heart_beat_state().get_heart_beat_version().value();
-                val.update_time = eps.get_update_timestamp().time_since_epoch().count();
-                for (const auto& [as_type, app_state] : eps.get_application_state_map()) {
-                    fd::version_value version_val;
-                    // We return the enum index and not it's name to stay compatible to origin
-                    // method that the state index are static but the name can be changed.
-                    version_val.application_state = static_cast<std::underlying_type<gms::application_state>::type>(as_type);
-                    version_val.value = app_state.value();
-                    version_val.version = app_state.version().value();
-                    val.application_state.push(version_val);
-                }
-                res.emplace_back(std::move(val));
-            });
+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 : 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();
+            val.generation = i.second.get_heart_beat_state().get_generation();
+            val.version = i.second.get_heart_beat_state().get_heart_beat_version();
+            val.update_time = i.second.get_update_timestamp().time_since_epoch().count();
+            for (auto a : i.second.get_application_state_map()) {
+                fd::version_value version_val;
+                // We return the enum index and not it's name to stay compatible to origin
+                // method that the state index are static but the name can be changed.
+                version_val.application_state = static_cast<std::underlying_type<gms::application_state>::type>(a.first);
+                version_val.value = a.second.value;
+                version_val.version = a.second.version;
+                val.application_state.push(version_val);
+            }
+            res.push_back(val);
+        }
+        return make_ready_future<json::json_return_type>(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_up_endpoint_count.set(r, [&g](std::unique_ptr<request> req) {
-        return g.container().invoke_on(0, [] (gms::gossiper& g) {
-            int res = g.get_up_endpoint_count();
-            return make_ready_future<json::json_return_type>(res);
-        });
-    });
-
-    fd::get_down_endpoint_count.set(r, [&g](std::unique_ptr<request> req) {
-        return g.container().invoke_on(0, [] (gms::gossiper& g) {
-            int res = g.get_down_endpoint_count();
+    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);
         });
     });
 
     fd::get_phi_convict_threshold.set(r, [] (std::unique_ptr<request> req) {
-        return make_ready_future<json::json_return_type>(8);
+        return gms::get_phi_convict_threshold().then([](double res) {
+            return make_ready_future<json::json_return_type>(res);
+        });
     });
 
-    fd::get_simple_states.set(r, [&g] (std::unique_ptr<request> req) {
-        return g.container().invoke_on(0, [] (gms::gossiper& g) {
-            std::map<sstring, sstring> nodes_status;
-            g.for_each_endpoint_state([&] (const gms::inet_address& node, const gms::endpoint_state&) {
-                nodes_status.emplace(node.to_sstring(), g.is_alive(node) ? "UP" : "DOWN");
-            });
-            return make_ready_future<json::json_return_type>(map_to_key_value<fd::mapper>(nodes_status));
+    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));
         });
     });
 
     fd::set_phi_convict_threshold.set(r, [](std::unique_ptr<request> req) {
-        // TBD
-        unimplemented();
-        std::ignore = atof(req->get_query_param("phi").c_str());
-        return make_ready_future<json::json_return_type>("");
+        double phi = atof(req->get_query_param("phi").c_str());
+        return gms::set_phi_convict_threshold(phi).then([]() {
+            return make_ready_future<json::json_return_type>("");
+        });
     });
 
-    fd::get_endpoint_state.set(r, [&g] (std::unique_ptr<request> req) {
-        return g.container().invoke_on(0, [req = std::move(req)] (gms::gossiper& g) {
-            auto state = g.get_endpoint_state_ptr(gms::inet_address(req->get_path_param("addr")));
-            if (!state) {
-                return make_ready_future<json::json_return_type>(format("unknown endpoint {}", req->get_path_param("addr")));
-            }
-            std::stringstream ss;
-            g.append_endpoint_state(ss, *state);
-            return make_ready_future<json::json_return_type>(sstring(ss.str()));
+    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);
         });
     });
 
     fd::get_endpoint_phi_values.set(r, [](std::unique_ptr<request> req) {
-        // We no longer have a phi failure detector,
-        // just returning the empty value is good enough.
-        std::vector<fd::endpoint_phi_value> res;
-        return make_ready_future<json::json_return_type>(res);
+        return gms::get_arrival_samples().then([](std::map<gms::inet_address, gms::arrival_window> map) {
+            std::vector<fd::endpoint_phi_value> res;
+            auto now = gms::arrival_window::clk::now();
+            for (auto& p : map) {
+                fd::endpoint_phi_value val;
+                val.endpoint = p.first.to_sstring();
+                val.phi = p.second.phi(now);
+                res.emplace_back(std::move(val));
+            }
+            return make_ready_future<json::json_return_type>(res);
+        });
     });
 }
 

api/failure_detector.hh

@@ -1,23 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "api.hh"
 
