Update HISTORY.md and version for 8.10.2

Summary:
pdillinger This fixes the RocksJava build, is also needed in the 8.10.fb and 8.11.fb branches please?

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12358

Reviewed By: jaykorean

Differential Revision: D53859743

Pulled By: pdillinger

fbshipit-source-id: b8417fccfee931591805f9aecdfae7c086fee708

.circleci/config.yml

@@ -146,12 +146,9 @@ commands:
   install-maven:
     steps:
       - run:
-          name: Install Maven
+          name: Install maven
           command: |
-            wget --no-check-certificate https://dlcdn.apache.org/maven/maven-3/3.9.6/binaries/apache-maven-3.9.6-bin.tar.gz
-            tar zxf apache-maven-3.9.6-bin.tar.gz
-            echo "export M2_HOME=$(pwd)/apache-maven-3.9.6" >> $BASH_ENV
-            echo 'export PATH=$M2_HOME/bin:$PATH' >> $BASH_ENV
+            sudo apt-get update -y && sudo apt-get install -y maven
 
   setup-folly:
     steps:
@@ -234,7 +231,6 @@ executors:
       - image: zjay437/rocksdb:0.6
   linux-java-docker:
     docker:
-      # This is the Docker Image used for building RocksJava releases, see: https://github.com/evolvedbinary/docker-rocksjava
       - image: evolvedbinary/rocksjava:centos6_x64-be
 
 jobs:
@@ -248,7 +244,7 @@ jobs:
       - increase-max-open-files-on-macos
       - install-gflags-on-macos
       - pre-steps-macos
-      - run: ulimit -S -n `ulimit -H -n` && make V=1 J=16 -j16 all
+      - run: ulimit -S -n `ulimit -H -n` && OPT=-DCIRCLECI make V=1 J=16 -j16 all
       - post-steps
 
   build-macos-cmake:
@@ -547,7 +543,7 @@ jobs:
     resource_class: large
     steps:
       - pre-steps
-      - run: ulimit -S -n `ulimit -H -n` && make V=1 -j8 CRASH_TEST_EXT_ARGS='--duration=960 --max_key=2500000' blackbox_crash_test_with_atomic_flush
+      - run: ulimit -S -n `ulimit -H -n` && make V=1 -j8 CRASH_TEST_EXT_ARGS='--duration=960 --max_key=2500000 --use_io_uring=0' blackbox_crash_test_with_atomic_flush
       - post-steps
 
   build-linux-crashtest-tiered-storage-bb:
@@ -557,7 +553,7 @@ jobs:
       - pre-steps
       - run:
           name: "run crashtest"
-          command: ulimit -S -n `ulimit -H -n` && make V=1 -j32 CRASH_TEST_EXT_ARGS='--duration=10800' blackbox_crash_test_with_tiered_storage
+          command: ulimit -S -n `ulimit -H -n` && make V=1 -j32 CRASH_TEST_EXT_ARGS='--duration=10800 --use_io_uring=0' blackbox_crash_test_with_tiered_storage
           no_output_timeout: 100m
       - post-steps
 
@@ -568,7 +564,7 @@ jobs:
       - pre-steps
       - run:
           name: "run crashtest"
-          command: ulimit -S -n `ulimit -H -n` && make V=1 -j32 CRASH_TEST_EXT_ARGS='--duration=10800' whitebox_crash_test_with_tiered_storage
+          command: ulimit -S -n `ulimit -H -n` && make V=1 -j32 CRASH_TEST_EXT_ARGS='--duration=10800 --use_io_uring=0' whitebox_crash_test_with_tiered_storage
           no_output_timeout: 100m
       - post-steps
 
@@ -627,7 +623,7 @@ jobs:
       - windows-build-steps
 
   build-linux-java:
-    executor: linux-java-docker
+    executor: linux-docker
     resource_class: large
     steps:
       - pre-steps
@@ -640,13 +636,17 @@ jobs:
             which javac && javac -version
       - run:
           name: "Test RocksDBJava"
-          command: scl enable devtoolset-7 'make V=1 J=8 -j8 jtest'
+          command: make V=1 J=8 -j8 jtest
       - post-steps
 
   build-linux-java-pmd:
-    executor: linux-java-docker
+    machine:
+      image: ubuntu-2004:202111-02
     resource_class: large
+    environment:
+      JAVA_HOME: /usr/lib/jvm/java-8-openjdk-amd64
     steps:
+      - install-maven
       - pre-steps
       - run:
           name: "Set Java Environment"
@@ -655,10 +655,9 @@ jobs:
             echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
             which java && java -version
             which javac && javac -version
-      - install-maven
       - run:
           name: "PMD RocksDBJava"
-          command: scl enable devtoolset-7 'make V=1 J=8 -j8 jpmd'
+          command: make V=1 J=8 -j8 jpmd
       - post-pmd-steps
 
   build-linux-java-static:
@@ -878,11 +877,66 @@ jobs:
       - perform-benchmarks
       - post-benchmarks
 
-workflows: # Only jobs that haven't been successfully migrated to GitHub Actions
+workflows:
   version: 2
+  jobs-linux-run-tests:
+    jobs:
+      - build-linux
+      - build-linux-cmake-with-folly
+      - build-linux-cmake-with-folly-lite-no-test
+      - build-linux-gcc-7-with-folly
+      - build-linux-gcc-7-with-folly-lite-no-test
+      - build-linux-cmake-with-folly-coroutines
+      - build-linux-cmake-with-benchmark
+      - build-linux-encrypted_env-no_compression
+  jobs-linux-run-tests-san:
+    jobs:
+      - build-linux-clang10-asan
+      - build-linux-clang10-ubsan
+      - build-linux-clang10-mini-tsan
+      - build-linux-static_lib-alt_namespace-status_checked
+  jobs-linux-no-test-run:
+    jobs:
+      - build-linux-release
+      - build-linux-release-rtti
+      - build-examples
+      - build-fuzzers
+      - build-linux-clang-no_test_run
+      - build-linux-clang-13-no_test_run
+      - build-linux-gcc-8-no_test_run
+      - build-linux-gcc-10-cxx20-no_test_run
+      - build-linux-gcc-11-no_test_run
+      - build-linux-arm-cmake-no_test_run
+  jobs-linux-other-checks:
+    jobs:
+      - build-linux-clang10-clang-analyze
+      - build-linux-unity-and-headers
+      - build-linux-mini-crashtest
+  jobs-windows:
+    jobs:
+      - build-windows-vs2019
+      - build-cmake-mingw
+  jobs-java:
+    jobs:
+      - build-linux-java
+      - build-linux-java-static
+      - build-macos-java
+      - build-macos-java-static
+      - build-macos-java-static-universal
+      - build-linux-java-pmd
+  jobs-macos:
+    jobs:
+      - build-macos
+      - build-macos-cmake:
+          run_even_tests: true
+      - build-macos-cmake:
+          run_even_tests: false
   jobs-linux-arm:
     jobs:
       - build-linux-arm
+  build-fuzzers:
+    jobs:
+      - build-fuzzers
   benchmark-linux:
     triggers:
       - schedule:
@@ -902,4 +956,11 @@ workflows: # Only jobs that haven't been successfully migrated to GitHub Actions
               only:
                 - main
     jobs:
+      - build-format-compatible
       - build-linux-arm-test-full
+      - build-linux-run-microbench
+      - build-linux-non-shm
+      - build-linux-clang-13-asan-ubsan-with-folly
+      - build-linux-valgrind
+      - build-windows-vs2022-avx2
+      - build-windows-vs2022

.github/actions/build-folly/action.yml

@@ -1,7 +0,0 @@
-name: build-folly
-runs:
-  using: composite
-  steps:
-  - name: Build folly and dependencies
-    run: make build_folly
-    shell: bash

.github/actions/build-for-benchmarks/action.yml

@@ -1,8 +0,0 @@
-name: build-for-benchmarks
-runs:
-  using: composite
-  steps:
-  - uses: "./.github/actions/pre-steps"
-  - name: Linux build for benchmarks
-    run: make V=1 J=8 -j8 release
-    shell: bash

.github/actions/increase-max-open-files-on-macos/action.yml

@@ -1,10 +0,0 @@
-name: increase-max-open-files-on-macos
-runs:
-  using: composite
-  steps:
-  - name: Increase max open files
-    run: |-
-      sudo sysctl -w kern.maxfiles=1048576
-      sudo sysctl -w kern.maxfilesperproc=1048576
-      sudo launchctl limit maxfiles 1048576
-    shell: bash

.github/actions/install-gflags-on-macos/action.yml

@@ -1,7 +0,0 @@
-name: install-gflags-on-macos
-runs:
-  using: composite
-  steps:
-  - name: Install gflags on macos
-    run: HOMEBREW_NO_AUTO_UPDATE=1 brew install gflags
-    shell: bash

.github/actions/install-gflags/action.yml

@@ -1,7 +0,0 @@
-name: install-gflags
-runs:
-  using: composite
-  steps:
-  - name: Install gflags
-    run: sudo apt-get update -y && sudo apt-get install -y libgflags-dev
-    shell: bash

.github/actions/install-jdk8-on-macos/action.yml

@@ -1,9 +0,0 @@
-name: install-jdk8-on-macos
-runs:
-  using: composite
-  steps:
-  - name: Install JDK 8 on macos
-    run: |-
-      HOMEBREW_NO_AUTO_UPDATE=1 brew tap bell-sw/liberica
-      HOMEBREW_NO_AUTO_UPDATE=1 brew install --cask liberica-jdk8
-    shell: bash

.github/actions/install-maven/action.yml

@@ -1,11 +0,0 @@
-name: install-maven
-runs:
-  using: composite
-  steps:
-  - name: Install Maven
-    run: |
-      wget --no-check-certificate https://dlcdn.apache.org/maven/maven-3/3.9.6/binaries/apache-maven-3.9.6-bin.tar.gz
-      tar zxf apache-maven-3.9.6-bin.tar.gz
-      echo "export M2_HOME=$(pwd)/apache-maven-3.9.6" >> $GITHUB_ENV
-      echo "$(pwd)/apache-maven-3.9.6/bin" >> $GITHUB_PATH
-    shell: bash

.github/actions/perform-benchmarks/action.yml

@@ -1,22 +0,0 @@
-name: perform-benchmarks
-runs:
-  using: composite
-  steps:
-  - name: Test low-variance benchmarks
-    run: "./tools/benchmark_ci.py --db_dir ${{ runner.temp }}/rocksdb-benchmark-datadir --output_dir ${{ runner.temp }}/benchmark-results --num_keys 20000000"
-    env:
-      LD_LIBRARY_PATH: "/usr/local/lib"
-      DURATION_RO: 300
-      DURATION_RW: 500
-      NUM_THREADS: 1
-      MAX_BACKGROUND_JOBS: 4
-      CI_TESTS_ONLY: 'true'
-      WRITE_BUFFER_SIZE_MB: 16
-      TARGET_FILE_SIZE_BASE_MB: 16
-      MAX_BYTES_FOR_LEVEL_BASE_MB: 64
-      COMPRESSION_TYPE: none
-      CACHE_INDEX_AND_FILTER_BLOCKS: 1
-      MIN_LEVEL_TO_COMPRESS: 3
-      CACHE_SIZE_MB: 10240
-      MB_WRITE_PER_SEC: 2
-    shell: bash

.github/actions/post-benchmarks/action.yml

@@ -1,17 +0,0 @@
-name: post-benchmarks
-runs:
-  using: composite
-  steps:
-  - name: Upload Benchmark Results artifact
-    uses: actions/upload-artifact@v4.0.0
-    with:
-      name: benchmark-results
-      path: "${{ runner.temp }}/benchmark-results/**"
-      if-no-files-found: error
-  - name: Send benchmark report to visualisation
-    run: |-
-      set +e
-      set +o pipefail
-      ./build_tools/benchmark_log_tool.py --tsvfile ${{ runner.temp }}/benchmark-results/report.tsv --esdocument https://search-rocksdb-bench-k2izhptfeap2hjfxteolsgsynm.us-west-2.es.amazonaws.com/bench_test3_rix/_doc
-      true
-    shell: bash

.github/actions/post-steps/action.yml

@@ -1,38 +0,0 @@
-name: post-steps
-description: Steps that are taken after a RocksDB job
-inputs:
-  artifact-prefix:
-    description: Prefix to append to the name of artifacts that are uploaded
-    required: true
-    default: "${{ github.job }}"
-runs:
-  using: composite
-  steps:
-  - name: Upload Test Results artifact
-    uses: actions/upload-artifact@v4.0.0
-    with:
-      name: "${{ inputs.artifact-prefix }}-test-results"
-      path: "${{ runner.temp }}/test-results/**"
-  - name: Upload DB LOG file artifact
-    uses: actions/upload-artifact@v4.0.0
-    with:
-      name: "${{ inputs.artifact-prefix }}-db-log-file"
-      path: LOG
-  - name: Copy Test Logs (on Failure)
-    if: ${{ failure() }}
-    run: |
-      mkdir -p ${{ runner.temp }}/failure-test-logs
-      cp -r t/* ${{ runner.temp }}/failure-test-logs
-    shell: bash
-  - name: Upload Test Logs (on Failure) artifact
-    uses: actions/upload-artifact@v4.0.0
-    with:
-      name: "${{ inputs.artifact-prefix }}-failure-test-logs"
-      path: ${{ runner.temp }}/failure-test-logs/**
-      if-no-files-found: ignore
-  - name: Upload Core Dumps artifact
-    uses: actions/upload-artifact@v4.0.0
-    with:
-      name: "${{ inputs.artifact-prefix }}-core-dumps"
-      path: "core.*"
-      if-no-files-found: ignore

.github/actions/pre-steps-macos/action.yml

@@ -1,5 +0,0 @@
-name: pre-steps-macos
-runs:
-  using: composite
-  steps:
-  - uses: "./.github/actions/pre-steps"

.github/actions/pre-steps/action.yml

@@ -1,18 +0,0 @@
-name: pre-steps
-runs:
-  using: composite
-  steps:
-  - name: Setup Environment Variables
-    run: |-
-      echo "GTEST_THROW_ON_FAILURE=0" >> "$GITHUB_ENV"
-      echo "GTEST_OUTPUT=\"xml:${{ runner.temp }}/test-results/\"" >> "$GITHUB_ENV"
-      echo "SKIP_FORMAT_BUCK_CHECKS=1" >> "$GITHUB_ENV"
-      echo "GTEST_COLOR=1" >> "$GITHUB_ENV"
-      echo "CTEST_OUTPUT_ON_FAILURE=1" >> "$GITHUB_ENV"
-      echo "CTEST_TEST_TIMEOUT=300" >> "$GITHUB_ENV"
-      echo "ZLIB_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/zlib" >> "$GITHUB_ENV"
-      echo "BZIP2_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/bzip2" >> "$GITHUB_ENV"
-      echo "SNAPPY_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/snappy" >> "$GITHUB_ENV"
-      echo "LZ4_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/lz4" >> "$GITHUB_ENV"
-      echo "ZSTD_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/zstd" >> "$GITHUB_ENV"
-    shell: bash

.github/actions/setup-folly/action.yml

@@ -1,7 +0,0 @@
-name: setup-folly
-runs:
-  using: composite
-  steps:
-  - name: Checkout folly sources
-    run: make checkout_folly
-    shell: bash

.github/actions/setup-upstream/action.yml

@@ -1,20 +0,0 @@
-name: build-folly
-runs:
-  using: composite
-  steps:
-  - name: Fix repo ownership
-    # Needed in some cases, as safe.directory setting doesn't take effect
-    # under env -i
-    run: chown `whoami` . || true
-    shell: bash
-  - name: Set upstream
-    run: git remote add upstream https://github.com/facebook/rocksdb.git
-    shell: bash
-  - name: Fetch upstream
-    run: git fetch upstream
-    shell: bash
-  - name: Git status
-    # NOTE: some old branch builds under check_format_compatible.sh invoke
-    # git under env -i
-    run: git status && git remote -v && env -i git branch
-    shell: bash

.github/actions/windows-build-steps/action.yml

@@ -1,54 +0,0 @@
-name: windows-build-steps
-runs:
-  using: composite
-  steps:
-  - name: Add msbuild to PATH
-    uses: microsoft/setup-msbuild@v1.3.1
-  - name: Custom steps
-    env:
-      THIRDPARTY_HOME: ${{ github.workspace }}/thirdparty
-      CMAKE_HOME: C:/Program Files/CMake
-      CMAKE_BIN: C:/Program Files/CMake/bin/cmake.exe
-      CTEST_BIN: C:/Program Files/CMake/bin/ctest.exe
-      JAVA_HOME: C:/Program Files/BellSoft/LibericaJDK-8
-      SNAPPY_HOME: ${{ github.workspace }}/thirdparty/snappy-1.1.8
-      SNAPPY_INCLUDE: ${{ github.workspace }}/thirdparty/snappy-1.1.8;${{ github.workspace }}/thirdparty/snappy-1.1.8/build
-      SNAPPY_LIB_DEBUG: ${{ github.workspace }}/thirdparty/snappy-1.1.8/build/Debug/snappy.lib
-    run: |-
-      # NOTE: if ... Exit $LASTEXITCODE lines needed to exit and report failure
-      echo ===================== Install Dependencies =====================
-      choco install liberica8jdk -y
-      if(!$?) { Exit $LASTEXITCODE }
-      mkdir $Env:THIRDPARTY_HOME
-      cd $Env:THIRDPARTY_HOME
-      echo "Building Snappy dependency..."
-      curl -Lo snappy-1.1.8.zip https://github.com/google/snappy/archive/refs/tags/1.1.8.zip
-      if(!$?) { Exit $LASTEXITCODE }
-      unzip -q snappy-1.1.8.zip
-      if(!$?) { Exit $LASTEXITCODE }
-      cd snappy-1.1.8
-      mkdir build
-      cd build
-      & cmake -G "$Env:CMAKE_GENERATOR" ..
-      if(!$?) { Exit $LASTEXITCODE }
-      msbuild Snappy.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
-      if(!$?) { Exit $LASTEXITCODE }
-      echo ======================== Build RocksDB =========================
-      cd ${{ github.workspace }}
-      $env:Path = $env:JAVA_HOME + ";" + $env:Path
-      mkdir build
-      cd build
-      & cmake -G "$Env:CMAKE_GENERATOR" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE="$Env:CMAKE_PORTABLE" -DSNAPPY=1 -DJNI=1 ..
-      if(!$?) { Exit $LASTEXITCODE }
-      cd ..
-      echo "Building with VS version: $Env:CMAKE_GENERATOR"
-      msbuild build/rocksdb.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
-      if(!$?) { Exit $LASTEXITCODE }
-      echo ========================= Test RocksDB =========================
-      build_tools\run_ci_db_test.ps1 -SuiteRun arena_test,db_basic_test,db_test,db_test2,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test -Concurrency 16
-      if(!$?) { Exit $LASTEXITCODE }
-      echo ======================== Test RocksJava ========================
-      cd build\java
-      & ctest -C Debug -j 16
-      if(!$?) { Exit $LASTEXITCODE }
-    shell: pwsh

.github/workflows/benchmark-linux.yml

@@ -1,15 +0,0 @@
-name: facebook/rocksdb/benchmark-linux
-on: workflow_dispatch
-permissions: {}
-  # FIXME: Disabled temporarily
-  # schedule:
-  # - cron: 7 */2 * * *  # At minute 7 past every 2nd hour
-jobs:
-  benchmark-linux:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: ubuntu-latest # FIXME: change this back to self-hosted when ready
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/build-for-benchmarks"
-    - uses: "./.github/actions/perform-benchmarks"
-    - uses: "./.github/actions/post-benchmarks"

.github/workflows/nightly-candidate.yml

@@ -1,19 +0,0 @@
-name: facebook/rocksdb/nightly
-on: workflow_dispatch
-permissions: {}
-jobs:
-  # These jobs would be in nightly but are failing or otherwise broken for
-  # some reason.
-  build-linux-arm-test-full:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: arm64large
-    container:
-      image: ubuntu-2004:202111-02
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/install-gflags"
-    - run: make V=1 J=4 -j4 check
-    - uses: "./.github/actions/post-steps"

.github/workflows/nightly.yml

@@ -1,112 +0,0 @@
-name: facebook/rocksdb/nightly
-on:
-  schedule:
-  - cron: 0 9 * * *
-  workflow_dispatch:
-permissions: {}
-jobs:
-  build-format-compatible:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-      with:
-        fetch-depth: 0 # Need full repo history
-        fetch-tags: true
-    - uses: "./.github/actions/setup-upstream"
-    - uses: "./.github/actions/pre-steps"
-    - name: test
-      run: |-
-        export TEST_TMPDIR=/dev/shm/rocksdb
-        rm -rf /dev/shm/rocksdb
-        mkdir /dev/shm/rocksdb
-        git config --global --add safe.directory /__w/rocksdb/rocksdb
-        tools/check_format_compatible.sh
-    - uses: "./.github/actions/post-steps"
-  build-linux-run-microbench:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: DEBUG_LEVEL=0 make -j32 run_microbench
-    - uses: "./.github/actions/post-steps"
-  build-linux-non-shm:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      TEST_TMPDIR: "/tmp/rocksdb_test_tmp"
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: make V=1 -j32 check
-    - uses: "./.github/actions/post-steps"
-  build-linux-clang-13-asan-ubsan-with-folly:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      CC: clang-13
-      CXX: clang++-13
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/setup-folly"
-    - uses: "./.github/actions/build-folly"
-    - run: LIB_MODE=static USE_CLANG=1 USE_FOLLY=1 COMPILE_WITH_UBSAN=1 COMPILE_WITH_ASAN=1 make -j32 check
-    - uses: "./.github/actions/post-steps"
-  build-linux-valgrind:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: make V=1 -j32 valgrind_test
-    - uses: "./.github/actions/post-steps"
-  build-windows-vs2022-avx2:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: windows-2022
-    env:
-      CMAKE_GENERATOR: Visual Studio 17 2022
-      CMAKE_PORTABLE: AVX2
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/windows-build-steps"
-  build-windows-vs2022:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: windows-2022
-    env:
-      CMAKE_GENERATOR: Visual Studio 17 2022
-      CMAKE_PORTABLE: 1
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/windows-build-steps"
-  build-linux-arm-test-full:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu-arm
-    steps:
-      - uses: actions/checkout@v4.1.0
-      - uses: "./.github/actions/pre-steps"
-      - run: sudo apt-get update && sudo apt-get install -y build-essential libgflags-dev
-      - run: make V=1 J=4 -j4 check
-      - uses: "./.github/actions/post-steps"

.github/workflows/pr-jobs-candidate.yml

@@ -1,47 +0,0 @@
-name: facebook/rocksdb/pr-jobs-candidate
-on: workflow_dispatch
-permissions: {}
-jobs:
-  # These jobs would be in pr-jobs but are failing or otherwise broken for
-  # some reason.
-  # =========================== ARM Jobs ============================ #
-  build-linux-arm:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: arm64large # GitHub hosted ARM runners do not yet exist
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/install-gflags"
-    - run: ROCKSDBTESTS_PLATFORM_DEPENDENT=only make V=1 J=4 -j4 all_but_some_tests check_some
-    - uses: "./.github/actions/post-steps"
-  build-linux-arm-cmake-no_test_run:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: arm64large # GitHub hosted ARM runners do not yet exist
-    env:
-      JAVA_HOME: "/usr/lib/jvm/java-8-openjdk-arm64"
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/install-gflags"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
-        which java && java -version
-        which javac && javac -version
-    - name: Build with cmake
-      run: |-
-        mkdir build
-        cd build
-        cmake -DCMAKE_BUILD_TYPE=Release -DWITH_TESTS=0 -DWITH_GFLAGS=1 -DWITH_BENCHMARK_TOOLS=0 -DWITH_TOOLS=0 -DWITH_CORE_TOOLS=1 ..
-        make -j4
-    - name: Build Java with cmake
-      run: |-
-        rm -rf build
-        mkdir build
-        cd build
-        cmake -DJNI=1 -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 ..
-        make -j4 rocksdb rocksdbjni
-    - uses: "./.github/actions/post-steps"

.github/workflows/pr-jobs.yml

@@ -1,632 +0,0 @@
-name: facebook/rocksdb/pr-jobs
-on: [push, pull_request]
-permissions: {}
-jobs:
-  # NOTE: multiple workflows would be recommended, but the current GHA UI in
-  # PRs doesn't make it clear when there's an overall error with a workflow,
-  # making it easy to overlook something broken. Grouping everything into one
-  # workflow minimizes the problem because it will be suspicious if there are
-  # no GHA results.
-  #
-  # The if: ${{ github.repository_owner == 'facebook' }} lines prevent the
-  # jobs from attempting to run on repo forks, because of a few problems:
-  # * runs-on labels are repository (owner) specific, so the job might wait
-  # for days waiting for a runner that simply isn't available.
-  # * Pushes to branches on forks for pull requests (the normal process) would
-  # run the workflow jobs twice: once in the pull-from fork and once for the PR
-  # destination repo. This is wasteful and dumb.
-  # * It is not known how to avoid copy-pasting the line to each job,
-  # increasing the risk of misconfiguration, especially on forks that might
-  # want to run with this GHA setup.
-  #
-  # DEBUGGING WITH SSH: Temporarily add this as a job step, either before the
-  # step of interest without the "if:" line or after the failing step with the
-  # "if:" line. Then use ssh command printed in CI output.
-  #  - name: Setup tmate session # TEMPORARY!
-  #    if: ${{ failure() }}
-  #    uses: mxschmitt/action-tmate@v3
-  #    with:
-  #      limit-access-to-actor: true
-
-  # ======================== Fast Initial Checks ====================== #
-  check-format-and-targets:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4.1.0
-      with:
-        fetch-depth: 0 # Need full checkout to determine merge base
-        fetch-tags: true
-    - uses: "./.github/actions/setup-upstream"
-    - name: Setup Python
-      uses: actions/setup-python@v5
-    - name: Install Dependencies
-      run: python -m pip install --upgrade pip
-    - name: Install argparse
-      run: pip install argparse
-    - name: Download clang-format-diff.py
-      run: wget https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
-    - name: Check format
-      run: VERBOSE_CHECK=1 make check-format
-    - name: Compare buckify output
-      run: make check-buck-targets
-    - name: Simple source code checks
-      run: make check-sources
-  # ========================= Linux With Tests ======================== #
-  build-linux:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: make V=1 J=32 -j32 check
-    - uses: "./.github/actions/post-steps"
-  build-linux-cmake-mingw:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix
-    - name: Build cmake-mingw
-      run: |-
-        export PATH=$JAVA_HOME/bin:$PATH
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-        mkdir build && cd build && cmake -DJNI=1 -DWITH_GFLAGS=OFF .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
-    - uses: "./.github/actions/post-steps"
-  build-linux-cmake-with-folly:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      CC: gcc-10
-      CXX: g++-10
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/setup-folly"
-    - uses: "./.github/actions/build-folly"
-    - run: "(mkdir build && cd build && cmake -DUSE_FOLLY=1 -DWITH_GFLAGS=1 -DROCKSDB_BUILD_SHARED=0 .. && make V=1 -j20 && ctest -j20)"
-    - uses: "./.github/actions/post-steps"
-  build-linux-cmake-with-folly-lite-no-test:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      CC: gcc-10
-      CXX: g++-10
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/setup-folly"
-    - run: "(mkdir build && cd build && cmake -DUSE_FOLLY_LITE=1 -DWITH_GFLAGS=1 .. && make V=1 -j20)"
-    - uses: "./.github/actions/post-steps"
-  build-linux-make-with-folly:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      CC: gcc-10
-      CXX: g++-10
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/setup-folly"
-    - uses: "./.github/actions/build-folly"
-    - run: USE_FOLLY=1 LIB_MODE=static V=1 make -j32 check
-    - uses: "./.github/actions/post-steps"
-  build-linux-make-with-folly-lite-no-test:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      CC: gcc-10
-      CXX: g++-10
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/setup-folly"
-    - run: USE_FOLLY_LITE=1 V=1 make -j32 all
-    - uses: "./.github/actions/post-steps"
-  build-linux-cmake-with-folly-coroutines:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    env:
-      CC: gcc-10
-      CXX: g++-10
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - uses: "./.github/actions/setup-folly"
-    - uses: "./.github/actions/build-folly"
-    - run: "(mkdir build && cd build && cmake -DUSE_COROUTINES=1 -DWITH_GFLAGS=1 -DROCKSDB_BUILD_SHARED=0 .. && make V=1 -j20 && ctest -j20)"
-    - uses: "./.github/actions/post-steps"
-  build-linux-cmake-with-benchmark:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: mkdir build && cd build && cmake -DWITH_GFLAGS=1 -DWITH_BENCHMARK=1 .. && make V=1 -j20 && ctest -j20
-    - uses: "./.github/actions/post-steps"
-  build-linux-encrypted_env-no_compression:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: ENCRYPTED_ENV=1 ROCKSDB_DISABLE_SNAPPY=1 ROCKSDB_DISABLE_ZLIB=1 ROCKSDB_DISABLE_BZIP=1 ROCKSDB_DISABLE_LZ4=1 ROCKSDB_DISABLE_ZSTD=1 make V=1 J=32 -j32 check
-    - run: "./sst_dump --help | grep -E -q 'Supported compression types: kNoCompression$' # Verify no compiled in compression\n"
-    - uses: "./.github/actions/post-steps"
-  # ======================== Linux No Test Runs ======================= #
-  build-linux-release:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - run: make V=1 -j32 LIB_MODE=shared release
-    - run: ls librocksdb.so
-    - run: "./db_stress --version"
-    - run: make clean
-    - run: make V=1 -j32 release
-    - run: ls librocksdb.a
-    - run: "./db_stress --version"
-    - run: make clean
-    - run: apt-get remove -y libgflags-dev
-    - run: make V=1 -j32 LIB_MODE=shared release
-    - run: ls librocksdb.so
-    - run: if ./db_stress --version; then false; else true; fi
-    - run: make clean
-    - run: make V=1 -j32 release
-    - run: ls librocksdb.a
-    - run: if ./db_stress --version; then false; else true; fi
-    - uses: "./.github/actions/post-steps"
-  build-linux-release-rtti:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 8-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - run: USE_RTTI=1 DEBUG_LEVEL=0 make V=1 -j16 static_lib tools db_bench
-    - run: "./db_stress --version"
-    - run: make clean
-    - run: apt-get remove -y libgflags-dev
-    - run: USE_RTTI=1 DEBUG_LEVEL=0 make V=1 -j16 static_lib tools db_bench
-    - run: if ./db_stress --version; then false; else true; fi
-  build-examples:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - name: Build examples
-      run: make V=1 -j4 static_lib && cd examples && make V=1 -j4
-    - uses: "./.github/actions/post-steps"
-  build-fuzzers:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - name: Build rocksdb lib
-      run: CC=clang-13 CXX=clang++-13 USE_CLANG=1 make -j4 static_lib
-    - name: Build fuzzers
-      run: cd fuzz && make sst_file_writer_fuzzer db_fuzzer db_map_fuzzer
-    - uses: "./.github/actions/post-steps"
-  build-linux-clang-no_test_run:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 8-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - run: CC=clang CXX=clang++ USE_CLANG=1 PORTABLE=1 make V=1 -j16 all
-    - uses: "./.github/actions/post-steps"
-  build-linux-clang-13-no_test_run:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: CC=clang-13 CXX=clang++-13 USE_CLANG=1 make -j32 all microbench
-    - uses: "./.github/actions/post-steps"
-  build-linux-gcc-8-no_test_run:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: CC=gcc-8 CXX=g++-8 V=1 make -j32 all
-    - uses: "./.github/actions/post-steps"
-  build-linux-gcc-10-cxx20-no_test_run:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: CC=gcc-10 CXX=g++-10 V=1 ROCKSDB_CXX_STANDARD=c++20 make -j32 all
-    - uses: "./.github/actions/post-steps"
-  build-linux-gcc-11-no_test_run:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: LIB_MODE=static CC=gcc-11 CXX=g++-11 V=1 make -j32 all microbench
-    - uses: "./.github/actions/post-steps"
-  # ======================== Linux Other Checks ======================= #
-  build-linux-clang10-clang-analyze:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: CC=clang-10 CXX=clang++-10 ROCKSDB_DISABLE_ALIGNED_NEW=1 CLANG_ANALYZER="/usr/bin/clang++-10" CLANG_SCAN_BUILD=scan-build-10 USE_CLANG=1 make V=1 -j32 analyze
-    - uses: "./.github/actions/post-steps"
-    - name: compress test report
-      run: tar -cvzf scan_build_report.tar.gz scan_build_report
-      if: failure()
-    - uses: actions/upload-artifact@v4.0.0
-      with:
-        name: scan-build-report
-        path: scan_build_report.tar.gz
-  build-linux-unity-and-headers:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: gcc:latest
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - run: apt-get update -y && apt-get install -y libgflags-dev
-    - name: Unity build
-      run: make V=1 -j8 unity_test
-    - run: make V=1 -j8 -k check-headers
-    - uses: "./.github/actions/post-steps"
-  build-linux-mini-crashtest:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: ulimit -S -n `ulimit -H -n` && make V=1 -j8 CRASH_TEST_EXT_ARGS='--duration=960 --max_key=2500000' blackbox_crash_test_with_atomic_flush
-    - uses: "./.github/actions/post-steps"
-  # ======================= Linux with Sanitizers ===================== #
-  build-linux-clang10-asan:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 32-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: COMPILE_WITH_ASAN=1 CC=clang-10 CXX=clang++-10 ROCKSDB_DISABLE_ALIGNED_NEW=1 USE_CLANG=1 make V=1 -j32 check
-    - uses: "./.github/actions/post-steps"
-  build-linux-clang10-ubsan:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: COMPILE_WITH_UBSAN=1 OPT="-fsanitize-blacklist=.circleci/ubsan_suppression_list.txt" CC=clang-10 CXX=clang++-10 ROCKSDB_DISABLE_ALIGNED_NEW=1 USE_CLANG=1 make V=1 -j32 ubsan_check
-    - uses: "./.github/actions/post-steps"
-  build-linux-clang10-mini-tsan:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 32-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: COMPILE_WITH_TSAN=1 CC=clang-13 CXX=clang++-13 ROCKSDB_DISABLE_ALIGNED_NEW=1 USE_CLANG=1 make V=1 -j32 check
-    - uses: "./.github/actions/post-steps"
-  build-linux-static_lib-alt_namespace-status_checked:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 16-core-ubuntu
-    container:
-      image: zjay437/rocksdb:0.6
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/pre-steps"
-    - run: ASSERT_STATUS_CHECKED=1 TEST_UINT128_COMPAT=1 ROCKSDB_MODIFY_NPHASH=1 LIB_MODE=static OPT="-DROCKSDB_NAMESPACE=alternative_rocksdb_ns" make V=1 -j24 check
-    - uses: "./.github/actions/post-steps"
-  # ========================= MacOS build only ======================== #
-  build-macos:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: macos-13
-    env:
-      ROCKSDB_DISABLE_JEMALLOC: 1
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: maxim-lobanov/setup-xcode@v1.6.0
-      with:
-        xcode-version: 14.3.1
-    - uses: "./.github/actions/increase-max-open-files-on-macos"
-    - uses: "./.github/actions/install-gflags-on-macos"
-    - uses: "./.github/actions/pre-steps-macos"
-    - name: Build
-      run: ulimit -S -n `ulimit -H -n` && make V=1 J=16 -j16 all
-    - uses: "./.github/actions/post-steps"
-  # ========================= MacOS with Tests ======================== #
-  build-macos-cmake:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: macos-13
-    strategy:
-      matrix:
-        run_even_tests: [true, false]
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: maxim-lobanov/setup-xcode@v1.6.0
-      with:
-        xcode-version: 14.3.1
-    - uses: "./.github/actions/increase-max-open-files-on-macos"
-    - uses: "./.github/actions/install-gflags-on-macos"
-    - uses: "./.github/actions/pre-steps-macos"
-    - name: cmake generate project file
-      run: ulimit -S -n `ulimit -H -n` && mkdir build && cd build && cmake -DWITH_GFLAGS=1 ..
-    - name: Build tests
-      run: cd build && make V=1 -j16
-    - name: Run even tests
-      run: ulimit -S -n `ulimit -H -n` && cd build && ctest -j16 -I 0,,2
-      if: ${{ matrix.run_even_tests }}
-    - name: Run odd tests
-      run: ulimit -S -n `ulimit -H -n` && cd build && ctest -j16 -I 1,,2
-      if: ${{ ! matrix.run_even_tests  }}
-    - uses: "./.github/actions/post-steps"
-  # ======================== Windows with Tests ======================= #
-  # NOTE: some windows jobs are in "nightly" to save resources
-  build-windows-vs2019:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: windows-2019
-    env:
-      CMAKE_GENERATOR: Visual Studio 16 2019
-      CMAKE_PORTABLE: 1
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/windows-build-steps"
-  # ============================ Java Jobs ============================ #
-  build-linux-java:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: evolvedbinary/rocksjava:centos6_x64-be
-      options: --shm-size=16gb
-    steps:
-    # The docker image is intentionally based on an OS that has an older GLIBC version.
-    # That GLIBC is incompatibile with GitHub's actions/checkout. Thus we implement a manual checkout step.
-    - name: Checkout
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        chown `whoami` . || true
-        git clone --no-checkout https://oath2:$GH_TOKEN@github.com/${{ github.repository }}.git .
-        git -c protocol.version=2 fetch --update-head-ok --no-tags --prune --no-recurse-submodules --depth=1 origin +${{ github.sha }}:${{ github.ref }}
-        git checkout --progress --force ${{ github.ref }}
-        git log -1 --format='%H'
-    - uses: "./.github/actions/pre-steps"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-    - name: Test RocksDBJava
-      run: scl enable devtoolset-7 'make V=1 J=8 -j8 jtest'
-    # NOTE: post-steps skipped because of compatibility issues with docker image
-  build-linux-java-static:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: evolvedbinary/rocksjava:centos6_x64-be
-      options: --shm-size=16gb
-    steps:
-    # The docker image is intentionally based on an OS that has an older GLIBC version.
-    # That GLIBC is incompatibile with GitHub's actions/checkout. Thus we implement a manual checkout step.
-    - name: Checkout
-      env:
-        GH_TOKEN: ${{ github.token }}
-      run: |
-        chown `whoami` . || true
-        git clone --no-checkout https://oath2:$GH_TOKEN@github.com/${{ github.repository }}.git .
-        git -c protocol.version=2 fetch --update-head-ok --no-tags --prune --no-recurse-submodules --depth=1 origin +${{ github.sha }}:${{ github.ref }}
-        git checkout --progress --force ${{ github.ref }}
-        git log -1 --format='%H'
-    - uses: "./.github/actions/pre-steps"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-    - name: Build RocksDBJava Static Library
-      run: scl enable devtoolset-7 'make V=1 J=8 -j8 rocksdbjavastatic'
-    # NOTE: post-steps skipped because of compatibility issues with docker image
-  build-macos-java:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: macos-13
-    env:
-      JAVA_HOME: "/Library/Java/JavaVirtualMachines/liberica-jdk-8.jdk/Contents/Home"
-      ROCKSDB_DISABLE_JEMALLOC: 1
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: maxim-lobanov/setup-xcode@v1.6.0
-      with:
-        xcode-version: 14.3.1
-    - uses: "./.github/actions/increase-max-open-files-on-macos"
-    - uses: "./.github/actions/install-gflags-on-macos"
-    - uses: "./.github/actions/install-jdk8-on-macos"
-    - uses: "./.github/actions/pre-steps-macos"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-    - name: Test RocksDBJava
-      run: make V=1 J=16 -j16 jtest
-    - uses: "./.github/actions/post-steps"
-  build-macos-java-static:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: macos-13
-    env:
-      JAVA_HOME: "/Library/Java/JavaVirtualMachines/liberica-jdk-8.jdk/Contents/Home"
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: maxim-lobanov/setup-xcode@v1.6.0
-      with:
-        xcode-version: 14.3.1
-    - uses: "./.github/actions/increase-max-open-files-on-macos"
-    - uses: "./.github/actions/install-gflags-on-macos"
-    - uses: "./.github/actions/install-jdk8-on-macos"
-    - uses: "./.github/actions/pre-steps-macos"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-    - name: Build RocksDBJava x86 and ARM Static Libraries
-      run: make V=1 J=16 -j16 rocksdbjavastaticosx
-    - uses: "./.github/actions/post-steps"
-  build-macos-java-static-universal:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: macos-13
-    env:
-      JAVA_HOME: "/Library/Java/JavaVirtualMachines/liberica-jdk-8.jdk/Contents/Home"
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: maxim-lobanov/setup-xcode@v1.6.0
-      with:
-        xcode-version: 14.3.1
-    - uses: "./.github/actions/increase-max-open-files-on-macos"
-    - uses: "./.github/actions/install-gflags-on-macos"
-    - uses: "./.github/actions/install-jdk8-on-macos"
-    - uses: "./.github/actions/pre-steps-macos"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-    - name: Build RocksDBJava Universal Binary Static Library
-      run: make V=1 J=16 -j16 rocksdbjavastaticosx_ub
-    - uses: "./.github/actions/post-steps"
-  build-linux-java-pmd:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu
-    container:
-      image: evolvedbinary/rocksjava:rockylinux8_x64-be
-      options: --shm-size=16gb
-    steps:
-    - uses: actions/checkout@v4.1.0
-    - uses: "./.github/actions/install-maven"
-    - uses: "./.github/actions/pre-steps"
-    - name: Set Java Environment
-      run: |-
-        echo "JAVA_HOME=${JAVA_HOME}"
-        which java && java -version
-        which javac && javac -version
-    - name: PMD RocksDBJava
-      run: make V=1 J=8 -j8 jpmd
-    - uses: actions/upload-artifact@v4.0.0
-      with:
-        name: pmd-report
-        path: "${{ github.workspace }}/java/target/pmd.xml"
-    - uses: actions/upload-artifact@v4.0.0
-      with:
-        name: maven-site
-        path: "${{ github.workspace }}/java/target/site"
-  build-linux-arm:
-    if: ${{ github.repository_owner == 'facebook' }}
-    runs-on:
-      labels: 4-core-ubuntu-arm
-    steps:
-      - uses: actions/checkout@v4.1.0
-      - uses: "./.github/actions/pre-steps"
-      - run: sudo apt-get update && sudo apt-get install -y build-essential
-      - run: ROCKSDBTESTS_PLATFORM_DEPENDENT=only make V=1 J=4 -j4 all_but_some_tests check_some
-      - uses: "./.github/actions/post-steps"

.github/workflows/sanity_check.yml

@@ -0,0 +1,45 @@
+name: Check buck targets and code format
+on: [push, pull_request]
+permissions:
+  contents: read
+
+jobs:
+  check:
+    name: Check TARGETS file and code format
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout feature branch
+      uses: actions/checkout@v2
+      with:
+        fetch-depth: 0
+
+    - name: Fetch from upstream
+      run: |
+        git remote add upstream https://github.com/facebook/rocksdb.git && git fetch upstream
+
+    - name: Where am I
+      run: |
+        echo git status && git status
+        echo "git remote -v" && git remote -v
+        echo git branch && git branch
+
+    - name: Setup Python
+      uses: actions/setup-python@v1
+
+    - name: Install Dependencies
+      run: python -m pip install --upgrade pip
+
+    - name: Install argparse
+      run: pip install argparse
+
+    - name: Download clang-format-diff.py
+      run: wget https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
+
+    - name: Check format
+      run: VERBOSE_CHECK=1 make check-format
+
+    - name: Compare buckify output
+      run: make check-buck-targets
+
+    - name: Simple source code checks
+      run: make check-sources

.gitignore

@@ -47,9 +47,6 @@ package/
 unity.a
 tags
 etags
-GPATH
-GRTAGS
-GTAGS
 rocksdb_dump
 rocksdb_undump
 db_test2

CMakeLists.txt

@@ -32,7 +32,7 @@
 # 3. cmake ..
 # 4. make -j
 
-cmake_minimum_required(VERSION 3.12)
+cmake_minimum_required(VERSION 3.10)
 
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
 include(ReadVersion)
@@ -44,29 +44,6 @@ project(rocksdb
   HOMEPAGE_URL https://rocksdb.org/
   LANGUAGES CXX C ASM)
 
-if(APPLE)
-  # On macOS Cmake, when cross-compiling, sometimes CMAKE_SYSTEM_PROCESSOR wrongfully stays
-  # the same as CMAKE_HOST_SYSTEM_PROCESSOR regardless the target CPU.
-  # The manual call to  set(CMAKE_SYSTEM_PROCESSOR) has to be set after the project() call.
-  # because project() might reset CMAKE_SYSTEM_PROCESSOR back to the value of CMAKE_HOST_SYSTEM_PROCESSOR.
-  # Check if CMAKE_SYSTEM_PROCESSOR is not equal to CMAKE_OSX_ARCHITECTURES
-  if(NOT CMAKE_OSX_ARCHITECTURES STREQUAL "")
-    if(NOT CMAKE_SYSTEM_PROCESSOR STREQUAL CMAKE_OSX_ARCHITECTURES)
-      # Split CMAKE_OSX_ARCHITECTURES into a list
-      string(REPLACE ";" " " ARCH_LIST ${CMAKE_OSX_ARCHITECTURES})
-      separate_arguments(ARCH_LIST UNIX_COMMAND ${ARCH_LIST})
-      # Count the number of architectures
-      list(LENGTH ARCH_LIST ARCH_COUNT)
-      # Ensure that exactly one architecture is specified
-      if(NOT ARCH_COUNT EQUAL 1)
-          message(FATAL_ERROR "CMAKE_OSX_ARCHITECTURES must have exactly one value. Current value: ${CMAKE_OSX_ARCHITECTURES}")
-      endif()
-      set(CMAKE_SYSTEM_PROCESSOR ${CMAKE_OSX_ARCHITECTURES})
-      message(STATUS "CMAKE_SYSTEM_PROCESSOR is manually set to ${CMAKE_SYSTEM_PROCESSOR}")
-    endif()
-  endif()
-endif()
-
 if(POLICY CMP0042)
   cmake_policy(SET CMP0042 NEW)
 endif()
@@ -99,6 +76,11 @@ if (WITH_WINDOWS_UTF8_FILENAMES)
 endif()
 option(ROCKSDB_BUILD_SHARED "Build shared versions of the RocksDB libraries" ON)
 
+if ($ENV{CIRCLECI})
+  message(STATUS "Build for CircieCI env, a few tests may be disabled")
+  add_definitions(-DCIRCLECI)
+endif()
+
 if( NOT DEFINED CMAKE_CXX_STANDARD )
   set(CMAKE_CXX_STANDARD 17)
 endif()
@@ -189,7 +171,7 @@ else()
   if(WITH_ZSTD)
     find_package(zstd REQUIRED)
     add_definitions(-DZSTD)
-    include_directories(${ZSTD_INCLUDE_DIRS})
+    include_directories(${ZSTD_INCLUDE_DIR})
     list(APPEND THIRDPARTY_LIBS zstd::zstd)
   endif()
 endif()
@@ -205,7 +187,7 @@ endif()
 
 if(MSVC)
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4996 /wd4100 /wd4324")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4800 /wd4996 /wd4351 /wd4100 /wd4204 /wd4324")
 else()
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall -pthread")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing -Wno-invalid-offsetof")
@@ -214,7 +196,6 @@ else()
   endif()
   if(MINGW)
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wa,-mbig-obj")
     add_definitions(-D_POSIX_C_SOURCE=1)
   endif()
   if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
@@ -267,8 +248,8 @@ endif(CMAKE_SYSTEM_PROCESSOR MATCHES "s390x")
 if(CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
   CHECK_C_COMPILER_FLAG("-march=loongarch64" HAS_LOONGARCH64)
   if(HAS_LOONGARCH64)
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=loongarch64 -mtune=loongarch64")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=loongarch64 -mtune=loongarch64")
+    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=loongarch64 -mtune=loongarch64")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=loongarch64 -mtune=loongarch64")
   endif(HAS_LOONGARCH64)
 endif(CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
 
@@ -395,7 +376,7 @@ option(WITH_NUMA "build with NUMA policy support" OFF)
 if(WITH_NUMA)
   find_package(NUMA REQUIRED)
   add_definitions(-DNUMA)
-  include_directories(${NUMA_INCLUDE_DIRS})
+  include_directories(${NUMA_INCLUDE_DIR})
   list(APPEND THIRDPARTY_LIBS NUMA::NUMA)
 endif()
 
@@ -488,8 +469,6 @@ if(CMAKE_SYSTEM_NAME MATCHES "Cygwin")
   add_definitions(-fno-builtin-memcmp -DCYGWIN)
 elseif(CMAKE_SYSTEM_NAME MATCHES "Darwin")
   add_definitions(-DOS_MACOSX)
-elseif(CMAKE_SYSTEM_NAME MATCHES "iOS")
-  add_definitions(-DOS_MACOSX -DIOS_CROSS_COMPILE)
 elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
   add_definitions(-DOS_LINUX)
 elseif(CMAKE_SYSTEM_NAME MATCHES "SunOS")
@@ -617,7 +596,7 @@ if(USE_FOLLY)
     FMT_INST_PATH)
     exec_program(ls ARGS -d ${FOLLY_INST_PATH}/../gflags* OUTPUT_VARIABLE
     GFLAGS_INST_PATH)
-    set(Boost_DIR ${BOOST_INST_PATH}/lib/cmake/Boost-1.83.0)
+    set(Boost_DIR ${BOOST_INST_PATH}/lib/cmake/Boost-1.78.0)
     if(EXISTS ${FMT_INST_PATH}/lib64)
       set(fmt_DIR ${FMT_INST_PATH}/lib64/cmake/fmt)
     else()
@@ -655,7 +634,6 @@ set(SOURCES
         cache/sharded_cache.cc
         cache/tiered_secondary_cache.cc
         db/arena_wrapped_db_iter.cc
-        db/attribute_group_iterator_impl.cc
         db/blob/blob_contents.cc
         db/blob/blob_fetcher.cc
         db/blob/blob_file_addition.cc
@@ -672,7 +650,6 @@ set(SOURCES
         db/blob/prefetch_buffer_collection.cc
         db/builder.cc
         db/c.cc
-        db/coalescing_iterator.cc
         db/column_family.cc
         db/compaction/compaction.cc
         db/compaction/compaction_iterator.cc
@@ -693,7 +670,6 @@ set(SOURCES
         db/db_impl/db_impl_write.cc
         db/db_impl/db_impl_compaction_flush.cc
         db/db_impl/db_impl_files.cc
-        db/db_impl/db_impl_follower.cc
         db/db_impl/db_impl_open.cc
         db/db_impl/db_impl_debug.cc
         db/db_impl/db_impl_experimental.cc
@@ -716,7 +692,6 @@ set(SOURCES
         db/log_reader.cc
         db/log_writer.cc
         db/malloc_stats.cc
-        db/manifest_ops.cc
         db/memtable.cc
         db/memtable_list.cc
         db/merge_helper.cc
@@ -752,7 +727,6 @@ set(SOURCES
         env/env_encryption.cc
         env/file_system.cc
         env/file_system_tracer.cc
-        env/fs_on_demand.cc
         env/fs_remap.cc
         env/mock_env.cc
         env/unique_id_gen.cc
@@ -780,7 +754,6 @@ set(SOURCES
         memtable/hash_skiplist_rep.cc
         memtable/skiplistrep.cc
         memtable/vectorrep.cc
-        memtable/wbwi_memtable.cc
         memtable/write_buffer_manager.cc
         monitoring/histogram.cc
         monitoring/histogram_windowing.cc
@@ -941,7 +914,6 @@ set(SOURCES
         utilities/persistent_cache/volatile_tier_impl.cc
         utilities/simulator_cache/cache_simulator.cc
         utilities/simulator_cache/sim_cache.cc
-        utilities/table_properties_collectors/compact_for_tiering_collector.cc
         utilities/table_properties_collectors/compact_on_deletion_collector.cc
         utilities/trace/file_trace_reader_writer.cc
         utilities/trace/replayer_impl.cc
@@ -962,7 +934,6 @@ set(SOURCES
         utilities/transactions/write_prepared_txn_db.cc
         utilities/transactions/write_unprepared_txn.cc
         utilities/transactions/write_unprepared_txn_db.cc
-        utilities/types_util.cc
         utilities/ttl/db_ttl_impl.cc
         utilities/wal_filter.cc
         utilities/write_batch_with_index/write_batch_with_index.cc
@@ -1054,7 +1025,6 @@ if(USE_FOLLY_LITE)
   list(APPEND SOURCES
     third-party/folly/folly/container/detail/F14Table.cpp
     third-party/folly/folly/detail/Futex.cpp
-    third-party/folly/folly/lang/Exception.cpp
     third-party/folly/folly/lang/SafeAssert.cpp
     third-party/folly/folly/lang/ToAscii.cpp
     third-party/folly/folly/ScopeGuard.cpp
@@ -1062,12 +1032,6 @@ if(USE_FOLLY_LITE)
     third-party/folly/folly/synchronization/DistributedMutex.cpp
     third-party/folly/folly/synchronization/ParkingLot.cpp)
   include_directories(${PROJECT_SOURCE_DIR}/third-party/folly)
-  exec_program(python3 ${PROJECT_SOURCE_DIR}/third-party/folly ARGS
-  build/fbcode_builder/getdeps.py show-source-dir boost OUTPUT_VARIABLE
-  BOOST_SOURCE_PATH)
-  exec_program(ls ARGS -d ${BOOST_SOURCE_PATH}/boost* OUTPUT_VARIABLE
-  BOOST_INCLUDE_DIR)
-  include_directories(${BOOST_INCLUDE_DIR})
   add_definitions(-DUSE_FOLLY -DFOLLY_NO_CONFIG)
   list(APPEND THIRDPARTY_LIBS glog)
 endif()
@@ -1377,7 +1341,6 @@ if(WITH_TESTS)
         db/file_indexer_test.cc
         db/filename_test.cc
         db/flush_job_test.cc
-        db/db_follower_test.cc
         db/import_column_family_test.cc
         db/listener_test.cc
         db/log_test.cc
@@ -1385,7 +1348,6 @@ if(WITH_TESTS)
         db/memtable_list_test.cc
         db/merge_helper_test.cc
         db/merge_test.cc
-        db/multi_cf_iterator_test.cc
         db/options_file_test.cc
         db/perf_context_test.cc
         db/periodic_task_scheduler_test.cc
@@ -1466,7 +1428,6 @@ if(WITH_TESTS)
         util/ribbon_test.cc
         util/slice_test.cc
         util/slice_transform_test.cc
-        util/string_util_test.cc
         util/timer_queue_test.cc
         util/timer_test.cc
         util/thread_list_test.cc
@@ -1491,7 +1452,6 @@ if(WITH_TESTS)
         utilities/persistent_cache/persistent_cache_test.cc
         utilities/simulator_cache/cache_simulator_test.cc
         utilities/simulator_cache/sim_cache_test.cc
-        utilities/table_properties_collectors/compact_for_tiering_collector_test.cc
         utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
         utilities/transactions/optimistic_transaction_test.cc
         utilities/transactions/transaction_test.cc
@@ -1502,7 +1462,6 @@ if(WITH_TESTS)
         utilities/transactions/lock/range/range_locking_test.cc
         utilities/transactions/timestamped_snapshot_test.cc
         utilities/ttl/ttl_test.cc
-        utilities/types_util_test.cc
         utilities/util_merge_operators_test.cc
         utilities/write_batch_with_index/write_batch_with_index_test.cc
 	${PLUGIN_TESTS}
@@ -1518,7 +1477,7 @@ if(WITH_TESTS)
       utilities/cassandra/test_utils.cc
   )
   enable_testing()
-  add_custom_target(rocksdb_check COMMAND ${CMAKE_CTEST_COMMAND})
+  add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND})
   set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
   add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
   target_link_libraries(${TESTUTILLIB} ${ROCKSDB_LIB} ${FOLLY_LIBS})
@@ -1543,7 +1502,7 @@ if(WITH_TESTS)
       target_link_libraries(${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} testharness gtest ${THIRDPARTY_LIBS} ${ROCKSDB_LIB})
       if(NOT "${exename}" MATCHES "db_sanity_test")
         gtest_discover_tests(${exename} DISCOVERY_TIMEOUT 120)
-        add_dependencies(rocksdb_check ${exename}${ARTIFACT_SUFFIX})
+        add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
       endif()
   endforeach(sourcefile ${TESTS})
 
@@ -1563,7 +1522,7 @@ if(WITH_TESTS)
     add_executable(c_test db/c_test.c)
     target_link_libraries(c_test ${ROCKSDB_LIB_FOR_C} testharness)
     add_test(NAME c_test COMMAND c_test${ARTIFACT_SUFFIX})
-    add_dependencies(rocksdb_check c_test)
+    add_dependencies(check c_test)
   endif()
 endif()
 