-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {
 
-void set_failure_detector(http_context& ctx, httpd::routes& r, gms::gossiper& g);
+void set_failure_detector(http_context& ctx, routes& r);
 
 }

api/gossiper.cc

@@ -1,70 +1,68 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <seastar/core/coroutine.hh>
-
 #include "gossiper.hh"
 #include "api/api-doc/gossiper.json.hh"
-#include "gms/endpoint_state.hh"
 #include "gms/gossiper.hh"
 
 namespace api {
-using namespace seastar::httpd;
 using namespace json;
 
-void set_gossiper(http_context& ctx, routes& r, gms::gossiper& g) {
-    httpd::gossiper_json::get_down_endpoint.set(r, [&g] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        auto res = co_await g.get_unreachable_members_synchronized();
-        co_return json::json_return_type(container_to_vec(res));
+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, [] (const_req req) {
+        auto res = gms::get_local_gossiper().get_live_members();
+        return container_to_vec(res);
+    });
 
-    httpd::gossiper_json::get_live_endpoint.set(r, [&g] (std::unique_ptr<request> req) {
-        return g.get_live_members_synchronized().then([] (auto res) {
-            return make_ready_future<json::json_return_type>(container_to_vec(res));
+    httpd::gossiper_json::get_endpoint_downtime.set(r, [] (const_req req) {
+        gms::inet_address ep(req.param["addr"]);
+        return gms::get_local_gossiper().get_endpoint_downtime(ep);
+    });
+
+    httpd::gossiper_json::get_current_generation_number.set(r, [] (std::unique_ptr<request> req) {
+        gms::inet_address ep(req->param["addr"]);
+        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_endpoint_downtime.set(r, [&g] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        gms::inet_address ep(req->get_path_param("addr"));
-        // synchronize unreachable_members on all shards
-        co_await g.get_unreachable_members_synchronized();
-        co_return g.get_endpoint_downtime(ep);
-    });
-
-    httpd::gossiper_json::get_current_generation_number.set(r, [&g] (std::unique_ptr<http::request> req) {
-        gms::inet_address ep(req->get_path_param("addr"));
-        return g.get_current_generation_number(ep).then([] (gms::generation_type res) {
-            return make_ready_future<json::json_return_type>(res.value());
+    httpd::gossiper_json::get_current_heart_beat_version.set(r, [] (std::unique_ptr<request> req) {
+        gms::inet_address ep(req->param["addr"]);
+        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::get_current_heart_beat_version.set(r, [&g] (std::unique_ptr<http::request> req) {
-        gms::inet_address ep(req->get_path_param("addr"));
-        return g.get_current_heart_beat_version(ep).then([] (gms::version_type res) {
-            return make_ready_future<json::json_return_type>(res.value());
-        });
-    });
-
-    httpd::gossiper_json::assassinate_endpoint.set(r, [&g](std::unique_ptr<http::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->get_path_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->get_path_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<http::request> req) {
-        gms::inet_address ep(req->get_path_param("addr"));
-        return g.force_remove_endpoint(ep, gms::null_permit_id).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

@@ -1,23 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
 #include "api.hh"
 
-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {
 
-void set_gossiper(http_context& ctx, httpd::routes& r, gms::gossiper& g);
+void set_gossiper(http_context& ctx, routes& r);
 
 }

api/hinted_handoff.cc

@@ -1,129 +1,69 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <algorithm>
-#include <vector>
-
 #include "hinted_handoff.hh"
 #include "api/api-doc/hinted_handoff.json.hh"
 
-#include "gms/inet_address.hh"
-#include "service/storage_proxy.hh"
-
 namespace api {
 
 using namespace json;
-using namespace seastar::httpd;
 namespace hh = httpd::hinted_handoff_json;
 
-void set_hinted_handoff(http_context& ctx, routes& r, sharded<service::storage_proxy>& proxy) {
-    hh::create_hints_sync_point.set(r, [&proxy] (std::unique_ptr<http::request> req) -> future<json::json_return_type> {
-        auto parse_hosts_list = [] (sstring arg) {
-            std::vector<sstring> hosts_str = split(arg, ",");
-            std::vector<gms::inet_address> hosts;
-            hosts.reserve(hosts_str.size());
-
-            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 proxy.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, [&proxy] (std::unique_ptr<http::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 proxy.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));
-        });
-    });
-
-    hh::list_endpoints_pending_hints.set(r, [] (std::unique_ptr<http::request> req) {
+void set_hinted_handoff(http_context& ctx, routes& r) {
+    hh::list_endpoints_pending_hints.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
         std::vector<sstring> res;
         return make_ready_future<json::json_return_type>(res);
     });
 
-    hh::truncate_all_hints.set(r, [] (std::unique_ptr<http::request> req) {
+    hh::truncate_all_hints.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
         sstring host = req->get_query_param("host");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    hh::schedule_hint_delivery.set(r, [] (std::unique_ptr<http::request> req) {
+    hh::schedule_hint_delivery.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
         sstring host = req->get_query_param("host");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    hh::pause_hints_delivery.set(r, [] (std::unique_ptr<http::request> req) {
+    hh::pause_hints_delivery.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
         sstring pause = req->get_query_param("pause");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    hh::get_create_hint_count.set(r, [] (std::unique_ptr<http::request> req) {
+    hh::get_create_hint_count.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
         sstring host = req->get_query_param("host");
         return make_ready_future<json::json_return_type>(0);
     });
 
-    hh::get_not_stored_hints_count.set(r, [] (std::unique_ptr<http::request> req) {
+    hh::get_not_stored_hints_count.set(r, [] (std::unique_ptr<request> req) {
         //TBD
         unimplemented();
         sstring host = req->get_query_param("host");
@@ -131,16 +71,5 @@ void set_hinted_handoff(http_context& ctx, routes& r, sharded<service::storage_p
     });
 }
 
-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

@@ -1,21 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
-#include <seastar/core/sharded.hh>
 #include "api.hh"
 
-namespace service { class storage_proxy; }
-
 namespace api {
 
-void set_hinted_handoff(http_context& ctx, httpd::routes& r, sharded<service::storage_proxy>& p);
-void unset_hinted_handoff(http_context& ctx, httpd::routes& r);
+void set_hinted_handoff(http_context& ctx, routes& r);
 
 }

api/lsa.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "api/api-doc/lsa.json.hh"
@@ -13,17 +26,15 @@
 #include <seastar/http/exception.hh>
 #include "utils/logalloc.hh"
 #include "log.hh"
-#include "replica/database.hh"
 
 namespace api {
-using namespace seastar::httpd;
 
 static logging::logger alogger("lsa-api");
 
 void set_lsa(http_context& ctx, routes& r) {
     httpd::lsa_json::lsa_compact.set(r, [&ctx](std::unique_ptr<request> req) {
         alogger.info("Triggering compaction");
-        return ctx.db.invoke_on_all([] (replica::database&) {
+        return ctx.db.invoke_on_all([] (database&) {
             logalloc::shard_tracker().reclaim(std::numeric_limits<size_t>::max());
         }).then([] {
             return json::json_return_type(json::json_void());

api/lsa.hh

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -12,6 +25,6 @@
 
 namespace api {
 
-void set_lsa(http_context& ctx, httpd::routes& r);
+void set_lsa(http_context& ctx, routes& r);
 
 }

api/messaging_service.cc

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "messaging_service.hh"
@@ -13,7 +26,6 @@
 #include <iostream>
 #include <sstream>
 
-using namespace seastar::httpd;
 using namespace httpd::messaging_service_json;
 using namespace netw;
 
@@ -29,7 +41,7 @@ std::vector<message_counter> map_to_message_counters(
     std::vector<message_counter> res;
     for (auto i : map) {
         res.push_back(message_counter());
-        res.back().key = fmt::to_string(i.first);
+        res.back().key = boost::lexical_cast<sstring>(i.first);
         res.back().value = i.second;
     }
     return res;
@@ -84,10 +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.
@@ -147,7 +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

@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
@@ -14,7 +27,7 @@ namespace netw { class messaging_service; }
 
 namespace api {
 
-void set_messaging_service(http_context& ctx, httpd::routes& r, sharded<netw::messaging_service>& ms);
-void unset_messaging_service(http_context& ctx, httpd::routes& r);
+void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
+void unset_messaging_service(http_context& ctx, routes& r);
 