HISTORY.md

@@ -1,317 +1,12 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
-## 9.10.0 (12/12/2024)
-### New Features
-* Introduce `TransactionOptions::commit_bypass_memtable` to enable transaction commit to bypass memtable insertions. This can be beneficial for transactions with many operations, as it reduces commit time that is mostly spent on memtable insertion.
-
-### Public API Changes
-* Deprecated Remote Compaction APIs (StartV2, WaitForCompleteV2) are completely removed from the codebase
-
-### Behavior Changes
-* DB::KeyMayExist() now follows its function comment, which means `value` parameter can be null, and it will be set only if `value_found` is passed in.
-
-### Bug Fixes
-* Fix the issue where compaction incorrectly drops a key when there is a snapshot with a sequence number of zero.
-* Honor ConfigOptions.ignore_unknown_options in ParseStruct()
-
-### Performance Improvements
-* Enable reuse of file system allocated buffer for synchronous prefetching.
-* In buffered IO mode, try to align writes on power of 2 if checksum handoff is not enabled for the file type being written.
-
-## 9.9.0 (11/18/2024)
-### New Features
-* Multi-Column-Family-Iterator (CoalescingIterator/AttributeGroupIterator) is no longer marked as experimental
-* Adds a new table property "rocksdb.newest.key.time" which records the unix timestamp of the newest key. Uses this table property for FIFO TTL and temperature change compaction.
-
-### Public API Changes
-* Added a new API `Transaction::GetAttributeGroupIterator` that can be used to create a multi-column-family attribute group iterator over the specified column families, including the data from both the transaction and the underlying database. This API is currently supported for optimistic and write-committed pessimistic transactions.
-* Added a new API `Transaction::GetCoalescingIterator` that can be used to create a multi-column-family coalescing iterator over the specified column families, including the data from both the transaction and the underlying database. This API is currently supported for optimistic and write-committed pessimistic transactions.
-
-### Behavior Changes
-* `BaseDeltaIterator` now honors the read option `allow_unprepared_value`.
-
-### Bug Fixes
-* `BaseDeltaIterator` now calls `PrepareValue` on the base iterator in case it has been created with the `allow_unprepared_value` read option set. Earlier, such base iterators could lead to incorrect values being exposed from `BaseDeltaIterator`.
-* Fix a leak of obsolete blob files left open until DB::Close(). This bug was introduced in version 9.4.0.
-* Fix missing cases of corruption retry during DB open and read API processing.
-* Fix a bug for transaction db with 2pc where an old WAL may be retained longer than needed (#13127).
-* Fix leaks of some open SST files (until `DB::Close()`) that are written but never become live due to various failures. (We now have a check for such leaks with no outstanding issues.)
-* Fix a bug for replaying WALs for WriteCommitted transaction DB when its user-defined timestamps setting is toggled on/off between DB sessions.
-
-### Performance Improvements
-* Fix regression in issue #12038 due to `Options::compaction_readahead_size` greater than `max_sectors_kb` (i.e, largest I/O size that the OS issues to a block device defined in linux)
-
-## 9.8.0 (10/25/2024)
-### New Features
-* All non-`block_cache` options in `BlockBasedTableOptions` are now mutable with `DB::SetOptions()`. See also Bug Fixes below.
-* When using iterators with BlobDB, it is now possible to load large values on an on-demand basis, i.e. only if they are actually needed by the application. This can save I/O in use cases where the values associated with certain keys are not needed. For more details, see the new read option `allow_unprepared_value` and the iterator API `PrepareValue`.
-* Add a new file ingestion option `IngestExternalFileOptions::fill_cache` to support not adding blocks from ingested files into block cache during file ingestion.
-* The option `allow_unprepared_value` is now also supported for multi-column-family iterators (i.e. `CoalescingIterator` and `AttributeGroupIterator`).
-* When a file with just one range deletion (standalone range deletion file) is ingested via bulk loading, it will be marked for compaction. During compaction, this type of files can be used to directly filter out some input files that are not protected by any snapshots and completely deleted by the standalone range deletion file.
-
-### Behavior Changes
-* During file ingestion, overlapping files level assignment are done in multiple batches, so that they can potentially be assigned to lower levels other than always land on L0.
-* OPTIONS file to be loaded by remote worker is now preserved so that it does not get purged by the primary host. A similar technique as how we are preserving new SST files from getting purged is used for this. min_options_file_numbers_ is tracked like pending_outputs_ is tracked.
-* Trim readahead_size during scans so data blocks containing keys that are not in the same prefix as the seek key in `Seek()` are not prefetched when `ReadOptions::auto_readahead_size=true` (default value) and `ReadOptions::prefix_same_as_start = true`
-* Assigning levels for external files are done in the same way for universal compaction and leveled compaction. The old behavior tends to assign files to L0 while the new behavior will assign the files to the lowest level possible.
-
-### Bug Fixes
-* Fix a longstanding race condition in SetOptions for `block_based_table_factory` options. The fix has some subtle behavior changes because of copying and replacing the TableFactory on a change with SetOptions, including requiring an Iterator::Refresh() for an existing Iterator to use the latest options.
-* Fix under counting of allocated memory in the compressed secondary cache due to looking at the compressed block size rather than the actual memory allocated, which could be larger due to internal fragmentation.
-* `GetApproximateMemTableStats()` could return disastrously bad estimates 5-25% of the time. The function has been re-engineered to return much better estimates with similar CPU cost.
-* Skip insertion of compressed blocks in the secondary cache if the lowest_used_cache_tier DB option is kVolatileTier.
-* Fix an issue in level compaction where a small CF with small compaction debt can cause the DB to allow parallel compactions. (#13054)
-* Several DB option settings could be lost through `GetOptionsFromString()`, possibly elsewhere as well. Affected options, now fixed:`background_close_inactive_wals`, `write_dbid_to_manifest`, `write_identity_file`, `prefix_seek_opt_in_only`
-
-## 9.7.0 (09/20/2024)
-### New Features
-* Make Cache a customizable class that can be instantiated by the object registry.
-* Add new option `prefix_seek_opt_in_only` that makes iterators generally safer when you might set a `prefix_extractor`. When `prefix_seek_opt_in_only=true`, which is expected to be the future default, prefix seek is only used when `prefix_same_as_start` or `auto_prefix_mode` are set. Also, `prefix_same_as_start` and `auto_prefix_mode` now allow prefix filtering even with `total_order_seek=true`.
-* Add a new table property "rocksdb.key.largest.seqno" which records the largest sequence number of all keys in file. It is verified to be zero during SST file ingestion.
-
-### Behavior Changes
-* Changed the semantics of the BlobDB configuration option `blob_garbage_collection_force_threshold` to define a threshold for the overall garbage ratio of all blob files currently eligible for garbage collection (according to `blob_garbage_collection_age_cutoff`). This can provide better control over space amplification at the cost of slightly higher write amplification.
-* Set `write_dbid_to_manifest=true` by default. This means DB ID will now be preserved through backups, checkpoints, etc. by default. Also add `write_identity_file` option which can be set to false for anticipated future behavior.
-* In FIFO compaction, compactions for changing file temperature (configured by option `file_temperature_age_thresholds`) will compact one file at a time, instead of merging multiple eligible file together (#13018).
-* Support ingesting db generated files using hard link, i.e. IngestExternalFileOptions::move_files/link_files and IngestExternalFileOptions::allow_db_generated_files.
-* Add a new file ingestion option `IngestExternalFileOptions::link_files` to hard link input files and preserve original files links after ingestion.
-* DB::Close now untracks files in SstFileManager, making avaialble any space used
-by them. Prior to this change they would be orphaned until the DB is re-opened.
-
-### Bug Fixes
-* Fix a bug in CompactRange() where result files may not be compacted in any future compaction. This can only happen when users configure CompactRangeOptions::change_level to true and the change level step of manual compaction fails (#13009).
-* Fix handling of dynamic change of `prefix_extractor` with memtable prefix filter. Previously, prefix seek could mix different prefix interpretations between memtable and SST files. Now the latest `prefix_extractor` at the time of iterator creation or refresh is respected.
-* Fix a bug with manual_wal_flush and auto error recovery from WAL failure that may cause CFs to be inconsistent (#12995). The fix will set potential WAL write failure as fatal error when manual_wal_flush is true, and disables auto error recovery from these errors.
-
-## 9.6.0 (08/19/2024)
-### New Features
-* Best efforts recovery supports recovering to incomplete Version with a clean seqno cut that presents a valid point in time view from the user's perspective, if versioning history doesn't include atomic flush.
-* New option `BlockBasedTableOptions::decouple_partitioned_filters` should improve efficiency in serving read queries because filter and index partitions can consistently target the configured `metadata_block_size`. This option is currently opt-in.
-* Introduce a new mutable CF option `paranoid_memory_checks`. It enables additional validation on data integrity during reads/scanning. Currently, skip list based memtable will validate key ordering during look up and scans.
-
-### Public API Changes
-* Add ticker stats to count file read retries due to checksum mismatch
-* Adds optional installation callback function for remote compaction
-
-### Behavior Changes
-* There may be less intra-L0 compaction triggered by total L0 size being too small. We now use compensated file size (tombstones are assigned some value size) when calculating L0 size and reduce the threshold for L0 size limit. This is to avoid accumulating too much data/tombstones in L0.
-
-### Bug Fixes
-* Make DestroyDB supports slow deletion when it's configured in `SstFileManager`. The slow deletion is subject to the configured `rate_bytes_per_sec`, but not subject to the `max_trash_db_ratio`.
-* Fixed a bug where we set unprep_seqs_ even when WriteImpl() fails. This was caught by stress test write fault injection in WriteImpl(). This may have incorrectly caused iteration creation failure for unvalidated writes or returned wrong result for WriteUnpreparedTxn::GetUnpreparedSequenceNumbers().
-* Fixed a bug where successful write right after error recovery for last failed write finishes causes duplicate WAL entries
-* Fixed a data race involving the background error status in `unordered_write` mode.
-* Fix a bug where file snapshot functions like backup, checkpoint may attempt to copy a non-existing manifest file. #12882
-* Fix a bug where per kv checksum corruption may be ignored in MultiGet().
-* Fix a race condition in pessimistic transactions that could allow multiple transactions with the same name to be registered simultaneously, resulting in a crash or other unpredictable behavior.
-
-## 9.5.0 (07/19/2024)
-### Public API Changes
-* Introduced new C API function rocksdb_writebatch_iterate_cf for column family-aware iteration over the contents of a WriteBatch
-* Add support to ingest SST files generated by a DB instead of SstFileWriter. This can be enabled with experimental option `IngestExternalFileOptions::allow_db_generated_files`.
-
-### Behavior Changes
-* When calculating total log size for the `log_size_for_flush` argument in `CreateCheckpoint` API, the size of the archived log will not be included to avoid unnecessary flush
-
-### Bug Fixes
-* Fix a major bug in which an iterator using prefix filtering and SeekForPrev might miss data when the DB is using `whole_key_filtering=false` and `partition_filters=true`.
-* Fixed a bug where `OnErrorRecoveryBegin()` is not called before auto recovery starts.
-* Fixed a bug where event listener reads ErrorHandler's `bg_error_` member without holding db mutex(#12803).
-* Fixed a bug in handling MANIFEST write error that caused the latest valid MANIFEST file to get deleted, resulting in the DB being unopenable.
-* Fixed a race between error recovery due to manifest sync or write failure and external SST file ingestion. Both attempt to write a new manifest file, which causes an assertion failure.
-
-### Performance Improvements
-* Fix an issue where compactions were opening table files and reading table properties while holding db mutex_.
-* Reduce unnecessary filesystem queries and DB mutex acquires in creating backups and checkpoints.
-
-## 9.4.0 (06/23/2024)
-### New Features
-* Added a `CompactForTieringCollectorFactory` to auto trigger compaction for tiering use case.
-* Optimistic transactions and pessimistic transactions with the WriteCommitted policy now support the `GetEntityForUpdate` API.
-* Added a new "count" command to the ldb repl shell. By default, it prints a count of keys in the database from start to end. The options --from=<key> and/or --to=<key> can be specified to limit the range.
-* Add `rocksdb_writebatch_update_timestamps`, `rocksdb_writebatch_wi_update_timestamps` in C API.
-* Add `rocksdb_iter_refresh` in C API.
-* Add `rocksdb_writebatch_create_with_params`, `rocksdb_writebatch_wi_create_with_params` to create WB and WBWI with all options in C API
-
-### Public API Changes
-* Deprecated names `LogFile` and `VectorLogPtr` in favor of new names `WalFile` and `VectorWalPtr`.
-* Introduce a new universal compaction option CompactionOptionsUniversal::max_read_amp which allows user to define the limit on the number of sorted runs separately from the trigger for compaction (`level0_file_num_compaction_trigger`) #12477.
-
-### Behavior Changes
-* Inactive WALs are immediately closed upon being fully sync-ed rather than in a background thread. This is to ensure LinkFile() is not called on files still open for write, which might not be supported by some FileSystem implementations. This should not be a performance issue, but an opt-out is available with with new DB option `background_close_inactive_wals`.
-
-### Bug Fixes
-* Fix a rare case in which a hard-linked WAL in a Checkpoint is not fully synced (so might lose data on power loss).
-* Fixed the output of the `ldb dump_wal` command for `PutEntity` records so it prints the key and correctly resets the hexadecimal formatting flag after printing the wide-column entity.
-* Fixed an issue where `PutEntity` records were handled incorrectly while rebuilding transactions during recovery.
-* Various read operations could ignore various ReadOptions that might be relevant. Fixed many such cases, which can result in behavior change but a better reflection of specified options.
-
-### Performance Improvements
-* Improved write throughput to memtable when there's a large number of concurrent writers and allow_concurrent_memtable_write=true(#12545)
-
-## 9.3.0 (05/17/2024)
-### New Features
-* Optimistic transactions and pessimistic transactions with the WriteCommitted policy now support the `GetEntity` API.
-* Added new `Iterator` property, "rocksdb.iterator.is-value-pinned", for checking whether the `Slice` returned by `Iterator::value()` can be used until the `Iterator` is destroyed.
-* Optimistic transactions and WriteCommitted pessimistic transactions now support the `MultiGetEntity` API.
-* Optimistic transactions and pessimistic transactions with the WriteCommitted policy now support the `PutEntity` API. Support for read APIs and other write policies (WritePrepared, WriteUnprepared) will be added later.
-
-### Public API Changes
-* Exposed block based metadata cache options via C API
-* Exposed compaction pri via c api.
-* Add a kAdmPolicyAllowAll option to TieredAdmissionPolicy that admits all blocks evicted from the primary block cache into the compressed secondary cache.
-
-### Behavior Changes
-* CompactRange() with change_level=true on a CF with FIFO compaction will return Status::NotSupported().
-* External file ingestion with FIFO compaction will always ingest to L0.
-
-### Bug Fixes
-* Fixed a bug for databases using `DBOptions::allow_2pc == true` (all `TransactionDB`s except `OptimisticTransactionDB`) that have exactly one column family. Due to a missing WAL sync, attempting to open the DB could have returned a `Status::Corruption` with a message like "SST file is ahead of WALs".
-* Fix a bug in CreateColumnFamilyWithImport() where if multiple CFs are imported, we were not resetting files' epoch number and L0 files can have overlapping key range but the same epoch number.
-* Fixed race conditions when `ColumnFamilyOptions::inplace_update_support == true` between user overwrites and reads on the same key.
-* Fix a bug where `CompactFiles()` can compact files of range conflict with other ongoing compactions' when `preclude_last_level_data_seconds > 0` is used
-* Fixed a false positive `Status::Corruption` reported when reopening a DB that used `DBOptions::recycle_log_file_num > 0` and `DBOptions::wal_compression != kNoCompression`.
-* While WAL is locked with LockWAL(), some operations like Flush() and IngestExternalFile() are now blocked as they should have been.
-* Fixed a bug causing stale memory access when using the TieredSecondaryCache with an NVM secondary cache, and a file system that supports return an FS allocated buffer for MultiRead (FSSupportedOps::kFSBuffer is set).
-
-## 9.2.0 (05/01/2024)
-### New Features
-* Added two options `deadline` and `max_size_bytes` for CacheDumper to exit early
-* Added a new API `GetEntityFromBatchAndDB` to `WriteBatchWithIndex` that can be used for wide-column point lookups with read-your-own-writes consistency. Similarly to `GetFromBatchAndDB`, the API can combine data from the write batch with data from the underlying database if needed. See the API comments for more details.
-* [Experimental] Introduce two new cross-column-family iterators - CoalescingIterator and AttributeGroupIterator. The CoalescingIterator enables users to iterate over multiple column families and access their values and columns. During this iteration, if the same key exists in more than one column family, the keys in the later column family will overshadow the previous ones. The AttributeGroupIterator allows users to gather wide columns per Column Family and create attribute groups while iterating over keys across all CFs.
-* Added a new API `MultiGetEntityFromBatchAndDB` to `WriteBatchWithIndex` that can be used for batched wide-column point lookups with read-your-own-writes consistency. Similarly to `MultiGetFromBatchAndDB`, the API can combine data from the write batch with data from the underlying database if needed. See the API comments for more details.
-* Adds a `SstFileReader::NewTableIterator` API to support programmatically read a SST file as a raw table file.
-* Add an option to `WaitForCompactOptions` - `wait_for_purge` to make `WaitForCompact()` API wait for background purge to complete
-
-### Public API Changes
-* DeleteRange() will return NotSupported() if row_cache is configured since they don't work together in some cases.
-* Deprecated `CompactionOptions::compression` since `CompactionOptions`'s API for configuring compression was incomplete, unsafe, and likely unnecessary
-* Using `OptionChangeMigration()` to migrate from non-FIFO to FIFO compaction
-with `Options::compaction_options_fifo.max_table_files_size` > 0 can cause
-the whole DB to be dropped right after migration if the migrated data is larger than
-`max_table_files_size`
-
-### Behavior Changes
-* Enabling `BlockBasedTableOptions::block_align` is now incompatible (i.e., APIs will return `Status::InvalidArgument`) with more ways of enabling compression: `CompactionOptions::compression`, `ColumnFamilyOptions::compression_per_level`, and `ColumnFamilyOptions::bottommost_compression`.
-* Changed the default value of `CompactionOptions::compression` to `kDisableCompressionOption`, which means the compression type is determined by the `ColumnFamilyOptions`.
-* `BlockBasedTableOptions::optimize_filters_for_memory` is now set to true by default. When `partition_filters=false`, this could lead to somewhat increased average RSS memory usage by the block cache, but this "extra" usage is within the allowed memory budget and should make memory usage more consistent (by minimizing internal fragmentation for more kinds of blocks).
-* Dump all keys for cache dumper impl if `SetDumpFilter()` is not called
-* `CompactRange()` with `CompactRangeOptions::change_level = true` and `CompactRangeOptions::target_level = 0` that ends up moving more than 1 file from non-L0 to L0 will return `Status::Aborted()`.
-* On distributed file systems that support file system level checksum verification and reconstruction reads, RocksDB will now retry a file read if the initial read fails RocksDB block level or record level checksum verification. This applies to MANIFEST file reads when the DB is opened, and to SST file reads at all times.
-
-### Bug Fixes
-* Fix a bug causing `VerifyFileChecksums()` to return false-positive corruption under `BlockBasedTableOptions::block_align=true`
-* Provide consistent view of the database across the column families for `NewIterators()` API.
-* Fixed feature interaction bug for `DeleteRange()` together with `ColumnFamilyOptions::memtable_insert_with_hint_prefix_extractor`. The impact of this bug would likely be corruption or crashing.
-* Fixed hang in `DisableManualCompactions()` where compactions waiting to be scheduled due to conflicts would not be canceled promptly
-* Fixed a regression when `ColumnFamilyOptions::max_successive_merges > 0` where the CPU overhead for deciding whether to merge could have increased unless the user had set the option `ColumnFamilyOptions::strict_max_successive_merges`
-* Fixed a bug in `MultiGet()` and `MultiGetEntity()` together with blob files (`ColumnFamilyOptions::enable_blob_files == true`). An error looking up one of the keys could cause the results to be wrong for other keys for which the statuses were `Status::OK`.
-* Fixed a bug where wrong padded bytes are used to generate file checksum and `DataVerificationInfo::checksum` upon file creation
-* Correctly implemented the move semantics of `PinnableWideColumns`.
-* Fixed a bug when the recycle_log_file_num in DBOptions is changed from 0 to non-zero when a DB is reopened. On a subsequent reopen, if a log file created when recycle_log_file_num==0 was reused previously, is alive and is empty, we could end up inserting stale WAL records into the memtable.
-* Fix a bug where obsolete files' deletion during DB::Open are not rate limited with `SstFilemManager`'s slow deletion feature even if it's configured.
-
-## 9.1.0 (03/22/2024)
-### New Features
-* Added an option, `GetMergeOperandsOptions::continue_cb`, to give users the ability to end `GetMergeOperands()`'s lookup process before all merge operands were found.
-* Add sanity checks for ingesting external files that currently checks if the user key comparator used to create the file is compatible with the column family's user key comparator.
-*Support ingesting external files for column family that has user-defined timestamps in memtable only enabled.
-* On file systems that support storage level data checksum and reconstruction, retry SST block reads for point lookups, scans, and flush and compaction if there's a checksum mismatch on the initial read.
-* Some enhancements and fixes to experimental Temperature handling features, including new `default_write_temperature` CF option and opening an `SstFileWriter` with a temperature.
-* `WriteBatchWithIndex` now supports wide-column point lookups via the `GetEntityFromBatch` API. See the API comments for more details.
-* Implement experimental features: API `Iterator::GetProperty("rocksdb.iterator.write-time")` to allow users to get data's approximate write unix time and write data with a specific write time via `WriteBatch::TimedPut` API.
-
-### Public API Changes
-* Best-effort recovery (`best_efforts_recovery == true`) may now be used together with atomic flush (`atomic_flush == true`). The all-or-nothing recovery guarantee for atomically flushed data will be upheld.
-* Remove deprecated option `bottommost_temperature`, already replaced by `last_level_temperature`
-* Added new PerfContext counters for block cache bytes read - block_cache_index_read_byte, block_cache_filter_read_byte, block_cache_compression_dict_read_byte, and block_cache_read_byte.
-* Deprecate experimental Remote Compaction APIs - StartV2() and WaitForCompleteV2() and introduce Schedule() and Wait(). The new APIs essentially does the same thing as the old APIs. They allow taking externally generated unique id to wait for remote compaction to complete.
-* For API `WriteCommittedTransaction::GetForUpdate`, if the column family enables user-defined timestamp, it was mandated that argument `do_validate` cannot be false, and UDT based validation has to be done with a user set read timestamp. It's updated to make the UDT based validation optional if user sets `do_validate` to false and does not set a read timestamp. With this, `GetForUpdate` skips UDT based validation and it's users' responsibility to enforce the UDT invariant. SO DO NOT skip this UDT-based validation if users do not have ways to enforce the UDT invariant. Ways to enforce the invariant on the users side include manage a monotonically increasing timestamp, commit transactions in a single thread etc.
-* Defined a new PerfLevel `kEnableWait` to measure time spent by user threads blocked in RocksDB other than mutex, such as a write thread waiting to be added to a write group, a write thread delayed or stalled etc.
-* `RateLimiter`'s API no longer requires the burst size to be the refill size. Users of `NewGenericRateLimiter()` can now provide burst size in `single_burst_bytes`. Implementors of `RateLimiter::SetSingleBurstBytes()` need to adapt their implementations to match the changed API doc.
-* Add `write_memtable_time` to the newly introduced PerfLevel `kEnableWait`.
-
-### Behavior Changes
-* `RateLimiter`s created by `NewGenericRateLimiter()` no longer modify the refill period when `SetSingleBurstBytes()` is called.
-* Merge writes will only keep merge operand count within `ColumnFamilyOptions::max_successive_merges` when the key's merge operands are all found in memory, unless `strict_max_successive_merges` is explicitly set.
-
-### Bug Fixes
-* Fixed `kBlockCacheTier` reads to return `Status::Incomplete` when I/O is needed to fetch a merge chain's base value from a blob file.
-* Fixed `kBlockCacheTier` reads to return `Status::Incomplete` on table cache miss rather than incorrectly returning an empty value.
-* Fixed a data race in WalManager that may affect how frequent PurgeObsoleteWALFiles() runs.
-* Re-enable the recycle_log_file_num option in DBOptions for kPointInTimeRecovery WAL recovery mode, which was previously disabled due to a bug in the recovery logic. This option is incompatible with WriteOptions::disableWAL. A Status::InvalidArgument() will be returned if disableWAL is specified.
-
-### Performance Improvements
-* Java API `multiGet()` variants now take advantage of the underlying batched `multiGet()` performance improvements.
-Before
-```
-Benchmark (columnFamilyTestType) (keyCount) (keySize) (multiGetSize) (valueSize) Mode Cnt Score Error Units
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 64 thrpt 25 6315.541 ± 8.106 ops/s
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 1024 thrpt 25 6975.468 ± 68.964 ops/s
-```
-After
-```
-Benchmark (columnFamilyTestType) (keyCount) (keySize) (multiGetSize) (valueSize) Mode Cnt Score Error Units
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 64 thrpt 25 7046.739 ± 13.299 ops/s
-MultiGetBenchmarks.multiGetList10 no_column_family 10000 16 100 1024 thrpt 25 7654.521 ± 60.121 ops/s
-```
-
-## 9.0.0 (02/16/2024)
-### New Features
-* Provide support for FSBuffer for point lookups. Also added support for scans and compactions that don't go through prefetching.
-* Make `SstFileWriter` create SST files without persisting user defined timestamps when the `Option.persist_user_defined_timestamps` flag is set to false.
-* Add support for user-defined timestamps in APIs `DeleteFilesInRanges` and `GetPropertiesOfTablesInRange`.
-* Mark wal\_compression feature as production-ready. Currently only compatible with ZSTD compression.
-
-### Public API Changes
-* Allow setting Stderr logger via C API
-* Declare one Get and one MultiGet variant as pure virtual, and make all the other variants non-overridable. The methods required to be implemented by derived classes of DB allow returning timestamps. It is up to the implementation to check and return an error if timestamps are not supported. The non-batched MultiGet APIs are reimplemented in terms of batched MultiGet, so callers might see a performance improvement.
-* Exposed mode option to Rate Limiter via c api.
-* Removed deprecated option `access_hint_on_compaction_start`
-* Removed deprecated option `ColumnFamilyOptions::check_flush_compaction_key_order`
-* Remove the default `WritableFile::GetFileSize` and `FSWritableFile::GetFileSize` implementation that returns 0 and make it pure virtual, so that subclasses are enforced to explicitly provide an implementation.
-* Removed deprecated option `ColumnFamilyOptions::level_compaction_dynamic_file_size`
-* Removed tickers with typos "rocksdb.error.handler.bg.errro.count", "rocksdb.error.handler.bg.io.errro.count", "rocksdb.error.handler.bg.retryable.io.errro.count".
-* Remove the force mode for `EnableFileDeletions` API because it is unsafe with no known legitimate use.
-* Removed deprecated option `ColumnFamilyOptions::ignore_max_compaction_bytes_for_input`
-* `sst_dump --command=check` now compares the number of records in a table with `num_entries` in table property, and reports corruption if there is a mismatch. API `SstFileDumper::ReadSequential()` is updated to optionally do this verification. (#12322)
-
-### Behavior Changes
-* format\_version=6 is the new default setting in BlockBasedTableOptions, for more robust data integrity checking. DBs and SST files written with this setting cannot be read by RocksDB versions before 8.6.0.
-* Compactions can be scheduled in parallel in an additional scenario: multiple files are marked for compaction within a single column family
-* For leveled compaction, RocksDB will try to do intra-L0 compaction if the total L0 size is small compared to Lbase (#12214). Users with atomic_flush=true are more likely to see the impact of this change.
-
-### Bug Fixes
-* Fixed a data race in `DBImpl::RenameTempFileToOptionsFile`.
-* Fix some perf context statistics error in write steps. which include missing write_memtable_time in unordered_write. missing write_memtable_time in PipelineWrite when Writer stat is STATE_PARALLEL_MEMTABLE_WRITER. missing write_delay_time when calling DelayWrite in WriteImplWALOnly function.
-* Fixed a bug that can, under rare circumstances, cause MultiGet to return an incorrect result for a duplicate key in a MultiGet batch.
-* Fix a bug where older data of an ingested key can be returned for read when universal compaction is used
-
-## 8.11.0 (01/19/2024)
-### New Features
-* Add new statistics: `rocksdb.sst.write.micros` measures time of each write to SST file; `rocksdb.file.write.{flush|compaction|db.open}.micros` measure time of each write to SST table (currently only block-based table format) and blob file for flush, compaction and db open.
-
-### Public API Changes
-* Added another enumerator `kVerify` to enum class `FileOperationType` in listener.h. Update your `switch` statements as needed.
-* Add CompressionOptions to the CompressedSecondaryCacheOptions structure to allow users to specify library specific options when creating the compressed secondary cache.
-* Deprecated several options: `level_compaction_dynamic_file_size`, `ignore_max_compaction_bytes_for_input`, `check_flush_compaction_key_order`, `flush_verify_memtable_count`, `compaction_verify_record_count`, `fail_if_options_file_error`, and `enforce_single_del_contracts`
-* Exposed options ttl via c api.
-
-### Behavior Changes
-* `rocksdb.blobdb.blob.file.write.micros` expands to also measure time writing the header and footer. Therefore the COUNT may be higher and values may be smaller than before. For stacked BlobDB, it no longer measures the time of explictly flushing blob file.
-* Files will be compacted to the next level if the data age exceeds periodic_compaction_seconds except for the last level.
-* Reduced the compaction debt ratio trigger for scheduling parallel compactions
-* For leveled compaction with default compaction pri (kMinOverlappingRatio), files marked for compaction will be prioritized over files not marked when picking a file from a level for compaction.
+## 8.10.2 (02/16/2024)
+* Update zlib to 1.3.1 for Java builds
 
+## 8.10.1 (01/16/2024)
 ### Bug Fixes
 * Fix bug in auto_readahead_size that combined with IndexType::kBinarySearchWithFirstKey + fails or iterator lands at a wrong key
-* Fixed some cases in which DB file corruption was detected but ignored on creating a backup with BackupEngine.
-* Fix bugs where `rocksdb.blobdb.blob.file.synced` includes blob files failed to get synced and `rocksdb.blobdb.blob.file.bytes.written` includes blob bytes failed to get written.
-* Fixed a possible memory leak or crash on a failure (such as I/O error) in automatic atomic flush of multiple column families.
-* Fixed some cases of in-memory data corruption using mmap reads with `BackupEngine`, `sst_dump`, or `ldb`.
-* Fixed issues with experimental `preclude_last_level_data_seconds` option that could interfere with expected data tiering.
-* Fixed the handling of the edge case when all existing blob files become unreferenced. Such files are now correctly deleted.
 
 ## 8.10.0 (12/15/2023)
 ### New Features

INSTALL.md

@@ -126,6 +126,7 @@ most processors made since roughly 2013.
         * Update XCode:  run `xcode-select --install` (or install it from XCode App's settting).
         * Install via [homebrew](http://brew.sh/).
             * If you're first time developer in MacOS, you still need to run: `xcode-select --install` in your command line.
+            * run `brew tap homebrew/versions; brew install gcc7 --use-llvm` to install gcc 7 (or higher).
     * run `brew install rocksdb`
 
 * **FreeBSD** (11.01):
@@ -168,26 +169,21 @@ most processors made since roughly 2013.
 
     * Install the dependencies for RocksDB:
 
-      `pkg_add gmake gflags snappy bzip2 lz4 zstd git bash findutils gnuwatch`
+        pkg_add gmake gflags snappy bzip2 lz4 zstd git jdk bash findutils gnuwatch
 
     * Build RocksDB from source:
 
-        ```bash
         cd ~
         git clone https://github.com/facebook/rocksdb.git
         cd rocksdb
         gmake static_lib
-        ```
 
     * Build RocksJava from source (optional):
-        * In OpenBSD, JDK depends on XWindows system, so please check that you installed OpenBSD with `xbase` package.
-        * Install dependencies : `pkg_add -v jdk%1.8`
-        ```bash
+
         cd rocksdb
         export JAVA_HOME=/usr/local/jdk-1.8.0
         export PATH=$PATH:/usr/local/jdk-1.8.0/bin
-        gmake rocksdbjava SHA256_CMD='sha256 -q'
-        ```
+        gmake rocksdbjava
 
 * **iOS**:
   * Run: `TARGET_OS=IOS make static_lib`. When building the project which uses rocksdb iOS library, make sure to define an important pre-processing macros: `IOS_CROSS_COMPILE`.

Makefile

@@ -103,7 +103,6 @@ dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
                   export LIB_MODE="$(LIB_MODE)"; \
 		  export ROCKSDB_CXX_STANDARD="$(ROCKSDB_CXX_STANDARD)"; \
 		  export USE_FOLLY="$(USE_FOLLY)"; \
-		  export USE_FOLLY_LITE="$(USE_FOLLY_LITE)"; \
                   "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
 # this file is generated by the previous line to set build flags and sources
 include make_config.mk
@@ -501,17 +500,6 @@ endif
 ifeq ($(USE_FOLLY_LITE),1)
 	# Path to the Folly source code and include files
 	FOLLY_DIR = ./third-party/folly
-ifneq ($(strip $(BOOST_SOURCE_PATH)),)
-	BOOST_INCLUDE = $(shell (ls -d $(BOOST_SOURCE_PATH)/boost*/))
-	# AIX: pre-defined system headers are surrounded by an extern "C" block
-	ifeq ($(PLATFORM), OS_AIX)
-		PLATFORM_CCFLAGS += -I$(BOOST_INCLUDE)
-		PLATFORM_CXXFLAGS += -I$(BOOST_INCLUDE)
-	else
-		PLATFORM_CCFLAGS += -isystem $(BOOST_INCLUDE)
-		PLATFORM_CXXFLAGS += -isystem $(BOOST_INCLUDE)
-	endif
-endif  # BOOST_SOURCE_PATH
 	# AIX: pre-defined system headers are surrounded by an extern "C" block
 	ifeq ($(PLATFORM), OS_AIX)
 		PLATFORM_CCFLAGS += -I$(FOLLY_DIR)
@@ -551,8 +539,7 @@ endif
 
 ifdef USE_CLANG
 	# Used by some teams in Facebook
-	WARNING_FLAGS += -Wshift-sign-overflow -Wambiguous-reversed-operator \
-	  -Wimplicit-fallthrough -Wreinterpret-base-class -Wundefined-reinterpret-cast
+	WARNING_FLAGS += -Wshift-sign-overflow -Wambiguous-reversed-operator -Wimplicit-fallthrough
 endif
 
 ifeq ($(PLATFORM), OS_OPENBSD)
@@ -630,11 +617,6 @@ VALGRIND_VER := $(join $(VALGRIND_VER),valgrind)
 VALGRIND_OPTS = --error-exitcode=$(VALGRIND_ERROR) --leak-check=full
 # Not yet supported: --show-leak-kinds=definite,possible,reachable --errors-for-leak-kinds=definite,possible,reachable
 
-# Work around valgrind hanging on systems with limited internet access
-ifneq ($(shell which git 2>/dev/null && git config --get https.proxy),)
-  export DEBUGINFOD_URLS=
-endif
-
 TEST_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(TEST_LIB_SOURCES) $(MOCK_LIB_SOURCES)) $(GTEST)
 BENCH_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(BENCH_LIB_SOURCES))
 CACHE_BENCH_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(CACHE_BENCH_LIB_SOURCES))
@@ -653,37 +635,26 @@ TESTS = $(patsubst %.cc, %, $(notdir $(TEST_MAIN_SOURCES)))
 TESTS += $(patsubst %.c, %, $(notdir $(TEST_MAIN_SOURCES_C)))
 TESTS += $(PLUGIN_TESTS)
 
-# `make check-headers` to verify that each header file includes its own deps
-# and that public headers do not depend on internal headers
+# `make check-headers` to very that each header file includes its own
+# dependencies
 ifneq ($(filter check-headers, $(MAKECMDGOALS)),)
 # TODO: add/support JNI headers
 	DEV_HEADER_DIRS := $(sort include/ $(dir $(ALL_SOURCES)))
 # Some headers like in port/ are platform-specific
-	DEV_HEADERS_TO_CHECK := $(shell $(FIND) $(DEV_HEADER_DIRS) -type f -name '*.h' | grep -E -v 'port/|plugin/|lua/|range_tree/|secondary_index/')
-	PUBLIC_HEADERS_TO_CHECK := $(shell $(FIND) include/ -type f -name '*.h' | grep -E -v 'lua/')
+	DEV_HEADERS := $(shell $(FIND) $(DEV_HEADER_DIRS) -type f -name '*.h' | grep -E -v 'port/|plugin/|lua/|range_tree/')
 else
-	DEV_HEADERS_TO_CHECK :=
-	PUBLIC_HEADERS_TO_CHECK :=
+	DEV_HEADERS :=
 endif
-HEADER_OK_FILES = $(patsubst %.h, %.h.ok, $(DEV_HEADERS_TO_CHECK)) \
-	$(patsubst %.h, %.h.pub, $(PUBLIC_HEADERS_TO_CHECK))
+HEADER_OK_FILES = $(patsubst %.h, %.h.ok, $(DEV_HEADERS))
 
 AM_V_CCH = $(am__v_CCH_$(V))
 am__v_CCH_ = $(am__v_CCH_$(AM_DEFAULT_VERBOSITY))
 am__v_CCH_0 = @echo "  CC.h    " $<;
 am__v_CCH_1 =
 
-# verify headers include their own dependencies, under dev build settings
 %.h.ok: %.h # .h.ok not actually created, so re-checked on each invocation
 # -DROCKSDB_NAMESPACE=42 ensures the namespace header is included
-	$(AM_V_CCH) echo '#include "$<"' | $(CXX) $(CXXFLAGS) \
-	  -DROCKSDB_NAMESPACE=42 -x c++ -c - -o /dev/null
-
-# verify public headers do not depend on internal headers, under typical
-# user build settings
-%.h.pub: %.h # .h.pub not actually created, so re-checked on each invocation
-	$(AM_V_CCH) cd include/ && echo '#include "$(patsubst include/%,%,$<)"' | \
-	  $(CXX) -I. -DROCKSDB_NAMESPACE=42 -x c++ -c - -o /dev/null
+	$(AM_V_CCH) echo '#include "$<"' | $(CXX) $(CXXFLAGS) -DROCKSDB_NAMESPACE=42 -x c++ -c - -o /dev/null
 
 check-headers: $(HEADER_OK_FILES)
 
@@ -1169,16 +1140,16 @@ ubsan_crash_test_with_best_efforts_recovery: clean
 	$(MAKE) clean
 
 full_valgrind_test:
-	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check
+	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
 full_valgrind_test_some:
-	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check_some
+	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check_some
 
 valgrind_test:
-	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check
+	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
 valgrind_test_some:
-	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check_some
+	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check_some
 
 valgrind_check: $(TESTS)
 	$(MAKE) DRIVER="$(VALGRIND_VER) $(VALGRIND_OPTS)" gen_parallel_tests
@@ -1638,9 +1609,6 @@ object_registry_test: $(OBJ_DIR)/utilities/object_registry_test.o $(TEST_LIBRARY
 ttl_test: $(OBJ_DIR)/utilities/ttl/ttl_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-types_util_test: $(OBJ_DIR)/utilities/types_util_test.o $(TEST_LIBRARY) $(LIBRARY)
-	$(AM_LINK)
-
 write_batch_with_index_test: $(OBJ_DIR)/utilities/write_batch_with_index/write_batch_with_index_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1659,9 +1627,6 @@ compaction_job_stats_test: $(OBJ_DIR)/db/compaction/compaction_job_stats_test.o
 compaction_service_test: $(OBJ_DIR)/db/compaction/compaction_service_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-compact_for_tiering_collector_test: $(OBJ_DIR)/utilities/table_properties_collectors/compact_for_tiering_collector_test.o $(TEST_LIBRARY) $(LIBRARY)
-	$(AM_LINK)
-
 compact_on_deletion_collector_test: $(OBJ_DIR)/utilities/table_properties_collectors/compact_on_deletion_collector_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1674,9 +1639,6 @@ wal_edit_test: $(OBJ_DIR)/db/wal_edit_test.o $(TEST_LIBRARY) $(LIBRARY)
 dbformat_test: $(OBJ_DIR)/db/dbformat_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-multi_cf_iterator_test: $(OBJ_DIR)/db/multi_cf_iterator_test.o $(TEST_LIBRARY) $(LIBRARY)
-	$(AM_LINK)
-
 env_basic_test: $(OBJ_DIR)/env/env_basic_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1806,9 +1768,6 @@ cuckoo_table_db_test: $(OBJ_DIR)/db/cuckoo_table_db_test.o $(TEST_LIBRARY) $(LIB
 listener_test: $(OBJ_DIR)/db/listener_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-string_util_test: $(OBJ_DIR)/util/string_util_test.o $(TEST_LIBRARY) $(LIBRARY)
-	$(AM_LINK)
-
 thread_list_test: $(OBJ_DIR)/util/thread_list_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1953,9 +1912,6 @@ sst_file_reader_test: $(OBJ_DIR)/table/sst_file_reader_test.o $(TEST_LIBRARY) $(
 db_secondary_test: $(OBJ_DIR)/db/db_secondary_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-db_follower_test: $(OBJ_DIR)/db/db_follower_test.o $(TEST_LIBRARY) $(LIBRARY)
-	$(AM_LINK)
-
 block_cache_tracer_test: $(OBJ_DIR)/trace_replay/block_cache_tracer_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -2144,8 +2100,8 @@ ZLIB_DOWNLOAD_BASE ?= http://zlib.net
 BZIP2_VER ?= 1.0.8
 BZIP2_SHA256 ?= ab5a03176ee106d3f0fa90e381da478ddae405918153cca248e682cd0c4a2269
 BZIP2_DOWNLOAD_BASE ?= http://sourceware.org/pub/bzip2
-SNAPPY_VER ?= 1.2.1
-SNAPPY_SHA256 ?= 736aeb64d86566d2236ddffa2865ee5d7a82d26c9016b36218fcc27ea4f09f86
+SNAPPY_VER ?= 1.1.8
+SNAPPY_SHA256 ?= 16b677f07832a612b0836178db7f374e414f94657c138e6993cbfc5dcc58651f
 SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/archive
 LZ4_VER ?= 1.9.4
 LZ4_SHA256 ?= 0b0e3aa07c8c063ddf40b082bdf7e37a1562bda40a0ff5272957f3e987e0e54b
@@ -2242,7 +2198,7 @@ libsnappy.a: snappy-$(SNAPPY_VER).tar.gz
 	-rm -rf snappy-$(SNAPPY_VER)
 	tar xvzf snappy-$(SNAPPY_VER).tar.gz
 	mkdir snappy-$(SNAPPY_VER)/build
-	cd snappy-$(SNAPPY_VER)/build && CFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CCFLAGS} ${EXTRA_CFLAGS}' CXXFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CXXFLAGS} ${EXTRA_CXXFLAGS}' LDFLAGS='${JAVA_STATIC_DEPS_LDFLAGS} ${EXTRA_LDFLAGS}' cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DSNAPPY_BUILD_BENCHMARKS=OFF -DSNAPPY_BUILD_TESTS=OFF --compile-no-warning-as-error ${PLATFORM_CMAKE_FLAGS} .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
+	cd snappy-$(SNAPPY_VER)/build && CFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CCFLAGS} ${EXTRA_CFLAGS}' CXXFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CXXFLAGS} ${EXTRA_CXXFLAGS}' LDFLAGS='${JAVA_STATIC_DEPS_LDFLAGS} ${EXTRA_LDFLAGS}' cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON ${PLATFORM_CMAKE_FLAGS} .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
 	cp snappy-$(SNAPPY_VER)/build/libsnappy.a .
 
 lz4-$(LZ4_VER).tar.gz:
@@ -2372,47 +2328,47 @@ rocksdbjavastaticreleasedocker: rocksdbjavastaticosx rocksdbjavastaticdockerx86
 
 rocksdbjavastaticdockerx86:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-be --platform linux/386 --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_x86-be --platform linux/386 --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerx86_64:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x64-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_x64-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerppc64le:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_ppc64le-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_ppc64le-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerarm64v8:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_arm64v8-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:centos7_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_arm64v8-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockers390x:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_s390x-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:ubuntu18_s390x-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_s390x-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:ubuntu18_s390x-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerriscv64:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_riscv64-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:ubuntu20_riscv64-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_riscv64-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:ubuntu20_riscv64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerx86musl:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-musl-be --platform linux/386 --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:alpine3_x86-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_x86-musl-be --platform linux/386 --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-alpine.sh
 
 rocksdbjavastaticdockerx86_64musl:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x64-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:alpine3_x64-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_x64-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-alpine.sh
 
 rocksdbjavastaticdockerppc64lemusl:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_ppc64le-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:alpine3_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_ppc64le-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-alpine.sh
 
 rocksdbjavastaticdockerarm64v8musl:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_arm64v8-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:alpine3_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_arm64v8-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-alpine.sh
 
 rocksdbjavastaticdockers390xmusl:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_s390x-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) --env J=$(J) evolvedbinary/rocksjava:alpine3_s390x-be /rocksdb-host/java/crossbuild/docker-build-linux.sh
+	docker run --rm --name rocksdb_linux_s390x-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_s390x-be /rocksdb-host/java/crossbuild/docker-build-linux-alpine.sh
 
 rocksdbjavastaticpublish: rocksdbjavastaticrelease rocksdbjavastaticpublishcentral
 
@@ -2489,13 +2445,14 @@ checkout_folly:
 	fi
 	@# Pin to a particular version for public CI, so that PR authors don't
 	@# need to worry about folly breaking our integration. Update periodically
-	cd third-party/folly && git reset --hard 33f5b67fcaeb8705b04fd1b850873a180dc89aaa
+	cd third-party/folly && git reset --hard beacd86d63cd71c904632262e6c36f60874d78ba
+	@# A hack to remove boost dependency.
+	@# NOTE: this hack is only needed if building using USE_FOLLY_LITE
+	perl -pi -e 's/^(#include <boost)/\/\/$$1/' third-party/folly/folly/functional/Invoke.h
 	@# NOTE: this hack is required for clang in some cases
 	perl -pi -e 's/int rv = syscall/int rv = (int)syscall/' third-party/folly/folly/detail/Futex.cpp
 	@# NOTE: this hack is required for gcc in some cases
 	perl -pi -e 's/(__has_include.<experimental.memory_resource>.)/__cpp_rtti && $$1/' third-party/folly/folly/memory/MemoryResource.h
-	@# NOTE: boost source will be needed for any build including `USE_FOLLY_LITE` builds as those depend on boost headers
-	cd third-party/folly && $(PYTHON) build/fbcode_builder/getdeps.py fetch boost
 
 CXX_M_FLAGS = $(filter -m%, $(CXXFLAGS))
 
@@ -2507,6 +2464,8 @@ build_folly:
 		echo "Please run checkout_folly first"; \
 		false; \
 	fi
+	# Restore the original version of Invoke.h with boost dependency
+	cd third-party/folly && ${GIT_COMMAND} checkout folly/functional/Invoke.h
 	cd third-party/folly && \
 		CXXFLAGS=" $(CXX_M_FLAGS) -DHAVE_CXX11_ATOMIC " $(PYTHON) build/fbcode_builder/getdeps.py build --no-tests
 

TARGETS

@@ -4,7 +4,6 @@
 # This file is a Facebook-specific integration for buck builds, so can
 # only be validated by Facebook employees.
 load("//rocks/buckifier:defs.bzl", "cpp_library_wrapper","rocks_cpp_library_wrapper","cpp_binary_wrapper","cpp_unittest_wrapper","fancy_bench_wrapper","add_c_test_wrapper")
-load("@fbcode_macros//build_defs:export_files.bzl", "export_file")
 
 
 cpp_library_wrapper(name="rocksdb_lib", srcs=[
@@ -22,7 +21,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "cache/sharded_cache.cc",
         "cache/tiered_secondary_cache.cc",
         "db/arena_wrapped_db_iter.cc",
-        "db/attribute_group_iterator_impl.cc",
         "db/blob/blob_contents.cc",
         "db/blob/blob_fetcher.cc",
         "db/blob/blob_file_addition.cc",
@@ -39,7 +37,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "db/blob/prefetch_buffer_collection.cc",
         "db/builder.cc",
         "db/c.cc",
-        "db/coalescing_iterator.cc",
         "db/column_family.cc",
         "db/compaction/compaction.cc",
         "db/compaction/compaction_iterator.cc",
@@ -61,7 +58,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "db/db_impl/db_impl_debug.cc",
         "db/db_impl/db_impl_experimental.cc",
         "db/db_impl/db_impl_files.cc",
-        "db/db_impl/db_impl_follower.cc",
         "db/db_impl/db_impl_open.cc",
         "db/db_impl/db_impl_readonly.cc",
         "db/db_impl/db_impl_secondary.cc",
@@ -83,7 +79,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "db/log_writer.cc",
         "db/logs_with_prep_tracker.cc",
         "db/malloc_stats.cc",
-        "db/manifest_ops.cc",
         "db/memtable.cc",
         "db/memtable_list.cc",
         "db/merge_helper.cc",
@@ -120,7 +115,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "env/env_posix.cc",
         "env/file_system.cc",
         "env/file_system_tracer.cc",
-        "env/fs_on_demand.cc",
         "env/fs_posix.cc",
         "env/fs_remap.cc",
         "env/io_posix.cc",
@@ -150,7 +144,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "memtable/hash_skiplist_rep.cc",
         "memtable/skiplistrep.cc",
         "memtable/vectorrep.cc",
-        "memtable/wbwi_memtable.cc",
         "memtable/write_buffer_manager.cc",
         "monitoring/histogram.cc",
         "monitoring/histogram_windowing.cc",
@@ -319,7 +312,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "utilities/persistent_cache/volatile_tier_impl.cc",
         "utilities/simulator_cache/cache_simulator.cc",
         "utilities/simulator_cache/sim_cache.cc",
-        "utilities/table_properties_collectors/compact_for_tiering_collector.cc",
         "utilities/table_properties_collectors/compact_on_deletion_collector.cc",
         "utilities/trace/file_trace_reader_writer.cc",
         "utilities/trace/replayer_impl.cc",
@@ -353,7 +345,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "utilities/transactions/write_unprepared_txn.cc",
         "utilities/transactions/write_unprepared_txn_db.cc",
         "utilities/ttl/db_ttl_impl.cc",
-        "utilities/types_util.cc",
         "utilities/wal_filter.cc",
         "utilities/write_batch_with_index/write_batch_with_index.cc",
         "utilities/write_batch_with_index/write_batch_with_index_internal.cc",
@@ -364,14 +355,9 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "//folly/experimental/coro:coroutine",
         "//folly/experimental/coro:task",
         "//folly/synchronization:distributed_mutex",
-    ], headers=glob(["**/*.h"]), link_whole=False, extra_test_libs=False)
+    ], headers=None, link_whole=False, extra_test_libs=False)
 
-cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[], deps=[":rocksdb_lib"], headers=[], link_whole=True, extra_test_libs=False)
-
-cpp_library_wrapper(name="rocksdb_with_faiss_lib", srcs=["utilities/secondary_index/faiss_ivf_index.cc"], deps=[
-        "//faiss:faiss",
-        ":rocksdb_lib",
-    ], headers=[], link_whole=False, extra_test_libs=False)
+cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[], deps=[":rocksdb_lib"], headers=None, link_whole=True, extra_test_libs=False)
 
 cpp_library_wrapper(name="rocksdb_test_lib", srcs=[
         "db/db_test_util.cc",
@@ -385,21 +371,7 @@ cpp_library_wrapper(name="rocksdb_test_lib", srcs=[
         "tools/trace_analyzer_tool.cc",
         "utilities/agg_merge/test_agg_merge.cc",
         "utilities/cassandra/test_utils.cc",
-    ], deps=[":rocksdb_lib"], headers=[], link_whole=False, extra_test_libs=True)
-
-cpp_library_wrapper(name="rocksdb_with_faiss_test_lib", srcs=[
-        "db/db_test_util.cc",
-        "db/db_with_timestamp_test_util.cc",
-        "table/mock_table.cc",
-        "test_util/mock_time_env.cc",
-        "test_util/secondary_cache_test_util.cc",
-        "test_util/testharness.cc",
-        "test_util/testutil.cc",
-        "tools/block_cache_analyzer/block_cache_trace_analyzer.cc",
-        "tools/trace_analyzer_tool.cc",
-        "utilities/agg_merge/test_agg_merge.cc",
-        "utilities/cassandra/test_utils.cc",
-    ], deps=[":rocksdb_with_faiss_lib"], headers=[], link_whole=False, extra_test_libs=True)
+    ], deps=[":rocksdb_lib"], headers=None, link_whole=False, extra_test_libs=True)
 
 cpp_library_wrapper(name="rocksdb_tools_lib", srcs=[
         "test_util/testutil.cc",
@@ -407,16 +379,15 @@ cpp_library_wrapper(name="rocksdb_tools_lib", srcs=[
         "tools/db_bench_tool.cc",
         "tools/simulated_hybrid_file_system.cc",
         "tools/trace_analyzer_tool.cc",
-    ], deps=[":rocksdb_lib"], headers=[], link_whole=False, extra_test_libs=False)
+    ], deps=[":rocksdb_lib"], headers=None, link_whole=False, extra_test_libs=False)
 
-cpp_library_wrapper(name="rocksdb_cache_bench_tools_lib", srcs=["cache/cache_bench_tool.cc"], deps=[":rocksdb_lib"], headers=[], link_whole=False, extra_test_libs=False)
+cpp_library_wrapper(name="rocksdb_cache_bench_tools_lib", srcs=["cache/cache_bench_tool.cc"], deps=[":rocksdb_lib"], headers=None, link_whole=False, extra_test_libs=False)
 
 rocks_cpp_library_wrapper(name="rocksdb_stress_lib", srcs=[
         "db_stress_tool/batched_ops_stress.cc",
         "db_stress_tool/cf_consistency_stress.cc",
         "db_stress_tool/db_stress_common.cc",
         "db_stress_tool/db_stress_driver.cc",
-        "db_stress_tool/db_stress_filters.cc",
         "db_stress_tool/db_stress_gflags.cc",
         "db_stress_tool/db_stress_listener.cc",
         "db_stress_tool/db_stress_shared_state.cc",
@@ -431,15 +402,11 @@ rocks_cpp_library_wrapper(name="rocksdb_stress_lib", srcs=[
         "test_util/testutil.cc",
         "tools/block_cache_analyzer/block_cache_trace_analyzer.cc",
         "tools/trace_analyzer_tool.cc",
-    ], headers=[])
+    ], headers=None)
 
 
-cpp_binary_wrapper(name="ldb", srcs=["tools/ldb.cc"], deps=[":rocksdb_tools_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
-
 cpp_binary_wrapper(name="db_stress", srcs=["db_stress_tool/db_stress.cc"], deps=[":rocksdb_stress_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
 
-cpp_binary_wrapper(name="db_bench", srcs=["tools/db_bench.cc"], deps=[":rocksdb_tools_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
-
 cpp_binary_wrapper(name="cache_bench", srcs=["cache/cache_bench.cc"], deps=[":rocksdb_cache_bench_tools_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
 
 cpp_binary_wrapper(name="ribbon_bench", srcs=["microbench/ribbon_bench.cc"], deps=[], extra_preprocessor_flags=[], extra_bench_libs=True)
@@ -4651,12 +4618,6 @@ cpp_unittest_wrapper(name="compact_files_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="compact_for_tiering_collector_test",
-            srcs=["utilities/table_properties_collectors/compact_for_tiering_collector_test.cc"],
-            deps=[":rocksdb_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="compact_on_deletion_collector_test",
             srcs=["utilities/table_properties_collectors/compact_on_deletion_collector_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -4831,12 +4792,6 @@ cpp_unittest_wrapper(name="db_flush_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="db_follower_test",
-            srcs=["db/db_follower_test.cc"],
-            deps=[":rocksdb_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="db_inplace_update_test",
             srcs=["db/db_inplace_update_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -5047,7 +5002,7 @@ cpp_unittest_wrapper(name="dynamic_bloom_test",
             extra_compiler_flags=[])
 
 
-cpp_library_wrapper(name="env_basic_test_lib", srcs=["env/env_basic_test.cc"], deps=[":rocksdb_test_lib"], headers=[], link_whole=False, extra_test_libs=True)
+cpp_library_wrapper(name="env_basic_test_lib", srcs=["env/env_basic_test.cc"], deps=[":rocksdb_test_lib"], headers=None, link_whole=False, extra_test_libs=True)
 
 cpp_unittest_wrapper(name="env_basic_test",
             srcs=["env/env_basic_test.cc"],
@@ -5097,12 +5052,6 @@ cpp_unittest_wrapper(name="external_sst_file_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="faiss_ivf_index_test",
-            srcs=["utilities/secondary_index/faiss_ivf_index_test.cc"],
-            deps=[":rocksdb_with_faiss_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="fault_injection_test",
             srcs=["db/fault_injection_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -5277,12 +5226,6 @@ cpp_unittest_wrapper(name="mock_env_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="multi_cf_iterator_test",
-            srcs=["db/multi_cf_iterator_test.cc"],
-            deps=[":rocksdb_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="object_registry_test",
             srcs=["utilities/object_registry_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -5577,12 +5520,6 @@ cpp_unittest_wrapper(name="ttl_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="types_util_test",
-            srcs=["utilities/types_util_test.cc"],
-            deps=[":rocksdb_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="udt_util_test",
             srcs=["util/udt_util_test.cc"],
             deps=[":rocksdb_test_lib"],

USERS.md

@@ -38,11 +38,12 @@ Snowflake [uses](https://www.snowflake.com/blog/how-foundationdb-powers-snowflak
 The Bing search engine from Microsoft uses RocksDB as the storage engine for its web data platform: https://blogs.bing.com/Engineering-Blog/october-2021/RocksDB-in-Microsoft-Bing
 
 ## LinkedIn
-1. [Venice](https://venicedb.org/) is a derived data platform using RocksDB as its storage engine. It is LinkedIn's ML feature store, powering thousands of recommender use cases, including the Feed, Video recommendations, and People You May Know.
-2. LinkedIn's follow feed for storing user's activities. Check out the blog post: https://engineering.linkedin.com/blog/2016/03/followfeed--linkedin-s-feed-made-faster-and-smarter
-3. Apache Samza, open source framework for stream processing.
+Two different use cases at Linkedin are using RocksDB as a storage engine:
 
-Learn more about LinkedIn's follow feed and Apache Samza in a Tech Talk by Ankit Gupta and Naveen Somasundaram: http://www.youtube.com/watch?v=plqVp_OnSzg
+1. LinkedIn's follow feed for storing user's activities. Check out the blog post: https://engineering.linkedin.com/blog/2016/03/followfeed--linkedin-s-feed-made-faster-and-smarter
+2. Apache Samza, open source framework for stream processing
+
+Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasundaram: http://www.youtube.com/watch?v=plqVp_OnSzg
 
 ## Yahoo
 Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa. Learn more about it here: http://yahooeng.tumblr.com/post/120730204806/sherpa-scales-new-heights

buckifier/buckify_rocksdb.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 try:
     from builtins import str
@@ -10,14 +11,14 @@ import json
 import os
 import sys
 
-from targets_builder import TARGETSBuilder, LiteralValue
+from targets_builder import TARGETSBuilder
 
 from util import ColorString
 
-# This script generates BUCK file for Buck.
+# This script generates TARGETS file for Buck.
 # Buck is a build tool specifying dependencies among different build targets.
 # User can pass extra dependencies as a JSON object via command line, and this
-# script can include these dependencies in the generate BUCK file.
+# script can include these dependencies in the generate TARGETS file.
 # Usage:
 # $python3 buckifier/buckify_rocksdb.py
 # (This generates a TARGET file without user-specified dependency for unit
@@ -28,7 +29,7 @@ from util import ColorString
 #                      "extra_compiler_flags": ["-DFOO_BAR", "-Os"]
 #                  }
 #         }'
-# (Generated BUCK file has test_dep and mock1 as dependencies for RocksDB
+# (Generated TARGETS file has test_dep and mock1 as dependencies for RocksDB
 # unit tests, and will use the extra_compiler_flags to compile the unit test
 # source.)
 