 }

api/raft.cc

@@ -1,70 +0,0 @@
-/*
- * Copyright (C) 2024-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <seastar/core/coroutine.hh>
-
-#include "api/api.hh"
-#include "api/api-doc/raft.json.hh"
-
-#include "service/raft/raft_group_registry.hh"
-
-using namespace seastar::httpd;
-
-extern logging::logger apilog;
-
-namespace api {
-
-namespace r = httpd::raft_json;
-using namespace json;
-
-void set_raft(http_context&, httpd::routes& r, sharded<service::raft_group_registry>& raft_gr) {
-    r::trigger_snapshot.set(r, [&raft_gr] (std::unique_ptr<http::request> req) -> future<json_return_type> {
-        raft::group_id gid{utils::UUID{req->get_path_param("group_id")}};
-        auto timeout_dur = std::invoke([timeout_str = req->get_query_param("timeout")] {
-            if (timeout_str.empty()) {
-                return std::chrono::seconds{60};
-            }
-            auto dur = std::stoll(timeout_str);
-            if (dur <= 0) {
-                throw std::runtime_error{"Timeout must be a positive number."};
-            }
-            return std::chrono::seconds{dur};
-        });
-
-        std::atomic<bool> found_srv{false};
-        co_await raft_gr.invoke_on_all([gid, timeout_dur, &found_srv] (service::raft_group_registry& raft_gr) -> future<> {
-            auto* srv = raft_gr.find_server(gid);
-            if (!srv) {
-                co_return;
-            }
-
-            found_srv = true;
-            abort_on_expiry aoe(lowres_clock::now() + timeout_dur);
-            apilog.info("Triggering Raft group {} snapshot", gid);
-            auto result = co_await srv->trigger_snapshot(&aoe.abort_source());
-            if (result) {
-                apilog.info("New snapshot for Raft group {} created", gid);
-            } else {
-                apilog.info("Could not create new snapshot for Raft group {}, no new entries applied", gid);
-            }
-        });
-
-        if (!found_srv) {
-            throw std::runtime_error{fmt::format("Server for group ID {} not found", gid)};
-        }
-
-        co_return json_void{};
-    });
-}
-
-void unset_raft(http_context&, httpd::routes& r) {
-    r::trigger_snapshot.unset(r);
-}
-
-}
-

api/raft.hh

@@ -1,18 +0,0 @@
-/*
- * Copyright (C) 2023-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include "api_init.hh"
-
-namespace api {
-
-void set_raft(http_context& ctx, httpd::routes& r, sharded<service::raft_group_registry>& raft_gr);
-void unset_raft(http_context& ctx, httpd::routes& r);
-
-}

api/storage_proxy.cc

@@ -1,30 +1,40 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "storage_proxy.hh"
 #include "service/storage_proxy.hh"
 #include "api/api-doc/storage_proxy.json.hh"
 #include "api/api-doc/utils.json.hh"
+#include "service/storage_service.hh"
 #include "db/config.hh"
 #include "utils/histogram.hh"
-#include "replica/database.hh"
-#include <seastar/core/scheduling_specific.hh>
+#include "database.hh"
+#include "seastar/core/scheduling_specific.hh"
 
 namespace api {
 
 namespace sp = httpd::storage_proxy_json;
 using proxy = service::storage_proxy;
-using namespace seastar::httpd;
 using namespace json;
 
-utils::time_estimated_histogram timed_rate_moving_average_summary_merge(utils::time_estimated_histogram a, const utils::timed_rate_moving_average_summary_and_histogram& b) {
-    return a.merge(b.histogram());
-}
 
 /**
  * This function implement a two dimentional map reduce where
@@ -58,10 +68,10 @@ future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
  * @param initial_value - the initial value to use for both aggregations* @return
  * @return A future that resolves to the result of the aggregation.
  */
-template<typename V, typename Reducer, typename F, typename C>
+template<typename V, typename Reducer, typename F>
 future<V> two_dimensional_map_reduce(distributed<service::storage_proxy>& d,
-        C F::*f, Reducer reducer, V initial_value) {
-    return two_dimensional_map_reduce(d, [f] (F& stats) -> V {
+        V F::*f, Reducer reducer, V initial_value) {
+    return two_dimensional_map_reduce(d, [f] (F& stats) {
         return stats.*f;
     }, reducer, initial_value);
 }
@@ -115,17 +125,17 @@ utils_json::estimated_histogram time_to_json_histogram(const utils::time_estimat
     return res;
 }
 
-static future<json::json_return_type>  sum_estimated_histogram(sharded<service::storage_proxy>& proxy, utils::timed_rate_moving_average_summary_and_histogram service::storage_proxy_stats::stats::*f) {
-    return two_dimensional_map_reduce(proxy, [f] (service::storage_proxy_stats::stats& stats) {
-        return (stats.*f).histogram();
-    }, utils::time_estimated_histogram_merge, utils::time_estimated_histogram()).then([](const utils::time_estimated_histogram& val) {
+static future<json::json_return_type>  sum_estimated_histogram(http_context& ctx, utils::time_estimated_histogram service::storage_proxy_stats::stats::*f) {
+
+    return two_dimensional_map_reduce(ctx.sp, f, utils::time_estimated_histogram_merge,
+            utils::time_estimated_histogram()).then([](const utils::time_estimated_histogram& val) {
         return make_ready_future<json::json_return_type>(time_to_json_histogram(val));
     });
 }
 
-static future<json::json_return_type>  sum_estimated_histogram(sharded<service::storage_proxy>& proxy, utils::estimated_histogram service::storage_proxy_stats::stats::*f) {
+static future<json::json_return_type>  sum_estimated_histogram(http_context& ctx, utils::estimated_histogram service::storage_proxy_stats::stats::*f) {
 
-    return two_dimensional_map_reduce(proxy, f, utils::estimated_histogram_merge,
+    return two_dimensional_map_reduce(ctx.sp, f, utils::estimated_histogram_merge,
             utils::estimated_histogram()).then([](const utils::estimated_histogram& val) {
         utils_json::estimated_histogram res;
         res = val;
@@ -133,8 +143,8 @@ static future<json::json_return_type>  sum_estimated_histogram(sharded<service::
     });
 }
 
-static future<json::json_return_type>  total_latency(sharded<service::storage_proxy>& proxy, utils::timed_rate_moving_average_summary_and_histogram service::storage_proxy_stats::stats::*f) {
-    return two_dimensional_map_reduce(proxy, [f] (service::storage_proxy_stats::stats& stats) {
+static future<json::json_return_type>  total_latency(http_context& ctx, utils::timed_rate_moving_average_and_histogram service::storage_proxy_stats::stats::*f) {
+    return two_dimensional_map_reduce(ctx.sp, [f] (service::storage_proxy_stats::stats& stats) {
             return (stats.*f).hist.mean * (stats.*f).hist.count;
         }, std::plus<double>(), 0.0).then([](double val) {
         int64_t res = val;
@@ -153,7 +163,7 @@ static future<json::json_return_type>  total_latency(sharded<service::storage_pr
 template<typename F>
 future<json::json_return_type>
 sum_histogram_stats_storage_proxy(distributed<proxy>& d,
-        utils::timed_rate_moving_average_summary_and_histogram F::*f) {
+        utils::timed_rate_moving_average_and_histogram F::*f) {
     return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
         return (stats.*f).hist;
     }, std::plus<utils::ihistogram>(), utils::ihistogram()).
@@ -173,7 +183,7 @@ sum_histogram_stats_storage_proxy(distributed<proxy>& d,
 template<typename F>
 future<json::json_return_type>
 sum_timer_stats_storage_proxy(distributed<proxy>& d,
-        utils::timed_rate_moving_average_summary_and_histogram F::*f) {
+        utils::timed_rate_moving_average_and_histogram F::*f) {
 
     return two_dimensional_map_reduce(d, [f] (service::storage_proxy_stats::stats& stats) {
         return (stats.*f).rate();
@@ -183,76 +193,66 @@ sum_timer_stats_storage_proxy(distributed<proxy>& d,
     });
 }
 
-void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_proxy>& proxy) {
-    sp::get_total_hints.set(r, [](std::unique_ptr<http::request> req)  {
+void set_storage_proxy(http_context& ctx, routes& r) {
+    sp::get_total_hints.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::get_hinted_handoff_enabled.set(r, [&proxy](std::unique_ptr<http::request> req)  {
-        const auto& filter = proxy.local().get_hints_host_filter();
-        return make_ready_future<json::json_return_type>(!filter.is_disabled_for_all());
+    sp::get_hinted_handoff_enabled.set(r, [&ctx](std::unique_ptr<request> req)  {
+        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, [&proxy](std::unique_ptr<http::request> req)  {
+    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 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, [&proxy](std::unique_ptr<http::request> req)  {
-        std::vector<sstring> res;
-        const auto& filter = 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));
+    sp::get_hinted_handoff_enabled_by_dc.set(r, [](std::unique_ptr<request> req)  {
+        //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, [&proxy](std::unique_ptr<http::request> req)  {
-        auto dcs = req->get_query_param("dcs");
-        auto filter = db::hints::host_filter::parse_from_dc_list(std::move(dcs));
-        return 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());
-        });
+    sp::set_hinted_handoff_enabled_by_dc_list.set(r, [](std::unique_ptr<request> req)  {
+        //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<http::request> req)  {
+    sp::get_max_hint_window.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(0);
     });
 
-    sp::set_max_hint_window.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_max_hint_window.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("ms");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    sp::get_max_hints_in_progress.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::get_max_hints_in_progress.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(1);
     });
 
-    sp::set_max_hints_in_progress.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_max_hints_in_progress.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("qs");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    sp::get_hints_in_progress.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::get_hints_in_progress.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(0);
@@ -262,7 +262,7 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().request_timeout_in_ms()/1000.0;
     });
 
-    sp::set_rpc_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_rpc_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
@@ -273,7 +273,7 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().read_request_timeout_in_ms()/1000.0;
     });
 
-    sp::set_read_rpc_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_read_rpc_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
@@ -284,7 +284,7 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().write_request_timeout_in_ms()/1000.0;
     });
 
-    sp::set_write_rpc_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_write_rpc_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
@@ -295,7 +295,7 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().counter_write_request_timeout_in_ms()/1000.0;
     });
 
-    sp::set_counter_write_rpc_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_counter_write_rpc_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
@@ -306,7 +306,7 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().cas_contention_timeout_in_ms()/1000.0;
     });
 