@@ -114,9 +115,9 @@ def get_dependencies():
     return deps_map
 
 
-# Prepare BUCK file for buck
-def generate_buck(repo_path, deps_map):
-    print(ColorString.info("Generating BUCK"))
+# Prepare TARGETS file for buck
+def generate_targets(repo_path, deps_map):
+    print(ColorString.info("Generating TARGETS"))
     # parsed src.mk file
     src_mk = parse_src_mk(repo_path)
     # get all .cc files
@@ -131,12 +132,12 @@ def generate_buck(repo_path, deps_map):
     if len(sys.argv) >= 2:
         # Heuristically quote and canonicalize whitespace for inclusion
         # in how the file was generated.
-        extra_argv = " '{}'".format(" ".join(sys.argv[1].split()))
+        extra_argv = " '{0}'".format(" ".join(sys.argv[1].split()))
 
-    BUCK = TARGETSBuilder("%s/BUCK" % repo_path, extra_argv)
+    TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path, extra_argv)
 
     # rocksdb_lib
-    BUCK.add_library(
+    TARGETS.add_library(
         "rocksdb_lib",
         src_mk["LIB_SOURCES"] +
         # always add range_tree, it's only excluded on ppc64, which we don't use internally
@@ -149,29 +150,20 @@ def generate_buck(repo_path, deps_map):
             "//folly/experimental/coro:task",
             "//folly/synchronization:distributed_mutex",
         ],
-        headers=LiteralValue("glob([\"**/*.h\"])")
     )
     # rocksdb_whole_archive_lib
-    BUCK.add_library(
+    TARGETS.add_library(
         "rocksdb_whole_archive_lib",
         [],
         deps=[
             ":rocksdb_lib",
         ],
+        headers=None,
         extra_external_deps="",
         link_whole=True,
     )
-    # rocksdb_with_faiss_lib
-    BUCK.add_library(
-        "rocksdb_with_faiss_lib",
-        src_mk.get("WITH_FAISS_LIB_SOURCES", []),
-        deps=[
-            "//faiss:faiss",
-            ":rocksdb_lib",
-        ],
-    )
     # rocksdb_test_lib
-    BUCK.add_library(
+    TARGETS.add_library(
         "rocksdb_test_lib",
         src_mk.get("MOCK_LIB_SOURCES", [])
         + src_mk.get("TEST_LIB_SOURCES", [])
@@ -180,20 +172,8 @@ def generate_buck(repo_path, deps_map):
         [":rocksdb_lib"],
         extra_test_libs=True,
     )
-    # rocksdb_with_faiss_test_lib
-    BUCK.add_library(
-        "rocksdb_with_faiss_test_lib",
-        src_mk.get("MOCK_LIB_SOURCES", [])
-        + src_mk.get("TEST_LIB_SOURCES", [])
-        + src_mk.get("EXP_LIB_SOURCES", [])
-        + src_mk.get("ANALYZER_LIB_SOURCES", []),
-        deps=[
-            ":rocksdb_with_faiss_lib",
-        ],
-        extra_test_libs=True,
-    )
     # rocksdb_tools_lib
-    BUCK.add_library(
+    TARGETS.add_library(
         "rocksdb_tools_lib",
         src_mk.get("BENCH_LIB_SOURCES", [])
         + src_mk.get("ANALYZER_LIB_SOURCES", [])
@@ -201,51 +181,43 @@ def generate_buck(repo_path, deps_map):
         [":rocksdb_lib"],
     )
     # rocksdb_cache_bench_tools_lib
-    BUCK.add_library(
+    TARGETS.add_library(
         "rocksdb_cache_bench_tools_lib",
         src_mk.get("CACHE_BENCH_LIB_SOURCES", []),
         [":rocksdb_lib"],
     )
     # rocksdb_stress_lib
-    BUCK.add_rocksdb_library(
+    TARGETS.add_rocksdb_library(
         "rocksdb_stress_lib",
         src_mk.get("ANALYZER_LIB_SOURCES", [])
         + src_mk.get("STRESS_LIB_SOURCES", [])
         + ["test_util/testutil.cc"],
     )
-    # ldb binary
-    BUCK.add_binary(
-        "ldb", ["tools/ldb.cc"], [":rocksdb_tools_lib"]
-    )
     # db_stress binary
-    BUCK.add_binary(
+    TARGETS.add_binary(
         "db_stress", ["db_stress_tool/db_stress.cc"], [":rocksdb_stress_lib"]
     )
-    # db_bench binary
-    BUCK.add_binary(
-        "db_bench", ["tools/db_bench.cc"], [":rocksdb_tools_lib"]
-    )
     # cache_bench binary
-    BUCK.add_binary(
+    TARGETS.add_binary(
         "cache_bench", ["cache/cache_bench.cc"], [":rocksdb_cache_bench_tools_lib"]
     )
     # bench binaries
     for src in src_mk.get("MICROBENCH_SOURCES", []):
         name = src.rsplit("/", 1)[1].split(".")[0] if "/" in src else src.split(".")[0]
-        BUCK.add_binary(name, [src], [], extra_bench_libs=True)
-    print(f"Extra dependencies:\n{json.dumps(deps_map)}")
+        TARGETS.add_binary(name, [src], [], extra_bench_libs=True)
+    print("Extra dependencies:\n{0}".format(json.dumps(deps_map)))
 
     # Dictionary test executable name -> relative source file path
     test_source_map = {}
 
-    # c_test.c is added through BUCK.add_c_test(). If there
+    # c_test.c is added through TARGETS.add_c_test(). If there
     # are more than one .c test file, we need to extend
-    # BUCK.add_c_test() to include other C tests too.
+    # TARGETS.add_c_test() to include other C tests too.
     for test_src in src_mk.get("TEST_MAIN_SOURCES_C", []):
         if test_src != "db/c_test.c":
             print("Don't know how to deal with " + test_src)
             return False
-    BUCK.add_c_test()
+    TARGETS.add_c_test()
 
     try:
         with open(f"{repo_path}/buckifier/bench.json") as json_file:
@@ -260,7 +232,7 @@ def generate_buck(repo_path, deps_map):
                         for metric in overloaded_metric_list:
                             if not isinstance(metric, dict):
                                 clean_benchmarks[binary][benchmark].append(metric)
-                BUCK.add_fancy_bench_config(
+                TARGETS.add_fancy_bench_config(
                     config_dict["name"],
                     clean_benchmarks,
                     False,
@@ -282,7 +254,7 @@ def generate_buck(repo_path, deps_map):
                             if not isinstance(metric, dict):
                                 clean_benchmarks[binary][benchmark].append(metric)
             for config_dict in slow_fancy_bench_config_list:
-                BUCK.add_fancy_bench_config(
+                TARGETS.add_fancy_bench_config(
                     config_dict["name"] + "_slow",
                     clean_benchmarks,
                     True,
@@ -295,20 +267,15 @@ def generate_buck(repo_path, deps_map):
     except Exception:
         pass
 
-    BUCK.add_test_header()
+    TARGETS.add_test_header()
 
     for test_src in src_mk.get("TEST_MAIN_SOURCES", []):
         test = test_src.split(".c")[0].strip().split("/")[-1].strip()
-        test_source_map[test] = (test_src, False)
+        test_source_map[test] = test_src
         print("" + test + " " + test_src)
 
-    for test_src in src_mk.get("WITH_FAISS_TEST_MAIN_SOURCES", []):
-        test = test_src.split(".c")[0].strip().split("/")[-1].strip()
-        test_source_map[test] = (test_src, True)
-        print("" + test + " " + test_src + " [FAISS]")
-
     for target_alias, deps in deps_map.items():
-        for test, (test_src, with_faiss) in sorted(test_source_map.items()):
+        for test, test_src in sorted(test_source_map.items()):
             if len(test) == 0:
                 print(ColorString.warning("Failed to get test name for %s" % test_src))
                 continue
@@ -317,39 +284,31 @@ def generate_buck(repo_path, deps_map):
 
             if test in _EXPORTED_TEST_LIBS:
                 test_library = "%s_lib" % test_target_name
-                BUCK.add_library(
+                TARGETS.add_library(
                     test_library,
                     [test_src],
                     deps=[":rocksdb_test_lib"],
                     extra_test_libs=True,
                 )
-                BUCK.register_test(
+                TARGETS.register_test(
                     test_target_name,
                     test_src,
                     deps=json.dumps(deps["extra_deps"] + [":" + test_library]),
                     extra_compiler_flags=json.dumps(deps["extra_compiler_flags"]),
                 )
             else:
-                if with_faiss:
-                    BUCK.register_test(
-                        test_target_name,
-                        test_src,
-                        deps=json.dumps(deps["extra_deps"] + [":rocksdb_with_faiss_test_lib"]),
-                        extra_compiler_flags=json.dumps(deps["extra_compiler_flags"]),
-                    )
-                else:
-                    BUCK.register_test(
-                        test_target_name,
-                        test_src,
-                        deps=json.dumps(deps["extra_deps"] + [":rocksdb_test_lib"]),
-                        extra_compiler_flags=json.dumps(deps["extra_compiler_flags"]),
-                    )
-    BUCK.export_file("tools/db_crashtest.py")
+                TARGETS.register_test(
+                    test_target_name,
+                    test_src,
+                    deps=json.dumps(deps["extra_deps"] + [":rocksdb_test_lib"]),
+                    extra_compiler_flags=json.dumps(deps["extra_compiler_flags"]),
+                )
+    TARGETS.export_file("tools/db_crashtest.py")
 
-    print(ColorString.info("Generated BUCK Summary:"))
-    print(ColorString.info("- %d libs" % BUCK.total_lib))
-    print(ColorString.info("- %d binarys" % BUCK.total_bin))
-    print(ColorString.info("- %d tests" % BUCK.total_test))
+    print(ColorString.info("Generated TARGETS Summary:"))
+    print(ColorString.info("- %d libs" % TARGETS.total_lib))
+    print(ColorString.info("- %d binarys" % TARGETS.total_bin))
+    print(ColorString.info("- %d tests" % TARGETS.total_test))
     return True
 
 
@@ -369,10 +328,10 @@ def exit_with_error(msg):
 
 def main():
     deps_map = get_dependencies()
-    # Generate BUCK file for buck
-    ok = generate_buck(get_rocksdb_path(), deps_map)
+    # Generate TARGETS file for buck
+    ok = generate_targets(get_rocksdb_path(), deps_map)
     if not ok:
-        exit_with_error("Failed to generate BUCK files")
+        exit_with_error("Failed to generate TARGETS files")
 
 
 if __name__ == "__main__":

buckifier/check_buck_targets.sh

@@ -1,44 +1,32 @@
 #!/usr/bin/env bash
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+# If clang_format_diff.py command is not specfied, we assume we are able to
+# access directly without any path.
 
-if [[ ! -f "BUCK" ]]
-then
-  echo "BUCK file is missing!"
-  echo "Please do not remove / rename BUCK file in your commit(s)."
-  exit 1
-fi
-
-TGT_DIFF=`git diff BUCK | head -n 1`
+TGT_DIFF=`git diff TARGETS | head -n 1`
 
 if [ ! -z "$TGT_DIFF" ]
 then
-  echo "BUCK file has uncommitted changes. Skip this check."
+  echo "TARGETS file has uncommitted changes. Skip this check."
   exit 0
 fi
 
-echo Backup original BUCK file.
+echo Backup original TARGETS file.
 
-cp BUCK BUCK.bkp
+cp TARGETS TARGETS.bkp
 
 ${PYTHON:-python3} buckifier/buckify_rocksdb.py
 
-if [[ ! -f "BUCK" ]]
-then
-  echo "BUCK file went missing after running buckifier/buckify_rocksdb.py!"
-  echo "Please do not remove the BUCK file."
-  exit 1
-fi
-
-TGT_DIFF=`git diff BUCK | head -n 1`
+TGT_DIFF=`git diff TARGETS | head -n 1`
 
 if [ -z "$TGT_DIFF" ]
 then
-  mv BUCK.bkp BUCK
+  mv TARGETS.bkp TARGETS
   exit 0
 else
-  echo "Please run '${PYTHON:-python3} buckifier/buckify_rocksdb.py' to update BUCK file."
-  echo "Do not manually update BUCK file."
+  echo "Please run '${PYTHON:-python3} buckifier/buckify_rocksdb.py' to update TARGETS file."
+  echo "Do not manually update TARGETS file."
   ${PYTHON:-python3} --version
-  mv BUCK.bkp BUCK
+  mv TARGETS.bkp TARGETS
   exit 1
 fi

buckifier/targets_builder.py

@@ -1,4 +1,5 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 try:
     from builtins import object, str
@@ -8,28 +9,17 @@ import pprint
 
 import targets_cfg
 
-class LiteralValue:
-    def __init__(self, value):
-        self.value = value
-
-    def __str__(self):
-        return str(self.value)
-
-def smart_quote_value(val):
-    if isinstance(val, LiteralValue):
-        return str(val)
-    return '"%s"' % val
 
 def pretty_list(lst, indent=8):
     if lst is None or len(lst) == 0:
         return ""
 
     if len(lst) == 1:
-        return smart_quote_value(lst[0])
+        return '"%s"' % lst[0]
 
-    separator = ',\n%s' % (" " * indent)
-    res = separator.join(sorted(map(smart_quote_value, lst)))
-    res = "\n" + (" " * indent) + res + ',\n' + (" " * (indent - 4))
+    separator = '",\n%s"' % (" " * indent)
+    res = separator.join(sorted(lst))
+    res = "\n" + (" " * indent) + '"' + res + '",\n' + (" " * (indent - 4))
     return res
 
 
@@ -58,12 +48,7 @@ class TARGETSBuilder:
         extra_test_libs=False,
     ):
         if headers is not None:
-            if isinstance(headers, LiteralValue):
-                headers = str(headers)
-            else:
-                headers = "[" + pretty_list(headers) + "]"
-        else:
-            headers = "[]"
+            headers = "[" + pretty_list(headers) + "]"
         with open(self.path, "ab") as targets_file:
             targets_file.write(
                 targets_cfg.library_template.format(
@@ -80,7 +65,8 @@ class TARGETSBuilder:
         self.total_lib = self.total_lib + 1
 
     def add_rocksdb_library(self, name, srcs, headers=None, external_dependencies=None):
-        headers = "[" + pretty_list(headers) + "]"
+        if headers is not None:
+            headers = "[" + pretty_list(headers) + "]"
         with open(self.path, "ab") as targets_file:
             targets_file.write(
                 targets_cfg.rocksdb_library_template.format(

buckifier/targets_cfg.py

@@ -1,4 +1,5 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 rocksdb_target_header_template = """# This file \100generated by:
 #$ python3 buckifier/buckify_rocksdb.py{extra_argv}
@@ -6,7 +7,6 @@ rocksdb_target_header_template = """# This file \100generated by:
 # This file is a Facebook-specific integration for buck builds, so can
 # only be validated by Facebook employees.
 load("//rocks/buckifier:defs.bzl", "cpp_library_wrapper","rocks_cpp_library_wrapper","cpp_binary_wrapper","cpp_unittest_wrapper","fancy_bench_wrapper","add_c_test_wrapper")
-load("@fbcode_macros//build_defs:export_files.bzl", "export_file")
 
 """
 

buckifier/util.py

@@ -2,6 +2,7 @@
 """
 This module keeps commonly used components.
 """
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 try:
     from builtins import object

build_tools/amalgamate.py

@@ -25,6 +25,7 @@
 #
 # The solution is to move the include out of the #ifdef.
 
+from __future__ import print_function
 
 import argparse
 import re
@@ -61,7 +62,7 @@ def expand_include(
 
     included.add(include_path)
     with open(include_path) as f:
-        print(f'#line 1 "{include_path}"', file=source_out)
+        print('#line 1 "{}"'.format(include_path), file=source_out)
         process_file(
             f, include_path, source_out, header_out, include_paths, public_include_paths
         )
@@ -117,7 +118,7 @@ def process_file(
                     )
 
             if expanded:
-                print(f'#line {line + 1} "{abs_path}"', file=source_out)
+                print('#line {} "{}"'.format(line + 1, abs_path), file=source_out)
         elif text != "#pragma once\n":
             source_out.write(text)
 
@@ -156,8 +157,8 @@ def main():
     with open(filename) as f, open(args.source_out, "w") as source_out, open(
         args.header_out, "w"
     ) as header_out:
-        print(f'#line 1 "{filename}"', file=source_out)
-        print(f'#include "{header_out.name}"', file=source_out)
+        print('#line 1 "{}"'.format(filename), file=source_out)
+        print('#include "{}"'.format(header_out.name), file=source_out)
         process_file(
             f, abs_path, source_out, header_out, include_paths, public_include_paths
         )

build_tools/benchmark_log_tool.py

@@ -102,7 +102,7 @@ class BenchmarkUtils:
 
 
 class ResultParser:
-    def __init__(self, field=r"(\w|[+-:.%])+", intrafield=r"(\s)+", separator="\t"):
+    def __init__(self, field="(\w|[+-:.%])+", intrafield="(\s)+", separator="\t"):
         self.field = re.compile(field)
         self.intra = re.compile(intrafield)
         self.sep = re.compile(separator)
@@ -159,7 +159,7 @@ class ResultParser:
 
 
 def load_report_from_tsv(filename: str):
-    file = open(filename)
+    file = open(filename, "r")
     contents = file.readlines()
     file.close()
     parser = ResultParser()

build_tools/build_detect_platform

@@ -163,6 +163,24 @@ case "$TARGET_OS" in
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
         fi
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt -ldl"
+        if test -z "$ROCKSDB_USE_IO_URING"; then
+            ROCKSDB_USE_IO_URING=1
+        fi
+        if test "$ROCKSDB_USE_IO_URING" -ne 0; then
+            # check for liburing
+            $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o test.o 2>/dev/null  <<EOF
+              #include <liburing.h>
+              int main() {
+                struct io_uring ring;
+                io_uring_queue_init(1, &ring, 0);
+                return 0;
+              }
+EOF
+            if [ "$?" = 0 ]; then
+                PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
+                COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
+            fi
+        fi
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
@@ -585,7 +603,7 @@ EOF
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbenchmark"
         fi
     fi
-    if test $USE_FOLLY || test $USE_FOLLY_LITE; then
+    if test $USE_FOLLY; then
         # Test whether libfolly library is installed
         $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
           #include <folly/synchronization/DistributedMutex.h>
@@ -596,29 +614,11 @@ EOF
         fi
     fi
 
-    if test -z "$ROCKSDB_USE_IO_URING"; then
-        ROCKSDB_USE_IO_URING=1
-    fi
-    if [ "$ROCKSDB_USE_IO_URING" -ne 0 -a "$PLATFORM" = OS_LINUX ]; then
-        # check for liburing
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o test.o 2>/dev/null  <<EOF
-          #include <liburing.h>
-          int main() {
-            struct io_uring ring;
-            io_uring_queue_init(1, &ring, 0);
-            return 0;
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
-        fi
-    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.
 # -Wshorten-64-to-32 breaks compilation on FreeBSD aarch64 and i386
-if ! { [ "$TARGET_OS" = FreeBSD -o "$TARGET_OS" = OpenBSD ] && [ "$TARGET_ARCHITECTURE" = arm64 -o "$TARGET_ARCHITECTURE" = i386 ]; }; then
+if ! { [ "$TARGET_OS" = FreeBSD ] && [ "$TARGET_ARCHITECTURE" = arm64 -o "$TARGET_ARCHITECTURE" = i386 ]; }; then
   # Test whether -Wshorten-64-to-32 is available
   $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o -Wshorten-64-to-32 2>/dev/null  <<EOF
     int main() {}
@@ -751,11 +751,6 @@ if [ "$USE_FOLLY" ]; then
     FOLLY_PATH=`cd $FOLLY_DIR && $PYTHON build/fbcode_builder/getdeps.py show-inst-dir folly`
   fi
 fi
-if [ "$USE_FOLLY_LITE" ]; then
-  if [ "$FOLLY_DIR" ]; then
-    BOOST_SOURCE_PATH=`cd $FOLLY_DIR && $PYTHON build/fbcode_builder/getdeps.py show-source-dir boost`
-  fi
-fi
 
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"
@@ -797,7 +792,6 @@ echo "PROFILING_FLAGS=$PROFILING_FLAGS" >> "$OUTPUT"
 echo "FIND=$FIND" >> "$OUTPUT"
 echo "WATCH=$WATCH" >> "$OUTPUT"
 echo "FOLLY_PATH=$FOLLY_PATH" >> "$OUTPUT"
-echo "BOOST_SOURCE_PATH=$BOOST_SOURCE_PATH" >> "$OUTPUT"
 
 # This will enable some related identifiers for the preprocessor
 if test -n "$JEMALLOC"; then

build_tools/dependencies_platform010.sh

@@ -1,22 +1,22 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # The file is generated using update_dependencies.sh.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/62de5a92e5f23c661c3d4b9f322e04eb14e7a5bd/11.x/centos8-native/886b5eb
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1f6edd1ff15c99c861afc8f3cd69054cd974dd64/15/platform010/72a2ff8
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d1129753c8361ac8e9453c0f4291337a4507ebe6/11.x/platform010/5684a5a
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/fed6e93d87571fb162734c86636119d45a398963/2.34/platform010/f259413
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/31a346126a1f3b64812c362511cb04cc1bd40855/1.1.8/platform010/76ebdda
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/0c65c05468b5a38cef1a106a1f526463e120c8dd/1.2.8/platform010/76ebdda
+GCC_BASE=/mnt/gvfs/third-party2/gcc/e40bde78650fa91b8405a857e3f10bf336633fb0/11.x/centos7-native/886b5eb
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/2043340983c032915adbb6f78903dc855b65aee8/12/platform010/9520e0f
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/c00dcc6a3e4125c7e8b248e9a79c14b78ac9e0ca/11.x/platform010/5684a5a
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/0b9c8e4b060eda62f3bc1c6127bbe1256697569b/2.34/platform010/f259413
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/bc9647f7912b131315827d65cb6189c21f381d05/1.1.3/platform010/76ebdda
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/a6f5f3f1d063d2d00cd02fc12f0f05fc3ab3a994/1.2.11/platform010/76ebdda
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/09703139cfc376bd8a82642385a0e97726b28287/1.0.6/platform010/76ebdda
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/ff23d17b932725cc1734a14896a8b67c518ba169/1.9.4/platform010/76ebdda
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/576397d8b1d9cea7306ad1e454d5e55caaa2ff1c/1.4.x/platform010/64091f4
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/fecac07861cb829f5e60dbeff0503d3272db73c0/2.2.0/platform010/76ebdda
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/0bb3f5756788ce26e2e16a1cb2f2af2c59b51abe/master/platform010/f57cc4a
-NUMA_BASE=/mnt/gvfs/third-party2/numa/5b602edd46fda54cdd7ea45f77dbe4061206e174/2.0.11/platform010/76ebdda
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/97cac22a149c2e202917e05d44e87e516b68216f/1.4/platform010/5074a48
-TBB_BASE=/mnt/gvfs/third-party2/tbb/53953ebc4e3eda85ad6fc3e429ba146035e97b90/2018_U5/platform010/76ebdda
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/60220d6a5bf7722b9cc239a1368c596619b12060/1.9.1/platform010/76ebdda
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/50eace8143eaaea9473deae1f3283e0049e05633/1.4.x/platform010/64091f4
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/5d27e5919771603da06000a027b12f799e58a4f7/2.2.0/platform010/76ebdda
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b62912d333ef33f9760efa6219dbe3fe6abb3b0e/master/platform010/f57cc4a
+NUMA_BASE=/mnt/gvfs/third-party2/numa/6b412770957aa3c8a87e5e0dcd8cc2f45f393bc0/2.0.11/platform010/76ebdda
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/52f69816e936e147664ad717eb71a1a0e9dc973a/1.4/platform010/5074a48
+TBB_BASE=/mnt/gvfs/third-party2/tbb/c9cc192099fa84c0dcd0ffeedd44a373ad6e4925/2018_U5/platform010/76ebdda
 LIBURING_BASE=/mnt/gvfs/third-party2/liburing/a98e2d137007e3ebf7f33bd6f99c2c56bdaf8488/20210212/platform010/76ebdda
 BENCHMARK_BASE=/mnt/gvfs/third-party2/benchmark/780c7a0f9cf0967961e69ad08e61cddd85d61821/trunk/platform010/76ebdda
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/624a2f8f6c93c3c1df8aa4a6255d8202631a6c80/fb/platform010/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/39579e8603b48b3540f8b0633f43adf29acccb8b/2.37/centos8-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/cd9cc656d49ecb53797ce4d055e49fde29fd57ff/3.19.0/platform010/76ebdda
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/02d9f76aaaba580611cf75e741753c800c7fdc12/fb/platform010/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/938dc3f064ef3a48c0446f5b11d788d50b3eb5ee/2.37/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/429a6b3203eb415f1599bd15183659153129188e/3.15.0/platform010/76ebdda
 LUA_BASE=/mnt/gvfs/third-party2/lua/363787fa5cac2a8aa20638909210443278fa138e/5.3.4/platform010/9079c97

build_tools/error_filter.py

@@ -9,6 +9,7 @@
     - Prints those error messages to stdout
 """
 
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 import re
 import sys
@@ -42,7 +43,7 @@ class GTestErrorParser(ErrorParserBase):
             return None
         gtest_fail_match = self._GTEST_FAIL_PATTERN.match(line)
         if gtest_fail_match:
-            return "{} failed: {}".format(self._last_gtest_name, gtest_fail_match.group(1))
+            return "%s failed: %s" % (self._last_gtest_name, gtest_fail_match.group(1))
         return None
 
 
@@ -65,52 +66,52 @@ class CompilerErrorParser(MatchErrorParser):
         # format (link error):
         #   '<filename>:<line #>: error: <error msg>'
         # The below regex catches both
-        super().__init__(r"\S+:\d+: error:")
+        super(CompilerErrorParser, self).__init__(r"\S+:\d+: error:")
 
 
 class ScanBuildErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"scan-build: \d+ bugs found.$")
+        super(ScanBuildErrorParser, self).__init__(r"scan-build: \d+ bugs found.$")
 
 
 class DbCrashErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"\*\*\*.*\^$|TEST FAILED.")
+        super(DbCrashErrorParser, self).__init__(r"\*\*\*.*\^$|TEST FAILED.")
 
 
 class WriteStressErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(
+        super(WriteStressErrorParser, self).__init__(
             r"ERROR: write_stress died with exitcode=\d+"
         )
 
 
 class AsanErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"==\d+==ERROR: AddressSanitizer:")
+        super(AsanErrorParser, self).__init__(r"==\d+==ERROR: AddressSanitizer:")
 
 
 class UbsanErrorParser(MatchErrorParser):
     def __init__(self):
         # format: '<filename>:<line #>:<column #>: runtime error: <error msg>'
-        super().__init__(r"\S+:\d+:\d+: runtime error:")
+        super(UbsanErrorParser, self).__init__(r"\S+:\d+:\d+: runtime error:")
 
 
 class ValgrindErrorParser(MatchErrorParser):
     def __init__(self):
         # just grab the summary, valgrind doesn't clearly distinguish errors
         # from other log messages.
-        super().__init__(r"==\d+== ERROR SUMMARY:")
+        super(ValgrindErrorParser, self).__init__(r"==\d+== ERROR SUMMARY:")
 
 
 class CompatErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"==== .*[Ee]rror.* ====$")
+        super(CompatErrorParser, self).__init__(r"==== .*[Ee]rror.* ====$")
 
 
 class TsanErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"WARNING: ThreadSanitizer:")
+        super(TsanErrorParser, self).__init__(r"WARNING: ThreadSanitizer:")
 
 
 _TEST_NAME_TO_PARSERS = {

build_tools/fbcode_config.sh

@@ -113,7 +113,7 @@ CLANG_LIB="$CLANG_BASE/lib"
 CLANG_SRC="$CLANG_BASE/../../src"
 
 CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_BIN/scan-build
+CLANG_SCAN_BUILD="$CLANG_SRC/llvm/tools/clang/tools/scan-build/bin/scan-build"
 
 if [ -z "$USE_CLANG" ]; then
   # gcc

build_tools/fbcode_config_platform010.sh

@@ -110,7 +110,7 @@ CLANG_LIB="$CLANG_BASE/lib"
 CLANG_SRC="$CLANG_BASE/../../src"
 
 CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_BIN/scan-build"
+CLANG_SCAN_BUILD="$CLANG_SRC/llvm/clang/tools/scan-build/bin/scan-build"
 
 if [ -z "$USE_CLANG" ]; then
   # gcc

build_tools/format-diff.sh

@@ -137,11 +137,11 @@ then
   # should be relevant for formatting fixes.
   FORMAT_UPSTREAM_MERGE_BASE="$(git merge-base "$FORMAT_UPSTREAM" HEAD)"
   # Get the differences
-  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1) || true
+  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1)
   echo "Checking format of changes not yet in $FORMAT_UPSTREAM..."
 else
   # Check the format of uncommitted lines,
-  diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1) || true
+  diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
   echo "Checking format of uncommitted changes..."
 fi
 
@@ -149,9 +149,6 @@ if [ -z "$diffs" ]
 then
   echo "Nothing needs to be reformatted!"
   exit 0
-elif [ $? -ne 1 ]; then
-  # CLANG_FORMAT_DIFF will exit on 1 while there is suggested changes.
-  exit $?
 elif [ $CHECK_ONLY ]
 then
   echo "Your change has unformatted code. Please run make format!"

build_tools/gnu_parallel

@@ -1561,7 +1561,7 @@ sub save_stdin_stdout_stderr {
 	::die_bug("Can't dup STDERR: $!");
     open $Global::original_stdin, "<&", "STDIN" or
 	::die_bug("Can't dup STDIN: $!");
-    $Global::is_terminal = (-t $Global::original_stderr) && !$ENV{'CIRCLECI'}&& !$ENV{'GITHUB_ACTIONS'}  && !$ENV{'TRAVIS'};
+    $Global::is_terminal = (-t $Global::original_stderr) && !$ENV{'CIRCLECI'} && !$ENV{'TRAVIS'};
 }
 
 sub enough_file_handles {

build_tools/update_dependencies.sh

@@ -75,8 +75,8 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"
 
 # Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/11.x/centos8-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/15/platform010/*/`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/11.x/centos7-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/12/platform010/*/`
 
 log_header
 log_variable GCC_BASE
@@ -86,7 +86,7 @@ log_variable CLANG_BASE
 get_lib_base libgcc     11.x    platform010
 get_lib_base glibc      2.34    platform010
 get_lib_base snappy     LATEST  platform010
-get_lib_base zlib       1.2.8   platform010
+get_lib_base zlib       LATEST  platform010
 get_lib_base bzip2      LATEST  platform010
 get_lib_base lz4        LATEST  platform010
 get_lib_base zstd       LATEST  platform010
@@ -99,7 +99,7 @@ get_lib_base liburing   LATEST  platform010
 get_lib_base benchmark  LATEST  platform010
 
 get_lib_base kernel-headers fb platform010
-get_lib_base binutils   LATEST centos8-native
+get_lib_base binutils   LATEST centos7-native
 get_lib_base valgrind   LATEST platform010
 get_lib_base lua        5.3.4  platform010
 

cache/cache.cc

@@ -133,25 +133,19 @@ Status Cache::CreateFromString(const ConfigOptions& config_options,
                                std::shared_ptr<Cache>* result) {
   Status status;
   std::shared_ptr<Cache> cache;
-  if (StartsWith(value, "null")) {
-    cache = nullptr;
-  } else if (value.find("://") == std::string::npos) {
-    if (value.find('=') == std::string::npos) {
-      cache = NewLRUCache(ParseSizeT(value));
-    } else {
-      LRUCacheOptions cache_opts;
-      status = OptionTypeInfo::ParseStruct(config_options, "",
-                                           &lru_cache_options_type_info, "",
-                                           value, &cache_opts);
-      if (status.ok()) {
-        cache = NewLRUCache(cache_opts);
-      }
-    }
-    if (status.ok()) {
-      result->swap(cache);
-    }
+  if (value.find('=') == std::string::npos) {
+    cache = NewLRUCache(ParseSizeT(value));
   } else {
-    status = LoadSharedObject<Cache>(config_options, value, result);
+    LRUCacheOptions cache_opts;
+    status = OptionTypeInfo::ParseStruct(config_options, "",
+                                         &lru_cache_options_type_info, "",
+                                         value, &cache_opts);
+    if (status.ok()) {
+      cache = NewLRUCache(cache_opts);
+    }
+  }
+  if (status.ok()) {
+    result->swap(cache);
   }
   return status;
 }

cache/cache_bench_tool.cc

@@ -194,7 +194,7 @@ class SharedState {
       : cv_(&mu_),
         cache_bench_(cache_bench) {}
 
-  ~SharedState() = default;
+  ~SharedState() {}
 
   port::Mutex* GetMutex() { return &mu_; }
 
@@ -425,7 +425,7 @@ class CacheBench {
     }
   }
 
-  ~CacheBench() = default;
+  ~CacheBench() {}
 
   void PopulateCache() {
     Random64 rnd(FLAGS_seed);

cache/cache_reservation_manager_test.cc

@@ -129,6 +129,7 @@ TEST_F(CacheReservationManagerTest,
 
 TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,
      IncreaseCacheReservationOnFullCache) {
+  ;
   constexpr std::size_t kSizeDummyEntry =
       CacheReservationManagerImpl<CacheEntryRole::kMisc>::GetDummyEntrySize();
   constexpr std::size_t kSmallCacheCapacity = 4 * kSizeDummyEntry;

cache/cache_test.cc

@@ -18,7 +18,6 @@
 #include "cache/lru_cache.h"
 #include "cache/typed_cache.h"
 #include "port/stack_trace.h"
-#include "table/block_based/block_cache.h"
 #include "test_util/secondary_cache_test_util.h"
 #include "test_util/testharness.h"
 #include "util/coding.h"
@@ -107,7 +106,7 @@ class CacheTest : public testing::Test,
     type_ = GetParam();
   }
 
-  ~CacheTest() override = default;
+  ~CacheTest() override {}
 
   // These functions encode/decode keys in tests cases that use
   // int keys.
@@ -767,9 +766,7 @@ TEST_P(CacheTest, OverCapacity) {
     std::string key = EncodeKey(i + 1);
     auto h = cache.Lookup(key);
     ASSERT_TRUE(h != nullptr);
-    if (h) {
-      cache.Release(h);
-    }
+    if (h) cache.Release(h);
   }
 
   // the cache is over capacity since nothing could be evicted
@@ -780,7 +777,7 @@ TEST_P(CacheTest, OverCapacity) {
 
   if (IsHyperClock()) {
     // Make sure eviction is triggered.
-    ASSERT_OK(cache.Insert(EncodeKey(-1), nullptr, 1, handles.data()));
+    ASSERT_OK(cache.Insert(EncodeKey(-1), nullptr, 1, &handles[0]));
 
     // cache is under capacity now since elements were released
     ASSERT_GE(n, cache.get()->GetUsage());
@@ -886,32 +883,6 @@ TEST_P(CacheTest, ApplyToAllEntriesDuringResize) {
   ASSERT_EQ(special_count, kSpecialCount);
 }
 
-TEST_P(CacheTest, ApplyToHandleTest) {
-  std::string callback_state;
-  const auto callback = [&](const Slice& key, Cache::ObjectPtr value,
-                            size_t charge,
-                            const Cache::CacheItemHelper* helper) {
-    callback_state = std::to_string(DecodeKey(key)) + "," +
-                     std::to_string(DecodeValue(value)) + "," +
-                     std::to_string(charge);
-    assert(helper == &CacheTest::kHelper);
-  };
-
-  std::vector<std::string> inserted;
-
-  for (int i = 0; i < 10; ++i) {
-    Insert(i, i * 2, i + 1);
-    inserted.push_back(std::to_string(i) + "," + std::to_string(i * 2) + "," +
-                       std::to_string(i + 1));
-  }
-  for (int i = 0; i < 10; ++i) {
-    Cache::Handle* handle = cache_->Lookup(EncodeKey(i));
-    cache_->ApplyToHandle(cache_.get(), handle, callback);
-    EXPECT_EQ(inserted[i], callback_state);
-    cache_->Release(handle);
-  }
-}
-
 TEST_P(CacheTest, DefaultShardBits) {
   // Prevent excessive allocation (to save time & space)
   estimated_value_size_ = 100000;
@@ -1044,63 +1015,6 @@ INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest,
                         testing::Values(secondary_cache_test_util::kLRU));
 
-TEST(MiscBlockCacheTest, UncacheAggressivenessAdvisor) {
-  // Aggressiveness to a sequence of Report() calls (as string of 0s and 1s)
-  // exactly until the first ShouldContinue() == false.
-  const std::vector<std::pair<uint32_t, Slice>> expectedTraces{
-      // Aggressiveness 1 aborts on first unsuccessful erasure.
-      {1, "0"},
-      {1, "11111111111111111111110"},
-      // For sufficient evidence, aggressiveness 2 requires a minimum of two
-      // unsuccessful erasures.
-      {2, "00"},
-      {2, "0110"},
-      {2, "1100"},
-      {2, "011111111111111111111111111111111111111111111111111111111111111100"},
-      {2, "0111111111111111111111111111111111110"},
-      // For sufficient evidence, aggressiveness 3 and higher require a minimum
-      // of three unsuccessful erasures.
-      {3, "000"},
-      {3, "01010"},
-      {3, "111000"},
-      {3, "00111111111111111111111111111111111100"},
-      {3, "00111111111111111111110"},
-
-      {4, "000"},
-      {4, "01010"},
-      {4, "111000"},
-      {4, "001111111111111111111100"},
-      {4, "0011111111111110"},
-
-      {6, "000"},
-      {6, "01010"},
-      {6, "111000"},
-      {6, "00111111111111100"},
-      {6, "0011111110"},
-
-      // 69 -> 50% threshold, now up to minimum of 4
-      {69, "0000"},
-      {69, "010000"},
-      {69, "01010000"},
-      {69, "101010100010101000"},
-
-      // 230 -> 10% threshold, appropriately higher minimum
-      {230, "000000000000"},
-      {230, "0000000000010000000000"},
-      {230, "00000000000100000000010000000000"}};
-  for (const auto& [aggressiveness, t] : expectedTraces) {
-    SCOPED_TRACE("aggressiveness=" + std::to_string(aggressiveness) + " with " +
-                 t.ToString());
-    UncacheAggressivenessAdvisor uaa(aggressiveness);
-    for (size_t i = 0; i < t.size(); ++i) {
-      SCOPED_TRACE("i=" + std::to_string(i));
-      ASSERT_TRUE(uaa.ShouldContinue());
-      uaa.Report(t[i] & 1);
-    }
-    ASSERT_FALSE(uaa.ShouldContinue());
-  }
-}
-
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

cache/clock_cache.cc

@@ -560,7 +560,7 @@ void BaseClockTable::TrackAndReleaseEvictedEntry(ClockHandle* h) {
     took_value_ownership =
         eviction_callback_(ClockCacheShard<FixedHyperClockTable>::ReverseHash(
                                h->GetHash(), &unhashed, hash_seed_),
-                           static_cast<Cache::Handle*>(h),
+                           reinterpret_cast<Cache::Handle*>(h),
                            h->meta.LoadRelaxed() & ClockHandle::kHitBitMask);
   }
   if (!took_value_ownership) {
@@ -1428,38 +1428,22 @@ BaseHyperClockCache<Table>::BaseHyperClockCache(
 
 template <class Table>
 Cache::ObjectPtr BaseHyperClockCache<Table>::Value(Handle* handle) {
-  return static_cast<const typename Table::HandleImpl*>(handle)->value;
+  return reinterpret_cast<const typename Table::HandleImpl*>(handle)->value;
 }
 
 template <class Table>
 size_t BaseHyperClockCache<Table>::GetCharge(Handle* handle) const {
-  return static_cast<const typename Table::HandleImpl*>(handle)
+  return reinterpret_cast<const typename Table::HandleImpl*>(handle)
       ->GetTotalCharge();
 }
 
 template <class Table>
 const Cache::CacheItemHelper* BaseHyperClockCache<Table>::GetCacheItemHelper(
     Handle* handle) const {
-  auto h = static_cast<const typename Table::HandleImpl*>(handle);
+  auto h = reinterpret_cast<const typename Table::HandleImpl*>(handle);
   return h->helper;
 }
 
-template <class Table>
-void BaseHyperClockCache<Table>::ApplyToHandle(
-    Cache* cache, Handle* handle,
-    const std::function<void(const Slice& key, Cache::ObjectPtr value,
-                             size_t charge, const CacheItemHelper* helper)>&
-        callback) {
-  BaseHyperClockCache<Table>* cache_ptr =
-      static_cast<BaseHyperClockCache<Table>*>(cache);
-  auto h = static_cast<const typename Table::HandleImpl*>(handle);
-  UniqueId64x2 unhashed;
-  auto hash_seed = cache_ptr->GetShard(h->GetHash()).GetTable().GetHashSeed();
-  callback(
-      ClockCacheShard<Table>::ReverseHash(h->hashed_key, &unhashed, hash_seed),
-      h->value, h->GetTotalCharge(), h->helper);
-}
-
 namespace {
 
 // For each cache shard, estimate what the table load factor would be if

cache/clock_cache.h

@@ -298,7 +298,7 @@ class ClockCacheTest;
 
 // ----------------------------------------------------------------------- //
 
-struct ClockHandleBasicData : public Cache::Handle {
+struct ClockHandleBasicData {
   Cache::ObjectPtr value = nullptr;
   const Cache::CacheItemHelper* helper = nullptr;
   // A lossless, reversible hash of the fixed-size (16 byte) cache key. This
@@ -1128,12 +1128,6 @@ class BaseHyperClockCache : public ShardedCache<ClockCacheShard<Table>> {
 
   const CacheItemHelper* GetCacheItemHelper(Handle* handle) const override;
 
-  void ApplyToHandle(
-      Cache* cache, Handle* handle,
-      const std::function<void(const Slice& key, Cache::ObjectPtr obj,
-                               size_t charge, const CacheItemHelper* helper)>&
-          callback) override;
-
   void ReportProblems(
       const std::shared_ptr<Logger>& /*info_log*/) const override;
 };

cache/compressed_secondary_cache.cc

@@ -26,7 +26,7 @@ CompressedSecondaryCache::CompressedSecondaryCache(
               cache_))),
       disable_cache_(opts.capacity == 0) {}
 
-CompressedSecondaryCache::~CompressedSecondaryCache() = default;
+CompressedSecondaryCache::~CompressedSecondaryCache() {}
 
 std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
     const Slice& key, const Cache::CacheItemHelper* helper,
@@ -79,11 +79,7 @@ std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
     data_ptr = GetVarint32Ptr(data_ptr, data_ptr + 1,
                               static_cast<uint32_t*>(&source_32));
     source = static_cast<CacheTier>(source_32);
-    uint64_t data_size = 0;
-    data_ptr = GetVarint64Ptr(data_ptr, ptr->get() + handle_value_charge,
-                              static_cast<uint64_t*>(&data_size));
-    assert(handle_value_charge > data_size);
-    handle_value_charge = data_size;
+    handle_value_charge -= (data_ptr - ptr->get());
   }
   MemoryAllocator* allocator = cache_options_.memory_allocator.get();
 
@@ -173,15 +169,13 @@ Status CompressedSecondaryCache::InsertInternal(
   }
 
   auto internal_helper = GetHelper(cache_options_.enable_custom_split_merge);
-  char header[20];
+  char header[10];
   char* payload = header;
   payload = EncodeVarint32(payload, static_cast<uint32_t>(type));
   payload = EncodeVarint32(payload, static_cast<uint32_t>(source));
-  size_t data_size = (*helper->size_cb)(value);
-  char* data_size_ptr = payload;
-  payload = EncodeVarint64(payload, data_size);
 
   size_t header_size = payload - header;
+  size_t data_size = (*helper->size_cb)(value);
   size_t total_size = data_size + header_size;
   CacheAllocationPtr ptr =
       AllocateBlock(total_size, cache_options_.memory_allocator.get());
@@ -198,13 +192,13 @@ Status CompressedSecondaryCache::InsertInternal(
       type == kNoCompression &&
       !cache_options_.do_not_compress_roles.Contains(helper->role)) {
     PERF_COUNTER_ADD(compressed_sec_cache_uncompressed_bytes, data_size);
+    CompressionOptions compression_opts;
     CompressionContext compression_context(cache_options_.compression_type,
-                                           cache_options_.compression_opts);
+                                           compression_opts);
     uint64_t sample_for_compression{0};
     CompressionInfo compression_info(
-        cache_options_.compression_opts, compression_context,
-        CompressionDict::GetEmptyDict(), cache_options_.compression_type,
-        sample_for_compression);
+        compression_opts, compression_context, CompressionDict::GetEmptyDict(),
+        cache_options_.compression_type, sample_for_compression);
 
     bool success =
         CompressData(val, compression_info,
@@ -216,8 +210,6 @@ Status CompressedSecondaryCache::InsertInternal(
 
     val = Slice(compressed_val);
     data_size = compressed_val.size();
-    payload = EncodeVarint64(data_size_ptr, data_size);
-    header_size = payload - header;
     total_size = header_size + data_size;
     PERF_COUNTER_ADD(compressed_sec_cache_compressed_bytes, data_size);
 
@@ -230,21 +222,14 @@ Status CompressedSecondaryCache::InsertInternal(
 
   PERF_COUNTER_ADD(compressed_sec_cache_insert_real_count, 1);
   if (cache_options_.enable_custom_split_merge) {
-    size_t split_charge{0};
-    CacheValueChunk* value_chunks_head = SplitValueIntoChunks(
-        val, cache_options_.compression_type, split_charge);
-    return cache_->Insert(key, value_chunks_head, internal_helper,
-                          split_charge);
+    size_t charge{0};
+    CacheValueChunk* value_chunks_head =
+        SplitValueIntoChunks(val, cache_options_.compression_type, charge);
+    return cache_->Insert(key, value_chunks_head, internal_helper, charge);
   } else {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-    size_t charge = malloc_usable_size(ptr.get());
-#else
-    size_t charge = total_size;
-#endif
     std::memcpy(ptr.get(), header, header_size);
     CacheAllocationPtr* buf = new CacheAllocationPtr(std::move(ptr));
-    charge += sizeof(CacheAllocationPtr);
-    return cache_->Insert(key, buf, internal_helper, charge);
+    return cache_->Insert(key, buf, internal_helper, total_size);
   }
 }
 
@@ -306,11 +291,6 @@ std::string CompressedSecondaryCache::GetPrintableOptions() const {
   snprintf(buffer, kBufferSize, "    compression_type : %s\n",
            CompressionTypeToString(cache_options_.compression_type).c_str());
   ret.append(buffer);
-  snprintf(buffer, kBufferSize, "    compression_opts : %s\n",
-           CompressionOptionsToString(
-               const_cast<CompressionOptions&>(cache_options_.compression_opts))
-               .c_str());
-  ret.append(buffer);
   snprintf(buffer, kBufferSize, "    compress_format_version : %d\n",
            cache_options_.compress_format_version);
   ret.append(buffer);
@@ -399,7 +379,7 @@ const Cache::CacheItemHelper* CompressedSecondaryCache::GetHelper(
             chunks_head = chunks_head->next;
             tmp_chunk->Free();
             obj = nullptr;
-          }
+          };
         }};
     return &kHelper;
   } else {
@@ -413,21 +393,6 @@ const Cache::CacheItemHelper* CompressedSecondaryCache::GetHelper(
   }
 }
 
-size_t CompressedSecondaryCache::TEST_GetCharge(const Slice& key) {
-  Cache::Handle* lru_handle = cache_->Lookup(key);
-  if (lru_handle == nullptr) {
-    return 0;
-  }
-
-  size_t charge = cache_->GetCharge(lru_handle);
-  if (cache_->Value(lru_handle) != nullptr &&
-      !cache_options_.enable_custom_split_merge) {
-    charge -= 10;
-  }
-  cache_->Release(lru_handle, /*erase_if_last_ref=*/false);
-  return charge;
-}
-
 std::shared_ptr<SecondaryCache>
 CompressedSecondaryCacheOptions::MakeSharedSecondaryCache() const {
   return std::make_shared<CompressedSecondaryCache>(*this);

cache/compressed_secondary_cache.h

@@ -139,8 +139,6 @@ class CompressedSecondaryCache : public SecondaryCache {
                         const Cache::CacheItemHelper* helper,
                         CompressionType type, CacheTier source);
 
-  size_t TEST_GetCharge(const Slice& key);
-
   // TODO: clean up to use cleaner interfaces in typed_cache.h
   const Cache::CacheItemHelper* GetHelper(bool enable_custom_split_merge) const;
   std::shared_ptr<Cache> cache_;

cache/compressed_secondary_cache_test.cc

@@ -33,14 +33,12 @@ const std::string key3 = "____    ____key3";
 class CompressedSecondaryCacheTestBase : public testing::Test,
                                          public WithCacheType {
  public:
-  CompressedSecondaryCacheTestBase() = default;
+  CompressedSecondaryCacheTestBase() {}
   ~CompressedSecondaryCacheTestBase() override = default;
 
  protected:
   void BasicTestHelper(std::shared_ptr<SecondaryCache> sec_cache,
                        bool sec_cache_is_compressed) {
-    CompressedSecondaryCache* comp_sec_cache =
-        static_cast<CompressedSecondaryCache*>(sec_cache.get());
     get_perf_context()->Reset();
     bool kept_in_sec_cache{true};
     // Lookup an non-existent key.
@@ -68,8 +66,6 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_real_count, 1);
 
-    ASSERT_GT(comp_sec_cache->TEST_GetCharge(key1), 1000);
-
     std::unique_ptr<SecondaryCacheResultHandle> handle1_2 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/true,
                           /*stats=*/nullptr, kept_in_sec_cache);
@@ -1066,7 +1062,7 @@ bool CacheUsageWithinBounds(size_t val1, size_t val2, size_t error) {
 
 TEST_P(CompressedSecCacheTestWithTiered, CacheReservationManager) {
   CompressedSecondaryCache* sec_cache =
-      static_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
 
   // Use EXPECT_PRED3 instead of EXPECT_NEAR to void too many size_t to
   // double explicit casts
@@ -1089,7 +1085,7 @@ TEST_P(CompressedSecCacheTestWithTiered, CacheReservationManager) {
 TEST_P(CompressedSecCacheTestWithTiered,
        CacheReservationManagerMultipleUpdate) {
   CompressedSecondaryCache* sec_cache =
-      static_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
 
   EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
                GetPercent(30 << 20, 1));
@@ -1175,7 +1171,7 @@ TEST_P(CompressedSecCacheTestWithTiered, AdmissionPolicy) {
 
 TEST_P(CompressedSecCacheTestWithTiered, DynamicUpdate) {
   CompressedSecondaryCache* sec_cache =
-      static_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
   std::shared_ptr<Cache> tiered_cache = GetTieredCache();
 
   // Use EXPECT_PRED3 instead of EXPECT_NEAR to void too many size_t to
@@ -1239,7 +1235,7 @@ TEST_P(CompressedSecCacheTestWithTiered, DynamicUpdate) {
 
 TEST_P(CompressedSecCacheTestWithTiered, DynamicUpdateWithReservation) {
   CompressedSecondaryCache* sec_cache =
-      static_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
   std::shared_ptr<Cache> tiered_cache = GetTieredCache();
 
   ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(10 << 20));
@@ -1333,7 +1329,7 @@ TEST_P(CompressedSecCacheTestWithTiered, DynamicUpdateWithReservation) {
 
 TEST_P(CompressedSecCacheTestWithTiered, ReservationOverCapacity) {
   CompressedSecondaryCache* sec_cache =
-      static_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
   std::shared_ptr<Cache> tiered_cache = GetTieredCache();
 
   ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(110 << 20));

cache/lru_cache.cc

@@ -277,8 +277,8 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->SetInHighPriPool(false);
     e->SetInLowPriPool(true);
     low_pri_pool_usage_ += e->total_charge;
-    lru_low_pri_ = e;
     MaintainPoolSize();
+    lru_low_pri_ = e;
   } else {
     // Insert "e" to the head of bottom-pri pool.
     e->next = lru_bottom_pri_->next;
@@ -301,7 +301,6 @@ void LRUCacheShard::MaintainPoolSize() {
     // Overflow last entry in high-pri pool to low-pri pool.
     lru_low_pri_ = lru_low_pri_->next;
     assert(lru_low_pri_ != &lru_);
-    assert(lru_low_pri_->InHighPriPool());
     lru_low_pri_->SetInHighPriPool(false);
     lru_low_pri_->SetInLowPriPool(true);
     assert(high_pri_pool_usage_ >= lru_low_pri_->total_charge);
@@ -313,7 +312,6 @@ void LRUCacheShard::MaintainPoolSize() {
     // Overflow last entry in low-pri pool to bottom-pri pool.
     lru_bottom_pri_ = lru_bottom_pri_->next;
     assert(lru_bottom_pri_ != &lru_);
-    assert(lru_bottom_pri_->InLowPriPool());
     lru_bottom_pri_->SetInHighPriPool(false);
     lru_bottom_pri_->SetInLowPriPool(false);
     assert(low_pri_pool_usage_ >= lru_bottom_pri_->total_charge);
@@ -341,7 +339,8 @@ void LRUCacheShard::NotifyEvicted(
   MemoryAllocator* alloc = table_.GetAllocator();
   for (LRUHandle* entry : evicted_handles) {
     if (eviction_callback_ &&
-        eviction_callback_(entry->key(), static_cast<Cache::Handle*>(entry),
+        eviction_callback_(entry->key(),
+                           reinterpret_cast<Cache::Handle*>(entry),
                            entry->HasHit())) {
       // Callback took ownership of obj; just free handle
       free(entry);
@@ -507,7 +506,7 @@ bool LRUCacheShard::Release(LRUHandle* e, bool /*useful*/,
     // Only call eviction callback if we're sure no one requested erasure
     // FIXME: disabled because of test churn
     if (false && was_in_cache && !erase_if_last_ref && eviction_callback_ &&
-        eviction_callback_(e->key(), static_cast<Cache::Handle*>(e),
+        eviction_callback_(e->key(), reinterpret_cast<Cache::Handle*>(e),
                            e->HasHit())) {
       // Callback took ownership of obj; just free handle
       free(e);
@@ -662,32 +661,21 @@ LRUCache::LRUCache(const LRUCacheOptions& opts) : ShardedCache(opts) {
 }
 
 Cache::ObjectPtr LRUCache::Value(Handle* handle) {
-  auto h = static_cast<const LRUHandle*>(handle);
+  auto h = reinterpret_cast<const LRUHandle*>(handle);
   return h->value;
 }
 
 size_t LRUCache::GetCharge(Handle* handle) const {
-  return static_cast<const LRUHandle*>(handle)->GetCharge(
+  return reinterpret_cast<const LRUHandle*>(handle)->GetCharge(
       GetShard(0).metadata_charge_policy_);
 }
 
 const Cache::CacheItemHelper* LRUCache::GetCacheItemHelper(
     Handle* handle) const {
-  auto h = static_cast<const LRUHandle*>(handle);
+  auto h = reinterpret_cast<const LRUHandle*>(handle);
   return h->helper;
 }
 
-void LRUCache::ApplyToHandle(
-    Cache* cache, Handle* handle,
-    const std::function<void(const Slice& key, ObjectPtr value, size_t charge,
-                             const CacheItemHelper* helper)>& callback) {
-  auto cache_ptr = static_cast<LRUCache*>(cache);
-  auto h = static_cast<const LRUHandle*>(handle);
-  callback(h->key(), h->value,
-           h->GetCharge(cache_ptr->GetShard(0).metadata_charge_policy_),
-           h->helper);
-}
-
 size_t LRUCache::TEST_GetLRUSize() {
   return SumOverShards([](LRUCacheShard& cs) { return cs.TEST_GetLRUSize(); });
 }

cache/lru_cache.h

@@ -47,7 +47,7 @@ namespace lru_cache {
 // LRUCacheShard::Lookup.
 // While refs > 0, public properties like value and deleter must not change.
 