-    sp::set_cas_contention_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_cas_contention_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
@@ -317,7 +317,7 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().range_request_timeout_in_ms()/1000.0;
     });
 
-    sp::set_range_rpc_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_range_rpc_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
@@ -328,147 +328,160 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return ctx.db.local().get_config().truncate_request_timeout_in_ms()/1000.0;
     });
 
-    sp::set_truncate_rpc_timeout.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::set_truncate_rpc_timeout.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         auto enable = req->get_query_param("timeout");
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    sp::reload_trigger_classes.set(r, [](std::unique_ptr<http::request> req)  {
+    sp::reload_trigger_classes.set(r, [](std::unique_ptr<request> req)  {
         //TBD
         unimplemented();
         return make_ready_future<json::json_return_type>(json_void());
     });
 
-    sp::get_read_repair_attempted.set(r, [&proxy](std::unique_ptr<http::request> req)  {
-        return sum_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::read_repair_attempts);
+    sp::get_read_repair_attempted.set(r, [&ctx](std::unique_ptr<request> req)  {
+        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_attempts);
     });
 
-    sp::get_read_repair_repaired_blocking.set(r, [&proxy](std::unique_ptr<http::request> req)  {
-        return sum_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::read_repair_repaired_blocking);
+    sp::get_read_repair_repaired_blocking.set(r, [&ctx](std::unique_ptr<request> req)  {
+        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_blocking);
     });
 
-    sp::get_read_repair_repaired_background.set(r, [&proxy](std::unique_ptr<http::request> req)  {
-        return sum_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::read_repair_repaired_background);
+    sp::get_read_repair_repaired_background.set(r, [&ctx](std::unique_ptr<request> req)  {
+        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_background);
     });
 
-    sp::get_cas_read_timeouts.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &proxy::stats::cas_read_timeouts);
+    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;
+                entry.key = std::move(e.first);
+                entry.value = std::move(e.second);
+                res.emplace_back(std::move(entry));
+            }
+            return make_ready_future<json::json_return_type>(std::move(res));
+        });
     });
 
-    sp::get_cas_read_unavailables.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &proxy::stats::cas_read_unavailables);
+    sp::get_cas_read_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_read_timeouts);
     });
 
-    sp::get_cas_write_timeouts.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &proxy::stats::cas_write_timeouts);
+    sp::get_cas_read_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_read_unavailables);
     });
 
-    sp::get_cas_write_unavailables.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &proxy::stats::cas_write_unavailables);
+    sp::get_cas_write_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_write_timeouts);
     });
 
-    sp::get_cas_write_metrics_unfinished_commit.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_stats(proxy, &proxy::stats::cas_write_unfinished_commit);
+    sp::get_cas_write_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &proxy::stats::cas_write_unavailables);
     });
 
-    sp::get_cas_write_metrics_contention.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_estimated_histogram(proxy, &proxy::stats::cas_write_contention);
+    sp::get_cas_write_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_stats(ctx.sp, &proxy::stats::cas_write_unfinished_commit);
     });
 
-    sp::get_cas_write_metrics_condition_not_met.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_stats(proxy, &proxy::stats::cas_write_condition_not_met);
+    sp::get_cas_write_metrics_contention.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_estimated_histogram(ctx, &proxy::stats::cas_write_contention);
     });
 
-    sp::get_cas_write_metrics_failed_read_round_optimization.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_stats(proxy, &proxy::stats::cas_failed_read_round_optimization);
+    sp::get_cas_write_metrics_condition_not_met.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_stats(ctx.sp, &proxy::stats::cas_write_condition_not_met);
     });
 
-    sp::get_cas_read_metrics_unfinished_commit.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_stats(proxy, &proxy::stats::cas_read_unfinished_commit);
+    sp::get_cas_write_metrics_failed_read_round_optimization.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_stats(ctx.sp, &proxy::stats::cas_failed_read_round_optimization);
     });
 
-    sp::get_cas_read_metrics_contention.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_estimated_histogram(proxy, &proxy::stats::cas_read_contention);
+    sp::get_cas_read_metrics_unfinished_commit.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_stats(ctx.sp, &proxy::stats::cas_read_unfinished_commit);
     });
 
-    sp::get_read_metrics_timeouts.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &service::storage_proxy_stats::stats::read_timeouts);
+    sp::get_cas_read_metrics_contention.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_estimated_histogram(ctx, &proxy::stats::cas_read_contention);
     });
 
-    sp::get_read_metrics_unavailables.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &service::storage_proxy_stats::stats::read_unavailables);
+    sp::get_read_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
     });
 
-    sp::get_range_metrics_timeouts.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &service::storage_proxy_stats::stats::range_slice_timeouts);
+    sp::get_read_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
     });
 
-    sp::get_range_metrics_unavailables.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &service::storage_proxy_stats::stats::range_slice_unavailables);
+    sp::get_range_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
     });
 