-struct LRUHandle : public Cache::Handle {
+struct LRUHandle {
   Cache::ObjectPtr value;
   const Cache::CacheItemHelper* helper;
   LRUHandle* next_hash;
@@ -452,12 +452,6 @@ class LRUCache
   size_t GetCharge(Handle* handle) const override;
   const CacheItemHelper* GetCacheItemHelper(Handle* handle) const override;
 
-  void ApplyToHandle(
-      Cache* cache, Handle* handle,
-      const std::function<void(const Slice& key, ObjectPtr obj, size_t charge,
-                               const CacheItemHelper* helper)>& callback)
-      override;
-
   // Retrieves number of elements in LRU, for unit test purpose only.
   size_t TEST_GetLRUSize();
   // Retrieves high pri pool ratio.

cache/lru_cache_test.cc

@@ -32,7 +32,7 @@ namespace ROCKSDB_NAMESPACE {
 
 class LRUCacheTest : public testing::Test {
  public:
-  LRUCacheTest() = default;
+  LRUCacheTest() {}
   ~LRUCacheTest() override { DeleteCache(); }
 
   void DeleteCache() {
@@ -47,7 +47,7 @@ class LRUCacheTest : public testing::Test {
                 double low_pri_pool_ratio = 1.0,
                 bool use_adaptive_mutex = kDefaultToAdaptiveMutex) {
     DeleteCache();
-    cache_ = static_cast<LRUCacheShard*>(
+    cache_ = reinterpret_cast<LRUCacheShard*>(
         port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
     new (cache_) LRUCacheShard(capacity, /*strict_capacity_limit=*/false,
                                high_pri_pool_ratio, low_pri_pool_ratio,
@@ -57,11 +57,10 @@ class LRUCacheTest : public testing::Test {
   }
 
   void Insert(const std::string& key,
-              Cache::Priority priority = Cache::Priority::LOW,
-              size_t charge = 1) {
+              Cache::Priority priority = Cache::Priority::LOW) {
     EXPECT_OK(cache_->Insert(key, 0 /*hash*/, nullptr /*value*/,
-                             &kNoopCacheItemHelper, charge, nullptr /*handle*/,
-                             priority));
+                             &kNoopCacheItemHelper, 1 /*charge*/,
+                             nullptr /*handle*/, priority));
   }
 
   void Insert(char key, Cache::Priority priority = Cache::Priority::LOW) {
@@ -145,10 +144,8 @@ class LRUCacheTest : public testing::Test {
     ASSERT_EQ(num_bottom_pri_pool_keys, bottom_pri_pool_keys);
   }
 
- protected:
-  LRUCacheShard* cache_ = nullptr;
-
  private:
+  LRUCacheShard* cache_ = nullptr;
   Cache::EvictionCallback eviction_callback_;
 };
 
@@ -381,7 +378,7 @@ class ClockCacheTest : public testing::Test {
   using Table = typename Shard::Table;
   using TableOpts = typename Table::Opts;
 
-  ClockCacheTest() = default;
+  ClockCacheTest() {}
   ~ClockCacheTest() override { DeleteShard(); }
 
   void DeleteShard() {
@@ -395,7 +392,8 @@ class ClockCacheTest : public testing::Test {
   void NewShard(size_t capacity, bool strict_capacity_limit = true,
                 int eviction_effort_cap = 30) {
     DeleteShard();
-    shard_ = static_cast<Shard*>(port::cacheline_aligned_alloc(sizeof(Shard)));
+    shard_ =
+        reinterpret_cast<Shard*>(port::cacheline_aligned_alloc(sizeof(Shard)));
 
     TableOpts opts{1 /*value_size*/, eviction_effort_cap};
     new (shard_)
@@ -1979,7 +1977,7 @@ TEST_P(BasicSecondaryCacheTest, BasicWaitAllTest) {
     ah.priority = Cache::Priority::LOW;
     cache->StartAsyncLookup(ah);
   }
-  cache->WaitAll(async_handles.data(), async_handles.size());
+  cache->WaitAll(&async_handles[0], async_handles.size());
   for (size_t i = 0; i < async_handles.size(); ++i) {
     SCOPED_TRACE("i = " + std::to_string(i));
     Cache::Handle* result = async_handles[i].Result();
@@ -2706,23 +2704,6 @@ TEST_P(DBSecondaryCacheTest, TestSecondaryCacheOptionTwoDB) {
   ASSERT_OK(DestroyDB(dbname2, options));
 }
 
-TEST_F(LRUCacheTest, InsertAfterReducingCapacity) {
-  // Fix a bug in LRU cache where it may try to remove a low pri entry's
-  // charge from high pri pool. It causes
-  // Assertion failed: (high_pri_pool_usage_ >= lru_low_pri_->total_charge),
-  // function MaintainPoolSize, file lru_cache.cc
-  NewCache(/*capacity=*/10, /*high_pri_pool_ratio=*/0.2,
-           /*low_pri_pool_ratio=*/0.8);
-  // high pri pool size and usage are both 2
-  Insert("x", Cache::Priority::HIGH);
-  Insert("y", Cache::Priority::HIGH);
-  cache_->SetCapacity(5);
-  // high_pri_pool_size is 1, the next time we try to maintain pool size,
-  // we will move entries from high pri pool to low pri pool
-  // The bug was deducting this entry's charge from high pri pool usage.
-  Insert("aaa", Cache::Priority::LOW, /*charge=*/3);
-}
-
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

cache/secondary_cache_adapter.cc

@@ -134,14 +134,12 @@ bool CacheWithSecondaryAdapter::EvictionHandler(const Slice& key,
     auto obj = target_->Value(handle);
     // Ignore dummy entry
     if (obj != kDummyObj) {
-      bool force = false;
+      bool hit = false;
       if (adm_policy_ == TieredAdmissionPolicy::kAdmPolicyAllowCacheHits) {
-        force = was_hit;
-      } else if (adm_policy_ == TieredAdmissionPolicy::kAdmPolicyAllowAll) {
-        force = true;
+        hit = was_hit;
       }
       // Spill into secondary cache.
-      secondary_cache_->Insert(key, obj, helper, force).PermitUncheckedError();
+      secondary_cache_->Insert(key, obj, helper, hit).PermitUncheckedError();
     }
   }
   // Never takes ownership of obj
@@ -271,8 +269,7 @@ Status CacheWithSecondaryAdapter::Insert(const Slice& key, ObjectPtr value,
   // Warm up the secondary cache with the compressed block. The secondary
   // cache may choose to ignore it based on the admission policy.
   if (value != nullptr && !compressed_value.empty() &&
-      adm_policy_ == TieredAdmissionPolicy::kAdmPolicyThreeQueue &&
-      helper->IsSecondaryCacheCompatible()) {
+      adm_policy_ == TieredAdmissionPolicy::kAdmPolicyThreeQueue) {
     Status status = secondary_cache_->InsertSaved(key, compressed_value, type);
     assert(status.ok() || status.IsNotSupported());
   }
@@ -664,7 +661,6 @@ std::shared_ptr<Cache> NewTieredCache(const TieredCacheOptions& _opts) {
         break;
       case TieredAdmissionPolicy::kAdmPolicyPlaceholder:
       case TieredAdmissionPolicy::kAdmPolicyAllowCacheHits:
-      case TieredAdmissionPolicy::kAdmPolicyAllowAll:
         if (opts.nvm_sec_cache) {
           valid_adm_policy = false;
         }

cache/sharded_cache.h

@@ -139,7 +139,7 @@ class ShardedCache : public ShardedCacheBase {
 
   explicit ShardedCache(const ShardedCacheOptions& opts)
       : ShardedCacheBase(opts),
-        shards_(static_cast<CacheShard*>(port::cacheline_aligned_alloc(
+        shards_(reinterpret_cast<CacheShard*>(port::cacheline_aligned_alloc(
             sizeof(CacheShard) * GetNumShards()))),
         destroy_shards_in_dtor_(false) {}
 
@@ -192,7 +192,7 @@ class ShardedCache : public ShardedCacheBase {
     HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     HandleImpl* result = GetShard(hash).CreateStandalone(
         key, hash, obj, helper, charge, allow_uncharged);
-    return static_cast<Handle*>(result);
+    return reinterpret_cast<Handle*>(result);
   }
 
   Handle* Lookup(const Slice& key, const CacheItemHelper* helper = nullptr,
@@ -202,7 +202,7 @@ class ShardedCache : public ShardedCacheBase {
     HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     HandleImpl* result = GetShard(hash).Lookup(key, hash, helper,
                                                create_context, priority, stats);
-    return static_cast<Handle*>(result);
+    return reinterpret_cast<Handle*>(result);
   }
 
   void Erase(const Slice& key) override {
@@ -212,11 +212,11 @@ class ShardedCache : public ShardedCacheBase {
 
   bool Release(Handle* handle, bool useful,
                bool erase_if_last_ref = false) override {
-    auto h = static_cast<HandleImpl*>(handle);
+    auto h = reinterpret_cast<HandleImpl*>(handle);
     return GetShard(h->GetHash()).Release(h, useful, erase_if_last_ref);
   }
   bool Ref(Handle* handle) override {
-    auto h = static_cast<HandleImpl*>(handle);
+    auto h = reinterpret_cast<HandleImpl*>(handle);
     return GetShard(h->GetHash()).Ref(h);
   }
   bool Release(Handle* handle, bool erase_if_last_ref = false) override {
@@ -259,7 +259,7 @@ class ShardedCache : public ShardedCacheBase {
     } while (remaining_work);
   }
 
-  void EraseUnRefEntries() override {
+  virtual void EraseUnRefEntries() override {
     ForEachShard([](CacheShard* cs) { cs->EraseUnRefEntries(); });
   }
 

cache/tiered_secondary_cache.h

@@ -42,25 +42,27 @@ class TieredSecondaryCache : public SecondaryCacheWrapper {
 
   // This is a no-op as we currently don't allow demotion (i.e
   // insertion by the upper layer) of evicted blocks.
-  Status Insert(const Slice& /*key*/, Cache::ObjectPtr /*obj*/,
-                const Cache::CacheItemHelper* /*helper*/,
-                bool /*force_insert*/) override {
+  virtual Status Insert(const Slice& /*key*/, Cache::ObjectPtr /*obj*/,
+                        const Cache::CacheItemHelper* /*helper*/,
+                        bool /*force_insert*/) override {
     return Status::OK();
   }
 
   // Warm up the nvm tier directly
-  Status InsertSaved(const Slice& key, const Slice& saved,
-                     CompressionType type = CompressionType::kNoCompression,
-                     CacheTier source = CacheTier::kVolatileTier) override {
+  virtual Status InsertSaved(
+      const Slice& key, const Slice& saved,
+      CompressionType type = CompressionType::kNoCompression,
+      CacheTier source = CacheTier::kVolatileTier) override {
     return nvm_sec_cache_->InsertSaved(key, saved, type, source);
   }
 
-  std::unique_ptr<SecondaryCacheResultHandle> Lookup(
+  virtual std::unique_ptr<SecondaryCacheResultHandle> Lookup(
       const Slice& key, const Cache::CacheItemHelper* helper,
       Cache::CreateContext* create_context, bool wait, bool advise_erase,
       Statistics* stats, bool& kept_in_sec_cache) override;
 
-  void WaitAll(std::vector<SecondaryCacheResultHandle*> handles) override;
+  virtual void WaitAll(
+      std::vector<SecondaryCacheResultHandle*> handles) override;
 
  private:
   struct CreateContext : public Cache::CreateContext {

cache/tiered_secondary_cache_test.cc

@@ -253,7 +253,6 @@ TEST_F(DBTieredSecondaryCacheTest, BasicTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   // Disable paranoid_file_checks so that flush will not read back the newly
@@ -365,7 +364,6 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   options.paranoid_file_checks = false;
@@ -388,7 +386,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 3u);
@@ -402,7 +400,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(20));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -416,7 +414,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -430,7 +428,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -444,7 +442,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -458,7 +456,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(20));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -472,7 +470,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(20));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -486,7 +484,7 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   keys.push_back(Key(20));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -508,7 +506,6 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   options.paranoid_file_checks = false;
@@ -531,7 +528,7 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 3u);
@@ -545,7 +542,7 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   keys.push_back(Key(20));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -564,7 +561,7 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   keys.push_back(Key(36));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 10u);
@@ -585,7 +582,7 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 10u);
@@ -609,7 +606,6 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   options.statistics = CreateDBStatistics();
 
@@ -633,7 +629,7 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 3u);
@@ -648,7 +644,7 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   keys.push_back(Key(20));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -663,7 +659,7 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   keys.push_back(Key(8));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 6u);
@@ -680,7 +676,7 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   keys.push_back(Key(36));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 8u);
@@ -695,7 +691,7 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   keys.push_back(Key(36));
   values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
   ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
+  for (auto value : values) {
     ASSERT_EQ(1007, value.size());
   }
   ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 8u);
@@ -721,7 +717,6 @@ TEST_F(DBTieredSecondaryCacheTest, IterateTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   options.paranoid_file_checks = false;
@@ -765,54 +760,6 @@ TEST_F(DBTieredSecondaryCacheTest, IterateTest) {
   Destroy(options);
 }
 
-TEST_F(DBTieredSecondaryCacheTest, VolatileTierTest) {
-  if (!LZ4_Supported()) {
-    ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-    return;
-  }
-
-  BlockBasedTableOptions table_options;
-  // We want a block cache of size 5KB, and a compressed secondary cache of
-  // size 5KB. However, we specify a block cache size of 256KB here in order
-  // to take into account the cache reservation in the block cache on
-  // behalf of the compressed cache. The unit of cache reservation is 256KB.
-  // The effective block cache capacity will be calculated as 256 + 5 = 261KB,
-  // and 256KB will be reserved for the compressed cache, leaving 5KB for
-  // the primary block cache. We only have to worry about this here because
-  // the cache size is so small.
-  table_options.block_cache = NewCache(256 * 1024, 5 * 1024, 256 * 1024);
-  table_options.block_size = 4 * 1024;
-  table_options.cache_index_and_filter_blocks = false;
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.compression = kLZ4Compression;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-
-  // Disable paranoid_file_checks so that flush will not read back the newly
-  // written file
-  options.paranoid_file_checks = false;
-  options.lowest_used_cache_tier = CacheTier::kVolatileTier;
-  DestroyAndReopen(options);
-  Random rnd(301);
-  const int N = 256;
-  for (int i = 0; i < N; i++) {
-    std::string p_v;
-    test::CompressibleString(&rnd, 0.5, 1007, &p_v);
-    ASSERT_OK(Put(Key(i), p_v));
-  }
-
-  ASSERT_OK(Flush());
-
-  // Since lowest_used_cache_tier is the volatile tier, nothing should be
-  // inserted in the secondary cache.
-  std::string v = Get(Key(0));
-  ASSERT_EQ(1007, v.size());
-  ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 0u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 0u);
-
-  Destroy(options);
-}
-
 class DBTieredAdmPolicyTest
     : public DBTieredSecondaryCacheTest,
       public testing::WithParamInterface<TieredAdmissionPolicy> {};
@@ -837,7 +784,6 @@ TEST_P(DBTieredAdmPolicyTest, CompressedOnlyTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   size_t comp_cache_usage = compressed_secondary_cache()->TEST_GetUsage();
@@ -870,176 +816,11 @@ TEST_P(DBTieredAdmPolicyTest, CompressedOnlyTest) {
   Destroy(options);
 }
 
-TEST_P(DBTieredAdmPolicyTest, CompressedCacheAdmission) {
-  if (!LZ4_Supported()) {
-    ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-    return;
-  }
-
-  BlockBasedTableOptions table_options;
-  // We want a block cache of size 5KB, and a compressed secondary cache of
-  // size 5KB. However, we specify a block cache size of 256KB here in order
-  // to take into account the cache reservation in the block cache on
-  // behalf of the compressed cache. The unit of cache reservation is 256KB.
-  // The effective block cache capacity will be calculated as 256 + 5 = 261KB,
-  // and 256KB will be reserved for the compressed cache, leaving 10KB for
-  // the primary block cache. We only have to worry about this here because
-  // the cache size is so small.
-  table_options.block_cache = NewCache(256 * 1024, 5 * 1024, 0, GetParam());
-  table_options.block_size = 4 * 1024;
-  table_options.cache_index_and_filter_blocks = false;
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.compression = kLZ4Compression;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-
-  size_t comp_cache_usage = compressed_secondary_cache()->TEST_GetUsage();
-  // Disable paranoid_file_checks so that flush will not read back the newly
-  // written file
-  options.paranoid_file_checks = false;
-  DestroyAndReopen(options);
-  Random rnd(301);
-  const int N = 256;
-  for (int i = 0; i < N; i++) {
-    std::string p_v;
-    test::CompressibleString(&rnd, 0.5, 1007, &p_v);
-    ASSERT_OK(Put(Key(i), p_v));
-  }
-
-  ASSERT_OK(Flush());
-
-  // The second Get (for 5) will evict the data block loaded by the first
-  // Get, which will be admitted into the compressed secondary cache only
-  // for the kAdmPolicyAllowAll policy
-  std::string v = Get(Key(0));
-  ASSERT_EQ(1007, v.size());
-
-  v = Get(Key(5));
-  ASSERT_EQ(1007, v.size());
-
-  if (GetParam() == TieredAdmissionPolicy::kAdmPolicyAllowAll) {
-    ASSERT_GT(compressed_secondary_cache()->TEST_GetUsage(),
-              comp_cache_usage + 128);
-  } else {
-    ASSERT_LT(compressed_secondary_cache()->TEST_GetUsage(),
-              comp_cache_usage + 128);
-  }
-
-  Destroy(options);
-}
-
-TEST_F(DBTieredSecondaryCacheTest, FSBufferTest) {
-  class WrapFS : public FileSystemWrapper {
-   public:
-    explicit WrapFS(const std::shared_ptr<FileSystem>& _target)
-        : FileSystemWrapper(_target) {}
-    ~WrapFS() override {}
-    const char* Name() const override { return "WrapFS"; }
-
-    IOStatus NewRandomAccessFile(const std::string& fname,
-                                 const FileOptions& opts,
-                                 std::unique_ptr<FSRandomAccessFile>* result,
-                                 IODebugContext* dbg) override {
-      class WrappedRandomAccessFile : public FSRandomAccessFileOwnerWrapper {
-       public:
-        explicit WrappedRandomAccessFile(
-            std::unique_ptr<FSRandomAccessFile>& file)
-            : FSRandomAccessFileOwnerWrapper(std::move(file)) {}
-
-        IOStatus MultiRead(FSReadRequest* reqs, size_t num_reqs,
-                           const IOOptions& options,
-                           IODebugContext* dbg) override {
-          for (size_t i = 0; i < num_reqs; ++i) {
-            FSReadRequest& req = reqs[i];
-            FSAllocationPtr buffer(new char[req.len], [](void* ptr) {
-              delete[] static_cast<char*>(ptr);
-            });
-            req.fs_scratch = std::move(buffer);
-            req.status = Read(req.offset, req.len, options, &req.result,
-                              static_cast<char*>(req.fs_scratch.get()), dbg);
-          }
-          return IOStatus::OK();
-        }
-      };
-
-      std::unique_ptr<FSRandomAccessFile> file;
-      IOStatus s = target()->NewRandomAccessFile(fname, opts, &file, dbg);
-      EXPECT_OK(s);
-      result->reset(new WrappedRandomAccessFile(file));
-
-      return s;
-    }
-
-    void SupportedOps(int64_t& supported_ops) override {
-      supported_ops = 1 << FSSupportedOps::kAsyncIO;
-      supported_ops |= 1 << FSSupportedOps::kFSBuffer;
-    }
-  };
-
-  if (!LZ4_Supported()) {
-    ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-    return;
-  }
-
-  std::shared_ptr<WrapFS> wrap_fs =
-      std::make_shared<WrapFS>(env_->GetFileSystem());
-  std::unique_ptr<Env> wrap_env(new CompositeEnvWrapper(env_, wrap_fs));
-  BlockBasedTableOptions table_options;
-  table_options.block_cache = NewCache(250 * 1024, 20 * 1024, 256 * 1024,
-                                       TieredAdmissionPolicy::kAdmPolicyAuto,
-                                       /*ready_before_wait=*/true);
-  table_options.block_size = 4 * 1024;
-  table_options.cache_index_and_filter_blocks = false;
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.compression = kLZ4Compression;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  options.statistics = CreateDBStatistics();
-  options.env = wrap_env.get();
-
-  options.paranoid_file_checks = false;
-  DestroyAndReopen(options);
-  Random rnd(301);
-  const int N = 256;
-  for (int i = 0; i < N; i++) {
-    std::string p_v;
-    test::CompressibleString(&rnd, 0.5, 1007, &p_v);
-    ASSERT_OK(Put(Key(i), p_v));
-  }
-
-  ASSERT_OK(Flush());
-
-  std::vector<std::string> keys;
-  std::vector<std::string> values;
-
-  keys.push_back(Key(0));
-  keys.push_back(Key(4));
-  keys.push_back(Key(8));
-  values = MultiGet(keys, /*snapshot=*/nullptr, /*async=*/true);
-  ASSERT_EQ(values.size(), keys.size());
-  for (const auto& value : values) {
-    ASSERT_EQ(1007, value.size());
-  }
-  ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 3u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 3u);
-  ASSERT_EQ(nvm_sec_cache()->num_hits(), 0u);
-
-  std::string v = Get(Key(12));
-  ASSERT_EQ(1007, v.size());
-  ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 4u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 4u);
-  ASSERT_EQ(options.statistics->getTickerCount(BLOCK_CACHE_MISS), 4u);
-
-  Close();
-  Destroy(options);
-}
-
 INSTANTIATE_TEST_CASE_P(
     DBTieredAdmPolicyTest, DBTieredAdmPolicyTest,
     ::testing::Values(TieredAdmissionPolicy::kAdmPolicyAuto,
                       TieredAdmissionPolicy::kAdmPolicyPlaceholder,
-                      TieredAdmissionPolicy::kAdmPolicyAllowCacheHits,
-                      TieredAdmissionPolicy::kAdmPolicyAllowAll));
+                      TieredAdmissionPolicy::kAdmPolicyAllowCacheHits));
 
 }  // namespace ROCKSDB_NAMESPACE
 

cache/typed_cache.h

@@ -155,7 +155,7 @@ class BasicTypedCacheInterface : public BaseCacheInterface<CachePtr>,
   using BaseCacheInterface<CachePtr>::BaseCacheInterface;
   struct TypedAsyncLookupHandle : public Cache::AsyncLookupHandle {
     TypedHandle* Result() {
-      return static_cast<TypedHandle*>(Cache::AsyncLookupHandle::Result());
+      return reinterpret_cast<TypedHandle*>(Cache::AsyncLookupHandle::Result());
     }
   };
 
@@ -169,7 +169,8 @@ class BasicTypedCacheInterface : public BaseCacheInterface<CachePtr>,
   }
 
   inline TypedHandle* Lookup(const Slice& key, Statistics* stats = nullptr) {
-    return static_cast<TypedHandle*>(this->cache_->BasicLookup(key, stats));
+    return reinterpret_cast<TypedHandle*>(
+        this->cache_->BasicLookup(key, stats));
   }
 
   inline void StartAsyncLookup(TypedAsyncLookupHandle& async_handle) {
@@ -346,7 +347,7 @@ class FullTypedCacheInterface
       Priority priority = Priority::LOW, Statistics* stats = nullptr,
       CacheTier lowest_used_cache_tier = CacheTier::kNonVolatileBlockTier) {
     if (lowest_used_cache_tier > CacheTier::kVolatileTier) {
-      return static_cast<TypedHandle*>(this->cache_->Lookup(
+      return reinterpret_cast<TypedHandle*>(this->cache_->Lookup(
           key, GetFullHelper(), create_context, priority, stats));
     } else {
       return BasicTypedCacheInterface<TValue, kRole, CachePtr>::Lookup(key,

cmake/modules/Findzstd.cmake

@@ -1,29 +1,29 @@
 # - Find zstd
 # Find the zstd compression library and includes
 #
-# ZSTD_INCLUDE_DIRS - where to find zstd.h, etc.
-# ZSTD_LIBRARIES - List of libraries when using zstd.
-# ZSTD_FOUND - True if zstd found.
+# zstd_INCLUDE_DIRS - where to find zstd.h, etc.
+# zstd_LIBRARIES - List of libraries when using zstd.
+# zstd_FOUND - True if zstd found.
 
-find_path(ZSTD_INCLUDE_DIRS
+find_path(zstd_INCLUDE_DIRS
   NAMES zstd.h
   HINTS ${zstd_ROOT_DIR}/include)
 
-find_library(ZSTD_LIBRARIES
+find_library(zstd_LIBRARIES
   NAMES zstd
   HINTS ${zstd_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(zstd DEFAULT_MSG ZSTD_LIBRARIES ZSTD_INCLUDE_DIRS)
+find_package_handle_standard_args(zstd DEFAULT_MSG zstd_LIBRARIES zstd_INCLUDE_DIRS)
 
 mark_as_advanced(
-  ZSTD_LIBRARIES
-  ZSTD_INCLUDE_DIRS)
+  zstd_LIBRARIES
+  zstd_INCLUDE_DIRS)
 
-if(ZSTD_FOUND AND NOT (TARGET zstd::zstd))
+if(zstd_FOUND AND NOT (TARGET zstd::zstd))
   add_library (zstd::zstd UNKNOWN IMPORTED)
   set_target_properties(zstd::zstd
     PROPERTIES
-      IMPORTED_LOCATION ${ZSTD_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${ZSTD_INCLUDE_DIRS})
+      IMPORTED_LOCATION ${zstd_LIBRARIES}
+      INTERFACE_INCLUDE_DIRECTORIES ${zstd_INCLUDE_DIRS})
 endif()

coverage/parse_gcov_output.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
+from __future__ import print_function
 
 import optparse
 import re
@@ -108,11 +109,11 @@ def report_coverage():
 
     # Check if we need to display coverage info for interested files.
     if len(interested_files):
-        per_file_coverage = {
-            fname: per_file_coverage[fname]
+        per_file_coverage = dict(
+            (fname, per_file_coverage[fname])
             for fname in interested_files
             if fname in per_file_coverage
-        }
+        )
         # If we only interested in several files, it makes no sense to report
         # the total_coverage
         total_coverage = None

db/arena_wrapped_db_iter.cc

@@ -43,68 +43,62 @@ void ArenaWrappedDBIter::Init(
     Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const Version* version,
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iteration,
-    uint64_t version_number, ReadCallback* read_callback,
-    ColumnFamilyHandleImpl* cfh, bool expose_blob_index, bool allow_refresh) {
+    uint64_t version_number, ReadCallback* read_callback, DBImpl* db_impl,
+    ColumnFamilyData* cfd, bool expose_blob_index, bool allow_refresh) {
+  auto mem = arena_.AllocateAligned(sizeof(DBIter));
+  db_iter_ =
+      new (mem) DBIter(env, read_options, ioptions, mutable_cf_options,
+                       ioptions.user_comparator, /* iter */ nullptr, version,
+                       sequence, true, max_sequential_skip_in_iteration,
+                       read_callback, db_impl, cfd, expose_blob_index);
+  sv_number_ = version_number;
   read_options_ = read_options;
+  allow_refresh_ = allow_refresh;
+  memtable_range_tombstone_iter_ = nullptr;
+
   if (!CheckFSFeatureSupport(env->GetFileSystem().get(),
                              FSSupportedOps::kAsyncIO)) {
     read_options_.async_io = false;
   }
-  read_options_.total_order_seek |= ioptions.prefix_seek_opt_in_only;
-
-  auto mem = arena_.AllocateAligned(sizeof(DBIter));
-  db_iter_ = new (mem) DBIter(env, read_options_, ioptions, mutable_cf_options,
-                              ioptions.user_comparator,
-                              /* iter */ nullptr, version, sequence, true,
-                              max_sequential_skip_in_iteration, read_callback,
-                              cfh, expose_blob_index);
-
-  sv_number_ = version_number;
-  allow_refresh_ = allow_refresh;
-  memtable_range_tombstone_iter_ = nullptr;
 }
 
 Status ArenaWrappedDBIter::Refresh() { return Refresh(nullptr); }
 
 Status ArenaWrappedDBIter::Refresh(const Snapshot* snapshot) {
-  if (cfh_ == nullptr || !allow_refresh_) {
+  if (cfd_ == nullptr || db_impl_ == nullptr || !allow_refresh_) {
     return Status::NotSupported("Creating renew iterator is not allowed.");
   }
   assert(db_iter_ != nullptr);
-  auto cfd = cfh_->cfd();
-  auto db_impl = cfh_->db();
-
   // TODO(yiwu): For last_seq_same_as_publish_seq_==false, this is not the
   // correct behavior. Will be corrected automatically when we take a snapshot
   // here for the case of WritePreparedTxnDB.
-  uint64_t cur_sv_number = cfd->GetSuperVersionNumber();
+  uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
   // If we recreate a new internal iterator below (NewInternalIterator()),
   // we will pass in read_options_. We need to make sure it
   // has the right snapshot.
   read_options_.snapshot = snapshot;
   TEST_SYNC_POINT("ArenaWrappedDBIter::Refresh:1");
   TEST_SYNC_POINT("ArenaWrappedDBIter::Refresh:2");
-
   auto reinit_internal_iter = [&]() {
     Env* env = db_iter_->env();
     db_iter_->~DBIter();
     arena_.~Arena();
     new (&arena_) Arena();
 
-    SuperVersion* sv = cfd->GetReferencedSuperVersion(db_impl);
+    SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
     assert(sv->version_number >= cur_sv_number);
-    SequenceNumber read_seq = GetSeqNum(db_impl, snapshot);
+    SequenceNumber read_seq = GetSeqNum(db_impl_, snapshot);
     if (read_callback_) {
       read_callback_->Refresh(read_seq);
     }
-    Init(env, read_options_, *(cfd->ioptions()), sv->mutable_cf_options,
+    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
          sv->current, read_seq,
          sv->mutable_cf_options.max_sequential_skip_in_iterations,
-         sv->version_number, read_callback_, cfh_, expose_blob_index_,
+         sv->version_number, read_callback_, db_impl_, cfd_, expose_blob_index_,
          allow_refresh_);
 
-    InternalIterator* internal_iter = db_impl->NewInternalIterator(
-        read_options_, cfd, sv, &arena_, read_seq,
+    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
+        read_options_, cfd_, sv, &arena_, read_seq,
         /* allow_unprepared_value */ true, /* db_iter */ this);
     SetIterUnderDBIter(internal_iter);
   };
@@ -113,10 +107,10 @@ Status ArenaWrappedDBIter::Refresh(const Snapshot* snapshot) {
       reinit_internal_iter();
       break;
     } else {
-      SequenceNumber read_seq = GetSeqNum(db_impl, snapshot);
+      SequenceNumber read_seq = GetSeqNum(db_impl_, snapshot);
       // Refresh range-tombstones in MemTable
       if (!read_options_.ignore_range_deletions) {
-        SuperVersion* sv = cfd->GetThreadLocalSuperVersion(db_impl);
+        SuperVersion* sv = cfd_->GetThreadLocalSuperVersion(db_impl_);
         TEST_SYNC_POINT_CALLBACK("ArenaWrappedDBIter::Refresh:SV", nullptr);
         auto t = sv->mem->NewRangeTombstoneIterator(
             read_options_, read_seq, false /* immutable_memtable */);
@@ -129,28 +123,28 @@ Status ArenaWrappedDBIter::Refresh(const Snapshot* snapshot) {
           // will be freed during db_iter destruction there.
           if (memtable_range_tombstone_iter_) {
             assert(!*memtable_range_tombstone_iter_ ||
-                   sv_number_ != cfd->GetSuperVersionNumber());
+                   sv_number_ != cfd_->GetSuperVersionNumber());
           }
           delete t;
         } else {  // current mutable memtable has range tombstones
           if (!memtable_range_tombstone_iter_) {
             delete t;
-            db_impl->ReturnAndCleanupSuperVersion(cfd, sv);
+            db_impl_->ReturnAndCleanupSuperVersion(cfd_, sv);
             // The memtable under DBIter did not have range tombstone before
             // refresh.
             reinit_internal_iter();
             break;
           } else {
-            *memtable_range_tombstone_iter_ =
-                std::make_unique<TruncatedRangeDelIterator>(
-                    std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
-                    &cfd->internal_comparator(), nullptr, nullptr);
+            delete *memtable_range_tombstone_iter_;
+            *memtable_range_tombstone_iter_ = new TruncatedRangeDelIterator(
+                std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
+                &cfd_->internal_comparator(), nullptr, nullptr);
           }
         }
-        db_impl->ReturnAndCleanupSuperVersion(cfd, sv);
+        db_impl_->ReturnAndCleanupSuperVersion(cfd_, sv);
       }
       // Check again if the latest super version number is changed
-      uint64_t latest_sv_number = cfd->GetSuperVersionNumber();
+      uint64_t latest_sv_number = cfd_->GetSuperVersionNumber();
       if (latest_sv_number != cur_sv_number) {
         // If the super version number is changed after refreshing,
         // fallback to Re-Init the InternalIterator
@@ -169,14 +163,14 @@ ArenaWrappedDBIter* NewArenaWrappedDbIterator(
     Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const Version* version,
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
-    uint64_t version_number, ReadCallback* read_callback,
-    ColumnFamilyHandleImpl* cfh, bool expose_blob_index, bool allow_refresh) {
+    uint64_t version_number, ReadCallback* read_callback, DBImpl* db_impl,
+    ColumnFamilyData* cfd, bool expose_blob_index, bool allow_refresh) {
   ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
   iter->Init(env, read_options, ioptions, mutable_cf_options, version, sequence,
              max_sequential_skip_in_iterations, version_number, read_callback,
-             cfh, expose_blob_index, allow_refresh);
-  if (cfh != nullptr && allow_refresh) {
-    iter->StoreRefreshInfo(cfh, read_callback, expose_blob_index);
+             db_impl, cfd, expose_blob_index, allow_refresh);
+  if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
+    iter->StoreRefreshInfo(db_impl, cfd, read_callback, expose_blob_index);
   }
 
   return iter;

db/arena_wrapped_db_iter.h

@@ -55,8 +55,7 @@ class ArenaWrappedDBIter : public Iterator {
     db_iter_->SetIter(iter);
   }
 
-  void SetMemtableRangetombstoneIter(
-      std::unique_ptr<TruncatedRangeDelIterator>* iter) {
+  void SetMemtableRangetombstoneIter(TruncatedRangeDelIterator** iter) {
     memtable_range_tombstone_iter_ = iter;
   }
 
@@ -83,21 +82,20 @@ class ArenaWrappedDBIter : public Iterator {
   Status Refresh() override;
   Status Refresh(const Snapshot*) override;
 
-  bool PrepareValue() override { return db_iter_->PrepareValue(); }
-
   void Init(Env* env, const ReadOptions& read_options,
             const ImmutableOptions& ioptions,
             const MutableCFOptions& mutable_cf_options, const Version* version,
             const SequenceNumber& sequence,
             uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-            ReadCallback* read_callback, ColumnFamilyHandleImpl* cfh,
+            ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
             bool expose_blob_index, bool allow_refresh);
 
   // Store some parameters so we can refresh the iterator at a later point
   // with these same params
-  void StoreRefreshInfo(ColumnFamilyHandleImpl* cfh,
+  void StoreRefreshInfo(DBImpl* db_impl, ColumnFamilyData* cfd,
                         ReadCallback* read_callback, bool expose_blob_index) {
-    cfh_ = cfh;
+    db_impl_ = db_impl;
+    cfd_ = cfd;
     read_callback_ = read_callback;
     expose_blob_index_ = expose_blob_index;
   }
@@ -106,25 +104,25 @@ class ArenaWrappedDBIter : public Iterator {
   DBIter* db_iter_ = nullptr;
   Arena arena_;
   uint64_t sv_number_;
-  ColumnFamilyHandleImpl* cfh_ = nullptr;
+  ColumnFamilyData* cfd_ = nullptr;
+  DBImpl* db_impl_ = nullptr;
   ReadOptions read_options_;
   ReadCallback* read_callback_;
   bool expose_blob_index_ = false;
   bool allow_refresh_ = true;
   // If this is nullptr, it means the mutable memtable does not contain range
   // tombstone when added under this DBIter.
-  std::unique_ptr<TruncatedRangeDelIterator>* memtable_range_tombstone_iter_ =
-      nullptr;
+  TruncatedRangeDelIterator** memtable_range_tombstone_iter_ = nullptr;
 };
 
 // Generate the arena wrapped iterator class.
-// `cfh` is used for reneweal. If left null, renewal will not
+// `db_impl` and `cfd` are used for reneweal. If left null, renewal will not
 // be supported.
-ArenaWrappedDBIter* NewArenaWrappedDbIterator(
+extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
     Env* env, const ReadOptions& read_options, const ImmutableOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const Version* version,
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
     uint64_t version_number, ReadCallback* read_callback,
-    ColumnFamilyHandleImpl* cfh = nullptr, bool expose_blob_index = false,
-    bool allow_refresh = true);
+    DBImpl* db_impl = nullptr, ColumnFamilyData* cfd = nullptr,
+    bool expose_blob_index = false, bool allow_refresh = true);
 }  // namespace ROCKSDB_NAMESPACE

db/attribute_group_iterator_impl.cc

@@ -1,20 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/attribute_group_iterator_impl.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-const AttributeGroups kNoAttributeGroups;
-const IteratorAttributeGroups kNoIteratorAttributeGroups;
-
-void AttributeGroupIteratorImpl::AddToAttributeGroups(
-    const autovector<MultiCfIteratorInfo>& items) {
-  for (const auto& item : items) {
-    attribute_groups_.emplace_back(item.cfh, &item.iterator->columns());
-  }
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/attribute_group_iterator_impl.h

@@ -1,108 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#pragma once
-
-#include "db/multi_cf_iterator_impl.h"
-#include "rocksdb/attribute_groups.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class AttributeGroupIteratorImpl : public AttributeGroupIterator {
- public:
-  AttributeGroupIteratorImpl(
-      const ReadOptions& read_options, const Comparator* comparator,
-      std::vector<std::pair<ColumnFamilyHandle*, std::unique_ptr<Iterator>>>&&
-          cfh_iter_pairs)
-      : impl_(read_options, comparator, std::move(cfh_iter_pairs),
-              ResetFunc(this), PopulateFunc(this)) {}
-  ~AttributeGroupIteratorImpl() override {}
-
-  // No copy allowed
-  AttributeGroupIteratorImpl(const AttributeGroupIteratorImpl&) = delete;
-  AttributeGroupIteratorImpl& operator=(const AttributeGroupIteratorImpl&) =
-      delete;
-
-  bool Valid() const override { return impl_.Valid(); }
-  void SeekToFirst() override { impl_.SeekToFirst(); }
-  void SeekToLast() override { impl_.SeekToLast(); }
-  void Seek(const Slice& target) override { impl_.Seek(target); }
-  void SeekForPrev(const Slice& target) override { impl_.SeekForPrev(target); }
-  void Next() override { impl_.Next(); }
-  void Prev() override { impl_.Prev(); }
-  Slice key() const override { return impl_.key(); }
-  Status status() const override { return impl_.status(); }
-
-  const IteratorAttributeGroups& attribute_groups() const override {
-    assert(Valid());
-    return attribute_groups_;
-  }
-
-  void Reset() { attribute_groups_.clear(); }
-
-  bool PrepareValue() override { return impl_.PrepareValue(); }
-
- private:
-  class ResetFunc {
-   public:
-    explicit ResetFunc(AttributeGroupIteratorImpl* iter) : iter_(iter) {}
-
-    void operator()() const {
-      assert(iter_);
-      iter_->Reset();
-    }
-
-   private:
-    AttributeGroupIteratorImpl* iter_;
-  };
-
-  class PopulateFunc {
-   public:
-    explicit PopulateFunc(AttributeGroupIteratorImpl* iter) : iter_(iter) {}
-
-    void operator()(const autovector<MultiCfIteratorInfo>& items) const {
-      assert(iter_);
-      iter_->AddToAttributeGroups(items);
-    }
-
-   private:
-    AttributeGroupIteratorImpl* iter_;
-  };
-
-  MultiCfIteratorImpl<ResetFunc, PopulateFunc> impl_;
-  IteratorAttributeGroups attribute_groups_;
-  void AddToAttributeGroups(const autovector<MultiCfIteratorInfo>& items);
-};
-
-class EmptyAttributeGroupIterator : public AttributeGroupIterator {
- public:
-  explicit EmptyAttributeGroupIterator(const Status& s) : status_(s) {}
-  bool Valid() const override { return false; }
-  void Seek(const Slice& /*target*/) override {}
-  void SeekForPrev(const Slice& /*target*/) override {}
-  void SeekToFirst() override {}
-  void SeekToLast() override {}
-  void Next() override { assert(false); }
-  void Prev() override { assert(false); }
-  Slice key() const override {
-    assert(false);
-    return Slice();
-  }
-  Status status() const override { return status_; }
-
-  const IteratorAttributeGroups& attribute_groups() const override {
-    return kNoIteratorAttributeGroups;
-  }
-
- private:
-  Status status_;
-};
-
-inline std::unique_ptr<AttributeGroupIterator> NewAttributeGroupErrorIterator(
-    const Status& status) {
-  return std::make_unique<EmptyAttributeGroupIterator>(status);
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_builder.cc

@@ -34,9 +34,9 @@ BlobFileBuilder::BlobFileBuilder(
     VersionSet* versions, FileSystem* fs,
     const ImmutableOptions* immutable_options,
     const MutableCFOptions* mutable_cf_options, const FileOptions* file_options,
-    const WriteOptions* write_options, std::string db_id,
-    std::string db_session_id, int job_id, uint32_t column_family_id,
-    const std::string& column_family_name, Env::WriteLifeTimeHint write_hint,
+    std::string db_id, std::string db_session_id, int job_id,
+    uint32_t column_family_id, const std::string& column_family_name,
+    Env::IOPriority io_priority, Env::WriteLifeTimeHint write_hint,
     const std::shared_ptr<IOTracer>& io_tracer,
     BlobFileCompletionCallback* blob_callback,
     BlobFileCreationReason creation_reason,
@@ -44,18 +44,18 @@ BlobFileBuilder::BlobFileBuilder(
     std::vector<BlobFileAddition>* blob_file_additions)
     : BlobFileBuilder([versions]() { return versions->NewFileNumber(); }, fs,
                       immutable_options, mutable_cf_options, file_options,
-                      write_options, db_id, db_session_id, job_id,
-                      column_family_id, column_family_name, write_hint,
-                      io_tracer, blob_callback, creation_reason,
-                      blob_file_paths, blob_file_additions) {}
+                      db_id, db_session_id, job_id, column_family_id,
+                      column_family_name, io_priority, write_hint, io_tracer,
+                      blob_callback, creation_reason, blob_file_paths,
+                      blob_file_additions) {}
 
 BlobFileBuilder::BlobFileBuilder(
     std::function<uint64_t()> file_number_generator, FileSystem* fs,
     const ImmutableOptions* immutable_options,
     const MutableCFOptions* mutable_cf_options, const FileOptions* file_options,
-    const WriteOptions* write_options, std::string db_id,
-    std::string db_session_id, int job_id, uint32_t column_family_id,
-    const std::string& column_family_name, Env::WriteLifeTimeHint write_hint,
+    std::string db_id, std::string db_session_id, int job_id,
+    uint32_t column_family_id, const std::string& column_family_name,
+    Env::IOPriority io_priority, Env::WriteLifeTimeHint write_hint,
     const std::shared_ptr<IOTracer>& io_tracer,
     BlobFileCompletionCallback* blob_callback,
     BlobFileCreationReason creation_reason,
@@ -69,12 +69,12 @@ BlobFileBuilder::BlobFileBuilder(
       blob_compression_type_(mutable_cf_options->blob_compression_type),
       prepopulate_blob_cache_(mutable_cf_options->prepopulate_blob_cache),
       file_options_(file_options),
-      write_options_(write_options),
       db_id_(std::move(db_id)),
       db_session_id_(std::move(db_session_id)),
       job_id_(job_id),
       column_family_id_(column_family_id),
       column_family_name_(column_family_name),
+      io_priority_(io_priority),
       write_hint_(write_hint),
       io_tracer_(io_tracer),
       blob_callback_(blob_callback),
@@ -87,7 +87,6 @@ BlobFileBuilder::BlobFileBuilder(
   assert(fs_);
   assert(immutable_options_);
   assert(file_options_);
-  assert(write_options_);
   assert(blob_file_paths_);
   assert(blob_file_paths_->empty());
   assert(blob_file_additions_);
@@ -208,14 +207,14 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
   blob_file_paths_->emplace_back(std::move(blob_file_path));
 
   assert(file);
-  file->SetIOPriority(write_options_->rate_limiter_priority);
+  file->SetIOPriority(io_priority_);
   file->SetWriteLifeTimeHint(write_hint_);
   FileTypeSet tmp_set = immutable_options_->checksum_handoff_file_types;
   Statistics* const statistics = immutable_options_->stats;
   std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
       std::move(file), blob_file_paths_->back(), *file_options_,
       immutable_options_->clock, io_tracer_, statistics,
-      Histograms::BLOB_DB_BLOB_FILE_WRITE_MICROS, immutable_options_->listeners,
+      immutable_options_->listeners,
       immutable_options_->file_checksum_gen_factory.get(),
       tmp_set.Contains(FileType::kBlobFile), false));
 
@@ -232,7 +231,7 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
                        expiration_range);
 
   {
-    Status s = blob_log_writer->WriteHeader(*write_options_, header);
+    Status s = blob_log_writer->WriteHeader(header);
 
     TEST_SYNC_POINT_CALLBACK(
         "BlobFileBuilder::OpenBlobFileIfNeeded:WriteHeader", &s);
@@ -297,8 +296,7 @@ Status BlobFileBuilder::WriteBlobToFile(const Slice& key, const Slice& blob,
 
   uint64_t key_offset = 0;
 
-  Status s =
-      writer_->AddRecord(*write_options_, key, blob, &key_offset, blob_offset);
+  Status s = writer_->AddRecord(key, blob, &key_offset, blob_offset);
 
   TEST_SYNC_POINT_CALLBACK("BlobFileBuilder::WriteBlobToFile:AddRecord", &s);
 
@@ -323,8 +321,7 @@ Status BlobFileBuilder::CloseBlobFile() {
   std::string checksum_method;
   std::string checksum_value;
 
-  Status s = writer_->AppendFooter(*write_options_, footer, &checksum_method,
-                                   &checksum_value);
+  Status s = writer_->AppendFooter(footer, &checksum_method, &checksum_value);
 
   TEST_SYNC_POINT_CALLBACK("BlobFileBuilder::WriteBlobToFile:AppendFooter", &s);
 

db/blob/blob_file_builder.h

@@ -13,7 +13,6 @@
 #include "rocksdb/advanced_options.h"
 #include "rocksdb/compression_type.h"
 #include "rocksdb/env.h"
-#include "rocksdb/options.h"
 #include "rocksdb/rocksdb_namespace.h"
 #include "rocksdb/types.h"
 
@@ -37,11 +36,11 @@ class BlobFileBuilder {
   BlobFileBuilder(VersionSet* versions, FileSystem* fs,
                   const ImmutableOptions* immutable_options,
                   const MutableCFOptions* mutable_cf_options,
-                  const FileOptions* file_options,
-                  const WriteOptions* write_options, std::string db_id,
+                  const FileOptions* file_options, std::string db_id,
                   std::string db_session_id, int job_id,
                   uint32_t column_family_id,
                   const std::string& column_family_name,
+                  Env::IOPriority io_priority,
                   Env::WriteLifeTimeHint write_hint,
                   const std::shared_ptr<IOTracer>& io_tracer,
                   BlobFileCompletionCallback* blob_callback,
@@ -52,11 +51,11 @@ class BlobFileBuilder {
   BlobFileBuilder(std::function<uint64_t()> file_number_generator,
                   FileSystem* fs, const ImmutableOptions* immutable_options,
                   const MutableCFOptions* mutable_cf_options,
-                  const FileOptions* file_options,
-                  const WriteOptions* write_options, std::string db_id,
+                  const FileOptions* file_options, std::string db_id,
                   std::string db_session_id, int job_id,
                   uint32_t column_family_id,
                   const std::string& column_family_name,
+                  Env::IOPriority io_priority,
                   Env::WriteLifeTimeHint write_hint,
                   const std::shared_ptr<IOTracer>& io_tracer,
                   BlobFileCompletionCallback* blob_callback,
@@ -93,12 +92,12 @@ class BlobFileBuilder {
   CompressionType blob_compression_type_;
   PrepopulateBlobCache prepopulate_blob_cache_;
   const FileOptions* file_options_;
-  const WriteOptions* write_options_;
   const std::string db_id_;
   const std::string db_session_id_;
   int job_id_;
   uint32_t column_family_id_;
   std::string column_family_name_;
+  Env::IOPriority io_priority_;
   Env::WriteLifeTimeHint write_hint_;
   std::shared_ptr<IOTracer> io_tracer_;
   BlobFileCompletionCallback* blob_callback_;

db/blob/blob_file_builder_test.cc

@@ -43,7 +43,6 @@ class BlobFileBuilderTest : public testing::Test {
     mock_env_.reset(MockEnv::Create(Env::Default()));
     fs_ = mock_env_->GetFileSystem().get();
     clock_ = mock_env_->GetSystemClock().get();
-    write_options_.rate_limiter_priority = Env::IO_HIGH;
   }
 
   void VerifyBlobFile(uint64_t blob_file_number,
@@ -114,7 +113,6 @@ class BlobFileBuilderTest : public testing::Test {
   FileSystem* fs_;
   SystemClock* clock_;
   FileOptions file_options_;
-  WriteOptions write_options_;
 };
 
 TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
@@ -138,6 +136,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -145,8 +144,8 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 
@@ -222,6 +221,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -229,8 +229,8 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 
@@ -309,6 +309,7 @@ TEST_F(BlobFileBuilderTest, InlinedValues) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -316,8 +317,8 @@ TEST_F(BlobFileBuilderTest, InlinedValues) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 
@@ -363,6 +364,7 @@ TEST_F(BlobFileBuilderTest, Compression) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -370,8 +372,8 @@ TEST_F(BlobFileBuilderTest, Compression) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 
@@ -446,6 +448,7 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -453,8 +456,8 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 
@@ -525,6 +528,7 @@ TEST_F(BlobFileBuilderTest, Checksum) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -532,8 +536,8 @@ TEST_F(BlobFileBuilderTest, Checksum) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 
@@ -585,13 +589,11 @@ class BlobFileBuilderIOErrorTest
   BlobFileBuilderIOErrorTest() : sync_point_(GetParam()) {
     mock_env_.reset(MockEnv::Create(Env::Default()));
     fs_ = mock_env_->GetFileSystem().get();
-    write_options_.rate_limiter_priority = Env::IO_HIGH;
   }
 
   std::unique_ptr<Env> mock_env_;
   FileSystem* fs_;
   FileOptions file_options_;
-  WriteOptions write_options_;
   std::string sync_point_;
 };
 
@@ -624,6 +626,7 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {
   constexpr int job_id = 1;
   constexpr uint32_t column_family_id = 123;
   constexpr char column_family_name[] = "foobar";
+  constexpr Env::IOPriority io_priority = Env::IO_HIGH;
   constexpr Env::WriteLifeTimeHint write_hint = Env::WLTH_MEDIUM;
 
   std::vector<std::string> blob_file_paths;
@@ -631,8 +634,8 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {
 
   BlobFileBuilder builder(
       TestFileNumberGenerator(), fs_, &immutable_options, &mutable_cf_options,
-      &file_options_, &write_options_, "" /*db_id*/, "" /*db_session_id*/,
-      job_id, column_family_id, column_family_name, write_hint,
+      &file_options_, "" /*db_id*/, "" /*db_session_id*/, job_id,
+      column_family_id, column_family_name, io_priority, write_hint,
       nullptr /*IOTracer*/, nullptr /*BlobFileCompletionCallback*/,
       BlobFileCreationReason::kFlush, &blob_file_paths, &blob_file_additions);
 

db/blob/blob_file_cache.cc

@@ -42,7 +42,6 @@ Status BlobFileCache::GetBlobFileReader(
   assert(blob_file_reader);
   assert(blob_file_reader->IsEmpty());
 
-  // NOTE: sharing same Cache with table_cache
   const Slice key = GetSliceForKey(&blob_file_number);
 
   assert(cache_);
@@ -99,13 +98,4 @@ Status BlobFileCache::GetBlobFileReader(
   return Status::OK();
 }
 
-void BlobFileCache::Evict(uint64_t blob_file_number) {
-  // NOTE: sharing same Cache with table_cache
-  const Slice key = GetSliceForKey(&blob_file_number);
-
-  assert(cache_);
-
-  cache_.get()->Erase(key);
-}
-
 }  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_cache.h

@@ -36,15 +36,6 @@ class BlobFileCache {
                            uint64_t blob_file_number,
                            CacheHandleGuard<BlobFileReader>* blob_file_reader);
 
-  // Called when a blob file is obsolete to ensure it is removed from the cache
-  // to avoid effectively leaking the open file and assicated memory
-  void Evict(uint64_t blob_file_number);
-
-  // Used to identify cache entries for blob files (not normally useful)
-  static const Cache::CacheItemHelper* GetHelper() {
-    return CacheInterface::GetBasicHelper();
-  }
-
  private:
   using CacheInterface =
       BasicTypedCacheInterface<BlobFileReader, CacheEntryRole::kMisc>;

db/blob/blob_file_cache_test.cc

@@ -57,7 +57,7 @@ void WriteBlobFile(uint32_t column_family_id,
   BlobLogHeader header(column_family_id, kNoCompression, has_ttl,
                        expiration_range);
 
-  ASSERT_OK(blob_log_writer.WriteHeader(WriteOptions(), header));
+  ASSERT_OK(blob_log_writer.WriteHeader(header));
 
   constexpr char key[] = "key";
   constexpr char blob[] = "blob";
@@ -67,8 +67,7 @@ void WriteBlobFile(uint32_t column_family_id,
   uint64_t key_offset = 0;
   uint64_t blob_offset = 0;
 
-  ASSERT_OK(blob_log_writer.AddRecord(WriteOptions(), key, blob, &key_offset,
-                                      &blob_offset));
+  ASSERT_OK(blob_log_writer.AddRecord(key, blob, &key_offset, &blob_offset));
 
   BlobLogFooter footer;
   footer.blob_count = 1;
@@ -77,8 +76,8 @@ void WriteBlobFile(uint32_t column_family_id,
   std::string checksum_method;
   std::string checksum_value;
 
-  ASSERT_OK(blob_log_writer.AppendFooter(WriteOptions(), footer,
-                                         &checksum_method, &checksum_value));
+  ASSERT_OK(
+      blob_log_writer.AppendFooter(footer, &checksum_method, &checksum_value));
 }
 
 }  // anonymous namespace

db/blob/blob_file_reader_test.cc

@@ -63,7 +63,7 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
   BlobLogHeader header(column_family_id, compression, has_ttl,
                        expiration_range_header);
 
-  ASSERT_OK(blob_log_writer.WriteHeader(WriteOptions(), header));
+  ASSERT_OK(blob_log_writer.WriteHeader(header));
 
   std::vector<std::string> compressed_blobs(num);
   std::vector<Slice> blobs_to_write(num);
@@ -91,8 +91,7 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
 
   for (size_t i = 0; i < num; ++i) {
     uint64_t key_offset = 0;
-    ASSERT_OK(blob_log_writer.AddRecord(WriteOptions(), keys[i],
-                                        blobs_to_write[i], &key_offset,
+    ASSERT_OK(blob_log_writer.AddRecord(keys[i], blobs_to_write[i], &key_offset,
                                         &blob_offsets[i]));
   }
 
@@ -102,8 +101,8 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
 
   std::string checksum_method;
   std::string checksum_value;
-  ASSERT_OK(blob_log_writer.AppendFooter(WriteOptions(), footer,
-                                         &checksum_method, &checksum_value));
+  ASSERT_OK(
+      blob_log_writer.AppendFooter(footer, &checksum_method, &checksum_value));
 }
 
 // Creates a test blob file with a single blob in it. Note: this method
@@ -405,7 +404,7 @@ TEST_F(BlobFileReaderTest, CreateReaderAndGetBlob) {
 
     requests_buf[0] =
         BlobReadRequest(key_refs[0], blob_offsets[0], blob_sizes[0],
-                        kNoCompression, nullptr, statuses_buf.data());
+                        kNoCompression, nullptr, &statuses_buf[0]);
     requests_buf[1] =
         BlobReadRequest(key_refs[1], blob_offsets[1], blob_sizes[1] + 1,
                         kNoCompression, nullptr, &statuses_buf[1]);
@@ -474,7 +473,7 @@ TEST_F(BlobFileReaderTest, Malformed) {
     BlobLogHeader header(column_family_id, kNoCompression, has_ttl,
                          expiration_range);
 
-    ASSERT_OK(blob_log_writer.WriteHeader(WriteOptions(), header));
+    ASSERT_OK(blob_log_writer.WriteHeader(header));
   }
 
   constexpr HistogramImpl* blob_file_read_hist = nullptr;

db/blob/blob_log_writer.cc

@@ -33,49 +33,35 @@ BlobLogWriter::BlobLogWriter(std::unique_ptr<WritableFileWriter>&& dest,
 
 BlobLogWriter::~BlobLogWriter() = default;
 
-Status BlobLogWriter::Sync(const WriteOptions& write_options) {
+Status BlobLogWriter::Sync() {
   TEST_SYNC_POINT("BlobLogWriter::Sync");
 
   StopWatch sync_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_SYNC_MICROS);
-  IOOptions opts;
-  Status s = WritableFileWriter::PrepareIOOptions(write_options, opts);
-  if (s.ok()) {
-    s = dest_->Sync(opts, use_fsync_);
-  }
-  if (s.ok()) {
-    RecordTick(statistics_, BLOB_DB_BLOB_FILE_SYNCED);
-  }
+  Status s = dest_->Sync(use_fsync_);
+  RecordTick(statistics_, BLOB_DB_BLOB_FILE_SYNCED);
   return s;
 }
 
-Status BlobLogWriter::WriteHeader(const WriteOptions& write_options,
-                                  BlobLogHeader& header) {
+Status BlobLogWriter::WriteHeader(BlobLogHeader& header) {
   assert(block_offset_ == 0);
   assert(last_elem_type_ == kEtNone);
   std::string str;
   header.EncodeTo(&str);
 