-    sp::get_write_metrics_timeouts.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &service::storage_proxy_stats::stats::write_timeouts);
+    sp::get_range_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
     });
 
-    sp::get_write_metrics_unavailables.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_long(proxy, &service::storage_proxy_stats::stats::write_unavailables);
+    sp::get_write_metrics_timeouts.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
     });
 
-    sp::get_read_metrics_timeouts_rates.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_obj(proxy, &service::storage_proxy_stats::stats::read_timeouts);
+    sp::get_write_metrics_unavailables.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_long(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
     });
 
-    sp::get_read_metrics_unavailables_rates.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_obj(proxy, &service::storage_proxy_stats::stats::read_unavailables);
+    sp::get_read_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_timeouts);
     });
 
-    sp::get_range_metrics_timeouts_rates.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_obj(proxy, &service::storage_proxy_stats::stats::range_slice_timeouts);
+    sp::get_read_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::read_unavailables);
     });
 
-    sp::get_range_metrics_unavailables_rates.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_obj(proxy, &service::storage_proxy_stats::stats::range_slice_unavailables);
+    sp::get_range_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_timeouts);
     });
 
-    sp::get_write_metrics_timeouts_rates.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_obj(proxy, &service::storage_proxy_stats::stats::write_timeouts);
+    sp::get_range_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::range_slice_unavailables);
     });
 
-    sp::get_write_metrics_unavailables_rates.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timed_rate_as_obj(proxy, &service::storage_proxy_stats::stats::write_unavailables);
+    sp::get_write_metrics_timeouts_rates.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_timeouts);
     });
 
-    sp::get_range_metrics_latency_histogram_depricated.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_histogram_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::range);
+    sp::get_write_metrics_unavailables_rates.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timed_rate_as_obj(ctx.sp, &service::storage_proxy_stats::stats::write_unavailables);
     });
 
-    sp::get_write_metrics_latency_histogram_depricated.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_histogram_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::write);
+    sp::get_range_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
     });
 
-    sp::get_read_metrics_latency_histogram_depricated.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_histogram_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::read);
+    sp::get_write_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
     });
 
-    sp::get_range_metrics_latency_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timer_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::range);
+    sp::get_read_metrics_latency_histogram_depricated.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_histogram_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
     });
 
-    sp::get_write_metrics_latency_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timer_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::write);
-    });
-    sp::get_cas_write_metrics_latency_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timer_stats(proxy, &proxy::stats::cas_write);
+    sp::get_range_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
     });
 
-    sp::get_cas_read_metrics_latency_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timer_stats(proxy, &proxy::stats::cas_read);
+    sp::get_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::write);
+    });
+    sp::get_cas_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timer_stats(ctx.sp, &proxy::stats::cas_write);
     });
 
-    sp::get_view_write_metrics_latency_histogram.set(r, [](std::unique_ptr<http::request> req) {
+    sp::get_cas_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timer_stats(ctx.sp, &proxy::stats::cas_read);
+    });
+
+    sp::get_view_write_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
         //TBD
         // FIXME
         // No View metrics are available, so just return empty moving average
@@ -476,100 +489,32 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_pr
         return make_ready_future<json::json_return_type>(get_empty_moving_average());
     });
 
-    sp::get_read_metrics_latency_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timer_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::read);
+    sp::get_read_metrics_latency_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read);
     });
 
-    sp::get_read_estimated_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_estimated_histogram(proxy, &service::storage_proxy_stats::stats::read);
+    sp::get_read_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_read);
     });
 
-    sp::get_read_latency.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return total_latency(proxy, &service::storage_proxy_stats::stats::read);
+    sp::get_read_latency.set(r, [&ctx](std::unique_ptr<request> req) {
+        return total_latency(ctx, &service::storage_proxy_stats::stats::read);
     });
-    sp::get_write_estimated_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_estimated_histogram(proxy, &service::storage_proxy_stats::stats::write);
+    sp::get_write_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_estimated_histogram(ctx, &service::storage_proxy_stats::stats::estimated_write);
     });
 
-    sp::get_write_latency.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return total_latency(proxy, &service::storage_proxy_stats::stats::write);
+    sp::get_write_latency.set(r, [&ctx](std::unique_ptr<request> req) {
+        return total_latency(ctx, &service::storage_proxy_stats::stats::write);
     });
 
-    sp::get_range_estimated_histogram.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return sum_timer_stats_storage_proxy(proxy, &service::storage_proxy_stats::stats::range);
+    sp::get_range_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
+        return sum_timer_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::range);
     });
 
-    sp::get_range_latency.set(r, [&proxy](std::unique_ptr<http::request> req) {
-        return total_latency(proxy, &service::storage_proxy_stats::stats::range);
+    sp::get_range_latency.set(r, [&ctx](std::unique_ptr<request> req) {
+        return total_latency(ctx, &service::storage_proxy_stats::stats::range);
     });
 }
 
-void unset_storage_proxy(http_context& ctx, routes& r) {
-    sp::get_total_hints.unset(r);
-    sp::get_hinted_handoff_enabled.unset(r);
-    sp::set_hinted_handoff_enabled.unset(r);
-    sp::get_hinted_handoff_enabled_by_dc.unset(r);
-    sp::set_hinted_handoff_enabled_by_dc_list.unset(r);
-    sp::get_max_hint_window.unset(r);
-    sp::set_max_hint_window.unset(r);
-    sp::get_max_hints_in_progress.unset(r);
-    sp::set_max_hints_in_progress.unset(r);
-    sp::get_hints_in_progress.unset(r);
-    sp::get_rpc_timeout.unset(r);
-    sp::set_rpc_timeout.unset(r);
-    sp::get_read_rpc_timeout.unset(r);
-    sp::set_read_rpc_timeout.unset(r);
-    sp::get_write_rpc_timeout.unset(r);
-    sp::set_write_rpc_timeout.unset(r);
-    sp::get_counter_write_rpc_timeout.unset(r);
-    sp::set_counter_write_rpc_timeout.unset(r);
-    sp::get_cas_contention_timeout.unset(r);
-    sp::set_cas_contention_timeout.unset(r);
-    sp::get_range_rpc_timeout.unset(r);
-    sp::set_range_rpc_timeout.unset(r);
-    sp::get_truncate_rpc_timeout.unset(r);
-    sp::set_truncate_rpc_timeout.unset(r);
-    sp::reload_trigger_classes.unset(r);
-    sp::get_read_repair_attempted.unset(r);
-    sp::get_read_repair_repaired_blocking.unset(r);
-    sp::get_read_repair_repaired_background.unset(r);
-    sp::get_cas_read_timeouts.unset(r);
-    sp::get_cas_read_unavailables.unset(r);
-    sp::get_cas_write_timeouts.unset(r);
-    sp::get_cas_write_unavailables.unset(r);
-    sp::get_cas_write_metrics_unfinished_commit.unset(r);
-    sp::get_cas_write_metrics_contention.unset(r);
-    sp::get_cas_write_metrics_condition_not_met.unset(r);
-    sp::get_cas_write_metrics_failed_read_round_optimization.unset(r);
-    sp::get_cas_read_metrics_unfinished_commit.unset(r);
-    sp::get_cas_read_metrics_contention.unset(r);
-    sp::get_read_metrics_timeouts.unset(r);
-    sp::get_read_metrics_unavailables.unset(r);
-    sp::get_range_metrics_timeouts.unset(r);
-    sp::get_range_metrics_unavailables.unset(r);
-    sp::get_write_metrics_timeouts.unset(r);
-    sp::get_write_metrics_unavailables.unset(r);
-    sp::get_read_metrics_timeouts_rates.unset(r);
-    sp::get_read_metrics_unavailables_rates.unset(r);
-    sp::get_range_metrics_timeouts_rates.unset(r);
-    sp::get_range_metrics_unavailables_rates.unset(r);
-    sp::get_write_metrics_timeouts_rates.unset(r);
-    sp::get_write_metrics_unavailables_rates.unset(r);
-    sp::get_range_metrics_latency_histogram_depricated.unset(r);
-    sp::get_write_metrics_latency_histogram_depricated.unset(r);
-    sp::get_read_metrics_latency_histogram_depricated.unset(r);
-    sp::get_range_metrics_latency_histogram.unset(r);
-    sp::get_write_metrics_latency_histogram.unset(r);
-    sp::get_cas_write_metrics_latency_histogram.unset(r);
-    sp::get_cas_read_metrics_latency_histogram.unset(r);
-    sp::get_view_write_metrics_latency_histogram.unset(r);
-    sp::get_read_metrics_latency_histogram.unset(r);
-    sp::get_read_estimated_histogram.unset(r);
-    sp::get_read_latency.unset(r);
-    sp::get_write_estimated_histogram.unset(r);
-    sp::get_write_latency.unset(r);
-    sp::get_range_estimated_histogram.unset(r);
-    sp::get_range_latency.unset(r);
-}
-
 }

api/storage_proxy.hh

@@ -1,21 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
  */
 
 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #pragma once
 
-#include <seastar/core/sharded.hh>
 #include "api.hh"
 
-namespace service { class storage_proxy; }
-
 namespace api {
 
-void set_storage_proxy(http_context& ctx, httpd::routes& r, sharded<service::storage_proxy>& proxy);
-void unset_storage_proxy(http_context& ctx, httpd::routes& r);
+void set_storage_proxy(http_context& ctx, routes& r);
 
 }