-  IOOptions opts;
-  Status s = WritableFileWriter::PrepareIOOptions(write_options, opts);
-  if (s.ok()) {
-    s = dest_->Append(opts, Slice(str));
-  }
+  Status s = dest_->Append(Slice(str));
   if (s.ok()) {
     block_offset_ += str.size();
     if (do_flush_) {
-      s = dest_->Flush(opts);
+      s = dest_->Flush();
     }
   }
   last_elem_type_ = kEtFileHdr;
-  if (s.ok()) {
-    RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
-               BlobLogHeader::kSize);
-  }
+  RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
+             BlobLogHeader::kSize);
   return s;
 }
 
-Status BlobLogWriter::AppendFooter(const WriteOptions& write_options,
-                                   BlobLogFooter& footer,
+Status BlobLogWriter::AppendFooter(BlobLogFooter& footer,
                                    std::string* checksum_method,
                                    std::string* checksum_value) {
   assert(block_offset_ != 0);
@@ -89,17 +75,14 @@ Status BlobLogWriter::AppendFooter(const WriteOptions& write_options,
     s.PermitUncheckedError();
     return Status::IOError("Seen Error. Skip closing.");
   } else {
-    IOOptions opts;
-    s = WritableFileWriter::PrepareIOOptions(write_options, opts);
-    if (s.ok()) {
-      s = dest_->Append(opts, Slice(str));
-    }
+    s = dest_->Append(Slice(str));
     if (s.ok()) {
       block_offset_ += str.size();
-      s = Sync(write_options);
+
+      s = Sync();
 
       if (s.ok()) {
-        s = dest_->Close(opts);
+        s = dest_->Close();
 
         if (s.ok()) {
           assert(!!checksum_method == !!checksum_value);
@@ -128,15 +111,12 @@ Status BlobLogWriter::AppendFooter(const WriteOptions& write_options,
   }
 
   last_elem_type_ = kEtFileFooter;
-  if (s.ok()) {
-    RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
-               BlobLogFooter::kSize);
-  }
+  RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
+             BlobLogFooter::kSize);
   return s;
 }
 
-Status BlobLogWriter::AddRecord(const WriteOptions& write_options,
-                                const Slice& key, const Slice& val,
+Status BlobLogWriter::AddRecord(const Slice& key, const Slice& val,
                                 uint64_t expiration, uint64_t* key_offset,
                                 uint64_t* blob_offset) {
   assert(block_offset_ != 0);
@@ -145,13 +125,11 @@ Status BlobLogWriter::AddRecord(const WriteOptions& write_options,
   std::string buf;
   ConstructBlobHeader(&buf, key, val, expiration);
 
-  Status s =
-      EmitPhysicalRecord(write_options, buf, key, val, key_offset, blob_offset);
+  Status s = EmitPhysicalRecord(buf, key, val, key_offset, blob_offset);
   return s;
 }
 
-Status BlobLogWriter::AddRecord(const WriteOptions& write_options,
-                                const Slice& key, const Slice& val,
+Status BlobLogWriter::AddRecord(const Slice& key, const Slice& val,
                                 uint64_t* key_offset, uint64_t* blob_offset) {
   assert(block_offset_ != 0);
   assert(last_elem_type_ == kEtFileHdr || last_elem_type_ == kEtRecord);
@@ -159,8 +137,7 @@ Status BlobLogWriter::AddRecord(const WriteOptions& write_options,
   std::string buf;
   ConstructBlobHeader(&buf, key, val, 0);
 
-  Status s =
-      EmitPhysicalRecord(write_options, buf, key, val, key_offset, blob_offset);
+  Status s = EmitPhysicalRecord(buf, key, val, key_offset, blob_offset);
   return s;
 }
 
@@ -173,34 +150,28 @@ void BlobLogWriter::ConstructBlobHeader(std::string* buf, const Slice& key,
   record.EncodeHeaderTo(buf);
 }
 
-Status BlobLogWriter::EmitPhysicalRecord(const WriteOptions& write_options,
-                                         const std::string& headerbuf,
+Status BlobLogWriter::EmitPhysicalRecord(const std::string& headerbuf,
                                          const Slice& key, const Slice& val,
                                          uint64_t* key_offset,
                                          uint64_t* blob_offset) {
-  IOOptions opts;
-  Status s = WritableFileWriter::PrepareIOOptions(write_options, opts);
+  StopWatch write_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_WRITE_MICROS);
+  Status s = dest_->Append(Slice(headerbuf));
   if (s.ok()) {
-    s = dest_->Append(opts, Slice(headerbuf));
+    s = dest_->Append(key);
   }
   if (s.ok()) {
-    s = dest_->Append(opts, key);
-  }
-  if (s.ok()) {
-    s = dest_->Append(opts, val);
+    s = dest_->Append(val);
   }
   if (do_flush_ && s.ok()) {
-    s = dest_->Flush(opts);
+    s = dest_->Flush();
   }
 
   *key_offset = block_offset_ + BlobLogRecord::kHeaderSize;
   *blob_offset = *key_offset + key.size();
   block_offset_ = *blob_offset + val.size();
   last_elem_type_ = kEtRecord;
-  if (s.ok()) {
-    RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
-               BlobLogRecord::kHeaderSize + key.size() + val.size());
-  }
+  RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
+             BlobLogRecord::kHeaderSize + key.size() + val.size());
   return s;
 }
 

db/blob/blob_log_writer.h

@@ -43,24 +43,20 @@ class BlobLogWriter {
   static void ConstructBlobHeader(std::string* buf, const Slice& key,
                                   const Slice& val, uint64_t expiration);
 
-  Status AddRecord(const WriteOptions& write_options, const Slice& key,
-                   const Slice& val, uint64_t* key_offset,
+  Status AddRecord(const Slice& key, const Slice& val, uint64_t* key_offset,
                    uint64_t* blob_offset);
 
-  Status AddRecord(const WriteOptions& write_options, const Slice& key,
-                   const Slice& val, uint64_t expiration, uint64_t* key_offset,
-                   uint64_t* blob_offset);
+  Status AddRecord(const Slice& key, const Slice& val, uint64_t expiration,
+                   uint64_t* key_offset, uint64_t* blob_offset);
 
-  Status EmitPhysicalRecord(const WriteOptions& write_options,
-                            const std::string& headerbuf, const Slice& key,
+  Status EmitPhysicalRecord(const std::string& headerbuf, const Slice& key,
                             const Slice& val, uint64_t* key_offset,
                             uint64_t* blob_offset);
 
-  Status AppendFooter(const WriteOptions& write_options, BlobLogFooter& footer,
-                      std::string* checksum_method,
+  Status AppendFooter(BlobLogFooter& footer, std::string* checksum_method,
                       std::string* checksum_value);
 
-  Status WriteHeader(const WriteOptions& write_options, BlobLogHeader& header);
+  Status WriteHeader(BlobLogHeader& header);
 
   WritableFileWriter* file() { return dest_.get(); }
 
@@ -68,7 +64,7 @@ class BlobLogWriter {
 
   uint64_t get_log_number() const { return log_number_; }
 
-  Status Sync(const WriteOptions& write_options);
+  Status Sync();
 
  private:
   std::unique_ptr<WritableFileWriter> dest_;

db/blob/blob_source.cc

@@ -20,24 +20,23 @@
 
 namespace ROCKSDB_NAMESPACE {
 
-BlobSource::BlobSource(const ImmutableOptions& immutable_options,
-                       const MutableCFOptions& mutable_cf_options,
+BlobSource::BlobSource(const ImmutableOptions* immutable_options,
                        const std::string& db_id,
                        const std::string& db_session_id,
                        BlobFileCache* blob_file_cache)
     : db_id_(db_id),
       db_session_id_(db_session_id),
-      statistics_(immutable_options.statistics.get()),
+      statistics_(immutable_options->statistics.get()),
       blob_file_cache_(blob_file_cache),
-      blob_cache_(immutable_options.blob_cache),
-      lowest_used_cache_tier_(immutable_options.lowest_used_cache_tier) {
+      blob_cache_(immutable_options->blob_cache),
+      lowest_used_cache_tier_(immutable_options->lowest_used_cache_tier) {
   auto bbto =
-      mutable_cf_options.table_factory->GetOptions<BlockBasedTableOptions>();
+      immutable_options->table_factory->GetOptions<BlockBasedTableOptions>();
   if (bbto &&
       bbto->cache_usage_options.options_overrides.at(CacheEntryRole::kBlobCache)
               .charged == CacheEntryRoleOptions::Decision::kEnabled) {
     blob_cache_ = SharedCacheInterface{std::make_shared<ChargedCache>(
-        immutable_options.blob_cache, bbto->block_cache)};
+        immutable_options->blob_cache, bbto->block_cache)};
   }
 }
 

db/blob/blob_source.h

@@ -21,7 +21,6 @@
 namespace ROCKSDB_NAMESPACE {
 
 struct ImmutableOptions;
-struct MutableCFOptions;
 class Status;
 class FilePrefetchBuffer;
 class Slice;
@@ -32,10 +31,7 @@ class Slice;
 // storage with minimal cost.
 class BlobSource {
  public:
-  // NOTE: db_id, db_session_id, and blob_file_cache are saved by reference or
-  // pointer.
-  BlobSource(const ImmutableOptions& immutable_options,
-             const MutableCFOptions& mutable_cf_options,
+  BlobSource(const ImmutableOptions* immutable_options,
              const std::string& db_id, const std::string& db_session_id,
              BlobFileCache* blob_file_cache);
 

db/blob/blob_source_test.cc

@@ -65,7 +65,7 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
   BlobLogHeader header(column_family_id, compression, has_ttl,
                        expiration_range_header);
 
-  ASSERT_OK(blob_log_writer.WriteHeader(WriteOptions(), header));
+  ASSERT_OK(blob_log_writer.WriteHeader(header));
 
   std::vector<std::string> compressed_blobs(num);
   std::vector<Slice> blobs_to_write(num);
@@ -93,8 +93,7 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
 
   for (size_t i = 0; i < num; ++i) {
     uint64_t key_offset = 0;
-    ASSERT_OK(blob_log_writer.AddRecord(WriteOptions(), keys[i],
-                                        blobs_to_write[i], &key_offset,
+    ASSERT_OK(blob_log_writer.AddRecord(keys[i], blobs_to_write[i], &key_offset,
                                         &blob_offsets[i]));
   }
 
@@ -104,8 +103,8 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
 
   std::string checksum_method;
   std::string checksum_value;
-  ASSERT_OK(blob_log_writer.AppendFooter(WriteOptions(), footer,
-                                         &checksum_method, &checksum_value));
+  ASSERT_OK(
+      blob_log_writer.AppendFooter(footer, &checksum_method, &checksum_value));
 }
 
 }  // anonymous namespace
@@ -148,7 +147,6 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -169,8 +167,8 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
 
   uint64_t file_size = BlobLogHeader::kSize;
   for (size_t i = 0; i < num_blobs; ++i) {
-    keys.emplace_back(key_strs[i]);
-    blobs.emplace_back(blob_strs[i]);
+    keys.push_back({key_strs[i]});
+    blobs.push_back({blob_strs[i]});
     file_size += BlobLogRecord::kHeaderSize + keys[i].size() + blobs[i].size();
   }
   file_size += BlobLogFooter::kSize;
@@ -194,8 +192,8 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -465,7 +463,6 @@ TEST_F(BlobSourceTest, GetCompressedBlobs) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -484,8 +481,8 @@ TEST_F(BlobSourceTest, GetCompressedBlobs) {
   std::vector<Slice> blobs;
 
   for (size_t i = 0; i < num_blobs; ++i) {
-    keys.emplace_back(key_strs[i]);
-    blobs.emplace_back(blob_strs[i]);
+    keys.push_back({key_strs[i]});
+    blobs.push_back({blob_strs[i]});
   }
 
   std::vector<uint64_t> blob_offsets(keys.size());
@@ -500,8 +497,8 @@ TEST_F(BlobSourceTest, GetCompressedBlobs) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, nullptr /*HistogramImpl*/, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -591,7 +588,6 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -613,8 +609,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
   uint64_t file_size = BlobLogHeader::kSize;
   uint64_t blob_value_bytes = 0;
   for (size_t i = 0; i < num_blobs; ++i) {
-    keys.emplace_back(key_strs[i]);
-    blobs.emplace_back(blob_strs[i]);
+    keys.push_back({key_strs[i]});
+    blobs.push_back({blob_strs[i]});
     blob_value_bytes += blobs[i].size();
     file_size += BlobLogRecord::kHeaderSize + keys[i].size() + blobs[i].size();
   }
@@ -647,8 +643,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -785,7 +781,6 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromCache) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -806,8 +801,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromCache) {
 
   uint64_t file_size = BlobLogHeader::kSize;
   for (size_t i = 0; i < num_blobs; ++i) {
-    keys.emplace_back(key_strs[i]);
-    blobs.emplace_back(blob_strs[i]);
+    keys.push_back({key_strs[i]});
+    blobs.push_back({blob_strs[i]});
     file_size += BlobLogRecord::kHeaderSize + keys[i].size() + blobs[i].size();
   }
   file_size += BlobLogFooter::kSize;
@@ -831,8 +826,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromCache) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -1109,7 +1104,6 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -1142,8 +1136,8 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
       backing_cache.get(), &immutable_options, &file_options, column_family_id,
       blob_file_read_hist, nullptr /*IOTracer*/));
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   CacheHandleGuard<BlobFileReader> file_reader;
   ReadOptions read_options;
@@ -1169,7 +1163,7 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
     ASSERT_OK(blob_source.GetBlob(read_options, keys[0], file_number,
                                   blob_offsets[0], file_size, blob_sizes[0],
                                   kNoCompression, nullptr /* prefetch_buffer */,
-                                  values.data(), nullptr /* bytes_read */));
+                                  &values[0], nullptr /* bytes_read */));
     // Release cache handle
     values[0].Reset();
 
@@ -1188,7 +1182,7 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
     ASSERT_OK(blob_source.GetBlob(read_options, keys[0], file_number,
                                   blob_offsets[0], file_size, blob_sizes[0],
                                   kNoCompression, nullptr /* prefetch_buffer */,
-                                  values.data(), nullptr /* bytes_read */));
+                                  &values[0], nullptr /* bytes_read */));
     ASSERT_EQ(values[0], blobs[0]);
     ASSERT_TRUE(
         blob_source.TEST_BlobInCache(file_number, file_size, blob_offsets[0]));
@@ -1268,7 +1262,7 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
       ASSERT_OK(blob_source.GetBlob(
           read_options, keys[0], file_number, blob_offsets[0], file_size,
           blob_sizes[0], kNoCompression, nullptr /* prefetch_buffer */,
-          values.data(), nullptr /* bytes_read */));
+          &values[0], nullptr /* bytes_read */));
       ASSERT_EQ(values[0], blobs[0]);
 
       // Release cache handle
@@ -1370,8 +1364,8 @@ class BlobSourceCacheReservationTest : public DBTestBase {
 
     blob_file_size_ = BlobLogHeader::kSize;
     for (size_t i = 0; i < kNumBlobs; ++i) {
-      keys_.emplace_back(key_strs_[i]);
-      blobs_.emplace_back(blob_strs_[i]);
+      keys_.push_back({key_strs_[i]});
+      blobs_.push_back({blob_strs_[i]});
       blob_file_size_ +=
           BlobLogRecord::kHeaderSize + keys_[i].size() + blobs_[i].size();
     }
@@ -1410,7 +1404,6 @@ TEST_F(BlobSourceCacheReservationTest, SimpleCacheReservation) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr ExpirationRange expiration_range;
 
@@ -1432,8 +1425,8 @@ TEST_F(BlobSourceCacheReservationTest, SimpleCacheReservation) {
           backing_cache.get(), &immutable_options, &file_options,
           kColumnFamilyId, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ConcurrentCacheReservationManager* cache_res_mgr =
       static_cast<ChargedCache*>(blob_source.GetBlobCache())
@@ -1525,8 +1518,6 @@ TEST_F(BlobSourceCacheReservationTest, IncreaseCacheReservation) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
-
   constexpr size_t blob_size = 24 << 10;  // 24KB
   for (size_t i = 0; i < kNumBlobs; ++i) {
     blob_file_size_ -= blobs_[i].size();  // old blob size
@@ -1554,8 +1545,8 @@ TEST_F(BlobSourceCacheReservationTest, IncreaseCacheReservation) {
           backing_cache.get(), &immutable_options, &file_options,
           kColumnFamilyId, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ConcurrentCacheReservationManager* cache_res_mgr =
       static_cast<ChargedCache*>(blob_source.GetBlobCache())

db/blob/db_blob_basic_test.cc

@@ -374,115 +374,6 @@ TEST_F(DBBlobBasicTest, IterateBlobsFromCachePinning) {
   }
 }
 
-TEST_F(DBBlobBasicTest, IterateBlobsAllowUnpreparedValue) {
-  Options options = GetDefaultOptions();
-  options.enable_blob_files = true;
-
-  Reopen(options);
-
-  constexpr size_t num_blobs = 5;
-  std::vector<std::string> keys;
-  std::vector<std::string> blobs;
-
-  for (size_t i = 0; i < num_blobs; ++i) {
-    keys.emplace_back("key" + std::to_string(i));
-    blobs.emplace_back("blob" + std::to_string(i));
-    ASSERT_OK(Put(keys[i], blobs[i]));
-  }
-
-  ASSERT_OK(Flush());
-
-  ReadOptions read_options;
-  read_options.allow_unprepared_value = true;
-
-  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-
-  {
-    size_t i = 0;
-
-    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_EQ(iter->value(), blobs[i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-
-  {
-    size_t i = 0;
-
-    for (iter->SeekToLast(); iter->Valid(); iter->Prev()) {
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_EQ(iter->value(), blobs[num_blobs - 1 - i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-
-  {
-    size_t i = 1;
-
-    for (iter->Seek(keys[i]); iter->Valid(); iter->Next()) {
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_EQ(iter->value(), blobs[i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-
-  {
-    size_t i = 1;
-
-    for (iter->SeekForPrev(keys[num_blobs - 1 - i]); iter->Valid();
-         iter->Prev()) {
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_EQ(iter->value(), blobs[num_blobs - 1 - i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-}
-
 TEST_F(DBBlobBasicTest, MultiGetBlobs) {
   constexpr size_t min_blob_size = 6;
 
@@ -527,8 +418,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobs) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -550,8 +441,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobs) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -621,8 +512,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromCache) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -643,8 +534,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromCache) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -662,8 +553,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromCache) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -683,8 +574,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromCache) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -867,8 +758,8 @@ TEST_F(DBBlobBasicTest, MultiGetWithDirectIO) {
     //
     // [offset=0, len=12288]
 
-    db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     SyncPoint::GetInstance()->DisableProcessing();
     SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -938,8 +829,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromMultipleFiles) {
   {
     std::array<PinnableSlice, kNumKeys> values;
     std::array<Status, kNumKeys> statuses;
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys, &keys[0],
+                  &values[0], &statuses[0]);
 
     for (size_t i = 0; i < kNumKeys; ++i) {
       ASSERT_OK(statuses[i]);
@@ -952,8 +843,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromMultipleFiles) {
   {
     std::array<PinnableSlice, kNumKeys> values;
     std::array<Status, kNumKeys> statuses;
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys, &keys[0],
+                  &values[0], &statuses[0]);
 
     for (size_t i = 0; i < kNumKeys; ++i) {
       ASSERT_TRUE(statuses[i].IsIncomplete());
@@ -967,8 +858,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromMultipleFiles) {
   {
     std::array<PinnableSlice, kNumKeys> values;
     std::array<Status, kNumKeys> statuses;
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys, &keys[0],
+                  &values[0], &statuses[0]);
 
     for (size_t i = 0; i < kNumKeys; ++i) {
       ASSERT_OK(statuses[i]);
@@ -981,8 +872,8 @@ TEST_F(DBBlobBasicTest, MultiGetBlobsFromMultipleFiles) {
   {
     std::array<PinnableSlice, kNumKeys> values;
     std::array<Status, kNumKeys> statuses;
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), kNumKeys, &keys[0],
+                  &values[0], &statuses[0]);
 
     for (size_t i = 0; i < kNumKeys; ++i) {
       ASSERT_OK(statuses[i]);
@@ -1291,30 +1182,6 @@ TEST_F(DBBlobBasicTest, GetMergeBlobWithPut) {
   ASSERT_EQ(Get("Key1"), "v1,v2,v3");
 }
 
-TEST_F(DBBlobBasicTest, GetMergeBlobFromMemoryTier) {
-  Options options = GetDefaultOptions();
-  options.merge_operator = MergeOperators::CreateStringAppendOperator();
-  options.enable_blob_files = true;
-  options.min_blob_size = 0;
-
-  Reopen(options);
-
-  ASSERT_OK(Put(Key(0), "v1"));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Merge(Key(0), "v2"));
-  ASSERT_OK(Flush());
-
-  // Regular `Get()` loads data block to cache.
-  std::string value;
-  ASSERT_OK(db_->Get(ReadOptions(), Key(0), &value));
-  ASSERT_EQ("v1,v2", value);
-
-  // Base value blob is still uncached, so an in-memory read will fail.
-  ReadOptions read_options;
-  read_options.read_tier = kBlockCacheTier;
-  ASSERT_TRUE(db_->Get(read_options, Key(0), &value).IsIncomplete());
-}
-
 TEST_F(DBBlobBasicTest, MultiGetMergeBlobWithPut) {
   constexpr size_t num_keys = 3;
 
@@ -1339,8 +1206,8 @@ TEST_F(DBBlobBasicTest, MultiGetMergeBlobWithPut) {
   std::array<PinnableSlice, num_keys> values;
   std::array<Status, num_keys> statuses;
 
-  db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys,
-                keys.data(), values.data(), statuses.data());
+  db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys, &keys[0],
+                &values[0], &statuses[0]);
 
   ASSERT_OK(statuses[0]);
   ASSERT_EQ(values[0], "v0_0,v0_1,v0_2");
@@ -1603,8 +1470,8 @@ TEST_P(DBBlobBasicIOErrorMultiGetTest, MultiGetBlobs_IOError) {
   });
   SyncPoint::GetInstance()->EnableProcessing();
 
-  db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys,
-                keys.data(), values.data(), statuses.data());
+  db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys, &keys[0],
+                &values[0], &statuses[0]);
 
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -1660,57 +1527,6 @@ TEST_P(DBBlobBasicIOErrorMultiGetTest, MultipleBlobFiles) {
   ASSERT_TRUE(statuses[1].IsIOError());
 }
 
-TEST_F(DBBlobBasicTest, MultiGetFindTable_IOError) {
-  // Repro test for a specific bug where `MultiGet()` would fail to open a table
-  // in `FindTable()` and then proceed to return raw blob handles for the other
-  // keys.
-  Options options = GetDefaultOptions();
-  options.enable_blob_files = true;
-  options.min_blob_size = 0;
-
-  Reopen(options);
-
-  // Force no table cache so every read will preload the SST file.
-  dbfull()->TEST_table_cache()->SetCapacity(0);
-
-  constexpr size_t num_keys = 2;
-
-  constexpr char key1[] = "key1";
-  constexpr char value1[] = "blob1";
-
-  ASSERT_OK(Put(key1, value1));
-  ASSERT_OK(Flush());
-
-  constexpr char key2[] = "key2";
-  constexpr char value2[] = "blob2";
-
-  ASSERT_OK(Put(key2, value2));
-  ASSERT_OK(Flush());
-
-  std::atomic<int> num_files_opened = 0;
-  // This test would be more realistic if we injected an `IOError` from the
-  // `FileSystem`
-  SyncPoint::GetInstance()->SetCallBack(
-      "TableCache::MultiGet:FindTable", [&](void* status) {
-        num_files_opened++;
-        if (num_files_opened == 2) {
-          Status* s = static_cast<Status*>(status);
-          *s = Status::IOError();
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  std::array<Slice, num_keys> keys{{key1, key2}};
-  std::array<PinnableSlice, num_keys> values;
-  std::array<Status, num_keys> statuses;
-  db_->MultiGet(ReadOptions(), db_->DefaultColumnFamily(), num_keys,
-                keys.data(), values.data(), statuses.data());
-
-  ASSERT_TRUE(statuses[0].IsIOError());
-  ASSERT_OK(statuses[1]);
-  ASSERT_EQ(value2, values[1]);
-}
-
 namespace {
 
 class ReadBlobCompactionFilter : public CompactionFilter {
@@ -1764,46 +1580,6 @@ TEST_P(DBBlobBasicIOErrorTest, CompactionFilterReadBlob_IOError) {
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
-TEST_P(DBBlobBasicIOErrorTest, IterateBlobsAllowUnpreparedValue_IOError) {
-  Options options;
-  options.env = fault_injection_env_.get();
-  options.enable_blob_files = true;
-
-  Reopen(options);
-
-  constexpr char key[] = "key";
-  constexpr char blob_value[] = "blob_value";
-
-  ASSERT_OK(Put(key, blob_value));
-
-  ASSERT_OK(Flush());
-
-  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
-    fault_injection_env_->SetFilesystemActive(false,
-                                              Status::IOError(sync_point_));
-  });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ReadOptions read_options;
-  read_options.allow_unprepared_value = true;
-
-  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-  iter->SeekToFirst();
-
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ(iter->key(), key);
-  ASSERT_TRUE(iter->value().empty());
-  ASSERT_OK(iter->status());
-
-  ASSERT_FALSE(iter->PrepareValue());
-
-  ASSERT_FALSE(iter->Valid());
-  ASSERT_TRUE(iter->status().IsIOError());
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 TEST_F(DBBlobBasicTest, WarmCacheWithBlobsDuringFlush) {
   Options options = GetDefaultOptions();
 
@@ -2044,7 +1820,7 @@ TEST_F(DBBlobBasicTest, GetEntityBlob) {
     std::array<Status, num_keys> statuses;
 
     db_->MultiGetEntity(ReadOptions(), db_->DefaultColumnFamily(), num_keys,
-                        keys.data(), results.data(), statuses.data());
+                        &keys[0], &results[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(results[0].columns(), expected_columns);
@@ -2141,8 +1917,8 @@ TEST_F(DBBlobWithTimestampTest, MultiGetBlobs) {
     std::array<PinnableSlice, num_keys> values;
     std::array<Status, num_keys> statuses;
 
-    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys,
-                  keys.data(), values.data(), statuses.data());
+    db_->MultiGet(read_options, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                  &values[0], &statuses[0]);
 
     ASSERT_OK(statuses[0]);
     ASSERT_EQ(values[0], first_value);
@@ -2225,8 +2001,8 @@ TEST_F(DBBlobWithTimestampTest, MultiGetMergeBlobWithPut) {
   std::array<PinnableSlice, num_keys> values;
   std::array<Status, num_keys> statuses;
 
-  db_->MultiGet(read_opts, db_->DefaultColumnFamily(), num_keys, keys.data(),
-                values.data(), statuses.data());
+  db_->MultiGet(read_opts, db_->DefaultColumnFamily(), num_keys, &keys[0],
+                &values[0], &statuses[0]);
 
   ASSERT_OK(statuses[0]);
   ASSERT_EQ(values[0], "v0_0,v0_1,v0_2");

db/blob/db_blob_index_test.cc

@@ -45,10 +45,10 @@ class DBBlobIndexTest : public DBTestBase {
   DBBlobIndexTest() : DBTestBase("db_blob_index_test", /*env_do_fsync=*/true) {}
 
   ColumnFamilyHandle* cfh() { return dbfull()->DefaultColumnFamily(); }
-  ColumnFamilyHandleImpl* cfh_impl() {
-    return static_cast_with_check<ColumnFamilyHandleImpl>(cfh());
+
+  ColumnFamilyData* cfd() {
+    return static_cast_with_check<ColumnFamilyHandleImpl>(cfh())->cfd();
   }
-  ColumnFamilyData* cfd() { return cfh_impl()->cfd(); }
 
   Status PutBlobIndex(WriteBatch* batch, const Slice& key,
                       const Slice& blob_index) {
@@ -96,9 +96,11 @@ class DBBlobIndexTest : public DBTestBase {
   }
 
   ArenaWrappedDBIter* GetBlobIterator() {
+    ColumnFamilyData* column_family = cfd();
     DBImpl* db_impl = dbfull();
     return db_impl->NewIteratorImpl(
-        ReadOptions(), cfh_impl(), cfd()->GetReferencedSuperVersion(db_impl),
+        ReadOptions(), column_family,
+        column_family->GetReferencedSuperVersion(db_impl),
         db_impl->GetLatestSequenceNumber(), nullptr /*read_callback*/,
         true /*expose_blob_index*/);
   }
@@ -323,7 +325,8 @@ TEST_F(DBBlobIndexTest, Iterate) {
 
   auto check_is_blob = [&](bool is_blob) {
     return [is_blob](Iterator* iterator) {
-      ASSERT_EQ(is_blob, static_cast<ArenaWrappedDBIter*>(iterator)->IsBlob());
+      ASSERT_EQ(is_blob,
+                reinterpret_cast<ArenaWrappedDBIter*>(iterator)->IsBlob());
     };
   };
 

db/blob/prefetch_buffer_collection.cc

@@ -11,10 +11,8 @@ FilePrefetchBuffer* PrefetchBufferCollection::GetOrCreatePrefetchBuffer(
     uint64_t file_number) {
   auto& prefetch_buffer = prefetch_buffers_[file_number];
   if (!prefetch_buffer) {
-    ReadaheadParams readahead_params;
-    readahead_params.initial_readahead_size = readahead_size_;
-    readahead_params.max_readahead_size = readahead_size_;
-    prefetch_buffer.reset(new FilePrefetchBuffer(readahead_params));
+    prefetch_buffer.reset(
+        new FilePrefetchBuffer(readahead_size_, readahead_size_));
   }
 
   return prefetch_buffer.get();

db/builder.cc

@@ -32,11 +32,9 @@
 #include "options/options_helper.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "rocksdb/file_system.h"
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
-#include "seqno_to_time_mapping.h"
 #include "table/block_based/block_based_table_builder.h"
 #include "table/format.h"
 #include "table/internal_iterator.h"
@@ -53,26 +51,27 @@ TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
   assert((tboptions.column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          tboptions.column_family_name.empty());
-  return tboptions.moptions.table_factory->NewTableBuilder(tboptions, file);
+  return tboptions.ioptions.table_factory->NewTableBuilder(tboptions, file);
 }
 
 Status BuildTable(
     const std::string& dbname, VersionSet* versions,
     const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
-    const FileOptions& file_options, TableCache* table_cache,
-    InternalIterator* iter,
+    const FileOptions& file_options, const ReadOptions& read_options,
+    TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
     FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
-    std::vector<SequenceNumber> snapshots, SequenceNumber earliest_snapshot,
+    std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     SequenceNumber job_snapshot, SnapshotChecker* snapshot_checker,
     bool paranoid_file_checks, InternalStats* internal_stats,
     IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
     BlobFileCreationReason blob_creation_reason,
-    UnownedPtr<const SeqnoToTimeMapping> seqno_to_time_mapping,
-    EventLogger* event_logger, int job_id, TableProperties* table_properties,
-    Env::WriteLifeTimeHint write_hint, const std::string* full_history_ts_low,
+    const SeqnoToTimeMapping& seqno_to_time_mapping, EventLogger* event_logger,
+    int job_id, const Env::IOPriority io_priority,
+    TableProperties* table_properties, Env::WriteLifeTimeHint write_hint,
+    const std::string* full_history_ts_low,
     BlobFileCompletionCallback* blob_callback, Version* version,
     uint64_t* num_input_entries, uint64_t* memtable_payload_bytes,
     uint64_t* memtable_garbage_bytes) {
@@ -83,8 +82,11 @@ Status BuildTable(
   auto& ioptions = tboptions.ioptions;
   // Reports the IOStats for flush for every following bytes.
   const size_t kReportFlushIOStatsEvery = 1048576;
-  OutputValidator output_validator(tboptions.internal_comparator,
-                                   /*enable_hash=*/paranoid_file_checks);
+  OutputValidator output_validator(
+      tboptions.internal_comparator,
+      /*enable_order_check=*/
+      mutable_cf_options.check_flush_compaction_key_order,
+      /*enable_hash=*/paranoid_file_checks);
   Status s;
   meta->fd.file_size = 0;
   iter->SeekToFirst();
@@ -162,11 +164,11 @@ Status BuildTable(
 
       table_file_created = true;
       FileTypeSet tmp_set = ioptions.checksum_handoff_file_types;
-      file->SetIOPriority(tboptions.write_options.rate_limiter_priority);
+      file->SetIOPriority(io_priority);
       file->SetWriteLifeTimeHint(write_hint);
       file_writer.reset(new WritableFileWriter(
           std::move(file), fname, file_options, ioptions.clock, io_tracer,
-          ioptions.stats, Histograms::SST_WRITE_MICROS, ioptions.listeners,
+          ioptions.stats, ioptions.listeners,
           ioptions.file_checksum_gen_factory.get(),
           tmp_set.Contains(FileType::kTableFile), false));
 
@@ -186,16 +188,15 @@ Status BuildTable(
          blob_file_additions)
             ? new BlobFileBuilder(
                   versions, fs, &ioptions, &mutable_cf_options, &file_options,
-                  &(tboptions.write_options), tboptions.db_id,
-                  tboptions.db_session_id, job_id, tboptions.column_family_id,
-                  tboptions.column_family_name, write_hint, io_tracer,
-                  blob_callback, blob_creation_reason, &blob_file_paths,
-                  blob_file_additions)
+                  tboptions.db_id, tboptions.db_session_id, job_id,
+                  tboptions.column_family_id, tboptions.column_family_name,
+                  io_priority, write_hint, io_tracer, blob_callback,
+                  blob_creation_reason, &blob_file_paths, blob_file_additions)
             : nullptr);
 
     const std::atomic<bool> kManualCompactionCanceledFalse{false};
     CompactionIterator c_iter(
-        iter, ucmp, &merge, kMaxSequenceNumber, &snapshots, earliest_snapshot,
+        iter, ucmp, &merge, kMaxSequenceNumber, &snapshots,
         earliest_write_conflict_snapshot, job_snapshot, snapshot_checker, env,
         ShouldReportDetailedTime(env, ioptions.stats),
         true /* internal key corruption is not ok */, range_del_agg.get(),
@@ -206,61 +207,44 @@ Status BuildTable(
         /*compaction=*/nullptr, compaction_filter.get(),
         /*shutting_down=*/nullptr, db_options.info_log, full_history_ts_low);
 
-    SequenceNumber smallest_preferred_seqno = kMaxSequenceNumber;
+    const size_t ts_sz = ucmp->timestamp_size();
+    const bool strip_timestamp =
+        ts_sz > 0 && !ioptions.persist_user_defined_timestamps;
+
     std::string key_after_flush_buf;
-    std::string value_buf;
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
-      ParsedInternalKey ikey = c_iter.ikey();
-      key_after_flush_buf.assign(key.data(), key.size());
-      Slice key_after_flush = key_after_flush_buf;
-      Slice value_after_flush = value;
-
-      if (ikey.type == kTypeValuePreferredSeqno) {
-        auto [unpacked_value, unix_write_time] =
-            ParsePackedValueWithWriteTime(value);
-        SequenceNumber preferred_seqno =
-            seqno_to_time_mapping
-                ? seqno_to_time_mapping->GetProximalSeqnoBeforeTime(
-                      unix_write_time)
-                : kMaxSequenceNumber;
-        if (preferred_seqno < ikey.sequence) {
-          value_after_flush =
-              PackValueAndSeqno(unpacked_value, preferred_seqno, &value_buf);
-          smallest_preferred_seqno =
-              std::min(smallest_preferred_seqno, preferred_seqno);
-        } else {
-          // Cannot get a useful preferred seqno, convert it to a kTypeValue.
-          UpdateInternalKey(&key_after_flush_buf, ikey.sequence, kTypeValue);
-          ikey = ParsedInternalKey(ikey.user_key, ikey.sequence, kTypeValue);
-          key_after_flush = key_after_flush_buf;
-          value_after_flush = ParsePackedValueForValue(value);
-        }
+      const ParsedInternalKey& ikey = c_iter.ikey();
+      Slice key_after_flush = key;
+      // If user defined timestamps will be stripped from user key after flush,
+      // the in memory version of the key act logically the same as one with a
+      // minimum timestamp. We update the timestamp here so file boundary and
+      // output validator, block builder all see the effect of the stripping.
+      if (strip_timestamp) {
+        key_after_flush_buf.clear();
+        ReplaceInternalKeyWithMinTimestamp(&key_after_flush_buf, key, ts_sz);
+        key_after_flush = key_after_flush_buf;
       }
 
       //  Generate a rolling 64-bit hash of the key and values
       //  Note :
       //  Here "key" integrates 'sequence_number'+'kType'+'user key'.
-      s = output_validator.Add(key_after_flush, value_after_flush);
+      s = output_validator.Add(key_after_flush, value);
       if (!s.ok()) {
         break;
       }
-      builder->Add(key_after_flush, value_after_flush);
+      builder->Add(key_after_flush, value);
 
-      s = meta->UpdateBoundaries(key_after_flush, value_after_flush,
-                                 ikey.sequence, ikey.type);
+      s = meta->UpdateBoundaries(key_after_flush, value, ikey.sequence,
+                                 ikey.type);
       if (!s.ok()) {
         break;
       }
 
       // TODO(noetzli): Update stats after flush, too.
-      // TODO(hx235): Replace `rate_limiter_priority` with `io_activity` for
-      // flush IO in repair when we have an `Env::IOActivity` enum for it
-      if ((tboptions.write_options.io_activity == Env::IOActivity::kFlush ||
-           tboptions.write_options.io_activity == Env::IOActivity::kDBOpen ||
-           tboptions.write_options.rate_limiter_priority == Env::IO_HIGH) &&
+      if (io_priority == Env::IO_HIGH &&
           IOSTATS(bytes_written) >= kReportFlushIOStatsEvery) {
         ThreadStatusUtil::SetThreadOperationProperty(
             ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
@@ -278,7 +262,8 @@ Status BuildTable(
       for (range_del_it->SeekToFirst(); range_del_it->Valid();
            range_del_it->Next()) {
         auto tombstone = range_del_it->Tombstone();
-        std::pair<InternalKey, Slice> kv = tombstone.Serialize();
+        auto kv = tombstone.Serialize();
+        // TODO(yuzhangyu): handle range deletion for UDT in memtables only.
         builder->Add(kv.first.Encode(), kv.second);
         InternalKey tombstone_end = tombstone.SerializeEndKey();
         meta->UpdateBoundariesForRange(kv.first, tombstone_end, tombstone.seq_,
@@ -290,7 +275,7 @@ Status BuildTable(
             SizeApproximationOptions approx_opts;
             approx_opts.files_size_error_margin = 0.1;
             meta->compensated_range_deletion_size += versions->ApproximateSize(
-                approx_opts, tboptions.read_options, version, kv.first.Encode(),
+                approx_opts, read_options, version, kv.first.Encode(),
                 tombstone_end.Encode(), 0 /* start_level */, -1 /* end_level */,
                 TableReaderCaller::kFlush);
           }
@@ -309,17 +294,12 @@ Status BuildTable(
     if (!s.ok() || empty) {
       builder->Abandon();
     } else {
-      SeqnoToTimeMapping relevant_mapping;
-      if (seqno_to_time_mapping) {
-        relevant_mapping.CopyFromSeqnoRange(
-            *seqno_to_time_mapping,
-            std::min(meta->fd.smallest_seqno, smallest_preferred_seqno),
-            meta->fd.largest_seqno);
-        relevant_mapping.SetCapacity(kMaxSeqnoTimePairsPerSST);
-        relevant_mapping.Enforce(tboptions.file_creation_time);
-      }
+      std::string seqno_to_time_mapping_str;
+      seqno_to_time_mapping.Encode(
+          seqno_to_time_mapping_str, meta->fd.smallest_seqno,
+          meta->fd.largest_seqno, meta->file_creation_time);
       builder->SetSeqnoTimeTableProperties(
-          relevant_mapping,
+          seqno_to_time_mapping_str,
           ioptions.compaction_style == CompactionStyle::kCompactionStyleFIFO
               ? meta->file_creation_time
               : meta->oldest_ancester_time);
@@ -366,16 +346,13 @@ Status BuildTable(
 
     // Finish and check for file errors
     TEST_SYNC_POINT("BuildTable:BeforeSyncTable");
-    IOOptions opts;
-    *io_status =
-        WritableFileWriter::PrepareIOOptions(tboptions.write_options, opts);
-    if (s.ok() && io_status->ok() && !empty) {
+    if (s.ok() && !empty) {
       StopWatch sw(ioptions.clock, ioptions.stats, TABLE_SYNC_MICROS);
-      *io_status = file_writer->Sync(opts, ioptions.use_fsync);
+      *io_status = file_writer->Sync(ioptions.use_fsync);
     }
     TEST_SYNC_POINT("BuildTable:BeforeCloseTableFile");
     if (s.ok() && io_status->ok() && !empty) {
-      *io_status = file_writer->Close(opts);
+      *io_status = file_writer->Close();
     }
     if (s.ok() && io_status->ok() && !empty) {
       // Add the checksum information to file metadata.
@@ -419,8 +396,9 @@ Status BuildTable(
       // No matter whether use_direct_io_for_flush_and_compaction is true,
       // the goal is to cache it here for further user reads.
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          tboptions.read_options, file_options, tboptions.internal_comparator,
-          *meta, nullptr /* range_del_agg */, mutable_cf_options, nullptr,
+          read_options, file_options, tboptions.internal_comparator, *meta,
+          nullptr /* range_del_agg */, mutable_cf_options.prefix_extractor,
+          nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : internal_stats->GetFileReadHist(0),
           TableReaderCaller::kFlush, /*arena=*/nullptr,
@@ -428,10 +406,12 @@ Status BuildTable(
           MaxFileSizeForL0MetaPin(mutable_cf_options),
           /*smallest_compaction_key=*/nullptr,
           /*largest_compaction_key*/ nullptr,
-          /*allow_unprepared_value*/ false));
+          /*allow_unprepared_value*/ false,
+          mutable_cf_options.block_protection_bytes_per_key));
       s = it->status();
       if (s.ok() && paranoid_file_checks) {
         OutputValidator file_validator(tboptions.internal_comparator,
+                                       /*enable_order_check=*/true,
                                        /*enable_hash=*/true);
         for (it->SeekToFirst(); it->Valid(); it->Next()) {
           // Generate a rolling 64-bit hash of the key and values
@@ -456,22 +436,8 @@ Status BuildTable(
     constexpr IODebugContext* dbg = nullptr;
 
     if (table_file_created) {
-      IOOptions opts;
-      Status prepare =
-          WritableFileWriter::PrepareIOOptions(tboptions.write_options, opts);
-      if (prepare.ok()) {
-        // FIXME: track file for "slow" deletion, e.g. into the
-        // VersionSet::obsolete_files_ pipeline
-        Status ignored = fs->DeleteFile(fname, opts, dbg);
-        ignored.PermitUncheckedError();
-      }
-      // Ensure we don't leak table cache entries when throwing away output
-      // files. (The usual logic in PurgeObsoleteFiles is not applicable because
-      // this function deletes the obsolete file itself, while they should
-      // probably go into the VersionSet::obsolete_files_ pipeline.)
-      TableCache::ReleaseObsolete(table_cache->get_cache().get(),
-                                  meta->fd.GetNumber(), nullptr /*handle*/,
-                                  mutable_cf_options.uncache_aggressiveness);
+      Status ignored = fs->DeleteFile(fname, IOOptions(), dbg);
+      ignored.PermitUncheckedError();
     }
 
     assert(blob_file_additions || blob_file_paths.empty());

db/builder.h

@@ -23,6 +23,7 @@
 #include "rocksdb/status.h"
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
+#include "table/scoped_arena_iterator.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -49,22 +50,23 @@ TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
 //
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown.
-Status BuildTable(
+extern Status BuildTable(
     const std::string& dbname, VersionSet* versions,
     const ImmutableDBOptions& db_options, const TableBuilderOptions& tboptions,
-    const FileOptions& file_options, TableCache* table_cache,
-    InternalIterator* iter,
+    const FileOptions& file_options, const ReadOptions& read_options,
+    TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
     FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
-    std::vector<SequenceNumber> snapshots, SequenceNumber earliest_snapshot,
+    std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     SequenceNumber job_snapshot, SnapshotChecker* snapshot_checker,
     bool paranoid_file_checks, InternalStats* internal_stats,
     IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
     BlobFileCreationReason blob_creation_reason,
-    UnownedPtr<const SeqnoToTimeMapping> seqno_to_time_mapping,
+    const SeqnoToTimeMapping& seqno_to_time_mapping,
     EventLogger* event_logger = nullptr, int job_id = 0,
+    const Env::IOPriority io_priority = Env::IO_HIGH,
     TableProperties* table_properties = nullptr,
     Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
     const std::string* full_history_ts_low = nullptr,

db/c.cc

@@ -46,7 +46,6 @@
 #include "rocksdb/utilities/write_batch_with_index.h"
 #include "rocksdb/write_batch.h"
 #include "rocksdb/write_buffer_manager.h"
-#include "util/stderr_logger.h"
 #include "utilities/merge_operators.h"
 
 using ROCKSDB_NAMESPACE::BackupEngine;
@@ -116,7 +115,6 @@ using ROCKSDB_NAMESPACE::Snapshot;
 using ROCKSDB_NAMESPACE::SstFileMetaData;
 using ROCKSDB_NAMESPACE::SstFileWriter;
 using ROCKSDB_NAMESPACE::Status;
-using ROCKSDB_NAMESPACE::StderrLogger;
 using ROCKSDB_NAMESPACE::TablePropertiesCollectorFactory;
 using ROCKSDB_NAMESPACE::Transaction;
 using ROCKSDB_NAMESPACE::TransactionDB;
@@ -231,7 +229,6 @@ struct rocksdb_livefiles_t {
 };
 struct rocksdb_column_family_handle_t {
   ColumnFamilyHandle* rep;
-  bool immortal;  /* only true for default cf */
 };
 struct rocksdb_column_family_metadata_t {
   ColumnFamilyMetaData rep;
@@ -447,7 +444,7 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
     size_t new_value_len;
     char* tmp_new_value = (*full_merge_)(
         state_, merge_in.key.data(), merge_in.key.size(), existing_value_data,
-        existing_value_len, operand_pointers.data(), operand_sizes.data(),
+        existing_value_len, &operand_pointers[0], &operand_sizes[0],
         static_cast<int>(n), &success, &new_value_len);
     merge_out->new_value.assign(tmp_new_value, new_value_len);
 
@@ -476,9 +473,8 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
     unsigned char success;
     size_t new_value_len;
     char* tmp_new_value = (*partial_merge_)(
-        state_, key.data(), key.size(), operand_pointers.data(),
-        operand_sizes.data(), static_cast<int>(operand_count), &success,
-        &new_value_len);
+        state_, key.data(), key.size(), &operand_pointers[0], &operand_sizes[0],
+        static_cast<int>(operand_count), &success, &new_value_len);
     new_value->assign(tmp_new_value, new_value_len);
 
     if (delete_value_ != nullptr) {
@@ -532,42 +528,6 @@ struct rocksdb_universal_compaction_options_t {
   ROCKSDB_NAMESPACE::CompactionOptionsUniversal* rep;
 };
 
-struct rocksdb_callback_logger_t : public Logger {
-  static const ssize_t STACK_BUFSZ = 512;
-  rocksdb_callback_logger_t(InfoLogLevel log_level,
-                            void (*logv_cb)(void*, unsigned, char*, size_t),
-                            void* priv)
-      : Logger(log_level), logv_cb_(logv_cb), priv_(priv) {}
-
-  using Logger::Logv;
-  void Logv(const InfoLogLevel level, const char* fmt, va_list ap0) override {
-    char stack_buf[STACK_BUFSZ];
-    char* alloc_buf = nullptr;
-    char* buf = stack_buf;
-    int len = 0;
-    va_list ap1;
-    if (!logv_cb_) return;
-    va_copy(ap1, ap0);
-    len = vsnprintf(buf, STACK_BUFSZ, fmt, ap0);
-    if (len <= 0)
-      goto cleanup;
-    else if (len >= STACK_BUFSZ) {
-      buf = alloc_buf = reinterpret_cast<char*>(malloc(len + 1));
-      if (!buf) goto cleanup;
-      len = vsnprintf(buf, len + 1, fmt, ap1);
-      if (len <= 0) goto cleanup;
-    }
-    logv_cb_(priv_, unsigned(level), buf, size_t(len));
-  cleanup:
-    va_end(ap1);
-    free(alloc_buf);
-  }
-
- private:
-  void (*logv_cb_)(void*, unsigned, char*, size_t) = nullptr;
-  void* priv_ = nullptr;
-};
-
 static bool SaveError(char** errptr, const Status& s) {
   assert(errptr != nullptr);
   if (s.ok()) {
@@ -583,7 +543,6 @@ static bool SaveError(char** errptr, const Status& s) {
   return true;
 }
 
-// Copies str to a new malloc()-ed buffer. The buffer is not NUL terminated.
 static char* CopyString(const std::string& str) {
   char* result = reinterpret_cast<char*>(malloc(sizeof(char) * str.size()));
   memcpy(result, str.data(), sizeof(char) * str.size());
@@ -925,9 +884,9 @@ rocksdb_t* rocksdb_open_and_trim_history(
     size_t trim_tslen, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
-    column_families.emplace_back(
+    column_families.push_back(ColumnFamilyDescriptor(
         std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
+        ColumnFamilyOptions(column_family_options[i]->rep)));
   }
 
   std::string trim_ts_(trim_ts, trim_tslen);
@@ -944,7 +903,6 @@ rocksdb_t* rocksdb_open_and_trim_history(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -959,9 +917,9 @@ rocksdb_t* rocksdb_open_column_families(
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
-    column_families.emplace_back(
+    column_families.push_back(ColumnFamilyDescriptor(
         std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
+        ColumnFamilyOptions(column_family_options[i]->rep)));
   }
 
   DB* db;
@@ -975,7 +933,6 @@ rocksdb_t* rocksdb_open_column_families(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -994,9 +951,9 @@ rocksdb_t* rocksdb_open_column_families_with_ttl(
   for (int i = 0; i < num_column_families; i++) {
     ttls_vec.push_back(ttls[i]);
 
-    column_families.emplace_back(
+    column_families.push_back(ColumnFamilyDescriptor(
         std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
+        ColumnFamilyOptions(column_family_options[i]->rep)));
   }
 
   ROCKSDB_NAMESPACE::DBWithTTL* db;
@@ -1011,7 +968,6 @@ rocksdb_t* rocksdb_open_column_families_with_ttl(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -1027,9 +983,9 @@ rocksdb_t* rocksdb_open_for_read_only_column_families(
     unsigned char error_if_wal_file_exists, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
-    column_families.emplace_back(
+    column_families.push_back(ColumnFamilyDescriptor(
         std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
+        ColumnFamilyOptions(column_family_options[i]->rep)));
   }
 
   DB* db;
@@ -1045,7 +1001,6 @@ rocksdb_t* rocksdb_open_for_read_only_column_families(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -1077,7 +1032,6 @@ rocksdb_t* rocksdb_open_as_secondary_column_families(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -1115,7 +1069,6 @@ rocksdb_column_family_handle_t* rocksdb_create_column_family(
   SaveError(errptr, db->rep->CreateColumnFamily(
                         ColumnFamilyOptions(column_family_options->rep),
                         std::string(column_family_name), &(handle->rep)));
-  handle->immortal = false;
   return handle;
 }
 
@@ -1126,7 +1079,7 @@ rocksdb_column_family_handle_t** rocksdb_create_column_families(
   std::vector<ColumnFamilyHandle*> handles;
   std::vector<std::string> names;
   for (int i = 0; i != num_column_families; ++i) {
-    names.emplace_back(column_family_names[i]);
+    names.push_back(std::string(column_family_names[i]));
   }
   SaveError(errptr, db->rep->CreateColumnFamilies(
                         ColumnFamilyOptions(column_family_options->rep), names,
@@ -1139,7 +1092,6 @@ rocksdb_column_family_handle_t** rocksdb_create_column_families(
   for (size_t i = 0; i != handles.size(); ++i) {
     c_handles[i] = new rocksdb_column_family_handle_t;
     c_handles[i]->rep = handles[i];
-    c_handles[i]->immortal = false;
   }
 
   return c_handles;
@@ -1159,7 +1111,6 @@ rocksdb_column_family_handle_t* rocksdb_create_column_family_with_ttl(
   SaveError(errptr, db_with_ttl->CreateColumnFamilyWithTtl(
                         ColumnFamilyOptions(column_family_options->rep),
                         std::string(column_family_name), &(handle->rep), ttl));
-  handle->immortal = false;
   return handle;
 }
 
@@ -1181,19 +1132,9 @@ char* rocksdb_column_family_handle_get_name(
   return CopyString(name);
 }
 
-rocksdb_column_family_handle_t* rocksdb_get_default_column_family_handle(
-    rocksdb_t* db) {
-  rocksdb_column_family_handle_t* handle = new rocksdb_column_family_handle_t;
-  handle->rep = db->rep->DefaultColumnFamily();
-  handle->immortal = true;
-  return handle;
-}
-
 void rocksdb_column_family_handle_destroy(
     rocksdb_column_family_handle_t* handle) {
-  if (!handle->immortal) {
-    delete handle->rep;
-  }
+  delete handle->rep;
   delete handle;
 }
 
@@ -1429,18 +1370,6 @@ char* rocksdb_get_cf_with_ts(rocksdb_t* db,
   return result;
 }
 
-char* rocksdb_get_db_identity(rocksdb_t* db, size_t* id_len) {
-  std::string identity_tmp;
-  Status s = db->rep->GetDbIdentity(identity_tmp);
-  if (!s.ok()) {
-    *id_len = 0;
-    return nullptr;
-  }
-
-  *id_len = identity_tmp.size();
-  return CopyString(identity_tmp);
-}
-
 void rocksdb_multi_get(rocksdb_t* db, const rocksdb_readoptions_t* options,
                        size_t num_keys, const char* const* keys_list,
                        const size_t* keys_list_sizes, char** values_list,
@@ -1756,11 +1685,6 @@ void rocksdb_release_snapshot(rocksdb_t* db,
   delete snapshot;
 }
 
-uint64_t rocksdb_snapshot_get_sequence_number(
-    const rocksdb_snapshot_t* snapshot) {
-  return snapshot->rep->GetSequenceNumber();
-}
-
 char* rocksdb_property_value(rocksdb_t* db, const char* propname) {
   std::string tmp;
   if (db->rep->GetProperty(Slice(propname), &tmp)) {
@@ -1838,26 +1762,6 @@ void rocksdb_approximate_sizes_cf(
   delete[] ranges;
 }
 
-extern ROCKSDB_LIBRARY_API void rocksdb_approximate_sizes_cf_with_flags(
-    rocksdb_t* db, rocksdb_column_family_handle_t* column_family,
-    int num_ranges, const char* const* range_start_key,
-    const size_t* range_start_key_len, const char* const* range_limit_key,
-    const size_t* range_limit_key_len, uint8_t include_flags, uint64_t* sizes,
-    char** errptr) {
-  Range* ranges = new Range[num_ranges];
-  for (int i = 0; i < num_ranges; i++) {
-    ranges[i].start = Slice(range_start_key[i], range_start_key_len[i]);
-    ranges[i].limit = Slice(range_limit_key[i], range_limit_key_len[i]);
-  }
-  Status s = db->rep->GetApproximateSizes(
-      column_family->rep, ranges, num_ranges, sizes,
-      static_cast<DB::SizeApproximationFlags>(include_flags));
-  if (!s.ok()) {
-    SaveError(errptr, s);
-  }
-  delete[] ranges;
-}
-
 void rocksdb_delete_file(rocksdb_t* db, const char* name) {
   db->rep->DeleteFile(name);
 }
@@ -1968,8 +1872,9 @@ void rocksdb_disable_file_deletions(rocksdb_t* db, char** errptr) {
   SaveError(errptr, db->rep->DisableFileDeletions());
 }
 
-void rocksdb_enable_file_deletions(rocksdb_t* db, char** errptr) {
-  SaveError(errptr, db->rep->EnableFileDeletions());
+void rocksdb_enable_file_deletions(rocksdb_t* db, unsigned char force,
+                                   char** errptr) {
+  SaveError(errptr, db->rep->EnableFileDeletions(force));
 }
 
 void rocksdb_destroy_db(const rocksdb_options_t* options, const char* name,
@@ -2035,10 +1940,6 @@ void rocksdb_iter_get_error(const rocksdb_iterator_t* iter, char** errptr) {
   SaveError(errptr, iter->rep->status());
 }
 
-void rocksdb_iter_refresh(const rocksdb_iterator_t* iter, char** errptr) {
-  SaveError(errptr, iter->rep->Refresh());
-}
-
 rocksdb_writebatch_t* rocksdb_writebatch_create() {
   return new rocksdb_writebatch_t;
 }
@@ -2050,15 +1951,6 @@ rocksdb_writebatch_t* rocksdb_writebatch_create_from(const char* rep,
   return b;
 }
 
-rocksdb_writebatch_t* rocksdb_writebatch_create_with_params(
-    size_t reserved_bytes, size_t max_bytes, size_t protection_bytes_per_key,
-    size_t default_cf_ts_sz) {
-  rocksdb_writebatch_t* b = new rocksdb_writebatch_t;
-  b->rep = WriteBatch(reserved_bytes, max_bytes, protection_bytes_per_key,
-                      default_cf_ts_sz);
-  return b;
-}
-
 void rocksdb_writebatch_destroy(rocksdb_writebatch_t* b) { delete b; }
 
 void rocksdb_writebatch_clear(rocksdb_writebatch_t* b) { b->rep.Clear(); }
@@ -2286,32 +2178,6 @@ class H : public WriteBatch::Handler {
   }
 };
 
-class HCF : public WriteBatch::Handler {
- public:
-  void* state_;
-  void (*put_cf_)(void*, uint32_t cfid, const char* k, size_t klen,
-                  const char* v, size_t vlen);
-  void (*deleted_cf_)(void*, uint32_t cfid, const char* k, size_t klen);
-  void (*merge_cf_)(void*, uint32_t cfid, const char* k, size_t klen,
-                    const char* v, size_t vlen);
-  Status PutCF(uint32_t column_family_id, const Slice& key,
-               const Slice& value) override {
-    (*put_cf_)(state_, column_family_id, key.data(), key.size(), value.data(),
-               value.size());
-    return Status::OK();
-  }
-  Status DeleteCF(uint32_t column_family_id, const Slice& key) override {
-    (*deleted_cf_)(state_, column_family_id, key.data(), key.size());
-    return Status::OK();
-  }
-  Status MergeCF(uint32_t column_family_id, const Slice& key,
-                 const Slice& value) override {
-    (*merge_cf_)(state_, column_family_id, key.data(), key.size(), value.data(),
-                 value.size());
-    return Status::OK();
-  }
-};
-
 void rocksdb_writebatch_iterate(rocksdb_writebatch_t* b, void* state,
                                 void (*put)(void*, const char* k, size_t klen,
                                             const char* v, size_t vlen),
@@ -2324,21 +2190,6 @@ void rocksdb_writebatch_iterate(rocksdb_writebatch_t* b, void* state,
   b->rep.Iterate(&handler);
 }
 
-void rocksdb_writebatch_iterate_cf(
-    rocksdb_writebatch_t* b, void* state,
-    void (*put_cf)(void*, uint32_t cfid, const char* k, size_t klen,
-                   const char* v, size_t vlen),
-    void (*deleted_cf)(void*, uint32_t cfid, const char* k, size_t klen),
-    void (*merge_cf)(void*, uint32_t cfid, const char* k, size_t klen,
-                     const char* v, size_t vlen)) {
-  HCF handler;
-  handler.state_ = state;
-  handler.put_cf_ = put_cf;
-  handler.deleted_cf_ = deleted_cf;
-  handler.merge_cf_ = merge_cf;
-  b->rep.Iterate(&handler);
-}
-
 const char* rocksdb_writebatch_data(rocksdb_writebatch_t* b, size_t* size) {
   *size = b->rep.GetDataSize();
   return b->rep.Data().c_str();
@@ -2365,35 +2216,6 @@ rocksdb_writebatch_wi_t* rocksdb_writebatch_wi_create(
   return b;
 }
 
-rocksdb_writebatch_wi_t* rocksdb_writebatch_wi_create_with_params(
-    rocksdb_comparator_t* backup_index_comparator, size_t reserved_bytes,
-    unsigned char overwrite_key, size_t max_bytes,
-    size_t protection_bytes_per_key) {
-  rocksdb_writebatch_wi_t* b = new rocksdb_writebatch_wi_t;
-  b->rep = new WriteBatchWithIndex(backup_index_comparator, reserved_bytes,
-                                   overwrite_key, max_bytes,
-                                   protection_bytes_per_key);
-  return b;
-}
-
-void rocksdb_writebatch_update_timestamps(
-    rocksdb_writebatch_t* wb, const char* ts, size_t tslen, void* state,
-    size_t (*get_ts_size)(void*, uint32_t), char** errptr) {
-  SaveError(errptr, wb->rep.UpdateTimestamps(
-                        Slice(ts, tslen), [&get_ts_size, &state](uint32_t cf) {
-                          return (*get_ts_size)(state, cf);
-                        }));
-}
-
-void rocksdb_writebatch_wi_update_timestamps(
-    rocksdb_writebatch_wi_t* wb, const char* ts, size_t tslen, void* state,
-    size_t (*get_ts_size)(void*, uint32_t), char** errptr) {
-  SaveError(errptr, wb->rep->GetWriteBatch()->UpdateTimestamps(
-                        Slice(ts, tslen), [&get_ts_size, &state](uint32_t cf) {
-                          return (*get_ts_size)(state, cf);
-                        }));
-}
-
 void rocksdb_writebatch_wi_destroy(rocksdb_writebatch_wi_t* b) {
   if (b->rep) {
     delete b->rep;
@@ -2916,24 +2738,6 @@ void rocksdb_options_set_block_based_table_factory(
   }
 }
 
-void rocksdb_block_based_options_set_top_level_index_pinning_tier(
-    rocksdb_block_based_table_options_t* options, int v) {
-  options->rep.metadata_cache_options.top_level_index_pinning =
-      static_cast<ROCKSDB_NAMESPACE::PinningTier>(v);
-}
-
-void rocksdb_block_based_options_set_partition_pinning_tier(
-    rocksdb_block_based_table_options_t* options, int v) {
-  options->rep.metadata_cache_options.partition_pinning =
-      static_cast<ROCKSDB_NAMESPACE::PinningTier>(v);
-}
-
-void rocksdb_block_based_options_set_unpartitioned_pinning_tier(
-    rocksdb_block_based_table_options_t* options, int v) {
-  options->rep.metadata_cache_options.unpartitioned_pinning =
-      static_cast<ROCKSDB_NAMESPACE::PinningTier>(v);
-}
-
 rocksdb_cuckoo_table_options_t* rocksdb_cuckoo_options_create() {
   return new rocksdb_cuckoo_table_options_t;
 }
@@ -2978,9 +2782,7 @@ void rocksdb_options_set_cuckoo_table_factory(
 void rocksdb_set_options(rocksdb_t* db, int count, const char* const keys[],
                          const char* const values[], char** errptr) {
   std::unordered_map<std::string, std::string> options_map;
-  for (int i = 0; i < count; i++) {
-    options_map[keys[i]] = values[i];
-  }
+  for (int i = 0; i < count; i++) options_map[keys[i]] = values[i];
   SaveError(errptr, db->rep->SetOptions(options_map));
 }
 
@@ -2989,9 +2791,7 @@ void rocksdb_set_options_cf(rocksdb_t* db,
                             const char* const keys[],
                             const char* const values[], char** errptr) {
   std::unordered_map<std::string, std::string> options_map;
-  for (int i = 0; i < count; i++) {
-    options_map[keys[i]] = values[i];
-  }
+  for (int i = 0; i < count; i++) options_map[keys[i]] = values[i];
   SaveError(errptr, db->rep->SetOptions(handle->rep, options_map));
 }
 
@@ -3119,32 +2919,6 @@ void rocksdb_options_set_cf_paths(rocksdb_options_t* opt,
   opt->rep.cf_paths = cf_paths;
 }
 
-rocksdb_logger_t* rocksdb_logger_create_stderr_logger(int log_level,
-                                                      const char* prefix) {
-  rocksdb_logger_t* logger = new rocksdb_logger_t;
-
-  if (prefix) {
-    logger->rep = std::make_shared<StderrLogger>(
-        static_cast<InfoLogLevel>(log_level), prefix);
-  } else {
-    logger->rep =
-        std::make_shared<StderrLogger>(static_cast<InfoLogLevel>(log_level));
-  }
-
-  return logger;
-}
-
-rocksdb_logger_t* rocksdb_logger_create_callback_logger(
-    int log_level, void (*callback)(void*, unsigned, char*, size_t),
-    void* priv) {
-  rocksdb_logger_t* logger = new rocksdb_logger_t;
-  logger->rep = std::make_shared<rocksdb_callback_logger_t>(
-      static_cast<InfoLogLevel>(log_level), callback, priv);
-  return logger;
-}
-
-void rocksdb_logger_destroy(rocksdb_logger_t* logger) { delete logger; }
-
 void rocksdb_options_set_env(rocksdb_options_t* opt, rocksdb_env_t* env) {
   opt->rep.env = (env ? env->rep : nullptr);
 }
@@ -3155,12 +2929,6 @@ void rocksdb_options_set_info_log(rocksdb_options_t* opt, rocksdb_logger_t* l) {
   }
 }
 
-rocksdb_logger_t* rocksdb_options_get_info_log(rocksdb_options_t* opt) {
-  rocksdb_logger_t* info_log = new rocksdb_logger_t;
-  info_log->rep = opt->rep.info_log;
-  return info_log;
-}
-
 void rocksdb_options_set_info_log_level(rocksdb_options_t* opt, int v) {
   opt->rep.info_log_level = static_cast<InfoLogLevel>(v);
 }
@@ -3281,14 +3049,6 @@ void rocksdb_options_set_max_bytes_for_level_multiplier_additional(
   }
 }
 
-void rocksdb_options_set_ttl(rocksdb_options_t* opt, uint64_t seconds) {
-  opt->rep.ttl = seconds;
-}
-
-uint64_t rocksdb_options_get_ttl(rocksdb_options_t* opt) {
-  return opt->rep.ttl;
-}
-
 void rocksdb_options_set_periodic_compaction_seconds(rocksdb_options_t* opt,
                                                      uint64_t seconds) {
   opt->rep.periodic_compaction_seconds = seconds;
@@ -3351,7 +3111,7 @@ void rocksdb_options_set_enable_blob_files(rocksdb_options_t* opt,
                                            unsigned char val) {
   opt->rep.enable_blob_files = val;
 }
-ROCKSDB_LIBRARY_API unsigned char rocksdb_options_get_enable_blob_files(
+extern ROCKSDB_LIBRARY_API unsigned char rocksdb_options_get_enable_blob_files(
     rocksdb_options_t* opt) {
   return opt->rep.enable_blob_files;
 }
@@ -3723,6 +3483,35 @@ unsigned char rocksdb_options_get_advise_random_on_open(
   return opt->rep.advise_random_on_open;
 }
 
+void rocksdb_options_set_access_hint_on_compaction_start(rocksdb_options_t* opt,
+                                                         int v) {
+  switch (v) {
+    case 0:
+      opt->rep.access_hint_on_compaction_start =
+          ROCKSDB_NAMESPACE::Options::NONE;
+      break;
+    case 1:
+      opt->rep.access_hint_on_compaction_start =
+          ROCKSDB_NAMESPACE::Options::NORMAL;
+      break;
+    case 2:
+      opt->rep.access_hint_on_compaction_start =
+          ROCKSDB_NAMESPACE::Options::SEQUENTIAL;
+      break;
+    case 3:
+      opt->rep.access_hint_on_compaction_start =
+          ROCKSDB_NAMESPACE::Options::WILLNEED;
+      break;
+    default:
+      assert(0);
+  }
+}
+
+int rocksdb_options_get_access_hint_on_compaction_start(
+    rocksdb_options_t* opt) {
+  return opt->rep.access_hint_on_compaction_start;
+}
+
 void rocksdb_options_set_use_adaptive_mutex(rocksdb_options_t* opt,
                                             unsigned char v) {
   opt->rep.use_adaptive_mutex = v;
@@ -4065,36 +3854,6 @@ void rocksdb_options_set_plain_table_factory(
   opt->rep.table_factory.reset(factory);
 }
 
-unsigned char rocksdb_options_get_write_dbid_to_manifest(
-    rocksdb_options_t* opt) {
-  return opt->rep.write_dbid_to_manifest;
-}
-
-void rocksdb_options_set_write_dbid_to_manifest(
-    rocksdb_options_t* opt, unsigned char write_dbid_to_manifest) {
-  opt->rep.write_dbid_to_manifest = write_dbid_to_manifest;
-}
-
-unsigned char rocksdb_options_get_write_identity_file(rocksdb_options_t* opt) {
-  return opt->rep.write_identity_file;
-}
-
-void rocksdb_options_set_write_identity_file(
-    rocksdb_options_t* opt, unsigned char write_identity_file) {
-  opt->rep.write_identity_file = write_identity_file;
-}
-
-unsigned char rocksdb_options_get_track_and_verify_wals_in_manifest(
-    rocksdb_options_t* opt) {
-  return opt->rep.track_and_verify_wals_in_manifest;
-}
-
-void rocksdb_options_set_track_and_verify_wals_in_manifest(
-    rocksdb_options_t* opt, unsigned char track_and_verify_wals_in_manifest) {
-  opt->rep.track_and_verify_wals_in_manifest =
-      track_and_verify_wals_in_manifest;
-}
-
 void rocksdb_options_set_max_successive_merges(rocksdb_options_t* opt,
                                                size_t v) {
   opt->rep.max_successive_merges = v;
@@ -4158,14 +3917,6 @@ void rocksdb_options_set_fifo_compaction_options(
   opt->rep.compaction_options_fifo = fifo->rep;
 }
 
-void rocksdb_options_set_compaction_pri(rocksdb_options_t* opt, int pri) {
-  opt->rep.compaction_pri = static_cast<ROCKSDB_NAMESPACE::CompactionPri>(pri);
-}
-
-int rocksdb_options_get_compaction_pri(rocksdb_options_t* opt) {
-  return opt->rep.compaction_pri;
-}
-
 char* rocksdb_options_statistics_get_string(rocksdb_options_t* opt) {
   ROCKSDB_NAMESPACE::Statistics* statistics = opt->rep.statistics.get();
   if (statistics) {
@@ -4246,16 +3997,6 @@ rocksdb_ratelimiter_t* rocksdb_ratelimiter_create_auto_tuned(
   return rate_limiter;
 }
 
-rocksdb_ratelimiter_t* rocksdb_ratelimiter_create_with_mode(
-    int64_t rate_bytes_per_sec, int64_t refill_period_us, int32_t fairness,
-    int mode, bool auto_tuned) {
-  rocksdb_ratelimiter_t* rate_limiter = new rocksdb_ratelimiter_t;
-  rate_limiter->rep.reset(
-      NewGenericRateLimiter(rate_bytes_per_sec, refill_period_us, fairness,
-                            static_cast<RateLimiter::Mode>(mode), auto_tuned));
-  return rate_limiter;
-}
-
 void rocksdb_ratelimiter_destroy(rocksdb_ratelimiter_t* limiter) {
   delete limiter;
 }
@@ -4474,8 +4215,13 @@ void rocksdb_perfcontext_destroy(rocksdb_perfcontext_t* context) {
 
 /*
 TODO:
+DB::OpenForReadOnly
+DB::KeyMayExist
 DB::GetOptions
 DB::GetSortedWalFiles
+DB::GetLatestSequenceNumber
+DB::GetUpdatesSince
+DB::GetDbIdentity
 DB::RunManualCompaction
 custom cache
 table_properties_collectors
@@ -4847,7 +4593,7 @@ void rocksdb_readoptions_set_io_timeout(rocksdb_readoptions_t* opt,
   opt->rep.io_timeout = std::chrono::microseconds(microseconds);
 }
 
-ROCKSDB_LIBRARY_API uint64_t
+extern ROCKSDB_LIBRARY_API uint64_t
 rocksdb_readoptions_get_io_timeout(rocksdb_readoptions_t* opt) {
   return opt->rep.io_timeout.count();
 }
@@ -5296,9 +5042,7 @@ void rocksdb_env_lower_high_priority_thread_pool_cpu_priority(
 }
 
 void rocksdb_env_destroy(rocksdb_env_t* env) {
-  if (!env->is_default) {
-    delete env->rep;
-  }
+  if (!env->is_default) delete env->rep;
   delete env;
 }
 
@@ -5682,7 +5426,9 @@ uint64_t rocksdb_livefiles_deletions(const rocksdb_livefiles_t* lf, int index) {
   return lf->rep[index].num_deletions;
 }
 
-void rocksdb_livefiles_destroy(const rocksdb_livefiles_t* lf) { delete lf; }
+extern void rocksdb_livefiles_destroy(const rocksdb_livefiles_t* lf) {
+  delete lf;
+}
 
 void rocksdb_get_options_from_string(const rocksdb_options_t* base_options,
                                      const char* opts_str,
@@ -5762,7 +5508,7 @@ size_t rocksdb_column_family_metadata_get_level_count(
 rocksdb_level_metadata_t* rocksdb_column_family_metadata_get_level_metadata(
     rocksdb_column_family_metadata_t* cf_meta, size_t i) {
   if (i >= cf_meta->rep.levels.size()) {
-    return nullptr;
+    return NULL;
   }
   rocksdb_level_metadata_t* level_meta =
       (rocksdb_level_metadata_t*)malloc(sizeof(rocksdb_level_metadata_t));
@@ -5952,7 +5698,6 @@ rocksdb_column_family_handle_t* rocksdb_transactiondb_create_column_family(
   SaveError(errptr, txn_db->rep->CreateColumnFamily(
                         ColumnFamilyOptions(column_family_options->rep),
                         std::string(column_family_name), &(handle->rep)));
-  handle->immortal = false;
   return handle;
 }
 
@@ -5978,9 +5723,9 @@ rocksdb_transactiondb_t* rocksdb_transactiondb_open_column_families(
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
-    column_families.emplace_back(
+    column_families.push_back(ColumnFamilyDescriptor(
         std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
+        ColumnFamilyOptions(column_family_options[i]->rep)));
   }
 
   TransactionDB* txn_db;
@@ -5995,7 +5740,6 @@ rocksdb_transactiondb_t* rocksdb_transactiondb_open_column_families(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_transactiondb_t* result = new rocksdb_transactiondb_t;
@@ -6773,9 +6517,9 @@ rocksdb_optimistictransactiondb_open_column_families(
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
-    column_families.emplace_back(
+    column_families.push_back(ColumnFamilyDescriptor(
         std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
+        ColumnFamilyOptions(column_family_options[i]->rep)));
   }
 
   OptimisticTransactionDB* otxn_db;
@@ -6790,7 +6534,6 @@ rocksdb_optimistictransactiondb_open_column_families(
     rocksdb_column_family_handle_t* c_handle =
         new rocksdb_column_family_handle_t;
     c_handle->rep = handles[i];
-    c_handle->immortal = false;
     column_family_handles[i] = c_handle;
   }
   rocksdb_optimistictransactiondb_t* result =

db/c_test.c

@@ -50,13 +50,12 @@ static void StartPhase(const char* name) {
 #endif
 static const char* GetTempDir(void) {
   const char* ret = getenv("TEST_TMPDIR");
-  if (ret == NULL || ret[0] == '\0') {
+  if (ret == NULL || ret[0] == '\0')
 #ifdef OS_WIN
     ret = getenv("TEMP");
 #else
     ret = "/tmp";
 #endif
-  }
   return ret;
 }
 #ifdef _MSC_VER
@@ -199,79 +198,6 @@ static void CheckDel(void* ptr, const char* k, size_t klen) {
   (*state)++;
 }
 
-// Callback from rocksdb_writebatch_iterate_cf()
-static void CheckPutCF(void* ptr, uint32_t cfid, const char* k, size_t klen,
-                       const char* v, size_t vlen) {
-  int* state = (int*)ptr;
-  switch (*state) {
-    case 0:
-      CheckEqual("bar", k, klen);
-      CheckEqual("b", v, vlen);
-      CheckCondition(cfid == 1);
-      break;
-    case 1:
-      CheckEqual("box", k, klen);
-      CheckEqual("c", v, vlen);
-      CheckCondition(cfid == 1);
-      break;
-    case 4:
-      CheckEqual("foo", k, klen);
-      CheckEqual("f", v, vlen);
-      CheckCondition(cfid == 0);
-      break;
-    case 6:
-      CheckEqual("baz", k, klen);
-      CheckEqual("a", v, vlen);
-      CheckCondition(cfid == 0);
-      break;
-    default:
-      CheckCondition(false);
-      break;
-  }
-  (*state)++;
-}
-
-// Callback from rocksdb_writebatch_iterate_cf()
-static void CheckDelCF(void* ptr, uint32_t cfid, const char* k, size_t klen) {
-  int* state = (int*)ptr;
-  switch (*state) {
-    case 2:
-      CheckEqual("bar", k, klen);
-      CheckCondition(cfid == 1);
-      break;
-    case 5:
-      CheckEqual("foo", k, klen);
-      CheckCondition(cfid == 0);
-      break;
-    default:
-      CheckCondition(false);
-      break;
-  }
-  (*state)++;
-}
-
-// Callback from rocksdb_writebatch_iterate_cf()
-static void CheckMergeCF(void* ptr, uint32_t cfid, const char* k, size_t klen,
-                         const char* v, size_t vlen) {
-  int* state = (int*)ptr;
-  switch (*state) {
-    case 3:
-      CheckEqual("box", k, klen);
-      CheckEqual("cc", v, vlen);
-      CheckCondition(cfid == 1);
-      break;
-    case 7:
-      CheckEqual("baz", k, klen);
-      CheckEqual("aa", v, vlen);
-      CheckCondition(cfid == 0);
-      break;
-    default:
-      CheckCondition(false);
-      break;
-  }
-  (*state)++;
-}
-
 static void CmpDestroy(void* arg) { (void)arg; }
 
 static int CmpCompare(void* arg, const char* a, size_t alen, const char* b,
@@ -280,11 +206,10 @@ static int CmpCompare(void* arg, const char* a, size_t alen, const char* b,
   size_t n = (alen < blen) ? alen : blen;
   int r = memcmp(a, b, n);
   if (r == 0) {
-    if (alen < blen) {
+    if (alen < blen)
       r = -1;
-    } else if (alen > blen) {
+    else if (alen > blen)
       r = +1;
-    }
   }
   return r;
 }
@@ -772,17 +697,11 @@ int main(int argc, char** argv) {
   rocksdb_options_set_write_buffer_size(options, 100000);
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
-  /* Compatibility with how test was written */
-  rocksdb_options_set_write_dbid_to_manifest(options, 0);
 
   table_options = rocksdb_block_based_options_create();
   rocksdb_block_based_options_set_block_cache(table_options, cache);
   rocksdb_block_based_options_set_data_block_index_type(table_options, 1);
   rocksdb_block_based_options_set_data_block_hash_ratio(table_options, 0.75);
-  rocksdb_block_based_options_set_top_level_index_pinning_tier(table_options,
-                                                               1);
-  rocksdb_block_based_options_set_partition_pinning_tier(table_options, 2);
-  rocksdb_block_based_options_set_unpartitioned_pinning_tier(table_options, 3);
   rocksdb_options_set_block_based_table_factory(options, table_options);
 
   rocksdb_options_set_compression(options, rocksdb_no_compression);
@@ -799,11 +718,6 @@ int main(int argc, char** argv) {
   rocksdb_options_set_ratelimiter(options, rate_limiter);
   rocksdb_ratelimiter_destroy(rate_limiter);
 
-  rate_limiter = rocksdb_ratelimiter_create_with_mode(1000 * 1024 * 1024,
-                                                      100 * 1000, 10, 0, true);
-  rocksdb_options_set_ratelimiter(options, rate_limiter);
-  rocksdb_ratelimiter_destroy(rate_limiter);
-
   roptions = rocksdb_readoptions_create();
   rocksdb_readoptions_set_verify_checksums(roptions, 1);
   rocksdb_readoptions_set_fill_cache(roptions, 1);
@@ -873,11 +787,6 @@ int main(int argc, char** argv) {
     rocksdb_delete(db, woptions, "foo", 3, &err);
     CheckNoError(err);
 
-    // get the identity before the backup
-    size_t before_db_id_len = 0;
-    char* before_db_id = rocksdb_get_db_identity(db, &before_db_id_len);
-    CheckCondition(before_db_id_len == 36);
-
     rocksdb_close(db);
 
     rocksdb_destroy_db(options, dbname, &err);
@@ -898,14 +807,6 @@ int main(int argc, char** argv) {
 
     CheckGet(db, roptions, "foo", "hello");
 
-    // the db_identity after the backup is different
-    size_t after_db_id_len = 0;
-    char* after_db_id = rocksdb_get_db_identity(db, &after_db_id_len);
-    CheckCondition(after_db_id_len == 36);
-    CheckCondition(memcmp(after_db_id, before_db_id, after_db_id_len) != 0);
-    Free(&before_db_id);
-    Free(&after_db_id);
-
     rocksdb_backup_engine_close(be);
   }
 
@@ -921,14 +822,6 @@ int main(int argc, char** argv) {
     rocksdb_checkpoint_create(checkpoint, dbcheckpointname, 0, &err);
     CheckNoError(err);
 
-    rocksdb_checkpoint_object_destroy(checkpoint);
-    checkpoint = NULL;
-
-    // get the identity before the checkpoint
-    size_t before_db_id_len = 0;
-    char* before_db_id = rocksdb_get_db_identity(db, &before_db_id_len);
-    CheckCondition(before_db_id_len == 36);
-
     // start a new database from the checkpoint
     rocksdb_close(db);
     rocksdb_options_set_error_if_exists(options, 0);
@@ -937,13 +830,7 @@ int main(int argc, char** argv) {
 
     CheckGet(db, roptions, "foo", "hello");
 
-    // the db_identity after the checkpoint is different
-    size_t after_db_id_len = 0;
-    char* after_db_id = rocksdb_get_db_identity(db, &after_db_id_len);
-    CheckCondition(after_db_id_len == 36);
-    CheckCondition(memcmp(after_db_id, before_db_id, after_db_id_len) != 0);
-    Free(&before_db_id);
-    Free(&after_db_id);
+    rocksdb_checkpoint_object_destroy(checkpoint);
 
     rocksdb_close(db);
     rocksdb_destroy_db(options, dbcheckpointname, &err);
@@ -954,82 +841,6 @@ int main(int argc, char** argv) {
     rocksdb_options_set_error_if_exists(options, 1);
   }
 
-  StartPhase("checkpoint_db_id_in_manifest");
-  {
-    // create new DB with set_write_dbid_to_manifest=true
-    // db_identity is now the same across checkpoints
-    rocksdb_close(db);
-    db = NULL;
-
-    rocksdb_options_t* options_dbid_in_manifest = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(options_dbid_in_manifest, 1);
-
-    rocksdb_options_set_write_dbid_to_manifest(options_dbid_in_manifest, false);
-    unsigned char write_to_manifest =
-        rocksdb_options_get_write_dbid_to_manifest(options_dbid_in_manifest);
-    CheckCondition(!write_to_manifest);
-    rocksdb_options_set_write_dbid_to_manifest(options_dbid_in_manifest, true);
-    write_to_manifest =
-        rocksdb_options_get_write_dbid_to_manifest(options_dbid_in_manifest);
-    CheckCondition(write_to_manifest);
-
-    rocksdb_options_set_write_identity_file(options_dbid_in_manifest, true);
-    unsigned char write_identity_file =
-        rocksdb_options_get_write_identity_file(options_dbid_in_manifest);
-    CheckCondition(write_identity_file);
-    rocksdb_options_set_write_identity_file(options_dbid_in_manifest, false);
-    write_identity_file =
-        rocksdb_options_get_write_identity_file(options_dbid_in_manifest);
-    CheckCondition(!write_identity_file);
-
-    db = rocksdb_open(options_dbid_in_manifest, dbbackupname, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_t* checkpoint =
-        rocksdb_checkpoint_object_create(db, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_create(checkpoint, dbcheckpointname, 0, &err);
-    CheckNoError(err);
-
-    rocksdb_checkpoint_object_destroy(checkpoint);
-    checkpoint = NULL;
-
-    // get the identity before the backup
-    size_t before_db_id_len = 0;
-    char* before_db_id = rocksdb_get_db_identity(db, &before_db_id_len);
-    CheckCondition(before_db_id_len == 36);
-
-    // open the checkpoint
-    rocksdb_close(db);
-    rocksdb_destroy_db(options_dbid_in_manifest, dbbackupname, &err);
-    CheckNoError(err);
-
-    rocksdb_options_set_error_if_exists(options_dbid_in_manifest, 0);
-    db = rocksdb_open(options_dbid_in_manifest, dbcheckpointname, &err);
-    CheckNoError(err);
-
-    // the db_identity after the checkpoint is the same
-    size_t after_db_id_len = 0;
-    char* after_db_id = rocksdb_get_db_identity(db, &after_db_id_len);
-    CheckCondition(after_db_id_len == 36);
-    CheckCondition(memcmp(after_db_id, before_db_id, after_db_id_len) == 0);
-    Free(&before_db_id);
-    Free(&after_db_id);
-
-    rocksdb_close(db);
-    rocksdb_destroy_db(options_dbid_in_manifest, dbcheckpointname, &err);
-    CheckNoError(err);
-    rocksdb_options_destroy(options_dbid_in_manifest);
-    options_dbid_in_manifest = NULL;
-
-    // re-open the default database
-    rocksdb_options_set_error_if_exists(options, 0);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_options_set_error_if_exists(options, 1);
-  }
-
   StartPhase("compactall");
   rocksdb_compact_range(db, NULL, 0, NULL, 0);
   CheckGet(db, roptions, "foo", "hello");
@@ -1067,8 +878,9 @@ int main(int argc, char** argv) {
   StartPhase("addfile");
   {
     rocksdb_envoptions_t* env_opt = rocksdb_envoptions_create();
+    rocksdb_options_t* io_options = rocksdb_options_create();
     rocksdb_sstfilewriter_t* writer =
-        rocksdb_sstfilewriter_create(env_opt, options);
+        rocksdb_sstfilewriter_create(env_opt, io_options);
 
     remove(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
@@ -1127,6 +939,7 @@ int main(int argc, char** argv) {
 
     rocksdb_ingestexternalfileoptions_destroy(ing_opt);
     rocksdb_sstfilewriter_destroy(writer);
+    rocksdb_options_destroy(io_options);
     rocksdb_envoptions_destroy(env_opt);
 
     // Delete all keys we just ingested
@@ -1500,8 +1313,6 @@ int main(int argc, char** argv) {
       policy = rocksdb_filterpolicy_create_ribbon_hybrid(8.0, 1);
     }
     rocksdb_block_based_options_set_filter_policy(table_options, policy);
-    rocksdb_block_based_options_set_optimize_filters_for_memory(table_options,
-                                                                0);
 
     // Create new database
     rocksdb_close(db);
@@ -1772,21 +1583,6 @@ int main(int argc, char** argv) {
     CheckPinGetCF(db, roptions, handles[1], "bar", NULL);
     CheckPinGetCF(db, roptions, handles[1], "box", "c");
     CheckPinGetCF(db, roptions, handles[1], "buff", "rocksdb");
-    rocksdb_writebatch_clear(wb);
-    // Test WriteBatch iteration with Column Family
-    int pos = 0;
-    rocksdb_writebatch_put_cf(wb, handles[1], "bar", 3, "b", 1);
-    rocksdb_writebatch_put_cf(wb, handles[1], "box", 3, "c", 1);
-    rocksdb_writebatch_delete_cf(wb, handles[1], "bar", 3);
-    rocksdb_writebatch_merge_cf(wb, handles[1], "box", 3, "cc", 2);
-    rocksdb_writebatch_put(wb, "foo", 3, "f", 1);
-    rocksdb_writebatch_delete(wb, "foo", 3);
-    rocksdb_writebatch_put(wb, "baz", 3, "a", 1);
-    rocksdb_writebatch_merge(wb, "baz", 3, "aa", 2);
-    rocksdb_writebatch_iterate_cf(wb, &pos, CheckPutCF, CheckDelCF,
-                                  CheckMergeCF);
-    CheckCondition(pos == 8);
-    rocksdb_writebatch_clear(wb);
     rocksdb_writebatch_destroy(wb);
 
     rocksdb_flush_wal(db, 1, &err);
@@ -2129,9 +1925,6 @@ int main(int argc, char** argv) {
     CheckCondition(100000 ==
                    rocksdb_options_get_periodic_compaction_seconds(o));
 
-    rocksdb_options_set_ttl(o, 5000);
-    CheckCondition(5000 == rocksdb_options_get_ttl(o));
-
     rocksdb_options_set_skip_stats_update_on_db_open(o, 1);
     CheckCondition(1 == rocksdb_options_get_skip_stats_update_on_db_open(o));
 
@@ -2238,6 +2031,9 @@ int main(int argc, char** argv) {
     rocksdb_options_set_advise_random_on_open(o, 1);
     CheckCondition(1 == rocksdb_options_get_advise_random_on_open(o));
 
+    rocksdb_options_set_access_hint_on_compaction_start(o, 3);
+    CheckCondition(3 == rocksdb_options_get_access_hint_on_compaction_start(o));
+
     rocksdb_options_set_use_adaptive_mutex(o, 1);
     CheckCondition(1 == rocksdb_options_get_use_adaptive_mutex(o));
 
@@ -2308,9 +2104,6 @@ int main(int argc, char** argv) {
     rocksdb_options_set_compaction_style(o, 2);
     CheckCondition(2 == rocksdb_options_get_compaction_style(o));
 
-    rocksdb_options_set_compaction_pri(o, 4);
-    CheckCondition(4 == rocksdb_options_get_compaction_pri(o));
-
     rocksdb_options_set_atomic_flush(o, 1);
     CheckCondition(1 == rocksdb_options_get_atomic_flush(o));
 
@@ -2333,12 +2126,6 @@ int main(int argc, char** argv) {
     CheckCondition(rocksdb_statistics_level_all ==
                    rocksdb_options_get_statistics_level(o));
 
-    CheckCondition(0 ==
-                   rocksdb_options_get_track_and_verify_wals_in_manifest(o));
-    rocksdb_options_set_track_and_verify_wals_in_manifest(o, 42);
-    CheckCondition(1 ==
-                   rocksdb_options_get_track_and_verify_wals_in_manifest(o));
-
     /* Blob Options */
     rocksdb_options_set_enable_blob_files(o, 1);
     CheckCondition(1 == rocksdb_options_get_enable_blob_files(o));
@@ -2441,6 +2228,8 @@ int main(int argc, char** argv) {
     CheckCondition(18 == rocksdb_options_get_stats_dump_period_sec(copy));
     CheckCondition(5 == rocksdb_options_get_stats_persist_period_sec(copy));
     CheckCondition(1 == rocksdb_options_get_advise_random_on_open(copy));
+    CheckCondition(3 ==
+                   rocksdb_options_get_access_hint_on_compaction_start(copy));
     CheckCondition(1 == rocksdb_options_get_use_adaptive_mutex(copy));
     CheckCondition(19 == rocksdb_options_get_bytes_per_sync(copy));
     CheckCondition(20 == rocksdb_options_get_wal_bytes_per_sync(copy));
@@ -2572,10 +2361,6 @@ int main(int argc, char** argv) {
     CheckCondition(100000 ==
                    rocksdb_options_get_periodic_compaction_seconds(o));
 
-    rocksdb_options_set_ttl(copy, 8000);
-    CheckCondition(8000 == rocksdb_options_get_ttl(copy));
-    CheckCondition(5000 == rocksdb_options_get_ttl(o));
-
     rocksdb_options_set_skip_stats_update_on_db_open(copy, 0);
     CheckCondition(0 == rocksdb_options_get_skip_stats_update_on_db_open(copy));
     CheckCondition(1 == rocksdb_options_get_skip_stats_update_on_db_open(o));
@@ -2723,6 +2508,11 @@ int main(int argc, char** argv) {
     CheckCondition(0 == rocksdb_options_get_advise_random_on_open(copy));
     CheckCondition(1 == rocksdb_options_get_advise_random_on_open(o));
 
+    rocksdb_options_set_access_hint_on_compaction_start(copy, 2);
+    CheckCondition(2 ==
+                   rocksdb_options_get_access_hint_on_compaction_start(copy));
+    CheckCondition(3 == rocksdb_options_get_access_hint_on_compaction_start(o));
+
     rocksdb_options_set_use_adaptive_mutex(copy, 0);
     CheckCondition(0 == rocksdb_options_get_use_adaptive_mutex(copy));
     CheckCondition(1 == rocksdb_options_get_use_adaptive_mutex(o));
@@ -2821,10 +2611,6 @@ int main(int argc, char** argv) {
     CheckCondition(1 == rocksdb_options_get_compaction_style(copy));
     CheckCondition(2 == rocksdb_options_get_compaction_style(o));
 
-    rocksdb_options_set_compaction_pri(copy, 1);
-    CheckCondition(1 == rocksdb_options_get_compaction_pri(copy));
-    CheckCondition(4 == rocksdb_options_get_compaction_pri(o));
-
     rocksdb_options_set_atomic_flush(copy, 0);
     CheckCondition(0 == rocksdb_options_get_atomic_flush(copy));
     CheckCondition(1 == rocksdb_options_get_atomic_flush(o));
@@ -2995,30 +2781,6 @@ int main(int argc, char** argv) {
     rocksdb_memory_allocator_destroy(allocator);
   }
 
-  StartPhase("stderr_logger");
-  {
-    rocksdb_options_t* o_no_prefix = rocksdb_options_create();
-    rocksdb_logger_t* no_prefix_logger =
-        rocksdb_logger_create_stderr_logger(3, NULL);
-    rocksdb_options_set_info_log(o_no_prefix, no_prefix_logger);
-    rocksdb_logger_t* no_prefix_info_log =
-        rocksdb_options_get_info_log(o_no_prefix);
-    CheckCondition(no_prefix_info_log != NULL);
-    rocksdb_logger_destroy(no_prefix_logger);
-    rocksdb_logger_destroy(no_prefix_info_log);
-    rocksdb_options_destroy(o_no_prefix);
-
-    rocksdb_options_t* o_prefix = rocksdb_options_create();
-    rocksdb_logger_t* prefix_logger =
-        rocksdb_logger_create_stderr_logger(3, "some prefix");
-    rocksdb_options_set_info_log(o_prefix, prefix_logger);
-    rocksdb_logger_t* prefix_info_log = rocksdb_options_get_info_log(o_prefix);
-    CheckCondition(prefix_info_log != NULL);
-    rocksdb_logger_destroy(prefix_logger);
-    rocksdb_logger_destroy(prefix_info_log);
-    rocksdb_options_destroy(o_prefix);
-  }
-
   StartPhase("env");
   {
     rocksdb_env_t* e;
@@ -3925,7 +3687,7 @@ int main(int argc, char** argv) {
 
   StartPhase("statistics");
   {
-    const uint32_t BYTES_WRITTEN_TICKER = 60;
+    const uint32_t BYTES_WRITTEN_TICKER = 40;
     const uint32_t DB_WRITE_HIST = 1;
 
     rocksdb_statistics_histogram_data_t* hist =

db/coalescing_iterator.cc

@@ -1,47 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/coalescing_iterator.h"
-
-#include "db/wide/wide_columns_helper.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-void CoalescingIterator::Coalesce(
-    const autovector<MultiCfIteratorInfo>& items) {
-  assert(wide_columns_.empty());
-  MinHeap heap;
-  for (const auto& item : items) {
-    assert(item.iterator);
-    for (auto& column : item.iterator->columns()) {
-      heap.push(WideColumnWithOrder{&column, item.order});
-    }
-  }
-  if (heap.empty()) {
-    return;
-  }
-  wide_columns_.reserve(heap.size());
-  auto current = heap.top();
-  heap.pop();
-  while (!heap.empty()) {
-    int comparison = current.column->name().compare(heap.top().column->name());
-    if (comparison < 0) {
-      wide_columns_.push_back(*current.column);
-    } else if (comparison > 0) {
-      // Shouldn't reach here.
-      // Current item in the heap is greater than the top item in the min heap
-      assert(false);
-    }
-    current = heap.top();
-    heap.pop();
-  }
-  wide_columns_.push_back(*current.column);
-
-  if (WideColumnsHelper::HasDefaultColumn(wide_columns_)) {
-    value_ = WideColumnsHelper::GetDefaultColumn(wide_columns_);
-  }
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/coalescing_iterator.h

@@ -1,104 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#pragma once
-
-#include "db/multi_cf_iterator_impl.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class CoalescingIterator : public Iterator {
- public:
-  CoalescingIterator(
-      const ReadOptions& read_options, const Comparator* comparator,
-      std::vector<std::pair<ColumnFamilyHandle*, std::unique_ptr<Iterator>>>&&
-          cfh_iter_pairs)
-      : impl_(read_options, comparator, std::move(cfh_iter_pairs),
-              ResetFunc(this), PopulateFunc(this)) {}
-  ~CoalescingIterator() override {}
-
-  // No copy allowed
-  CoalescingIterator(const CoalescingIterator&) = delete;
-  CoalescingIterator& operator=(const CoalescingIterator&) = delete;
-
-  bool Valid() const override { return impl_.Valid(); }
-  void SeekToFirst() override { impl_.SeekToFirst(); }
-  void SeekToLast() override { impl_.SeekToLast(); }
-  void Seek(const Slice& target) override { impl_.Seek(target); }
-  void SeekForPrev(const Slice& target) override { impl_.SeekForPrev(target); }
-  void Next() override { impl_.Next(); }
-  void Prev() override { impl_.Prev(); }
-  Slice key() const override { return impl_.key(); }
-  Status status() const override { return impl_.status(); }
-
-  Slice value() const override {
-    assert(Valid());
-    return value_;
-  }
-  const WideColumns& columns() const override {
-    assert(Valid());
-    return wide_columns_;
-  }
-
-  void Reset() {
-    value_.clear();
-    wide_columns_.clear();
-  }
-
-  bool PrepareValue() override { return impl_.PrepareValue(); }
-
- private:
-  class ResetFunc {
-   public:
-    explicit ResetFunc(CoalescingIterator* iter) : iter_(iter) {}
-
-    void operator()() const {
-      assert(iter_);
-      iter_->Reset();
-    }
-
-   private:
-    CoalescingIterator* iter_;
-  };
-
-  class PopulateFunc {
-   public:
-    explicit PopulateFunc(CoalescingIterator* iter) : iter_(iter) {}
-
-    void operator()(const autovector<MultiCfIteratorInfo>& items) const {
-      assert(iter_);
-      iter_->Coalesce(items);
-    }
-
-   private:
-    CoalescingIterator* iter_;
-  };
-
-  MultiCfIteratorImpl<ResetFunc, PopulateFunc> impl_;
-  Slice value_;
-  WideColumns wide_columns_;
-
-  struct WideColumnWithOrder {
-    const WideColumn* column;
-    int order;
-  };
-
-  class WideColumnWithOrderComparator {
-   public:
-    explicit WideColumnWithOrderComparator() {}
-    bool operator()(const WideColumnWithOrder& a,
-                    const WideColumnWithOrder& b) const {
-      int c = a.column->name().compare(b.column->name());
-      return c == 0 ? a.order - b.order > 0 : c > 0;
-    }
-  };
-
-  using MinHeap =
-      BinaryHeap<WideColumnWithOrder, WideColumnWithOrderComparator>;
-
-  void Coalesce(const autovector<MultiCfIteratorInfo>& items);
-};
-
-}  // namespace ROCKSDB_NAMESPACE

db/column_family.cc

@@ -96,16 +96,16 @@ const Comparator* ColumnFamilyHandleImpl::GetComparator() const {
   return cfd()->user_comparator();
 }
 
-void GetInternalTblPropCollFactory(
+void GetIntTblPropCollectorFactory(
     const ImmutableCFOptions& ioptions,
-    InternalTblPropCollFactories* internal_tbl_prop_coll_factories) {
-  assert(internal_tbl_prop_coll_factories);
+    IntTblPropCollectorFactories* int_tbl_prop_collector_factories) {
+  assert(int_tbl_prop_collector_factories);
 
   auto& collector_factories = ioptions.table_properties_collector_factories;
   for (size_t i = 0; i < ioptions.table_properties_collector_factories.size();
        ++i) {
     assert(collector_factories[i]);
-    internal_tbl_prop_coll_factories->emplace_back(
+    int_tbl_prop_collector_factories->emplace_back(
         new UserKeyTablePropertiesCollectorFactory(collector_factories[i]));
   }
 }
@@ -322,8 +322,8 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     }
     ROCKS_LOG_WARN(db_options.logger,
                    "Adjust the value to "
-                   "level0_stop_writes_trigger(%d) "
-                   "level0_slowdown_writes_trigger(%d) "
+                   "level0_stop_writes_trigger(%d)"
+                   "level0_slowdown_writes_trigger(%d)"
                    "level0_file_num_compaction_trigger(%d)",
                    result.level0_stop_writes_trigger,
                    result.level0_slowdown_writes_trigger,
@@ -358,16 +358,16 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
 
   if (result.level_compaction_dynamic_level_bytes) {
     if (result.compaction_style != kCompactionStyleLevel) {
-      ROCKS_LOG_INFO(db_options.info_log.get(),
-                     "level_compaction_dynamic_level_bytes only makes sense "
+      ROCKS_LOG_WARN(db_options.info_log.get(),
+                     "level_compaction_dynamic_level_bytes only makes sense"
                      "for level-based compaction");
       result.level_compaction_dynamic_level_bytes = false;
     } else if (result.cf_paths.size() > 1U) {
       // we don't yet know how to make both of this feature and multiple
       // DB path work.
       ROCKS_LOG_WARN(db_options.info_log.get(),
-                     "multiple cf_paths/db_paths and "
-                     "level_compaction_dynamic_level_bytes "
+                     "multiple cf_paths/db_paths and"
+                     "level_compaction_dynamic_level_bytes"
                      "can't be used together");
       result.level_compaction_dynamic_level_bytes = false;
     }
@@ -411,13 +411,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
           "periodic_compaction_seconds does not support FIFO compaction. You"
           "may want to set option TTL instead.");
     }
-    if (result.last_level_temperature != Temperature::kUnknown) {
-      ROCKS_LOG_WARN(
-          db_options.info_log.get(),
-          "last_level_temperature is ignored with FIFO compaction. Consider "
-          "CompactionOptionsFIFO::file_temperature_age_thresholds.");
-      result.last_level_temperature = Temperature::kUnknown;
-    }
   }
 
   // For universal compaction, `ttl` and `periodic_compaction_seconds` mean the
@@ -466,7 +459,7 @@ void SuperVersion::Cleanup() {
   // decrement reference to the immutable MemtableList
   // this SV object was pointing to.
   imm->Unref(&to_delete);
-  ReadOnlyMemTable* m = mem->Unref();
+  MemTable* m = mem->Unref();
   if (m != nullptr) {
     auto* memory_usage = current->cfd()->imm()->current_memory_usage();
     assert(*memory_usage >= m->ApproximateMemoryUsage());
@@ -477,16 +470,13 @@ void SuperVersion::Cleanup() {
   cfd->UnrefAndTryDelete();
 }
 
-void SuperVersion::Init(
-    ColumnFamilyData* new_cfd, MemTable* new_mem, MemTableListVersion* new_imm,
-    Version* new_current,
-    std::shared_ptr<const SeqnoToTimeMapping> new_seqno_to_time_mapping) {
+void SuperVersion::Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
+                        MemTableListVersion* new_imm, Version* new_current) {
   cfd = new_cfd;
   mem = new_mem;
   imm = new_imm;
   current = new_current;
   full_history_ts_low = cfd->GetFullHistoryTsLow();
-  seqno_to_time_mapping = std::move(new_seqno_to_time_mapping);
   cfd->Ref();
   mem->Ref();
   imm->Ref();
@@ -538,7 +528,6 @@ ColumnFamilyData::ColumnFamilyData(
       refs_(0),
       initialized_(false),
       dropped_(false),
-      flush_skip_reschedule_(false),
       internal_comparator_(cf_options.comparator),
       initial_cf_options_(SanitizeOptions(db_options, cf_options)),
       ioptions_(db_options, initial_cf_options_),
@@ -583,7 +572,7 @@ ColumnFamilyData::ColumnFamilyData(
   Ref();
 
   // Convert user defined table properties collector factories to internal ones.
-  GetInternalTblPropCollFactory(ioptions_, &internal_tbl_prop_coll_factories_);
+  GetIntTblPropCollectorFactory(ioptions_, &int_tbl_prop_collector_factories_);
 
   // if _dummy_versions is nullptr, then this is a dummy column family.
   if (_dummy_versions != nullptr) {
@@ -595,8 +584,8 @@ ColumnFamilyData::ColumnFamilyData(
     blob_file_cache_.reset(
         new BlobFileCache(_table_cache, ioptions(), soptions(), id_,
                           internal_stats_->GetBlobFileReadHist(), io_tracer));
-    blob_source_.reset(new BlobSource(ioptions_, mutable_cf_options_, db_id,
-                                      db_session_id, blob_file_cache_.get()));
+    blob_source_.reset(new BlobSource(ioptions(), db_id, db_session_id,
+                                      blob_file_cache_.get()));
 
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
@@ -693,9 +682,9 @@ ColumnFamilyData::~ColumnFamilyData() {
   if (mem_ != nullptr) {
     delete mem_->Unref();
   }
-  autovector<ReadOnlyMemTable*> to_delete;
+  autovector<MemTable*> to_delete;
   imm_.current()->Unref(&to_delete);
-  for (auto* m : to_delete) {
+  for (MemTable* m : to_delete) {
     delete m;
   }
 
@@ -881,7 +870,7 @@ uint64_t GetPendingCompactionBytesForCompactionSpeedup(
     const VersionStorageInfo* vstorage) {
   // Compaction debt relatively large compared to the stable (bottommost) data
   // size indicates compaction fell behind.
-  const uint64_t kBottommostSizeDivisor = 8;
+  const uint64_t kBottommostSizeMultiplier = 8;
   // Meaningful progress toward the slowdown trigger is another good indication.
   const uint64_t kSlowdownTriggerDivisor = 4;
 
@@ -901,21 +890,10 @@ uint64_t GetPendingCompactionBytesForCompactionSpeedup(
     return slowdown_threshold;
   }
 
-  // Prevent a small CF from triggering parallel compactions for other CFs.
-  // Require compaction debt to be more than a full L0 to Lbase compaction.
-  const uint64_t kMinDebtSize = 2 * mutable_cf_options.max_bytes_for_level_base;
   uint64_t size_threshold =
-      std::max(bottommost_files_size / kBottommostSizeDivisor, kMinDebtSize);
+      MultiplyCheckOverflow(bottommost_files_size, kBottommostSizeMultiplier);
   return std::min(size_threshold, slowdown_threshold);
 }
-
-uint64_t GetMarkedFileCountForCompactionSpeedup() {
-  // When just one file is marked, it is not clear that parallel compaction will
-  // help the compaction that the user nicely requested to happen sooner. When
-  // multiple files are marked, however, it is pretty clearly helpful, except
-  // for the rare case in which a single compaction grabs all the marked files.
-  return 2;
-}
 }  // anonymous namespace
 
 std::pair<WriteStallCondition, WriteStallCause>
@@ -1097,16 +1075,6 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
             "compaction "
             "bytes %" PRIu64,
             name_.c_str(), vstorage->estimated_compaction_needed_bytes());
-      } else if (uint64_t(vstorage->FilesMarkedForCompaction().size()) >=
-                 GetMarkedFileCountForCompactionSpeedup()) {
-        write_controller_token_ =
-            write_controller->GetCompactionPressureToken();
-        ROCKS_LOG_INFO(
-            ioptions_.logger,
-            "[%s] Increasing compaction threads because we have %" PRIu64
-            " files marked for compaction",
-            name_.c_str(),
-            uint64_t(vstorage->FilesMarkedForCompaction().size()));
       } else {
         write_controller_token_.reset();
       }
@@ -1176,12 +1144,10 @@ bool ColumnFamilyData::NeedsCompaction() const {
 
 Compaction* ColumnFamilyData::PickCompaction(
     const MutableCFOptions& mutable_options,
-    const MutableDBOptions& mutable_db_options,
-    const std::vector<SequenceNumber>& existing_snapshots,
-    const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer) {
+    const MutableDBOptions& mutable_db_options, LogBuffer* log_buffer) {
   auto* result = compaction_picker_->PickCompaction(
-      GetName(), mutable_options, mutable_db_options, existing_snapshots,
-      snapshot_checker, current_->storage_info(), log_buffer);
+      GetName(), mutable_options, mutable_db_options, current_->storage_info(),
+      log_buffer);
   if (result != nullptr) {
     result->FinalizeInputInfo(current_);
   }
@@ -1196,24 +1162,21 @@ bool ColumnFamilyData::RangeOverlapWithCompaction(
 }
 
 Status ColumnFamilyData::RangesOverlapWithMemtables(
-    const autovector<UserKeyRange>& ranges, SuperVersion* super_version,
+    const autovector<Range>& ranges, SuperVersion* super_version,
     bool allow_data_in_errors, bool* overlap) {
   assert(overlap != nullptr);
   *overlap = false;
   // Create an InternalIterator over all unflushed memtables
   Arena arena;
-  // TODO: plumb Env::IOActivity, Env::IOPriority
+  // TODO: plumb Env::IOActivity
   ReadOptions read_opts;
   read_opts.total_order_seek = true;
   MergeIteratorBuilder merge_iter_builder(&internal_comparator_, &arena);
-  merge_iter_builder.AddIterator(super_version->mem->NewIterator(
-      read_opts, /*seqno_to_time_mapping=*/nullptr, &arena,
-      /*prefix_extractor=*/nullptr, /*for_flush=*/false));
-  super_version->imm->AddIterators(read_opts, /*seqno_to_time_mapping=*/nullptr,
-                                   /*prefix_extractor=*/nullptr,
-                                   &merge_iter_builder,
+  merge_iter_builder.AddIterator(
+      super_version->mem->NewIterator(read_opts, &arena));
+  super_version->imm->AddIterators(read_opts, &merge_iter_builder,
                                    false /* add_range_tombstone_iter */);
-  ScopedArenaPtr<InternalIterator> memtable_iter(merge_iter_builder.Finish());
+  ScopedArenaIterator memtable_iter(merge_iter_builder.Finish());
 
   auto read_seq = super_version->current->version_set()->LastSequence();
   ReadRangeDelAggregator range_del_agg(&internal_comparator_, read_seq);
@@ -1243,8 +1206,7 @@ Status ColumnFamilyData::RangesOverlapWithMemtables(
 
     if (status.ok()) {
       if (memtable_iter->Valid() &&
-          ucmp->CompareWithoutTimestamp(seek_result.user_key,
-                                        ranges[i].limit) <= 0) {
+          ucmp->Compare(seek_result.user_key, ranges[i].limit) <= 0) {
         *overlap = true;
       } else if (range_del_agg.IsRangeOverlapped(ranges[i].start,
                                                  ranges[i].limit)) {
@@ -1349,12 +1311,7 @@ void ColumnFamilyData::InstallSuperVersion(
     const MutableCFOptions& mutable_cf_options) {
   SuperVersion* new_superversion = sv_context->new_superversion.release();
   new_superversion->mutable_cf_options = mutable_cf_options;
-  new_superversion->Init(this, mem_, imm_.current(), current_,
-                         sv_context->new_seqno_to_time_mapping
-                             ? std::move(sv_context->new_seqno_to_time_mapping)
-                         : super_version_
-                             ? super_version_->ShareSeqnoToTimeMapping()
-                             : nullptr);
+  new_superversion->Init(this, mem_, imm_.current(), current_);
   SuperVersion* old_superversion = super_version_;
   super_version_ = new_superversion;
   if (old_superversion == nullptr || old_superversion->current != current() ||
@@ -1537,20 +1494,6 @@ Status ColumnFamilyData::ValidateOptions(
       }
     }
   }
-
-  if (cf_options.compaction_style == kCompactionStyleUniversal) {
-    int max_read_amp = cf_options.compaction_options_universal.max_read_amp;
-    if (max_read_amp < -1) {
-      return Status::NotSupported(
-          "CompactionOptionsUniversal::max_read_amp should be at least -1.");
-    } else if (0 < max_read_amp &&
-               max_read_amp < cf_options.level0_file_num_compaction_trigger) {
-      return Status::NotSupported(
-          "CompactionOptionsUniversal::max_read_amp limits the number of sorted"
-          " runs but is smaller than the compaction trigger "
-          "level0_file_num_compaction_trigger.");
-    }
-  }
   return s;
 }
 
@@ -1561,11 +1504,6 @@ Status ColumnFamilyData::SetOptions(
       BuildColumnFamilyOptions(initial_cf_options_, mutable_cf_options_);
   ConfigOptions config_opts;
   config_opts.mutable_options_only = true;
-#ifndef NDEBUG
-  if (TEST_allowSetOptionsImmutableInMutable) {
-    config_opts.mutable_options_only = false;
-  }
-#endif
   Status s = GetColumnFamilyOptionsFromMap(config_opts, cf_opts, options_map,
                                            &cf_opts);
   if (s.ok()) {
@@ -1578,6 +1516,28 @@ Status ColumnFamilyData::SetOptions(
   return s;
 }
 
+// REQUIRES: DB mutex held
+Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
+  if (initial_cf_options_.compaction_style != kCompactionStyleLevel) {
+    return Env::WLTH_NOT_SET;
+  }
+  if (level == 0) {
+    return Env::WLTH_MEDIUM;
+  }
+  int base_level = current_->storage_info()->base_level();
+
+  // L1: medium, L2: long, ...
+  if (level - base_level >= 2) {
+    return Env::WLTH_EXTREME;
+  } else if (level < base_level) {
+    // There is no restriction which prevents level passed in to be smaller
+    // than base_level.
+    return Env::WLTH_MEDIUM;
+  }
+  return static_cast<Env::WriteLifeTimeHint>(
+      level - base_level + static_cast<int>(Env::WLTH_MEDIUM));
+}
+
 Status ColumnFamilyData::AddDirectories(
     std::map<std::string, std::shared_ptr<FSDirectory>>* created_dirs) {
   Status s;
@@ -1613,19 +1573,6 @@ FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
   return data_dirs_[path_id].get();
 }
 
-void ColumnFamilyData::SetFlushSkipReschedule() {
-  const Comparator* ucmp = user_comparator();
-  const size_t ts_sz = ucmp->timestamp_size();
-  if (ts_sz == 0 || ioptions_.persist_user_defined_timestamps) {
-    return;
-  }
-  flush_skip_reschedule_.store(true);
-}
-
-bool ColumnFamilyData::GetAndClearFlushSkipReschedule() {
-  return flush_skip_reschedule_.exchange(false);
-}
-
 bool ColumnFamilyData::ShouldPostponeFlushToRetainUDT(
     uint64_t max_memtable_id) {
   const Comparator* ucmp = user_comparator();
@@ -1643,9 +1590,6 @@ bool ColumnFamilyData::ShouldPostponeFlushToRetainUDT(
   }
   for (const Slice& table_newest_udt :
        imm()->GetTablesNewestUDT(max_memtable_id)) {
-    if (table_newest_udt.empty()) {
-      continue;
-    }
     assert(table_newest_udt.size() == full_history_ts_low.size());
     // Checking the newest UDT contained in MemTable with ascending ID up to
     // `max_memtable_id`. Return immediately on finding the first MemTable that

db/column_family.h

@@ -16,7 +16,6 @@
 
 #include "cache/cache_reservation_manager.h"
 #include "db/memtable_list.h"
-#include "db/snapshot_checker.h"
 #include "db/table_cache.h"
 #include "db/table_properties_collector.h"
 #include "db/write_batch_internal.h"
@@ -27,7 +26,6 @@
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "trace_replay/block_cache_tracer.h"
-#include "util/cast_util.h"
 #include "util/hash_containers.h"
 #include "util/thread_local.h"
 
@@ -170,12 +168,11 @@ class ColumnFamilyHandleImpl : public ColumnFamilyHandle {
   // destroy without mutex
   virtual ~ColumnFamilyHandleImpl();
   virtual ColumnFamilyData* cfd() const { return cfd_; }
-  virtual DBImpl* db() const { return db_; }
 
-  uint32_t GetID() const override;
-  const std::string& GetName() const override;
-  Status GetDescriptor(ColumnFamilyDescriptor* desc) override;
-  const Comparator* GetComparator() const override;
+  virtual uint32_t GetID() const override;
+  virtual const std::string& GetName() const override;
+  virtual Status GetDescriptor(ColumnFamilyDescriptor* desc) override;
+  virtual const Comparator* GetComparator() const override;
 
  private:
   ColumnFamilyData* cfd_;
@@ -196,7 +193,7 @@ class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
         internal_cfd_(nullptr) {}
 
   void SetCFD(ColumnFamilyData* _cfd) { internal_cfd_ = _cfd; }
-  ColumnFamilyData* cfd() const override { return internal_cfd_; }
+  virtual ColumnFamilyData* cfd() const override { return internal_cfd_; }
 
  private:
   ColumnFamilyData* internal_cfd_;
@@ -207,7 +204,7 @@ struct SuperVersion {
   // Accessing members of this class is not thread-safe and requires external
   // synchronization (ie db mutex held or on write thread).
   ColumnFamilyData* cfd;
-  ReadOnlyMemTable* mem;
+  MemTable* mem;
   MemTableListVersion* imm;
   Version* current;
   MutableCFOptions mutable_cf_options;
@@ -221,9 +218,6 @@ struct SuperVersion {
   // enable UDT feature, this is an empty string.
   std::string full_history_ts_low;
 
-  // A shared copy of the DB's seqno to time mapping.
-  std::shared_ptr<const SeqnoToTimeMapping> seqno_to_time_mapping{nullptr};
-
   // should be called outside the mutex
   SuperVersion() = default;
   ~SuperVersion();
@@ -237,23 +231,8 @@ struct SuperVersion {
   // that needs to be deleted in to_delete vector. Unrefing those
   // objects needs to be done in the mutex
   void Cleanup();
-  void Init(
-      ColumnFamilyData* new_cfd, MemTable* new_mem,
-      MemTableListVersion* new_imm, Version* new_current,
-      std::shared_ptr<const SeqnoToTimeMapping> new_seqno_to_time_mapping);
-
-  // Share the ownership of the seqno to time mapping object referred to in this
-  // SuperVersion. To be used by the new SuperVersion to be installed after this
-  // one if seqno to time mapping does not change in between these two
-  // SuperVersions. Or to share the ownership of the mapping with a FlushJob.
-  std::shared_ptr<const SeqnoToTimeMapping> ShareSeqnoToTimeMapping() {
-    return seqno_to_time_mapping;
-  }
-
-  // Access the seqno to time mapping object in this SuperVersion.
-  UnownedPtr<const SeqnoToTimeMapping> GetSeqnoToTimeMapping() const {
-    return seqno_to_time_mapping.get();
-  }
+  void Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
+            MemTableListVersion* new_imm, Version* new_current);
 
   // The value of dummy is not actually used. kSVInUse takes its address as a
   // mark in the thread local storage to indicate the SuperVersion is in use
@@ -269,24 +248,25 @@ struct SuperVersion {
   // We need to_delete because during Cleanup(), imm->Unref() returns
   // all memtables that we need to free through this vector. We then
   // delete all those memtables outside of mutex, during destruction
-  autovector<ReadOnlyMemTable*> to_delete;
+  autovector<MemTable*> to_delete;
 };
 
-Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options);
+extern Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options);
 
-Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options);
+extern Status CheckConcurrentWritesSupported(
+    const ColumnFamilyOptions& cf_options);
 
-Status CheckCFPathsSupported(const DBOptions& db_options,
-                             const ColumnFamilyOptions& cf_options);
+extern Status CheckCFPathsSupported(const DBOptions& db_options,
+                                    const ColumnFamilyOptions& cf_options);
 
-ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
-                                    const ColumnFamilyOptions& src);
+extern ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
+                                           const ColumnFamilyOptions& src);
 // Wrap user defined table properties collector factories `from cf_options`
-// into internal ones in internal_tbl_prop_coll_factories. Add a system internal
+// into internal ones in int_tbl_prop_collector_factories. Add a system internal
 // one too.
-void GetInternalTblPropCollFactory(
+extern void GetIntTblPropCollectorFactory(
     const ImmutableCFOptions& ioptions,
-    InternalTblPropCollFactories* internal_tbl_prop_coll_factories);
+    IntTblPropCollectorFactories* int_tbl_prop_collector_factories);
 
 class ColumnFamilySet;
 
@@ -330,10 +310,6 @@ class ColumnFamilyData {
   void SetDropped();
   bool IsDropped() const { return dropped_.load(std::memory_order_relaxed); }
 
-  void SetFlushSkipReschedule();
-
-  bool GetAndClearFlushSkipReschedule();
-
   // thread-safe
   int NumberLevels() const { return ioptions_.num_levels; }
 
@@ -386,16 +362,12 @@ class ColumnFamilyData {
   uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
   uint64_t GetLiveSstFilesSize() const;   // REQUIRE: DB mutex held
   uint64_t GetTotalBlobFileSize() const;  // REQUIRE: DB mutex held
-  // REQUIRE: DB mutex held
   void SetMemtable(MemTable* new_mem) {
-    AssignMemtableID(new_mem);
+    uint64_t memtable_id = last_memtable_id_.fetch_add(1) + 1;
+    new_mem->SetID(memtable_id);
     mem_ = new_mem;
   }
 
-  void AssignMemtableID(ReadOnlyMemTable* new_imm) {
-    new_imm->SetID(++last_memtable_id_);
-  }
-
   // calculate the oldest log needed for the durability of this column family
   uint64_t OldestLogToKeep();
 
@@ -406,18 +378,15 @@ class ColumnFamilyData {
                          SequenceNumber earliest_seq);
 
   TableCache* table_cache() const { return table_cache_.get(); }
-  BlobFileCache* blob_file_cache() const { return blob_file_cache_.get(); }
   BlobSource* blob_source() const { return blob_source_.get(); }
 
   // See documentation in compaction_picker.h
   // REQUIRES: DB mutex held
   bool NeedsCompaction() const;
   // REQUIRES: DB mutex held
-  Compaction* PickCompaction(
-      const MutableCFOptions& mutable_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& existing_snapshots,
-      const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer);
+  Compaction* PickCompaction(const MutableCFOptions& mutable_options,
+                             const MutableDBOptions& mutable_db_options,
+                             LogBuffer* log_buffer);
 
   // Check if the passed range overlap with any running compactions.
   // REQUIRES: DB mutex held
@@ -432,7 +401,7 @@ class ColumnFamilyData {
   //    duration of this function.
   //
   // Thread-safe
-  Status RangesOverlapWithMemtables(const autovector<UserKeyRange>& ranges,
+  Status RangesOverlapWithMemtables(const autovector<Range>& ranges,
                                     SuperVersion* super_version,
                                     bool allow_data_in_errors, bool* overlap);
 
@@ -461,8 +430,8 @@ class ColumnFamilyData {
     return internal_comparator_;
   }
 
-  const InternalTblPropCollFactories* internal_tbl_prop_coll_factories() const {
-    return &internal_tbl_prop_coll_factories_;
+  const IntTblPropCollectorFactories* int_tbl_prop_collector_factories() const {
+    return &int_tbl_prop_collector_factories_;
   }
 
   SuperVersion* GetSuperVersion() { return super_version_; }
@@ -519,6 +488,8 @@ class ColumnFamilyData {
     return initial_cf_options_;
   }
 
+  Env::WriteLifeTimeHint CalculateSSTWriteHint(int level);
+
   // created_dirs remembers directory created, so that we don't need to call
   // the same data creation operation again.
   Status AddDirectories(
@@ -578,10 +549,6 @@ class ColumnFamilyData {
   // of its files (if missing)
   void RecoverEpochNumbers();
 
-  int GetUnflushedMemTableCountForWriteStallCheck() const {
-    return (mem_->IsEmpty() ? 0 : 1) + imm_.NumNotFlushed();
-  }
-
  private:
   friend class ColumnFamilySet;
   ColumnFamilyData(uint32_t id, const std::string& name,
@@ -606,17 +573,8 @@ class ColumnFamilyData {
   std::atomic<bool> initialized_;
   std::atomic<bool> dropped_;  // true if client dropped it
 
-  // When user-defined timestamps in memtable only feature is enabled, this
-  // flag indicates a successfully requested flush that should
-  // skip being rescheduled and haven't undergone the rescheduling check yet.
-  // This flag is cleared when a check skips rescheduling a FlushRequest.
-  // With this flag, automatic flushes in regular cases can continue to
-  // retain UDTs by getting rescheduled as usual while manual flushes and
-  // error recovery flushes will proceed without getting rescheduled.
-  std::atomic<bool> flush_skip_reschedule_;
-
   const InternalKeyComparator internal_comparator_;
-  InternalTblPropCollFactories internal_tbl_prop_coll_factories_;
+  IntTblPropCollectorFactories int_tbl_prop_collector_factories_;
 
   const ColumnFamilyOptions initial_cf_options_;
   const ImmutableOptions ioptions_;
@@ -677,7 +635,7 @@ class ColumnFamilyData {
   bool allow_2pc_;
 
   // Memtable id to track flush.
-  uint64_t last_memtable_id_;
+  std::atomic<uint64_t> last_memtable_id_;
 
   // Directories corresponding to cf_paths.
   std::vector<std::shared_ptr<FSDirectory>> data_dirs_;
@@ -896,17 +854,17 @@ class ColumnFamilyMemTablesImpl : public ColumnFamilyMemTables {
   // REQUIRES: Seek() called first
   // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
   //           under a DB mutex OR from a write thread
-  MemTable* GetMemTable() const override;
+  virtual MemTable* GetMemTable() const override;
 
   // Returns column family handle for the selected column family
   // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
   //           under a DB mutex OR from a write thread
-  ColumnFamilyHandle* GetColumnFamilyHandle() override;
+  virtual ColumnFamilyHandle* GetColumnFamilyHandle() override;
 
   // Cannot be called while another thread is calling Seek().
   // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
   //           under a DB mutex OR from a write thread
-  ColumnFamilyData* current() override { return current_; }
+  virtual ColumnFamilyData* current() override { return current_; }
 
  private:
   ColumnFamilySet* column_family_set_;
@@ -914,11 +872,12 @@ class ColumnFamilyMemTablesImpl : public ColumnFamilyMemTables {
   ColumnFamilyHandleInternal handle_;
 };
 
-uint32_t GetColumnFamilyID(ColumnFamilyHandle* column_family);
+extern uint32_t GetColumnFamilyID(ColumnFamilyHandle* column_family);
 
-const Comparator* GetColumnFamilyUserComparator(
+extern const Comparator* GetColumnFamilyUserComparator(
     ColumnFamilyHandle* column_family);
 
-const ImmutableOptions& GetImmutableOptions(ColumnFamilyHandle* column_family);
+extern const ImmutableOptions& GetImmutableOptions(
+    ColumnFamilyHandle* column_family);
 
 }  // namespace ROCKSDB_NAMESPACE

db/column_family_test.cc

@@ -23,7 +23,6 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
-#include "rocksdb/listener.h"
 #include "rocksdb/utilities/object_registry.h"
 #include "test_util/sync_point.h"
 #include "test_util/testharness.h"
@@ -35,13 +34,6 @@
 #include "utilities/merge_operators.h"
 
 namespace ROCKSDB_NAMESPACE {
-namespace {
-std::string EncodeAsUint64(uint64_t number) {
-  std::string result;
-  PutFixed64(&result, number);
-  return result;
-}
-}  // namespace
 
 static const int kValueSize = 1000;
 
@@ -278,7 +270,7 @@ class ColumnFamilyTestBase : public testing::Test {
 
   void Reopen(const std::vector<ColumnFamilyOptions> options = {}) {
     std::vector<std::string> names;
-    for (const auto& name : names_) {
+    for (auto name : names_) {
       if (name != "") {
         names.push_back(name);
       }
@@ -615,7 +607,7 @@ TEST_P(FlushEmptyCFTestWithParam, FlushEmptyCFTest) {
   // Preserve file system state up to here to simulate a crash condition.
   fault_env->SetFilesystemActive(false);
   std::vector<std::string> names;
-  for (const auto& name : names_) {
+  for (auto name : names_) {
     if (name != "") {
       names.push_back(name);
     }
@@ -677,7 +669,7 @@ TEST_P(FlushEmptyCFTestWithParam, FlushEmptyCFTest2) {
   // Preserve file system state up to here to simulate a crash condition.
   fault_env->SetFilesystemActive(false);
   std::vector<std::string> names;
-  for (const auto& name : names_) {
+  for (auto name : names_) {
     if (name != "") {
       names.push_back(name);
     }
@@ -1042,7 +1034,7 @@ TEST_P(ColumnFamilyTest, CrashAfterFlush) {
   fault_env->SetFilesystemActive(false);
 
   std::vector<std::string> names;
-  for (const auto& name : names_) {
+  for (auto name : names_) {
     if (name != "") {
       names.push_back(name);
     }
@@ -2612,92 +2604,90 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
   mutable_cf_options.hard_pending_compaction_bytes_limit = 2000;
   mutable_cf_options.disable_auto_compactions = false;
 
-  auto dbmu = dbfull()->TEST_Mutex();
-
-  vstorage->TEST_set_estimated_compaction_needed_bytes(50, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(50);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(201, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(201);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(400, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(400);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(500, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(500);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(450, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(450);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(205, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(205);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(202, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(202);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(201, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(201);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(198, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(198);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(399, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(399);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(599, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(599);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(2001, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(2001);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(3001, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(3001);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(390, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(390);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(100, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(100);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
@@ -2716,7 +2706,7 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(0);
-  vstorage->TEST_set_estimated_compaction_needed_bytes(300, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(300);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
@@ -2728,14 +2718,14 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25 / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(200, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(200);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(0);
-  vstorage->TEST_set_estimated_compaction_needed_bytes(0, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(0);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
@@ -2754,7 +2744,7 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
   ASSERT_EQ(kBaseRate, dbfull()->TEST_write_controler().delayed_write_rate());
 
   vstorage->set_l0_delay_trigger_count(60);
-  vstorage->TEST_set_estimated_compaction_needed_bytes(300, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(300);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
@@ -2763,14 +2753,14 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
 
   mutable_cf_options.disable_auto_compactions = false;
   vstorage->set_l0_delay_trigger_count(70);
-  vstorage->TEST_set_estimated_compaction_needed_bytes(500, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(500);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(71);
-  vstorage->TEST_set_estimated_compaction_needed_bytes(501, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(501);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
@@ -2795,21 +2785,19 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
   mutable_cf_options.soft_pending_compaction_bytes_limit = 200;
   mutable_cf_options.hard_pending_compaction_bytes_limit = 2000;
 
-  auto dbmu = dbfull()->TEST_Mutex();
-
-  vstorage->TEST_set_estimated_compaction_needed_bytes(40, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(40);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(50, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(50);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(300, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(300);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(45, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(45);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
@@ -2865,55 +2853,53 @@ TEST_P(ColumnFamilyTest, WriteStallTwoColumnFamilies) {
   MutableCFOptions mutable_cf_options1 = mutable_cf_options;
   mutable_cf_options1.soft_pending_compaction_bytes_limit = 500;
 
-  auto dbmu = dbfull()->TEST_Mutex();
-
-  vstorage->TEST_set_estimated_compaction_needed_bytes(50, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(50);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(201, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(201);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(600, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(600);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(70, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(70);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(800, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(800);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(300, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(300);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(700, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(700);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(500, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(500);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(600, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(600);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
@@ -2946,31 +2932,29 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
   MutableCFOptions mutable_cf_options1 = mutable_cf_options;
   mutable_cf_options1.level0_slowdown_writes_trigger = 16;
 
-  auto dbmu = dbfull()->TEST_Mutex();
-
-  vstorage->TEST_set_estimated_compaction_needed_bytes(40, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(40);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(60, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(60);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(30, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(30);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(70, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(70);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage->TEST_set_estimated_compaction_needed_bytes(20, dbmu);
+  vstorage->TEST_set_estimated_compaction_needed_bytes(20);
   RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
-  vstorage1->TEST_set_estimated_compaction_needed_bytes(3, dbmu);
+  vstorage1->TEST_set_estimated_compaction_needed_bytes(3);
   RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
@@ -2996,13 +2980,10 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupForCompactionDebt) {
   mutable_cf_options.soft_pending_compaction_bytes_limit =
       std::numeric_limits<uint64_t>::max();
 
-  auto dbmu = dbfull()->TEST_Mutex();
-
   {
     // No bottommost data, so debt ratio cannot trigger speedup.
     VersionStorageInfo* vstorage = cfd->current()->storage_info();
-    vstorage->TEST_set_estimated_compaction_needed_bytes(1048576 /* 1MB */,
-                                                         dbmu);
+    vstorage->TEST_set_estimated_compaction_needed_bytes(1048576 /* 1MB */);
     RecalculateWriteStallConditions(cfd, mutable_cf_options);
     ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
   }
@@ -3012,102 +2993,18 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupForCompactionDebt) {
   ASSERT_OK(db_->Flush(FlushOptions()));
 
   {
+    // 1MB debt is way bigger than bottommost data so definitely triggers
+    // speedup.
     VersionStorageInfo* vstorage = cfd->current()->storage_info();
-    // Eight bytes is way smaller than bottommost data so definitely does not
-    // trigger speedup.
-    vstorage->TEST_set_estimated_compaction_needed_bytes(8, dbmu);
-    RecalculateWriteStallConditions(cfd, mutable_cf_options);
-    ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-
-    // 1MB is much larger than bottommost level size. However, since it's too
-    // small in terms of absolute size, it does not trigger parallel compaction
-    // in this case (see GetPendingCompactionBytesForCompactionSpeedup()).
-    vstorage->TEST_set_estimated_compaction_needed_bytes(1048576 /* 1MB */,
-                                                         dbmu);
-    RecalculateWriteStallConditions(cfd, mutable_cf_options);
-    ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-
-    vstorage->TEST_set_estimated_compaction_needed_bytes(
-        2 * mutable_cf_options.max_bytes_for_level_base, dbmu);
+    vstorage->TEST_set_estimated_compaction_needed_bytes(1048576 /* 1MB */);
     RecalculateWriteStallConditions(cfd, mutable_cf_options);
     ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
-  }
-}
 
-TEST_P(ColumnFamilyTest, CompactionSpeedupForMarkedFiles) {
-  const int kParallelismLimit = 3;
-  class AlwaysCompactTpc : public TablePropertiesCollector {
-   public:
-    Status Finish(UserCollectedProperties* /* properties */) override {
-      return Status::OK();
-    }
-
-    UserCollectedProperties GetReadableProperties() const override {
-      return UserCollectedProperties{};
-    }
-
-    const char* Name() const override { return "AlwaysCompactTpc"; }
-
-    bool NeedCompact() const override { return true; }
-  };
-
-  class AlwaysCompactTpcf : public TablePropertiesCollectorFactory {
-   public:
-    TablePropertiesCollector* CreateTablePropertiesCollector(
-        TablePropertiesCollectorFactory::Context /* context */) override {
-      return new AlwaysCompactTpc();
-    }
-
-    const char* Name() const override { return "AlwaysCompactTpcf"; }
-  };
-
-  column_family_options_.num_levels = 2;
-  column_family_options_.table_properties_collector_factories.emplace_back(
-      std::make_shared<AlwaysCompactTpcf>());
-  db_options_.max_background_compactions = kParallelismLimit;
-  Open();
-
-  // Make a nonempty last level. Only marked files in upper levels count.
-  ASSERT_OK(db_->Put(WriteOptions(), "foo", "bar"));
-  ASSERT_OK(db_->Flush(FlushOptions()));
-  WaitForCompaction();
-  AssertFilesPerLevel("0,1", 0 /* cf */);
-
-  // We should calculate the limit by obtaining the number of env background
-  // threads, because the current test case will share the same env
-  // with another case that may have already increased the number of
-  // background threads which is larger than kParallelismLimit
-  const auto limit = env_->GetBackgroundThreads(Env::Priority::LOW);
-
-  // Block the compaction thread pool so marked files accumulate in L0.
-  std::vector<std::shared_ptr<test::SleepingBackgroundTask>> sleeping_tasks;
-  for (int i = 0; i < limit; i++) {
-    sleeping_tasks.emplace_back(
-        std::make_shared<test::SleepingBackgroundTask>());
-    env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask,
-                   sleeping_tasks[i].get(), Env::Priority::LOW);
-    sleeping_tasks[i]->WaitUntilSleeping();
-  }
-
-  // Zero marked upper-level files. No speedup.
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-  AssertFilesPerLevel("0,1", 0 /* cf */);
-
-  // One marked upper-level file. No speedup.
-  ASSERT_OK(db_->Put(WriteOptions(), "foo", "bar"));
-  ASSERT_OK(db_->Flush(FlushOptions()));
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-  AssertFilesPerLevel("1,1", 0 /* cf */);
-
-  // Two marked upper-level files. Speedup.
-  ASSERT_OK(db_->Put(WriteOptions(), "foo", "bar"));
-  ASSERT_OK(db_->Flush(FlushOptions()));
-  ASSERT_EQ(kParallelismLimit, dbfull()->TEST_BGCompactionsAllowed());
-  AssertFilesPerLevel("2,1", 0 /* cf */);
-
-  for (int i = 0; i < limit; i++) {
-    sleeping_tasks[i]->WakeUp();
-    sleeping_tasks[i]->WaitUntilDone();
+    // Eight bytes is way smaller than bottommost data so definitely does not
+    // trigger speedup.
+    vstorage->TEST_set_estimated_compaction_needed_bytes(8);
+    RecalculateWriteStallConditions(cfd, mutable_cf_options);
+    ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
   }
 }
 
@@ -3192,8 +3089,6 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile1) {
   SpecialEnv env(Env::Default());
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  // When this option is removed, the test will need re-engineering
-  db_options_.background_close_inactive_wals = true;
   column_family_options_.memtable_factory.reset(
       test::NewSpecialSkipListFactory(2));
   Open();
@@ -3246,8 +3141,6 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile2) {
   env.SetBackgroundThreads(2, Env::HIGH);
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  // When this option is removed, the test will need re-engineering
-  db_options_.background_close_inactive_wals = true;
   column_family_options_.memtable_factory.reset(
       test::NewSpecialSkipListFactory(2));
   Open();
@@ -3305,8 +3198,6 @@ TEST_P(ColumnFamilyTest, ForwardIteratorCloseWALFile) {
   env.SetBackgroundThreads(2, Env::HIGH);
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  // When this option is removed, the test will need re-engineering
-  db_options_.background_close_inactive_wals = true;
   column_family_options_.memtable_factory.reset(
       test::NewSpecialSkipListFactory(3));
   column_family_options_.level0_file_num_compaction_trigger = 2;
@@ -3435,13 +3326,9 @@ TEST_P(ColumnFamilyTest, DISABLED_LogTruncationTest) {
   for (size_t i = 0; i < filenames.size(); i++) {
     uint64_t number;
     FileType type;
-    if (!(ParseFileName(filenames[i], &number, &type))) {
-      continue;
-    }
+    if (!(ParseFileName(filenames[i], &number, &type))) continue;
 
-    if (type != kWalFile) {
-      continue;
-    }
+    if (type != kWalFile) continue;
 
     logfs.push_back(filenames[i]);
   }
@@ -3631,9 +3518,7 @@ TEST(ColumnFamilyTest, ValidateMemtableKVChecksumOption) {
 }
 
 // Tests the flushing behavior of a column family to retain user-defined
-// timestamp when `persist_user_defined_timestamp` is false. The behavior of
-// auto flush is it makes some effort to retain user-defined timestamps while
-// the behavior of manual flush is that it skips retaining UDTs.
+// timestamp when `persist_user_defined_timestamp` is false.
 class ColumnFamilyRetainUDTTest : public ColumnFamilyTestBase {
  public:
   ColumnFamilyRetainUDTTest() : ColumnFamilyTestBase(kLatestFormatVersion) {}
@@ -3651,27 +3536,6 @@ class ColumnFamilyRetainUDTTest : public ColumnFamilyTestBase {
     return db_->Put(WriteOptions(), handles_[cf], Slice(key), Slice(ts),
                     Slice(value));
   }
-
-  std::string Get(int cf, const std::string& key, const std::string& read_ts) {
-    ReadOptions ropts;
-    Slice timestamp = read_ts;
-    ropts.timestamp = &timestamp;
-    std::string value;
-    Status s = db_->Get(ropts, handles_[cf], Slice(key), &value);
-    if (s.IsNotFound()) {
-      return "NOT_FOUND";
-    } else if (s.ok()) {
-      return value;
-    }
-    return "";
-  }
-
-  void CheckEffectiveCutoffTime(uint64_t expected_cutoff) {
-    std::string effective_full_history_ts_low;
-    EXPECT_OK(
-        db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
-    EXPECT_EQ(EncodeAsUint64(expected_cutoff), effective_full_history_ts_low);
-  }
 };
 
 class TestTsComparator : public Comparator {
@@ -3715,9 +3579,7 @@ TEST_F(ColumnFamilyRetainUDTTest, SanityCheck) {
   Close();
 }
 
-class AutoFlushRetainUDTTest : public ColumnFamilyRetainUDTTest {};
-
-TEST_F(AutoFlushRetainUDTTest, FullHistoryTsLowNotSet) {
+TEST_F(ColumnFamilyRetainUDTTest, FullHistoryTsLowNotSet) {
   SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
         ASSERT_NE(nullptr, arg);
@@ -3727,22 +3589,28 @@ TEST_F(AutoFlushRetainUDTTest, FullHistoryTsLowNotSet) {
 
   SyncPoint::GetInstance()->EnableProcessing();
   Open();
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-  // No `full_history_ts_low` explicitly set by user, auto flush is continued
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  // No `full_history_ts_low` explicitly set by user, flush is continued
   // without checking if its UDTs expired.
-  ASSERT_OK(dbfull()->TEST_SwitchWAL());
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+  ASSERT_OK(Flush(0));
 
   // After flush, `full_history_ts_low` should be automatically advanced to
   // the effective cutoff timestamp: write_ts + 1
-  CheckEffectiveCutoffTime(2);
+  std::string cutoff_ts;
+  PutFixed64(&cutoff_ts, 2);
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
   Close();
 
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
-TEST_F(AutoFlushRetainUDTTest, AllKeysExpired) {
+TEST_F(ColumnFamilyRetainUDTTest, AllKeysExpired) {
   SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
         ASSERT_NE(nullptr, arg);
@@ -3752,22 +3620,27 @@ TEST_F(AutoFlushRetainUDTTest, AllKeysExpired) {
 
   SyncPoint::GetInstance()->EnableProcessing();
   Open();
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(3)));
-  // All keys expired w.r.t the configured `full_history_ts_low`, auto flush
-  // continue without the need for a re-schedule.
-  ASSERT_OK(dbfull()->TEST_SwitchWAL());
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  std::string cutoff_ts;
+  PutFixed64(&cutoff_ts, 3);
+  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
+  // All keys expired w.r.t the configured `full_history_ts_low`, flush continue
+  // without the need for a re-schedule.
+  ASSERT_OK(Flush(0));
 
   // `full_history_ts_low` stays unchanged after flush.
-  CheckEffectiveCutoffTime(3);
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
   Close();
 
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
-
-TEST_F(AutoFlushRetainUDTTest, NotAllKeysExpiredFlushToAvoidWriteStall) {
+TEST_F(ColumnFamilyRetainUDTTest, NotAllKeysExpiredFlushToAvoidWriteStall) {
   SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
         ASSERT_NE(nullptr, arg);
@@ -3777,303 +3650,72 @@ TEST_F(AutoFlushRetainUDTTest, NotAllKeysExpiredFlushToAvoidWriteStall) {
 
   SyncPoint::GetInstance()->EnableProcessing();
   Open();
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(1)));
+  std::string cutoff_ts;
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  PutFixed64(&cutoff_ts, 1);
+  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
   ASSERT_OK(db_->SetOptions(handles_[0], {{"max_write_buffer_number", "1"}}));
-  // Not all keys expired, but auto flush is continued without a re-schedule
-  // because of risk of write stall.
-  ASSERT_OK(dbfull()->TEST_SwitchWAL());
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+  // Not all keys expired, but flush is continued without a re-schedule because
+  // of risk of write stall.
+  ASSERT_OK(Flush(0));
 
   // After flush, `full_history_ts_low` should be automatically advanced to
   // the effective cutoff timestamp: write_ts + 1
-  CheckEffectiveCutoffTime(2);
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+
+  cutoff_ts.clear();
+  PutFixed64(&cutoff_ts, 2);
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
   Close();
 
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
-TEST_F(AutoFlushRetainUDTTest, NotAllKeysExpiredFlushRescheduled) {
-  std::atomic<int> local_counter{1};
+TEST_F(ColumnFamilyRetainUDTTest, NotAllKeysExpiredFlushRescheduled) {
+  std::string cutoff_ts;
   SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::AfterRetainUDTReschedule:cb", [&](void* /*arg*/) {
         // Increasing full_history_ts_low so all keys expired after the initial
         // FlushRequest is rescheduled
-        ASSERT_OK(
-            db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(3)));
+        cutoff_ts.clear();
+        PutFixed64(&cutoff_ts, 3);
+        ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
       });
   SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
         ASSERT_NE(nullptr, arg);
         auto reschedule_count = *static_cast<int*>(arg);
         ASSERT_EQ(2, reschedule_count);
-        local_counter.fetch_add(1);
       });
   SyncPoint::GetInstance()->EnableProcessing();
 
   Open();
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(1)));
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  PutFixed64(&cutoff_ts, 1);
+  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
   // Not all keys expired, and there is no risk of write stall. Flush is
   // rescheduled. The actual flush happens after `full_history_ts_low` is
   // increased to mark all keys expired.
-  ASSERT_OK(dbfull()->TEST_SwitchWAL());
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
-  // Make sure callback is not skipped.
-  ASSERT_EQ(2, local_counter);
+  ASSERT_OK(Flush(0));
 
-  CheckEffectiveCutoffTime(3);
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+  // `full_history_ts_low` stays unchanged.
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
   Close();
 
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
-class ManualFlushSkipRetainUDTTest : public ColumnFamilyRetainUDTTest {
- public:
-  // Write an entry with timestamp that is not expired w.r.t cutoff timestamp,
-  // and make sure automatic flush would be rescheduled to retain UDT.
-  void CheckAutomaticFlushRetainUDT(uint64_t write_ts) {
-    std::atomic<int> local_counter{1};
-    SyncPoint::GetInstance()->SetCallBack(
-        "DBImpl::AfterRetainUDTReschedule:cb", [&](void* /*arg*/) {
-          // Increasing full_history_ts_low so all keys expired after the
-          // initial FlushRequest is rescheduled
-          ASSERT_OK(db_->IncreaseFullHistoryTsLow(
-              handles_[0], EncodeAsUint64(write_ts + 1)));
-        });
-    SyncPoint::GetInstance()->SetCallBack(
-        "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
-          ASSERT_NE(nullptr, arg);
-          auto reschedule_count = *static_cast<int*>(arg);
-          ASSERT_EQ(2, reschedule_count);
-          local_counter.fetch_add(1);
-        });
-    SyncPoint::GetInstance()->EnableProcessing();
-    EXPECT_OK(Put(0, "foo", EncodeAsUint64(write_ts),
-                  "foo" + std::to_string(write_ts)));
-    EXPECT_OK(dbfull()->TEST_SwitchWAL());
-    EXPECT_OK(dbfull()->TEST_WaitForFlushMemTable());
-    // Make sure callback is not skipped.
-    EXPECT_EQ(2, local_counter);
-
-    SyncPoint::GetInstance()->DisableProcessing();
-    SyncPoint::GetInstance()->ClearAllCallBacks();
-  }
-};
-
-TEST_F(ManualFlushSkipRetainUDTTest, ManualFlush) {
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-
-  // Manual flush proceeds without trying to retain UDT.
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-  ASSERT_OK(Flush(0));
-  CheckEffectiveCutoffTime(2);
-  CheckAutomaticFlushRetainUDT(3);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, FlushRemovesStaleEntries) {
-  column_family_options_.max_write_buffer_number = 4;
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-
-  ColumnFamilyHandle* cfh = db_->DefaultColumnFamily();
-  ColumnFamilyData* cfd =
-      static_cast_with_check<ColumnFamilyHandleImpl>(cfh)->cfd();
-  for (int version = 0; version < 100; version++) {
-    if (version == 50) {
-      ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable(cfd));
-    }
-    ASSERT_OK(
-        Put(0, "foo", EncodeAsUint64(version), "v" + std::to_string(version)));
-  }
-
-  ASSERT_OK(Flush(0));
-  TablePropertiesCollection tables_properties;
-  ASSERT_OK(db_->GetPropertiesOfAllTables(&tables_properties));
-  ASSERT_EQ(1, tables_properties.size());
-  std::shared_ptr<const TableProperties> table_properties =
-      tables_properties.begin()->second;
-  ASSERT_EQ(1, table_properties->num_entries);
-  ASSERT_EQ(0, table_properties->num_deletions);
-  ASSERT_EQ(0, table_properties->num_range_deletions);
-  CheckEffectiveCutoffTime(100);
-  CheckAutomaticFlushRetainUDT(101);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, RangeDeletionFlushRemovesStaleEntries) {
-  column_family_options_.max_write_buffer_number = 4;
-  Open();
-  // TODO(yuzhangyu): a non 0 full history ts low is needed for this garbage
-  // collection to kick in. This doesn't work well for the very first flush of
-  // the column family. Not a big issue, but would be nice to improve this.
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(9)));
-
-  for (int i = 10; i < 100; i++) {
-    ASSERT_OK(Put(0, "foo" + std::to_string(i), EncodeAsUint64(i),
-                  "val" + std::to_string(i)));
-    if (i % 2 == 1) {
-      ASSERT_OK(db_->DeleteRange(WriteOptions(), "foo" + std::to_string(i - 1),
-                                 "foo" + std::to_string(i), EncodeAsUint64(i)));
-    }
-  }
-
-  ASSERT_OK(Flush(0));
-  CheckEffectiveCutoffTime(100);
-  std::string read_ts = EncodeAsUint64(100);
-  std::string min_ts = EncodeAsUint64(0);
-  ReadOptions ropts;
-  Slice read_ts_slice = read_ts;
-  std::string value;
-  ropts.timestamp = &read_ts_slice;
-  {
-    Iterator* iter = db_->NewIterator(ropts);
-    iter->SeekToFirst();
-    int i = 11;
-    while (iter->Valid()) {
-      ASSERT_TRUE(iter->Valid());
-      ASSERT_EQ("foo" + std::to_string(i), iter->key());
-      ASSERT_EQ("val" + std::to_string(i), iter->value());
-      ASSERT_EQ(min_ts, iter->timestamp());
-      iter->Next();
-      i += 2;
-    }
-    ASSERT_OK(iter->status());
-    delete iter;
-  }
-  TablePropertiesCollection tables_properties;
-  ASSERT_OK(db_->GetPropertiesOfAllTables(&tables_properties));
-  ASSERT_EQ(1, tables_properties.size());
-  std::shared_ptr<const TableProperties> table_properties =
-      tables_properties.begin()->second;
-  // 45 point data + 45 range deletions. 45 obsolete point data are garbage
-  // collected.
-  ASSERT_EQ(90, table_properties->num_entries);
-  ASSERT_EQ(45, table_properties->num_deletions);
-  ASSERT_EQ(45, table_properties->num_range_deletions);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, ManualCompaction) {
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-
-  // Manual compaction proceeds without trying to retain UDT.
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v2"));
-  ASSERT_OK(
-      db_->CompactRange(CompactRangeOptions(), handles_[0], nullptr, nullptr));
-  CheckEffectiveCutoffTime(2);
-  CheckAutomaticFlushRetainUDT(3);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, BulkLoading) {
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-
-  // Test flush behavior in bulk loading scenarios.
-  Options options(db_options_, column_family_options_);
-  std::string sst_files_dir = dbname_ + "/sst_files/";
-  ASSERT_OK(DestroyDir(env_, sst_files_dir));
-  ASSERT_OK(env_->CreateDir(sst_files_dir));
-  SstFileWriter sst_file_writer(EnvOptions(), options);
-  std::string file1 = sst_files_dir + "file1.sst";
-  ASSERT_OK(sst_file_writer.Open(file1));
-  ASSERT_OK(sst_file_writer.Put("foo", EncodeAsUint64(0), "v2"));
-  ExternalSstFileInfo file1_info;
-  ASSERT_OK(sst_file_writer.Finish(&file1_info));
-
-  // Bulk loading in UDT mode doesn't support external file key range overlap
-  // with DB key range.
-  ASSERT_TRUE(db_->IngestExternalFile({file1}, IngestExternalFileOptions())
-                  .IsInvalidArgument());
-
-  std::string file2 = sst_files_dir + "file2.sst";
-  ASSERT_OK(sst_file_writer.Open(file2));
-  ASSERT_OK(sst_file_writer.Put("bar", EncodeAsUint64(0), "val"));
-  ExternalSstFileInfo file2_info;
-  ASSERT_OK(sst_file_writer.Finish(&file2_info));
-  // A successful bulk loading, and it doesn't trigger any flush. As a result
-  // the effective cutoff timestamp is also unchanged.
-  ASSERT_OK(db_->IngestExternalFile({file2}, IngestExternalFileOptions()));
-
-  ASSERT_EQ(Get(0, "foo", EncodeAsUint64(1)), "v1");
-  ASSERT_EQ(Get(0, "bar", EncodeAsUint64(0)), "val");
-  CheckEffectiveCutoffTime(0);
-  CheckAutomaticFlushRetainUDT(1);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, AutomaticFlushQueued) {
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-
-  ASSERT_OK(Put(0, "foo", EncodeAsUint64(1), "v1"));
-  ASSERT_OK(dbfull()->TEST_SwitchWAL());
-  CheckEffectiveCutoffTime(0);
-
-  // Default `max_write_buffer_number=2` used, writing another memtable can get
-  // automatic flush to proceed because of memory pressure. Not doing that so
-  // we can test automatic flush gets to proceed because of an ongoing manual
-  // flush attempt.
-  ASSERT_OK(Flush(0));
-  CheckEffectiveCutoffTime(2);
-  CheckAutomaticFlushRetainUDT(3);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, ConcurrentManualFlushes) {
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-
-  std::vector<ROCKSDB_NAMESPACE::port::Thread> manual_flush_tds;
-  std::atomic<int> next_ts{0};
-  std::mutex mtx;
-  std::condition_variable cv;
-
-  auto manual_flush = [&](int write_ts) {
-    {
-      std::unique_lock<std::mutex> lock(mtx);
-      cv.wait(lock,
-              [&write_ts, &next_ts] { return write_ts == next_ts.load(); });
-      ASSERT_OK(Put(0, "foo" + std::to_string(write_ts),
-                    EncodeAsUint64(write_ts),
-                    "val_" + std::to_string(write_ts)));
-      next_ts.fetch_add(1);
-      cv.notify_all();
-    }
-    if (write_ts % 2 == 0) {
-      ASSERT_OK(Flush(0));
-    } else {
-      ASSERT_OK(db_->CompactRange(CompactRangeOptions(), handles_[0], nullptr,
-                                  nullptr));
-    }
-  };
-
-  for (int write_ts = 0; write_ts < 10; write_ts++) {
-    manual_flush_tds.emplace_back(manual_flush, write_ts);
-  }
-
-  for (auto& td : manual_flush_tds) {
-    td.join();
-  }
-
-  CheckEffectiveCutoffTime(10);
-  CheckAutomaticFlushRetainUDT(11);
-  Close();
-}
-
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/compact_files_test.cc

@@ -34,8 +34,8 @@ class CompactFilesTest : public testing::Test {
 // A class which remembers the name of each flushed file.
 class FlushedFileCollector : public EventListener {
  public:
-  FlushedFileCollector() = default;
-  ~FlushedFileCollector() override = default;
+  FlushedFileCollector() {}
+  ~FlushedFileCollector() override {}
 
   void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
     std::lock_guard<std::mutex> lock(mutex_);
@@ -45,7 +45,7 @@ class FlushedFileCollector : public EventListener {
   std::vector<std::string> GetFlushedFiles() {
     std::lock_guard<std::mutex> lock(mutex_);
     std::vector<std::string> result;
-    for (const auto& fname : flushed_files_) {
+    for (auto fname : flushed_files_) {
       result.push_back(fname);
     }
     return result;
@@ -159,9 +159,7 @@ TEST_F(CompactFilesTest, MultipleLevel) {
   // Compact files except the file in L3
   std::vector<std::string> files;
   for (int i = 0; i < 6; ++i) {
-    if (i == 3) {
-      continue;
-    }
+    if (i == 3) continue;
     for (auto& file : meta.levels[i].files) {
       files.push_back(file.db_path + "/" + file.name);
     }
@@ -230,7 +228,7 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
   ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForCompact());
 
   // verify all compaction input files are deleted
-  for (const auto& fname : l0_files) {
+  for (auto fname : l0_files) {
     ASSERT_EQ(Status::NotFound(), env_->FileExists(fname));
   }
   delete db;
@@ -441,50 +439,6 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
   }
 }
 
-TEST_F(CompactFilesTest, CompressionWithBlockAlign) {
-  Options options;
-  options.compression = CompressionType::kNoCompression;
-  options.create_if_missing = true;
-  options.disable_auto_compactions = true;
-
-  std::shared_ptr<FlushedFileCollector> collector =
-      std::make_shared<FlushedFileCollector>();
-  options.listeners.push_back(collector);
-
-  {
-    BlockBasedTableOptions bbto;
-    bbto.block_align = true;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-  }
-
-  std::unique_ptr<DB> db;
-  {
-    DB* _db = nullptr;
-    ASSERT_OK(DB::Open(options, db_name_, &_db));
-    db.reset(_db);
-  }
-
-  ASSERT_OK(db->Put(WriteOptions(), "key", "val"));
-  ASSERT_OK(db->Flush(FlushOptions()));
-
-  // Ensure background work is fully finished including listener callbacks
-  // before accessing listener state.
-  ASSERT_OK(
-      static_cast_with_check<DBImpl>(db.get())->TEST_WaitForBackgroundWork());
-  auto l0_files = collector->GetFlushedFiles();
-  ASSERT_EQ(1, l0_files.size());
-
-  // We can run this test even without Snappy support because we expect the
-  // `CompactFiles()` to fail before actually invoking Snappy compression.
-  CompactionOptions compaction_opts;
-  compaction_opts.compression = CompressionType::kSnappyCompression;
-  ASSERT_TRUE(db->CompactFiles(compaction_opts, l0_files, 1 /* output_level */)
-                  .IsInvalidArgument());
-
-  compaction_opts.compression = CompressionType::kDisableCompressionOption;
-  ASSERT_OK(db->CompactFiles(compaction_opts, l0_files, 1 /* output_level */));
-}
-
 TEST_F(CompactFilesTest, GetCompactionJobInfo) {
   Options options;
   options.create_if_missing = true;
@@ -538,3 +492,4 @@ int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }
+

db/compaction/compaction.cc

@@ -13,7 +13,6 @@
 #include <vector>
 
 #include "db/column_family.h"
-#include "db/dbformat.h"
 #include "logging/logging.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/sst_partitioner.h"
@@ -22,6 +21,9 @@
 
 namespace ROCKSDB_NAMESPACE {
 
+const uint64_t kRangeTombstoneSentinel =
+    PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
+
 int sstableKeyCompare(const Comparator* uc, const Slice& a, const Slice& b) {
   auto c = uc->CompareWithoutTimestamp(ExtractUserKey(a), ExtractUserKey(b));
   if (c != 0) {
@@ -63,9 +65,7 @@ uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
   return sum;
 }
 
-// TODO(hx235): consider making this function part of the construction so we
-// don't forget to call it
-void Compaction::FinalizeInputInfo(Version* _input_version) {
+void Compaction::SetInputVersion(Version* _input_version) {
   input_version_ = _input_version;
   cfd_ = input_version_->cfd();
 
@@ -162,9 +162,7 @@ std::vector<CompactionInputFiles> Compaction::PopulateWithAtomicBoundaries(
     AtomicCompactionUnitBoundary cur_boundary;
     size_t first_atomic_idx = 0;
     auto add_unit_boundary = [&](size_t to) {
-      if (first_atomic_idx == to) {
-        return;
-      }
+      if (first_atomic_idx == to) return;
       for (size_t k = first_atomic_idx; k < to; k++) {
         inputs[i].atomic_compaction_unit_boundaries.push_back(cur_boundary);
       }
@@ -283,10 +281,9 @@ Compaction::Compaction(
     uint32_t _output_path_id, CompressionType _compression,
     CompressionOptions _compression_opts, Temperature _output_temperature,
     uint32_t _max_subcompactions, std::vector<FileMetaData*> _grandparents,
-    std::optional<SequenceNumber> _earliest_snapshot,
-    const SnapshotChecker* _snapshot_checker, bool _manual_compaction,
-    const std::string& _trim_ts, double _score, bool _deletion_compaction,
-    bool l0_files_might_overlap, CompactionReason _compaction_reason,
+    bool _manual_compaction, const std::string& _trim_ts, double _score,
+    bool _deletion_compaction, bool l0_files_might_overlap,
+    CompactionReason _compaction_reason,
     BlobGarbageCollectionPolicy _blob_garbage_collection_policy,
     double _blob_garbage_collection_age_cutoff)
     : input_vstorage_(vstorage),
@@ -308,8 +305,6 @@ Compaction::Compaction(
       l0_files_might_overlap_(l0_files_might_overlap),
       inputs_(PopulateWithAtomicBoundaries(vstorage, std::move(_inputs))),
       grandparents_(std::move(_grandparents)),
-      earliest_snapshot_(_earliest_snapshot),
-      snapshot_checker_(_snapshot_checker),
       score_(_score),
       bottommost_level_(
           // For simplicity, we don't support the concept of "bottommost level"
@@ -345,9 +340,8 @@ Compaction::Compaction(
           _compaction_reason == CompactionReason::kExternalSstIngestion ||
                   _compaction_reason == CompactionReason::kRefitLevel
               ? Compaction::kInvalidLevel
-              : EvaluatePenultimateLevel(vstorage, mutable_cf_options_,
-                                         immutable_options_, start_level_,
-                                         output_level_)) {
+              : EvaluatePenultimateLevel(vstorage, immutable_options_,
+                                         start_level_, output_level_)) {
   MarkFilesBeingCompacted(true);
   if (is_manual_compaction_) {
     compaction_reason_ = CompactionReason::kManualCompaction;
@@ -358,9 +352,11 @@ Compaction::Compaction(
 
   // for the non-bottommost levels, it tries to build files match the target
   // file size, but not guaranteed. It could be 2x the size of the target size.
-  max_output_file_size_ = bottommost_level_ || grandparents_.empty()
-                              ? target_output_file_size_
-                              : 2 * target_output_file_size_;
+  max_output_file_size_ =
+      bottommost_level_ || grandparents_.empty() ||
+              !_immutable_options.level_compaction_dynamic_file_size
+          ? target_output_file_size_
+          : 2 * target_output_file_size_;
 
 #ifndef NDEBUG
   for (size_t i = 1; i < inputs_.size(); ++i) {
@@ -368,17 +364,12 @@ Compaction::Compaction(
   }
 #endif
 
-  // setup input_levels_ and filtered_input_levels_
+  // setup input_levels_
   {
     input_levels_.resize(num_input_levels());
-    filtered_input_levels_.resize(num_input_levels());
-    if (earliest_snapshot_.has_value()) {
-      FilterInputsForCompactionIterator();
-    } else {
-      for (size_t which = 0; which < num_input_levels(); which++) {
-        DoGenerateLevelFilesBrief(&input_levels_[which], inputs_[which].files,
-                                  &arena_);
-      }
+    for (size_t which = 0; which < num_input_levels(); which++) {
+      DoGenerateLevelFilesBrief(&input_levels_[which], inputs_[which].files,
+                                &arena_);
     }
   }
 
@@ -695,11 +686,12 @@ bool Compaction::KeyRangeNotExistsBeyondOutputLevel(
 };
 
 // Mark (or clear) each file that is being compacted
-void Compaction::MarkFilesBeingCompacted(bool being_compacted) const {
+void Compaction::MarkFilesBeingCompacted(bool mark_as_compacted) {
   for (size_t i = 0; i < num_input_levels(); i++) {
     for (size_t j = 0; j < inputs_[i].size(); j++) {
-      assert(being_compacted != inputs_[i][j]->being_compacted);
-      inputs_[i][j]->being_compacted = being_compacted;
+      assert(mark_as_compacted ? !inputs_[i][j]->being_compacted
+                               : inputs_[i][j]->being_compacted);
+      inputs_[i][j]->being_compacted = mark_as_compacted;
     }
   }
 }
@@ -743,7 +735,7 @@ uint64_t Compaction::CalculateTotalInputSize() const {
   return size;
 }
 
-void Compaction::ReleaseCompactionFiles(const Status& status) {
+void Compaction::ReleaseCompactionFiles(Status status) {
   MarkFilesBeingCompacted(false);
   cfd_->compaction_picker()->ReleaseCompactionFiles(this, status);
 }
@@ -754,10 +746,8 @@ void Compaction::ResetNextCompactionIndex() {
 }
 
 namespace {
-int InputSummary(const std::vector<FileMetaData*>& files,
-                 const std::vector<bool>& files_filtered, char* output,
+int InputSummary(const std::vector<FileMetaData*>& files, char* output,
                  int len) {
-  assert(files_filtered.empty() || (files.size() == files_filtered.size()));
   *output = '\0';
   int write = 0;
   for (size_t i = 0; i < files.size(); i++) {
@@ -765,17 +755,9 @@ int InputSummary(const std::vector<FileMetaData*>& files,
     int ret;
     char sztxt[16];
     AppendHumanBytes(files.at(i)->fd.GetFileSize(), sztxt, 16);
-    if (files_filtered.empty()) {
-      ret = snprintf(output + write, sz, "%" PRIu64 "(%s) ",
-                     files.at(i)->fd.GetNumber(), sztxt);
-    } else {
-      ret = snprintf(output + write, sz, "%" PRIu64 "(%s filtered:%s) ",
-                     files.at(i)->fd.GetNumber(), sztxt,
-                     files_filtered.at(i) ? "true" : "false");
-    }
-    if (ret < 0 || ret >= sz) {
-      break;
-    }
+    ret = snprintf(output + write, sz, "%" PRIu64 "(%s) ",
+                   files.at(i)->fd.GetNumber(), sztxt);
+    if (ret < 0 || ret >= sz) break;
     write += ret;
   }
   // if files.size() is non-zero, overwrite the last space
@@ -798,15 +780,8 @@ void Compaction::Summary(char* output, int len) {
         return;
       }
     }
-
-    assert(non_start_level_input_files_filtered_.empty() ||
-           non_start_level_input_files_filtered_.size() == inputs_.size() - 1);
-    write += InputSummary(
-        inputs_[level_iter].files,
-        (level_iter == 0 || non_start_level_input_files_filtered_.empty())
-            ? std::vector<bool>{}
-            : non_start_level_input_files_filtered_[level_iter - 1],
-        output + write, len - write);
+    write +=
+        InputSummary(inputs_[level_iter].files, output + write, len - write);
     if (write < 0 || write >= len) {
       return;
     }
@@ -889,11 +864,6 @@ bool Compaction::ShouldFormSubcompactions() const {
     return false;
   }
 
-  if (mutable_cf_options_.table_factory->Name() ==
-      TableFactory::kPlainTableName()) {
-    return false;
-  }
-
   // Round-Robin pri under leveled compaction allows subcompactions by default
   // and the number of subcompactions can be larger than max_subcompactions_
   if (cfd_->ioptions()->compaction_pri == kRoundRobin &&
@@ -937,25 +907,6 @@ bool Compaction::DoesInputReferenceBlobFiles() const {
   return false;
 }
 
-uint64_t Compaction::MaxInputFileNewestKeyTime(const InternalKey* start,
-                                               const InternalKey* end) const {
-  uint64_t newest_key_time = kUnknownNewestKeyTime;
-  const InternalKeyComparator& icmp =
-      column_family_data()->internal_comparator();
-  for (const auto& level_files : inputs_) {
-    for (const auto& file : level_files.files) {
-      if (start != nullptr && icmp.Compare(file->largest, *start) < 0) {
-        continue;
-      }
-      if (end != nullptr && icmp.Compare(file->smallest, *end) > 0) {
-        continue;
-      }
-      newest_key_time = std::max(newest_key_time, file->TryGetNewestKeyTime());
-    }
-  }
-  return newest_key_time;
-}
-
 uint64_t Compaction::MinInputFileOldestAncesterTime(
     const InternalKey* start, const InternalKey* end) const {
   uint64_t min_oldest_ancester_time = std::numeric_limits<uint64_t>::max();
@@ -991,7 +942,6 @@ uint64_t Compaction::MinInputFileEpochNumber() const {
 
 int Compaction::EvaluatePenultimateLevel(
     const VersionStorageInfo* vstorage,
-    const MutableCFOptions& mutable_cf_options,
     const ImmutableOptions& immutable_options, const int start_level,
     const int output_level) {
   // TODO: currently per_key_placement feature only support level and universal
@@ -1023,7 +973,7 @@ int Compaction::EvaluatePenultimateLevel(
   }
 
   bool supports_per_key_placement =
-      mutable_cf_options.preclude_last_level_data_seconds > 0;
+      immutable_options.preclude_last_level_data_seconds > 0;
 
   // it could be overridden by unittest
   TEST_SYNC_POINT_CALLBACK("Compaction::SupportsPerKeyPlacement:Enabled",
@@ -1035,70 +985,4 @@ int Compaction::EvaluatePenultimateLevel(
   return penultimate_level;
 }
 
-void Compaction::FilterInputsForCompactionIterator() {
-  assert(earliest_snapshot_.has_value());
-  // cfd_ is not populated at Compaction construction time, get it from
-  // VersionStorageInfo instead.
-  assert(input_vstorage_);
-  const auto* ucmp = input_vstorage_->user_comparator();
-  assert(ucmp);
-  // Simply comparing file boundaries when user-defined timestamp is defined
-  // is not as safe because we need to also compare timestamp to know for
-  // sure. Although entries with higher timestamp is also supposed to have
-  // higher sequence number for the same user key (without timestamp).
-  assert(ucmp->timestamp_size() == 0);
-  size_t num_input_levels = inputs_.size();
-  // TODO(yuzhangyu): filtering of older L0 file by new L0 file is not
-  // supported yet.
-  FileMetaData* rangedel_candidate = inputs_[0].level == 0
-                                         ? inputs_[0].files.back()
-                                         : inputs_[0].files.front();
-  assert(rangedel_candidate);
-  if (!rangedel_candidate->FileIsStandAloneRangeTombstone() ||
-      !DataIsDefinitelyInSnapshot(rangedel_candidate->fd.smallest_seqno,
-                                  earliest_snapshot_.value(),
-                                  snapshot_checker_)) {
-    for (size_t level = 0; level < num_input_levels; level++) {
-      DoGenerateLevelFilesBrief(&input_levels_[level], inputs_[level].files,
-                                &arena_);
-    }
-    return;
-  }
-
-  Slice rangedel_start_ukey = rangedel_candidate->smallest.user_key();
-  Slice rangedel_end_ukey = rangedel_candidate->largest.user_key();
-  SequenceNumber rangedel_seqno = rangedel_candidate->fd.smallest_seqno;
-
-  std::vector<std::vector<FileMetaData*>> non_start_level_input_files;
-  non_start_level_input_files.reserve(num_input_levels - 1);
-  non_start_level_input_files_filtered_.reserve(num_input_levels - 1);
-  for (size_t level = 1; level < num_input_levels; level++) {
-    non_start_level_input_files.emplace_back();
-    non_start_level_input_files_filtered_.emplace_back();
-    for (FileMetaData* file : inputs_[level].files) {
-      non_start_level_input_files_filtered_.back().push_back(false);
-      // When range data and point data has the same sequence number, point
-      // data wins. Range deletion end key is exclusive, so check it's bigger
-      // than file right boundary user key.
-      if (rangedel_seqno > file->fd.largest_seqno &&
-          ucmp->CompareWithoutTimestamp(rangedel_start_ukey,
-                                        file->smallest.user_key()) <= 0 &&
-          ucmp->CompareWithoutTimestamp(rangedel_end_ukey,
-                                        file->largest.user_key()) > 0) {
-        non_start_level_input_files_filtered_.back().back() = true;
-        filtered_input_levels_[level].push_back(file);
-      } else {
-        non_start_level_input_files.back().push_back(file);
-      }
-    }
-  }
-
-  DoGenerateLevelFilesBrief(&input_levels_[0], inputs_[0].files, &arena_);
-  assert(non_start_level_input_files.size() == num_input_levels - 1);
-  for (size_t level = 1; level < num_input_levels; level++) {
-    DoGenerateLevelFilesBrief(&input_levels_[level],
-                              non_start_level_input_files[level - 1], &arena_);
-  }
-}
-
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction.h

@@ -8,8 +8,6 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
 #pragma once
-
-#include "db/snapshot_checker.h"
 #include "db/version_set.h"
 #include "memory/arena.h"
 #include "options/cf_options.h"
@@ -92,8 +90,6 @@ class Compaction {
              CompressionOptions compression_opts,
              Temperature output_temperature, uint32_t max_subcompactions,
              std::vector<FileMetaData*> grandparents,
-             std::optional<SequenceNumber> earliest_snapshot,
-             const SnapshotChecker* snapshot_checker,
              bool manual_compaction = false, const std::string& trim_ts = "",
              double score = -1, bool deletion_compaction = false,
              bool l0_files_might_overlap = true,
@@ -184,16 +180,6 @@ class Compaction {
     return &input_levels_[compaction_input_level];
   }
 
-  // Returns the filtered input files of the specified compaction input level.
-  // For now, only non start level is filtered.
-  const std::vector<FileMetaData*>& filtered_input_levels(
-      size_t compaction_input_level) const {
-    const std::vector<FileMetaData*>& filtered_input_level =
-        filtered_input_levels_[compaction_input_level];
-    assert(compaction_input_level != 0 || filtered_input_level.size() == 0);
-    return filtered_input_level;
-  }
-
   // Maximum size of files to build during this compaction.
   uint64_t max_output_file_size() const { return max_output_file_size_; }
 
@@ -244,7 +230,7 @@ class Compaction {
   // Delete this compaction from the list of running compactions.
   //
   // Requirement: DB mutex held
-  void ReleaseCompactionFiles(const Status& status);
+  void ReleaseCompactionFiles(Status status);
 
   // Returns the summary of the compaction in "output" with maximum "len"
   // in bytes.  The caller is responsible for the memory management of
@@ -303,7 +289,14 @@ class Compaction {
   // is the sum of all input file sizes.
   uint64_t OutputFilePreallocationSize() const;
 
-  void FinalizeInputInfo(Version* input_version);
+  // TODO(hx235): eventually we should consider `InitInputTableProperties()`'s
+  // status and fail the compaction if needed
+  // TODO(hx235): consider making this function part of the construction so we
+  // don't forget to call it
+  void FinalizeInputInfo(Version* input_version) {
+    SetInputVersion(input_version);
+    InitInputTableProperties().PermitUncheckedError();
+  }
 
   struct InputLevelSummaryBuffer {
     char buffer[128];
@@ -340,16 +333,6 @@ class Compaction {
       int output_level, VersionStorageInfo* vstorage,
       const std::vector<CompactionInputFiles>& inputs);
 
-  // TODO(hx235): eventually we should consider `InitInputTableProperties()`'s
-  // status and fail the compaction if needed
-  //
-  // May open and read table files for table property.
-  // Should not be called while holding mutex_.
-  const TablePropertiesCollection& GetOrInitInputTableProperties() {
-    InitInputTableProperties().PermitUncheckedError();
-    return input_table_properties_;
-  }
-
   const TablePropertiesCollection& GetInputTableProperties() const {
     return input_table_properties_;
   }
@@ -415,12 +398,6 @@ class Compaction {
     return blob_garbage_collection_age_cutoff_;
   }
 
-  // start and end are sub compact range. Null if no boundary.
-  // This is used to calculate the newest_key_time table property after
-  // compaction.
-  uint64_t MaxInputFileNewestKeyTime(const InternalKey* start,
-                                     const InternalKey* end) const;
-
   // start and end are sub compact range. Null if no boundary.
   // This is used to filter out some input files' ancester's time range.
   uint64_t MinInputFileOldestAncesterTime(const InternalKey* start,
@@ -450,19 +427,19 @@ class Compaction {
   // penultimate level. The safe key range is populated by
   // `PopulatePenultimateLevelOutputRange()`.
   // Which could potentially disable all penultimate level output.
-  static int EvaluatePenultimateLevel(
-      const VersionStorageInfo* vstorage,
-      const MutableCFOptions& mutable_cf_options,
-      const ImmutableOptions& immutable_options, const int start_level,
-      const int output_level);
-
-  // mark (or clear) all files that are being compacted
-  void MarkFilesBeingCompacted(bool being_compacted) const;
+  static int EvaluatePenultimateLevel(const VersionStorageInfo* vstorage,
+                                      const ImmutableOptions& immutable_options,
+                                      const int start_level,
+                                      const int output_level);
 
  private:
+  void SetInputVersion(Version* input_version);
 
   Status InitInputTableProperties();
 
+  // mark (or clear) all files that are being compacted
+  void MarkFilesBeingCompacted(bool mark_as_compacted);
+
   // get the smallest and largest key present in files to be compacted
   static void GetBoundaryKeys(VersionStorageInfo* vstorage,
                               const std::vector<CompactionInputFiles>& inputs,
@@ -481,13 +458,6 @@ class Compaction {
   // `Compaction::WithinPenultimateLevelOutputRange()`.
   void PopulatePenultimateLevelOutputRange();
 
-  // If oldest snapshot is specified at Compaction construction time, we have
-  // an opportunity to optimize inputs for compaction iterator for this case:
-  // When a standalone range deletion file on the start level is recognized and
-  // can be determined to completely shadow some input files on non-start level.
-  // These files will be filtered out and later not feed to compaction iterator.
-  void FilterInputsForCompactionIterator();
-
   // Get the atomic file boundaries for all files in the compaction. Necessary
   // in order to avoid the scenario described in
   // https://github.com/facebook/rocksdb/pull/4432#discussion_r221072219 and
@@ -538,30 +508,12 @@ class Compaction {
   // Compaction input files organized by level. Constant after construction
   const std::vector<CompactionInputFiles> inputs_;
 
-  // All files from inputs_ that are not filtered and will be fed to compaction
-  // iterator, organized more closely in memory.
+  // A copy of inputs_, organized more closely in memory
   autovector<LevelFilesBrief, 2> input_levels_;
 
   // State used to check for number of overlapping grandparent files
   // (grandparent == "output_level_ + 1")
   std::vector<FileMetaData*> grandparents_;
-
-  // The earliest snapshot and snapshot checker at compaction picking time.
-  // These fields are only set for deletion triggered compactions picked in
-  // universal compaction. And when user-defined timestamp is not enabled.
-  // It will be used to possibly filter out some non start level input files.
-  std::optional<SequenceNumber> earliest_snapshot_;
-  const SnapshotChecker* snapshot_checker_;
-
-  // Markers for which non start level input files are filtered out if
-  // applicable. Only applicable if earliest_snapshot_ is provided and input
-  // start level has a standalone range deletion file. Filtered files are
-  // tracked in `filtered_input_levels_`.
-  std::vector<std::vector<bool>> non_start_level_input_files_filtered_;
-
-  // All files from inputs_ that are filtered.
-  std::vector<std::vector<FileMetaData*>> filtered_input_levels_;
-
   const double score_;  // score that was used to pick this compaction.
 
   // Is this compaction creating a file in the bottom most level?
@@ -643,6 +595,6 @@ struct PerKeyPlacementContext {
 #endif /* !NDEBUG */
 
 // Return sum of sizes of all files in `files`.
-uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);
+extern uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);
 
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_iteration_stats.h

@@ -44,13 +44,6 @@ struct CompactionIterationStats {
   uint64_t total_blob_bytes_read = 0;
   uint64_t num_blobs_relocated = 0;
   uint64_t total_blob_bytes_relocated = 0;
-
-  // TimedPut diagnostics
-  // Total number of kTypeValuePreferredSeqno records encountered.
-  uint64_t num_input_timed_put_records = 0;
-  // Number of kTypeValuePreferredSeqno records we ended up swapping in
-  // preferred seqno.
-  uint64_t num_timed_put_swap_preferred_seqno = 0;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_iterator.cc

@@ -25,7 +25,6 @@ namespace ROCKSDB_NAMESPACE {
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_snapshot,
     SequenceNumber earliest_write_conflict_snapshot,
     SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
     Env* env, bool report_detailed_time, bool expect_valid_internal_key,
@@ -41,7 +40,7 @@ CompactionIterator::CompactionIterator(
     const SequenceNumber preserve_time_min_seqno,
     const SequenceNumber preclude_last_level_min_seqno)
     : CompactionIterator(
-          input, cmp, merge_helper, last_sequence, snapshots, earliest_snapshot,
+          input, cmp, merge_helper, last_sequence, snapshots,
           earliest_write_conflict_snapshot, job_snapshot, snapshot_checker, env,
           report_detailed_time, expect_valid_internal_key, range_del_agg,
           blob_file_builder, allow_data_in_errors, enforce_single_del_contracts,
@@ -55,7 +54,6 @@ CompactionIterator::CompactionIterator(
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber /*last_sequence*/, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_snapshot,
     SequenceNumber earliest_write_conflict_snapshot,
     SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
     Env* env, bool report_detailed_time, bool expect_valid_internal_key,
@@ -93,7 +91,9 @@ CompactionIterator::CompactionIterator(
       // snapshots_ cannot be nullptr, but we will assert later in the body of
       // the constructor.
       visible_at_tip_(snapshots_ ? snapshots_->empty() : false),
-      earliest_snapshot_(earliest_snapshot),
+      earliest_snapshot_(!snapshots_ || snapshots_->empty()
+                             ? kMaxSequenceNumber
+                             : snapshots_->at(0)),
       info_log_(info_log),
       allow_data_in_errors_(allow_data_in_errors),
       enforce_single_del_contracts_(enforce_single_del_contracts),
@@ -491,8 +491,6 @@ void CompactionIterator::NextFromInput() {
     if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion ||
         ikey_.type == kTypeDeletionWithTimestamp) {
       iter_stats_.num_input_deletion_records++;
-    } else if (ikey_.type == kTypeValuePreferredSeqno) {
-      iter_stats_.num_input_timed_put_records++;
     }
     iter_stats_.total_input_raw_key_bytes += key_.size();
     iter_stats_.total_input_raw_value_bytes += value_.size();
@@ -620,8 +618,7 @@ void CompactionIterator::NextFromInput() {
       // not compact out.  We will keep this Put, but can drop it's data.
       // (See Optimization 3, below.)
       if (ikey_.type != kTypeValue && ikey_.type != kTypeBlobIndex &&
-          ikey_.type != kTypeWideColumnEntity &&
-          ikey_.type != kTypeValuePreferredSeqno) {
+          ikey_.type != kTypeWideColumnEntity) {
         ROCKS_LOG_FATAL(info_log_, "Unexpected key %s for compaction output",
                         ikey_.DebugString(allow_data_in_errors_, true).c_str());
         assert(false);
@@ -635,8 +632,7 @@ void CompactionIterator::NextFromInput() {
         assert(false);
       }
 
-      if (ikey_.type == kTypeBlobIndex || ikey_.type == kTypeWideColumnEntity ||
-          ikey_.type == kTypeValuePreferredSeqno) {
+      if (ikey_.type == kTypeBlobIndex || ikey_.type == kTypeWideColumnEntity) {
         ikey_.type = kTypeValue;
         current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
       }
@@ -802,8 +798,7 @@ void CompactionIterator::NextFromInput() {
             // happened
             if (next_ikey.type != kTypeValue &&
                 next_ikey.type != kTypeBlobIndex &&
-                next_ikey.type != kTypeWideColumnEntity &&
-                next_ikey.type != kTypeValuePreferredSeqno) {
+                next_ikey.type != kTypeWideColumnEntity) {
               ++iter_stats_.num_single_del_mismatch;
             }
 
@@ -872,8 +867,8 @@ void CompactionIterator::NextFromInput() {
       if (Valid()) {
         at_next_ = true;
       }
-    } else if (last_sequence != kMaxSequenceNumber &&
-               (last_snapshot == current_user_key_snapshot_ ||
+    } else if (last_snapshot == current_user_key_snapshot_ ||
+               (last_snapshot > 0 &&
                 last_snapshot < current_user_key_snapshot_)) {
       // If the earliest snapshot is which this key is visible in
       // is the same as the visibility of a previous instance of the
@@ -973,62 +968,6 @@ void CompactionIterator::NextFromInput() {
         validity_info_.SetValid(ValidContext::kKeepDel);
         at_next_ = true;
       }
-    } else if (ikey_.type == kTypeValuePreferredSeqno &&
-               DefinitelyInSnapshot(ikey_.sequence, earliest_snapshot_) &&
-               (bottommost_level_ ||
-                (compaction_ != nullptr &&
-                 compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
-                                                            &level_ptrs_)))) {
-      // This section that attempts to swap preferred sequence number will not
-      // be invoked if this is a CompactionIterator created for flush, since
-      // `compaction_` will be nullptr and it's not bottommost either.
-      //
-      // The entries with the same user key and smaller sequence numbers are
-      // all in this earliest snapshot range to be iterated. Since those entries
-      // will be hidden by this entry [rule A], it's safe to swap in the
-      // preferred seqno now.
-      //
-      // It's otherwise not safe to swap in the preferred seqno since it's
-      // possible for entries in earlier snapshots to have sequence number that
-      // is smaller than this entry's sequence number but bigger than this
-      // entry's preferred sequence number. Swapping in the preferred sequence
-      // number will break the internal key ordering invariant for this key.
-      //
-      // A special case involving range deletion is handled separately below.
-      auto [unpacked_value, preferred_seqno] =
-          ParsePackedValueWithSeqno(value_);
-      assert(preferred_seqno < ikey_.sequence || ikey_.sequence == 0);
-      if (range_del_agg_->ShouldDelete(
-              key_, RangeDelPositioningMode::kForwardTraversal)) {
-        ++iter_stats_.num_record_drop_hidden;
-        ++iter_stats_.num_record_drop_range_del;
-        AdvanceInputIter();
-      } else {
-        InternalKey ikey_after_swap(ikey_.user_key,
-                                    std::min(preferred_seqno, ikey_.sequence),
-                                    kTypeValue);
-        Slice ikey_after_swap_slice(*ikey_after_swap.rep());
-        if (range_del_agg_->ShouldDelete(
-                ikey_after_swap_slice,
-                RangeDelPositioningMode::kForwardTraversal)) {
-          // A range tombstone that doesn't cover this kTypeValuePreferredSeqno
-          // entry will end up covering the entry, so it's not safe to swap
-          // preferred sequence number. In this case, we output the entry as is.
-          validity_info_.SetValid(ValidContext::kNewUserKey);
-        } else {
-          if (ikey_.sequence != 0) {
-            iter_stats_.num_timed_put_swap_preferred_seqno++;
-            saved_seq_for_penul_check_ = ikey_.sequence;
-            ikey_.sequence = preferred_seqno;
-          }
-          ikey_.type = kTypeValue;
-          current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-          key_ = current_key_.GetInternalKey();
-          ikey_.user_key = current_key_.GetUserKey();
-          value_ = unpacked_value;
-          validity_info_.SetValid(ValidContext::kSwapPreferredSeqno);
-        }
-      }
     } else if (ikey_.type == kTypeMerge) {
       if (!merge_helper_->HasOperator()) {
         status_ = Status::InvalidArgument(
@@ -1280,21 +1219,6 @@ void CompactionIterator::DecideOutputLevel() {
   }
 #endif  // NDEBUG
 
-  // saved_seq_for_penul_check_ is populated in `NextFromInput` when the
-  // entry's sequence number is non zero and validity context for output this
-  // entry is kSwapPreferredSeqno for use in `DecideOutputLevel`. It should be
-  // cleared out here unconditionally. Otherwise, it may end up getting consumed
-  // incorrectly by a different entry.
-  SequenceNumber seq_for_range_check =
-      (saved_seq_for_penul_check_.has_value() &&
-       saved_seq_for_penul_check_.value() != kMaxSequenceNumber)
-          ? saved_seq_for_penul_check_.value()
-          : ikey_.sequence;
-  saved_seq_for_penul_check_ = std::nullopt;
-  ParsedInternalKey ikey_for_range_check = ikey_;
-  if (seq_for_range_check != ikey_.sequence) {
-    ikey_for_range_check.sequence = seq_for_range_check;
-  }
   if (output_to_penultimate_level_) {
     // If it's decided to output to the penultimate level, but unsafe to do so,
     // still output to the last level. For example, moving the data from a lower
@@ -1303,7 +1227,7 @@ void CompactionIterator::DecideOutputLevel() {
     // not from this compaction.
     // TODO: add statistic for declined output_to_penultimate_level
     bool safe_to_penultimate_level =
-        compaction_->WithinPenultimateLevelOutputRange(ikey_for_range_check);
+        compaction_->WithinPenultimateLevelOutputRange(ikey_);
     if (!safe_to_penultimate_level) {
       output_to_penultimate_level_ = false;
       // It could happen when disable/enable `last_level_temperature` while
@@ -1315,7 +1239,7 @@ void CompactionIterator::DecideOutputLevel() {
       // snapshot is released before enabling `last_level_temperature` feature
       // We will migrate the feature to `last_level_temperature` and maybe make
       // it not dynamically changeable.
-      if (seq_for_range_check > earliest_snapshot_) {
+      if (ikey_.sequence > earliest_snapshot_) {
         status_ = Status::Corruption(
             "Unsafe to store Seq later than snapshot in the last level if "
             "per_key_placement is enabled");

db/compaction/compaction_iterator.h

@@ -203,7 +203,6 @@ class CompactionIterator {
   CompactionIterator(
       InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
       SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_snapshot,
       SequenceNumber earliest_write_conflict_snapshot,
       SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
       Env* env, bool report_detailed_time, bool expect_valid_internal_key,
@@ -223,7 +222,6 @@ class CompactionIterator {
   CompactionIterator(
       InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
       SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_snapshot,
       SequenceNumber earliest_write_conflict_snapshot,
       SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
       Env* env, bool report_detailed_time, bool expect_valid_internal_key,
@@ -412,7 +410,6 @@ class CompactionIterator {
     kKeepDel = 9,
     kNewUserKey = 10,
     kRangeDeletion = 11,
-    kSwapPreferredSeqno = 12,
   };
 
   struct ValidityInfo {
@@ -439,17 +436,6 @@ class CompactionIterator {
   // iterator output (or current key in the underlying iterator during
   // NextFromInput()).
   ParsedInternalKey ikey_;
-
-  // When a kTypeValuePreferredSeqno entry's preferred seqno is safely swapped
-  // in in this compaction, this field saves its original sequence number for
-  // range checking whether it's safe to be placed on the penultimate level.
-  // This is to ensure when such an entry happens to be the right boundary of
-  // penultimate safe range, it won't get excluded because with the preferred
-  // seqno swapped in, it's now larger than the right boundary (itself before
-  // the swap). This is safe to do, because preferred seqno is swapped in only
-  // when no entries with the same user key exist on lower levels and this entry
-  // is already visible in the earliest snapshot.
-  std::optional<SequenceNumber> saved_seq_for_penul_check_ = kMaxSequenceNumber;
   // Stores whether ikey_.user_key is valid. If set to false, the user key is
   // not compared against the current key in the underlying iterator.
   bool has_current_user_key_ = false;
@@ -540,12 +526,18 @@ class CompactionIterator {
 
 inline bool CompactionIterator::DefinitelyInSnapshot(SequenceNumber seq,
                                                      SequenceNumber snapshot) {
-  return DataIsDefinitelyInSnapshot(seq, snapshot, snapshot_checker_);
+  return ((seq) <= (snapshot) &&
+          (snapshot_checker_ == nullptr ||
+           LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                  SnapshotCheckerResult::kInSnapshot)));
 }
 
 inline bool CompactionIterator::DefinitelyNotInSnapshot(
     SequenceNumber seq, SequenceNumber snapshot) {
-  return DataIsDefinitelyNotInSnapshot(seq, snapshot, snapshot_checker_);
+  return ((seq) > (snapshot) ||
+          (snapshot_checker_ != nullptr &&
+           UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                    SnapshotCheckerResult::kNotInSnapshot)));
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_iterator_test.cc

@@ -17,14 +17,6 @@
 #include "utilities/merge_operators.h"
 
 namespace ROCKSDB_NAMESPACE {
-namespace {
-std::string ValueWithPreferredSeqno(std::string val,
-                                    SequenceNumber preferred_seqno = 0) {
-  std::string result = val;
-  PutFixed64(&result, preferred_seqno);
-  return result;
-}
-}  // namespace
 
 // Expects no merging attempts.
 class NoMergingMergeOp : public MergeOperator {
@@ -296,7 +288,6 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
     iter_->SeekToFirst();
     c_iter_.reset(new CompactionIterator(
         iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
-        snapshots_.empty() ? kMaxSequenceNumber : snapshots_.at(0),
         earliest_write_conflict_snapshot, kMaxSequenceNumber,
         snapshot_checker_.get(), Env::Default(),
         false /* report_detailed_time */, false, range_del_agg_.get(),
@@ -401,17 +392,6 @@ TEST_P(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
   ASSERT_FALSE(c_iter_->Valid());
 }
 
-// Tests compatibility of TimedPut and SingleDelete. TimedPut should act as if
-// it's a Put.
-TEST_P(CompactionIteratorTest, TimedPutAndSingleDelete) {
-  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
-                 test::KeyStr("a", 3, kTypeValuePreferredSeqno)},
-                {"", "val"}, {}, {}, 5);
-  c_iter_->SeekToFirst();
-  ASSERT_OK(c_iter_->status());
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
 TEST_P(CompactionIteratorTest, SimpleRangeDeletion) {
   InitIterators({test::KeyStr("morning", 5, kTypeValue),
                  test::KeyStr("morning", 2, kTypeValue),
@@ -451,31 +431,6 @@ TEST_P(CompactionIteratorTest, RangeDeletionWithSnapshots) {
   ASSERT_FALSE(c_iter_->Valid());
 }
 
-// Tests compatibility of TimedPut and Range delete. TimedPut should act as if
-// it's a Put.
-TEST_P(CompactionIteratorTest, TimedPutAndRangeDeletion) {
-  InitIterators(
-      {test::KeyStr("morning", 5, kTypeValuePreferredSeqno),
-       test::KeyStr("morning", 2, kTypeValuePreferredSeqno),
-       test::KeyStr("night", 3, kTypeValuePreferredSeqno)},
-      {ValueWithPreferredSeqno("zao5"), ValueWithPreferredSeqno("zao2"),
-       ValueWithPreferredSeqno("wan")},
-      {test::KeyStr("ma", 4, kTypeRangeDeletion)}, {"mz"}, 5);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValuePreferredSeqno),
-            c_iter_->key().ToString());
-  ASSERT_EQ(ValueWithPreferredSeqno("zao5"), c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 3, kTypeValuePreferredSeqno),
-            c_iter_->key().ToString());
-  ASSERT_EQ(ValueWithPreferredSeqno("wan"), c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_OK(c_iter_->status());
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
 TEST_P(CompactionIteratorTest, CompactionFilterSkipUntil) {
   class Filter : public CompactionFilter {
     Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
@@ -547,11 +502,9 @@ TEST_P(CompactionIteratorTest, CompactionFilterSkipUntil) {
        test::KeyStr("f", 25, kTypeValue), test::KeyStr("g", 90, kTypeValue),
        test::KeyStr("h", 91, kTypeValue),  // keep
        test::KeyStr("i", 95, kTypeMerge),  // skip to "z"
-       test::KeyStr("j", 99, kTypeValue),
-       test::KeyStr("k", 100, kTypeValuePreferredSeqno)},
+       test::KeyStr("j", 99, kTypeValue)},
       {"av50", "am45", "bv60", "bv40", "cv35", "dm70", "em71", "fm65", "fm30",
-       "fv25", "gv90", "hv91", "im95", "jv99",
-       ValueWithPreferredSeqno("kv100")},
+       "fv25", "gv90", "hv91", "im95", "jv99"},
       {}, {}, kMaxSequenceNumber, kMaxSequenceNumber, &merge_op, &filter);
 
   // Compaction should output just "a", "e" and "h" keys.
@@ -661,87 +614,87 @@ TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
   EXPECT_EQ(2, filter.last_seen.load());
 }
 
-class Filter : public CompactionFilter {
-  Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                    const Slice& existing_value, std::string* /*new_value*/,
-                    std::string* /*skip_until*/) const override {
-    std::string k = key.ToString();
-    std::string v = existing_value.ToString();
-
-    // See InitIterators() call below for the sequence of keys and their
-    // filtering decisions. Here we closely assert that compaction filter is
-    // called with the expected keys and only them, and with the right values.
-    if (k == "a") {
-      EXPECT_EQ(ValueType::kMergeOperand, t);
-      EXPECT_EQ("av1", v);
-      return Decision::kKeep;
-    } else if (k == "b") {
-      EXPECT_EQ(ValueType::kMergeOperand, t);
-      return Decision::kKeep;
-    } else if (k == "c") {
-      return Decision::kKeep;
-    }
-
-    ADD_FAILURE();
-    return Decision::kKeep;
-  }
-
-  const char* Name() const override {
-    return "CompactionIteratorTest.SingleMergeOperand::Filter";
-  }
-};
-
-class SingleMergeOp : public MergeOperator {
- public:
-  bool FullMergeV2(const MergeOperationInput& merge_in,
-                   MergeOperationOutput* merge_out) const override {
-    // See InitIterators() call below for why "c" is the only key for which
-    // FullMergeV2 should be called.
-    EXPECT_EQ("c", merge_in.key.ToString());
-
-    std::string temp_value;
-    if (merge_in.existing_value != nullptr) {
-      temp_value = merge_in.existing_value->ToString();
-    }
-
-    for (auto& operand : merge_in.operand_list) {
-      temp_value.append(operand.ToString());
-    }
-    merge_out->new_value = temp_value;
-
-    return true;
-  }
-
-  bool PartialMergeMulti(const Slice& key,
-                         const std::deque<Slice>& operand_list,
-                         std::string* new_value,
-                         Logger* /*logger*/) const override {
-    std::string string_key = key.ToString();
-    EXPECT_TRUE(string_key == "a" || string_key == "b");
-
-    if (string_key == "a") {
-      EXPECT_EQ(1, operand_list.size());
-    } else if (string_key == "b") {
-      EXPECT_EQ(2, operand_list.size());
-    }
-
-    std::string temp_value;
-    for (auto& operand : operand_list) {
-      temp_value.append(operand.ToString());
-    }
-    swap(temp_value, *new_value);
-
-    return true;
-  }
-
-  const char* Name() const override {
-    return "CompactionIteratorTest SingleMergeOp";
-  }
-
-  bool AllowSingleOperand() const override { return true; }
-};
-
 TEST_P(CompactionIteratorTest, SingleMergeOperand) {
+  class Filter : public CompactionFilter {
+    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
+                      const Slice& existing_value, std::string* /*new_value*/,
+                      std::string* /*skip_until*/) const override {
+      std::string k = key.ToString();
+      std::string v = existing_value.ToString();
+
+      // See InitIterators() call below for the sequence of keys and their
+      // filtering decisions. Here we closely assert that compaction filter is
+      // called with the expected keys and only them, and with the right values.
+      if (k == "a") {
+        EXPECT_EQ(ValueType::kMergeOperand, t);
+        EXPECT_EQ("av1", v);
+        return Decision::kKeep;
+      } else if (k == "b") {
+        EXPECT_EQ(ValueType::kMergeOperand, t);
+        return Decision::kKeep;
+      } else if (k == "c") {
+        return Decision::kKeep;
+      }
+
+      ADD_FAILURE();
+      return Decision::kKeep;
+    }
+
+    const char* Name() const override {
+      return "CompactionIteratorTest.SingleMergeOperand::Filter";
+    }
+  };
+
+  class SingleMergeOp : public MergeOperator {
+   public:
+    bool FullMergeV2(const MergeOperationInput& merge_in,
+                     MergeOperationOutput* merge_out) const override {
+      // See InitIterators() call below for why "c" is the only key for which
+      // FullMergeV2 should be called.
+      EXPECT_EQ("c", merge_in.key.ToString());
+
+      std::string temp_value;
+      if (merge_in.existing_value != nullptr) {
+        temp_value = merge_in.existing_value->ToString();
+      }
+
+      for (auto& operand : merge_in.operand_list) {
+        temp_value.append(operand.ToString());
+      }
+      merge_out->new_value = temp_value;
+
+      return true;
+    }
+
+    bool PartialMergeMulti(const Slice& key,
+                           const std::deque<Slice>& operand_list,
+                           std::string* new_value,
+                           Logger* /*logger*/) const override {
+      std::string string_key = key.ToString();
+      EXPECT_TRUE(string_key == "a" || string_key == "b");
+
+      if (string_key == "a") {
+        EXPECT_EQ(1, operand_list.size());
+      } else if (string_key == "b") {
+        EXPECT_EQ(2, operand_list.size());
+      }
+
+      std::string temp_value;
+      for (auto& operand : operand_list) {
+        temp_value.append(operand.ToString());
+      }
+      swap(temp_value, *new_value);
+
+      return true;
+    }
+
+    const char* Name() const override {
+      return "CompactionIteratorTest SingleMergeOp";
+    }
+
+    bool AllowSingleOperand() const override { return true; }
+  };
+
   SingleMergeOp merge_op;
   Filter filter;
   InitIterators(
@@ -766,24 +719,6 @@ TEST_P(CompactionIteratorTest, SingleMergeOperand) {
   ASSERT_EQ("cv1cv2", c_iter_->value().ToString());
 }
 
-// Tests compatibility of TimedPut and Merge operation. When a TimedPut is
-// merged with some merge operand in compaction, it will become a regular Put
-// and lose its preferred sequence number.
-TEST_P(CompactionIteratorTest, TimedPutAndMerge) {
-  SingleMergeOp merge_op;
-  Filter filter;
-  InitIterators({test::KeyStr("c", 90, kTypeMerge),
-                 test::KeyStr("c", 80, kTypeValuePreferredSeqno)},
-                {"cv2", ValueWithPreferredSeqno("cv1")}, {}, {},
-                kMaxSequenceNumber, kMaxSequenceNumber, &merge_op, &filter);
-
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("c", 90, kTypeValue), c_iter_->key().ToString());
-  ASSERT_OK(c_iter_->status());
-  ASSERT_EQ("cv1cv2", c_iter_->value().ToString());
-}
-
 // In bottommost level, values earlier than earliest snapshot can be output
 // with sequence = 0.
 TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
@@ -833,14 +768,6 @@ TEST_P(CompactionIteratorTest, ConvertToPutAtBottom) {
           true /*bottomost_level*/);
 }
 
-TEST_P(CompactionIteratorTest, ZeroSeqOfKeyAndSnapshot) {
-  AddSnapshot(0);
-  const std::vector<std::string> input_keys = {
-      test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 0, kTypeValue)};
-  const std::vector<std::string> input_values = {"a1", "b1"};
-  RunTest(input_keys, input_values, input_keys, input_values);
-}
-
 INSTANTIATE_TEST_CASE_P(CompactionIteratorTestInstance, CompactionIteratorTest,
                         testing::Values(true, false));
 
@@ -1036,22 +963,6 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Value) {
       {"v4", "v3", "v1"}, 3 /*last_committed_seq*/);
 }
 
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_TimedPut) {
-  AddSnapshot(2, 1);
-  RunTest({test::KeyStr("foo", 4, kTypeValuePreferredSeqno),
-           test::KeyStr("foo", 3, kTypeValuePreferredSeqno),
-           test::KeyStr("foo", 2, kTypeValuePreferredSeqno),
-           test::KeyStr("foo", 1, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("v4"), ValueWithPreferredSeqno("v3"),
-           ValueWithPreferredSeqno("v2"), ValueWithPreferredSeqno("v1")},
-          {test::KeyStr("foo", 4, kTypeValuePreferredSeqno),
-           test::KeyStr("foo", 3, kTypeValuePreferredSeqno),
-           test::KeyStr("foo", 1, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("v4"), ValueWithPreferredSeqno("v3"),
-           ValueWithPreferredSeqno("v1")},
-          3 /*last_committed_seq*/);
-}
-
 TEST_F(CompactionIteratorWithSnapshotCheckerTest, DedupSameSnapshot_Deletion) {
   AddSnapshot(2, 1);
   RunTest(
@@ -1217,149 +1128,6 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
           2 /* earliest_write_conflict_snapshot */);
 }
 
-// Same as above but with a value with preferred seqno entry. In addition to the
-// value getting trimmed, the type of the KV is changed to kTypeValue.
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       KeepSingleDeletionForWriteConflictChecking_TimedPut) {
-  AddSnapshot(2, 0);
-  RunTest({test::KeyStr("a", 2, kTypeSingleDeletion),
-           test::KeyStr("a", 1, kTypeValuePreferredSeqno)},
-          {"", ValueWithPreferredSeqno("v1")},
-          {test::KeyStr("a", 2, kTypeSingleDeletion),
-           test::KeyStr("a", 1, kTypeValue)},
-          {"", ""}, 2 /* last_committed_seq */, nullptr /* merge_operator */,
-          nullptr /* compaction_filter */, false /* bottommost_level */,
-          2 /* earliest_write_conflict_snapshot */);
-}
-
-// Tests when a kTypeValuePreferredSeqno entry can have its preferred sequence
-// number swapped in. The required and sufficient conditions for an entry's
-// preferred sequence number to get swapped in are:
-// 1) The entry is visible to the earliest snapshot, AND
-// 2) No more entries with the same user key on lower levels, AND
-//    This is either because:
-//    2a) This is a compaction to the bottommost level, OR
-//    2b) Keys do not exist beyond output level
-// 3) The entry will not resurface a range deletion entry after swapping in the
-//    preferred sequence number.
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       TimedPut_NotVisibleToEarliestSnapshot_NoSwapPreferredSeqno) {
-  AddSnapshot(3);
-  RunTest({test::KeyStr("bar", 5, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("bv2", 2)},
-          {test::KeyStr("bar", 5, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("bv2", 2), "bv1"}, 5 /*last_committed_seq*/,
-          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-          true /*bottommost_level*/,
-          kMaxSequenceNumber /*earliest_write_conflict_snapshot*/,
-          true /*key_not_exists_beyond_output_level*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       TimedPut_MoreEntriesInLowerLevels_NoSwapPreferredSeqno) {
-  // This tests mimics more entries in lower levels with `bottommost_level` and
-  // `key_not_exists_beyond_output_level` set to false.
-  RunTest({test::KeyStr("bar", 5, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("bv2", 2)},
-          {test::KeyStr("bar", 5, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("bv2", 2)}, 5 /*last_committed_seq*/,
-          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-          false /*bottommost_level*/,
-          kMaxSequenceNumber /*earliest_write_conflict_snapshot*/,
-          false /*key_not_exists_beyond_output_level*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       TimedPut_ShouldBeCoverredByRangeDeletionBeforeSwap_NoOutput) {
-  InitIterators({test::KeyStr("morning", 5, kTypeValuePreferredSeqno),
-                 test::KeyStr("morning", 2, kTypeValuePreferredSeqno),
-                 test::KeyStr("night", 6, kTypeValue)},
-                {ValueWithPreferredSeqno("zao", 3),
-                 ValueWithPreferredSeqno("zao", 1), "wan"},
-                {test::KeyStr("ma", 6, kTypeRangeDeletion)}, {"mz"}, 6,
-                kMaxSequenceNumber /*last_committed_sequence*/,
-                nullptr /*merge_op*/, nullptr /*filter*/,
-                false /*bottommost_level*/,
-                kMaxSequenceNumber /*earliest_write_conflict_snapshot*/,
-                true /*key_not_exists_beyond_output_level*/);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 6, kTypeValue), c_iter_->key().ToString());
-  ASSERT_EQ("wan", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-  ASSERT_OK(c_iter_->status());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       TimedPut_WillBeHiddenByRangeDeletionAfterSwap_NoSwap) {
-  InitIterators({test::KeyStr("morning", 5, kTypeValuePreferredSeqno),
-                 test::KeyStr("night", 6, kTypeValue)},
-                {ValueWithPreferredSeqno("zao", 3), "wan"},
-                {test::KeyStr("ma", 4, kTypeRangeDeletion)}, {"mz"}, 6,
-                kMaxSequenceNumber /*last_committed_sequence*/,
-                nullptr /*merge_op*/, nullptr /*filter*/,
-                false /*bottommost_level*/,
-                kMaxSequenceNumber /*earliest_write_conflict_snapshot*/,
-                true /*key_not_exists_beyond_output_level*/);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValuePreferredSeqno),
-            c_iter_->key().ToString());
-  ASSERT_EQ(ValueWithPreferredSeqno("zao", 3), c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 6, kTypeValue), c_iter_->key().ToString());
-  ASSERT_EQ("wan", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-  ASSERT_OK(c_iter_->status());
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       TimedPut_BottomMostLevelVisibleToEarliestSnapshot_SwapPreferredSeqno) {
-  // Preferred seqno got swapped in and also zeroed out as a bottommost level
-  // optimization.
-  RunTest(
-      {test::KeyStr("bar", 5, kTypeValuePreferredSeqno),
-       test::KeyStr("bar", 4, kTypeValuePreferredSeqno),
-       test::KeyStr("foo", 6, kTypeValue)},
-      {ValueWithPreferredSeqno("bv2", 2), ValueWithPreferredSeqno("bv1", 1),
-       "fv1"},
-      {test::KeyStr("bar", 0, kTypeValue), test::KeyStr("foo", 0, kTypeValue)},
-      {"bv2", "fv1"}, 6 /*last_committed_seq*/, nullptr /*merge_operator*/,
-      nullptr /*compaction_filter*/, true /*bottommost_level*/);
-}
-
-TEST_F(
-    CompactionIteratorWithSnapshotCheckerTest,
-    TimedPut_NonBottomMostLevelVisibleToEarliestSnapshot_SwapPreferredSeqno) {
-  RunTest(
-      {test::KeyStr("bar", 5, kTypeValuePreferredSeqno),
-       test::KeyStr("bar", 4, kTypeValuePreferredSeqno),
-       test::KeyStr("foo", 6, kTypeValue)},
-      {ValueWithPreferredSeqno("bv2", 2), ValueWithPreferredSeqno("bv1", 1),
-       "fv1"},
-      {test::KeyStr("bar", 2, kTypeValue), test::KeyStr("foo", 6, kTypeValue)},
-      {"bv2", "fv1"}, 6 /*last_committed_seq*/, nullptr /*merge_operator*/,
-      nullptr /*compaction_filter*/, false /*bottommost_level*/,
-      kMaxSequenceNumber /*earliest_write_conflict_snapshot*/,
-      true /*key_not_exists_beyond_output_level*/);
-}
-
-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       TimedPut_SequenceNumberAlreadyZeroedOut_ChangeType) {
-  RunTest(
-      {test::KeyStr("bar", 0, kTypeValuePreferredSeqno),
-       test::KeyStr("bar", 0, kTypeValuePreferredSeqno),
-       test::KeyStr("foo", 0, kTypeValue)},
-      {ValueWithPreferredSeqno("bv2", 2), ValueWithPreferredSeqno("bv1", 1),
-       "fv1"},
-      {test::KeyStr("bar", 0, kTypeValue), test::KeyStr("foo", 0, kTypeValue)},
-      {"bv2", "fv1"}, 6 /*last_committed_seq*/, nullptr /*merge_operator*/,
-      nullptr /*compaction_filter*/, true /*bottommost_level*/);
-}
-
 // Compaction filter should keep uncommitted key as-is, and
 //   * Convert the latest value to deletion, and/or
 //   * if latest value is a merge, apply filter to all subsequent merges.
@@ -1377,22 +1145,6 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Value) {
       nullptr /*merge_operator*/, compaction_filter.get());
 }
 
-TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_TimedPut) {
-  // TODO(yuzhangyu): Add support for this type in compaction filter.
-  // Type kTypeValuePreferredSeqno is not explicitly exposed in the compaction
-  // filter API, so users can not operate on it through compaction filter API
-  // to remove/purge/change value etc. But this type of entry can be impacted by
-  // other entries' filter result, currently only kRemoveAndSkip type of result
-  // can affect it.
-  std::unique_ptr<CompactionFilter> compaction_filter(
-      new FilterAllKeysCompactionFilter());
-  RunTest({test::KeyStr("a", 2, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("v1")},
-          {test::KeyStr("a", 2, kTypeValuePreferredSeqno)},
-          {ValueWithPreferredSeqno("v1")}, 2 /*last_committed_seq*/,
-          nullptr /*merge_operator*/, compaction_filter.get());
-}
-
 TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Deletion) {
   std::unique_ptr<CompactionFilter> compaction_filter(
       new FilterAllKeysCompactionFilter());
@@ -1854,22 +1606,6 @@ TEST_P(CompactionIteratorTsGcTest, SingleDeleteAllKeysOlderThanThreshold) {
   }
 }
 
-TEST_P(CompactionIteratorTsGcTest, ZeroSeqOfKeyAndSnapshot) {
-  AddSnapshot(0);
-  std::string full_history_ts_low;
-  PutFixed64(&full_history_ts_low, std::numeric_limits<uint64_t>::max());
-  const std::vector<std::string> input_keys = {
-      test::KeyStr(101, "a", 0, kTypeValue),
-      test::KeyStr(102, "b", 0, kTypeValue)};
-  const std::vector<std::string> input_values = {"a1", "b1"};
-  RunTest(input_keys, input_values, input_keys, input_values,
-          /*last_committed_seq=*/kMaxSequenceNumber,
-          /*merge_operator=*/nullptr, /*compaction_filter=*/nullptr,
-          /*bottommost_level=*/false,
-          /*earliest_write_conflict_snapshot=*/kMaxSequenceNumber,
-          /*key_not_exists_beyond_output_level=*/false, &full_history_ts_low);
-}
-
 INSTANTIATE_TEST_CASE_P(CompactionIteratorTsGcTestInstance,
                         CompactionIteratorTsGcTest,
                         testing::Values(true, false));

db/compaction/compaction_job.cc

@@ -174,9 +174,6 @@ CompactionJob::CompactionJob(
       db_mutex_(db_mutex),
       db_error_handler_(db_error_handler),
       existing_snapshots_(std::move(existing_snapshots)),
-      earliest_snapshot_(existing_snapshots_.empty()
-                             ? kMaxSequenceNumber
-                             : existing_snapshots_.at(0)),
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
       snapshot_checker_(snapshot_checker),
       job_context_(job_context),
@@ -251,13 +248,12 @@ void CompactionJob::Prepare() {
 
   // Generate file_levels_ for compaction before making Iterator
   auto* c = compact_->compaction;
-  [[maybe_unused]] ColumnFamilyData* cfd = c->column_family_data();
+  ColumnFamilyData* cfd = c->column_family_data();
   assert(cfd != nullptr);
-  const VersionStorageInfo* storage_info = c->input_version()->storage_info();
-  assert(storage_info);
-  assert(storage_info->NumLevelFiles(compact_->compaction->level()) > 0);
+  assert(cfd->current()->storage_info()->NumLevelFiles(
+             compact_->compaction->level()) > 0);
 
-  write_hint_ = storage_info->CalculateSSTWriteHint(c->output_level());
+  write_hint_ = cfd->CalculateSSTWriteHint(c->output_level());
   bottommost_level_ = c->bottommost_level();
 
   if (c->ShouldFormSubcompactions()) {
@@ -286,60 +282,68 @@ void CompactionJob::Prepare() {
 
   // collect all seqno->time information from the input files which will be used
   // to encode seqno->time to the output files.
-
   uint64_t preserve_time_duration =
-      std::max(c->mutable_cf_options()->preserve_internal_time_seconds,
-               c->mutable_cf_options()->preclude_last_level_data_seconds);
+      std::max(c->immutable_options()->preserve_internal_time_seconds,
+               c->immutable_options()->preclude_last_level_data_seconds);
 
   if (preserve_time_duration > 0) {
     const ReadOptions read_options(Env::IOActivity::kCompaction);
-    // Setup seqno_to_time_mapping_ with relevant time range.
-    seqno_to_time_mapping_.SetMaxTimeSpan(preserve_time_duration);
+    // setup seqno_to_time_mapping_
+    seqno_to_time_mapping_.SetMaxTimeDuration(preserve_time_duration);
     for (const auto& each_level : *c->inputs()) {
       for (const auto& fmd : each_level.files) {
         std::shared_ptr<const TableProperties> tp;
-        Status s = c->input_version()->GetTableProperties(read_options, &tp,
-                                                          fmd, nullptr);
+        Status s =
+            cfd->current()->GetTableProperties(read_options, &tp, fmd, nullptr);
         if (s.ok()) {
-          s = seqno_to_time_mapping_.DecodeFrom(tp->seqno_to_time_mapping);
-        }
-        if (!s.ok()) {
-          ROCKS_LOG_WARN(
-              db_options_.info_log,
-              "Problem reading or processing seqno-to-time mapping: %s",
-              s.ToString().c_str());
+          seqno_to_time_mapping_.Add(tp->seqno_to_time_mapping)
+              .PermitUncheckedError();
+          seqno_to_time_mapping_.Add(fmd->fd.smallest_seqno,
+                                     fmd->oldest_ancester_time);
         }
       }
     }
 
+    auto status = seqno_to_time_mapping_.Sort();
+    if (!status.ok()) {
+      ROCKS_LOG_WARN(db_options_.info_log,
+                     "Invalid sequence number to time mapping: Status: %s",
+                     status.ToString().c_str());
+    }
     int64_t _current_time = 0;
-    Status s = db_options_.clock->GetCurrentTime(&_current_time);
-    if (!s.ok()) {
+    status = db_options_.clock->GetCurrentTime(&_current_time);
+    if (!status.ok()) {
       ROCKS_LOG_WARN(db_options_.info_log,
                      "Failed to get current time in compaction: Status: %s",
-                     s.ToString().c_str());
+                     status.ToString().c_str());
       // preserve all time information
       preserve_time_min_seqno_ = 0;
       preclude_last_level_min_seqno_ = 0;
-      seqno_to_time_mapping_.Enforce();
     } else {
-      seqno_to_time_mapping_.Enforce(_current_time);
-      seqno_to_time_mapping_.GetCurrentTieringCutoffSeqnos(
-          static_cast<uint64_t>(_current_time),
-          c->mutable_cf_options()->preserve_internal_time_seconds,
-          c->mutable_cf_options()->preclude_last_level_data_seconds,
-          &preserve_time_min_seqno_, &preclude_last_level_min_seqno_);
+      seqno_to_time_mapping_.TruncateOldEntries(_current_time);
+      uint64_t preserve_time =
+          static_cast<uint64_t>(_current_time) > preserve_time_duration
+              ? _current_time - preserve_time_duration
+              : 0;
+      // GetProximalSeqnoBeforeTime tells us the last seqno known to have been
+      // written at or before the given time. + 1 to get the minimum we should
+      // preserve without excluding anything that might have been written on or
+      // after the given time.
+      preserve_time_min_seqno_ =
+          seqno_to_time_mapping_.GetProximalSeqnoBeforeTime(preserve_time) + 1;
+      if (c->immutable_options()->preclude_last_level_data_seconds > 0) {
+        uint64_t preclude_last_level_time =
+            static_cast<uint64_t>(_current_time) >
+                    c->immutable_options()->preclude_last_level_data_seconds
+                ? _current_time -
+                      c->immutable_options()->preclude_last_level_data_seconds
+                : 0;
+        preclude_last_level_min_seqno_ =
+            seqno_to_time_mapping_.GetProximalSeqnoBeforeTime(
+                preclude_last_level_time) +
+            1;
+      }
     }
-    // For accuracy of the GetProximalSeqnoBeforeTime queries above, we only
-    // limit the capacity after them.
-    // Here If we set capacity to the per-SST limit, we could be throwing away
-    // fidelity when a compaction output file has a narrower seqno range than
-    // all the inputs. If we only limit capacity for each compaction output, we
-    // could be doing a lot of unnecessary recomputation in a large compaction
-    // (up to quadratic in number of files). Thus, we do soemthing in the
-    // middle: enforce a resonably large constant size limit substantially
-    // larger than kMaxSeqnoTimePairsPerSST.
-    seqno_to_time_mapping_.SetCapacity(kMaxSeqnoToTimeEntries);
   }
 }
 
@@ -392,9 +396,7 @@ void CompactionJob::AcquireSubcompactionResources(
 
 void CompactionJob::ShrinkSubcompactionResources(uint64_t num_extra_resources) {
   // Do nothing when we have zero resources to shrink
-  if (num_extra_resources == 0) {
-    return;
-  }
+  if (num_extra_resources == 0) return;
   db_mutex_->Lock();
   // We cannot release threads more than what we reserved before
   int extra_num_subcompaction_threads_released = env_->ReleaseThreads(
@@ -440,6 +442,14 @@ void CompactionJob::ReleaseSubcompactionResources() {
   ShrinkSubcompactionResources(extra_num_subcompaction_threads_reserved_);
 }
 
+struct RangeWithSize {
+  Range range;
+  uint64_t size;
+
+  RangeWithSize(const Slice& a, const Slice& b, uint64_t s = 0)
+      : range(a, b), size(s) {}
+};
+
 void CompactionJob::GenSubcompactionBoundaries() {
   // The goal is to find some boundary keys so that we can evenly partition
   // the compaction input data into max_subcompactions ranges.
@@ -466,14 +476,8 @@ void CompactionJob::GenSubcompactionBoundaries() {
   // overlap with N-1 other ranges. Since we requested a relatively large number
   // (128) of ranges from each input files, even N range overlapping would
   // cause relatively small inaccuracy.
-  ReadOptions read_options(Env::IOActivity::kCompaction);
-  read_options.rate_limiter_priority = GetRateLimiterPriority();
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
   auto* c = compact_->compaction;
-  if (c->mutable_cf_options()->table_factory->Name() ==
-      TableFactory::kPlainTableName()) {
-    return;
-  }
-
   if (c->max_subcompactions() <= 1 &&
       !(c->immutable_options()->compaction_pri == kRoundRobin &&
         c->immutable_options()->compaction_style == kCompactionStyleLevel)) {
@@ -506,7 +510,9 @@ void CompactionJob::GenSubcompactionBoundaries() {
         FileMetaData* f = flevel->files[i].file_metadata;
         std::vector<TableReader::Anchor> my_anchors;
         Status s = cfd->table_cache()->ApproximateKeyAnchors(
-            read_options, icomp, *f, *c->mutable_cf_options(), my_anchors);
+            read_options, icomp, *f,
+            c->mutable_cf_options()->block_protection_bytes_per_key,
+            my_anchors);
         if (!s.ok() || my_anchors.empty()) {
           my_anchors.emplace_back(f->largest.user_key(), f->fd.GetFileSize());
         }
@@ -577,9 +583,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
 
   TEST_SYNC_POINT_CALLBACK("CompactionJob::GenSubcompactionBoundaries:0",
                            &num_planned_subcompactions);
-  if (num_planned_subcompactions == 1) {
-    return;
-  }
+  if (num_planned_subcompactions == 1) return;
 
   // Group the ranges into subcompactions
   uint64_t target_range_size = std::max(
@@ -625,7 +629,6 @@ Status CompactionJob::Run() {
   const size_t num_threads = compact_->sub_compact_states.size();
   assert(num_threads > 0);
   const uint64_t start_micros = db_options_.clock->NowMicros();
-  compact_->compaction->GetOrInitInputTableProperties();
 
   // Launch a thread for each of subcompactions 1...num_threads-1
   std::vector<port::Thread> thread_pool;
@@ -637,7 +640,7 @@ Status CompactionJob::Run() {
 
   // Always schedule the first subcompaction (whether or not there are also
   // others) in the current thread to be efficient with resources
-  ProcessKeyValueCompaction(compact_->sub_compact_states.data());
+  ProcessKeyValueCompaction(&compact_->sub_compact_states[0]);
 
   // Wait for all other threads (if there are any) to finish execution
   for (auto& thread : thread_pool) {
@@ -709,6 +712,8 @@ Status CompactionJob::Run() {
       }
     }
     ColumnFamilyData* cfd = compact_->compaction->column_family_data();
+    auto& prefix_extractor =
+        compact_->compaction->mutable_cf_options()->prefix_extractor;
     std::atomic<size_t> next_file_idx(0);
     auto verify_table = [&](Status& output_status) {
       while (true) {
@@ -723,14 +728,12 @@ Status CompactionJob::Run() {
         // use_direct_io_for_flush_and_compaction is true, we will regard this
         // verification as user reads since the goal is to cache it here for
         // further user reads
-        ReadOptions verify_table_read_options(Env::IOActivity::kCompaction);
-        verify_table_read_options.rate_limiter_priority =
-            GetRateLimiterPriority();
+        const ReadOptions verify_table_read_options(
+            Env::IOActivity::kCompaction);
         InternalIterator* iter = cfd->table_cache()->NewIterator(
             verify_table_read_options, file_options_,
             cfd->internal_comparator(), files_output[file_idx]->meta,
-            /*range_del_agg=*/nullptr,
-            *compact_->compaction->mutable_cf_options(),
+            /*range_del_agg=*/nullptr, prefix_extractor,
             /*table_reader_ptr=*/nullptr,
             cfd->internal_stats()->GetFileReadHist(
                 compact_->compaction->output_level()),
@@ -740,11 +743,14 @@ Status CompactionJob::Run() {
                 *compact_->compaction->mutable_cf_options()),
             /*smallest_compaction_key=*/nullptr,
             /*largest_compaction_key=*/nullptr,
-            /*allow_unprepared_value=*/false);
+            /*allow_unprepared_value=*/false,
+            compact_->compaction->mutable_cf_options()
+                ->block_protection_bytes_per_key);
         auto s = iter->status();
 
         if (s.ok() && paranoid_file_checks_) {
           OutputValidator validator(cfd->internal_comparator(),
+                                    /*_enable_order_check=*/true,
                                     /*_enable_hash=*/true);
           for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
             s = validator.Add(iter->key(), iter->value());
@@ -801,12 +807,6 @@ Status CompactionJob::Run() {
     }
   }
 
-  // Before the compaction starts, is_remote_compaction was set to true if
-  // compaction_service is set. We now know whether each sub_compaction was
-  // done remotely or not. Reset is_remote_compaction back to false and allow
-  // AggregateCompactionStats() to set the right value.
-  compaction_job_stats_->is_remote_compaction = false;
-
   // Finish up all bookkeeping to unify the subcompaction results.
   compact_->AggregateCompactionStats(compaction_stats_, *compaction_job_stats_);
   uint64_t num_input_range_del = 0;
@@ -821,27 +821,24 @@ Status CompactionJob::Run() {
     // input keys. So the number of keys it processed is not suitable for
     // verification here.
     // TODO: support verification when trim_ts_ is non-empty.
-    if (!(ts_sz > 0 && !trim_ts_.empty())) {
+    if (!(ts_sz > 0 && !trim_ts_.empty()) &&
+        db_options_.compaction_verify_record_count) {
       assert(compaction_stats_.stats.num_input_records > 0);
       // TODO: verify the number of range deletion entries.
       uint64_t expected =
           compaction_stats_.stats.num_input_records - num_input_range_del;
       uint64_t actual = compaction_job_stats_->num_input_records;
       if (expected != actual) {
-        char scratch[2345];
-        compact_->compaction->Summary(scratch, sizeof(scratch));
         std::string msg =
-            "Compaction number of input keys does not match "
-            "number of keys processed. Expected " +
-            std::to_string(expected) + " but processed " +
-            std::to_string(actual) + ". Compaction summary: " + scratch;
+            "Total number of input records: " + std::to_string(expected) +
+            ", but processed " + std::to_string(actual) + " records.";
         ROCKS_LOG_WARN(
-            db_options_.info_log, "[%s] [JOB %d] Compaction with status: %s",
+            db_options_.info_log, "[%s] [JOB %d] Compaction %s",
             compact_->compaction->column_family_data()->GetName().c_str(),
             job_context_->job_id, msg.c_str());
-        if (db_options_.compaction_verify_record_count) {
-          status = Status::Corruption(msg);
-        }
+        status = Status::Corruption(
+            "Compaction number of input keys does not match number of keys "
+            "processed.");
       }
     }
   }
@@ -911,23 +908,19 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options,
   ROCKS_LOG_BUFFER(
       log_buffer_,
       "[%s] compacted to: %s, MB/sec: %.1f rd, %.1f wr, level %d, "
-      "files in(%d, %d) filtered(%d, %d) out(%d +%d blob) "
-      "MB in(%.1f, %.1f +%.1f blob) filtered(%.1f, %.1f) out(%.1f +%.1f blob), "
+      "files in(%d, %d) out(%d +%d blob) "
+      "MB in(%.1f, %.1f +%.1f blob) out(%.1f +%.1f blob), "
       "read-write-amplify(%.1f) write-amplify(%.1f) %s, records in: %" PRIu64
       ", records dropped: %" PRIu64 " output_compression: %s\n",
       column_family_name.c_str(), vstorage->LevelSummary(&tmp),
       bytes_read_per_sec, bytes_written_per_sec,
       compact_->compaction->output_level(),
       stats.num_input_files_in_non_output_levels,
-      stats.num_input_files_in_output_level,
-      stats.num_filtered_input_files_in_non_output_levels,
-      stats.num_filtered_input_files_in_output_level, stats.num_output_files,
+      stats.num_input_files_in_output_level, stats.num_output_files,
       stats.num_output_files_blob, stats.bytes_read_non_output_levels / kMB,
       stats.bytes_read_output_level / kMB, stats.bytes_read_blob / kMB,
-      stats.bytes_skipped_non_output_levels / kMB,
-      stats.bytes_skipped_output_level / kMB, stats.bytes_written / kMB,
-      stats.bytes_written_blob / kMB, read_write_amp, write_amp,
-      status.ToString().c_str(), stats.num_input_records,
+      stats.bytes_written / kMB, stats.bytes_written_blob / kMB, read_write_amp,
+      write_amp, status.ToString().c_str(), stats.num_input_records,
       stats.num_dropped_records,
       CompressionTypeToString(compact_->compaction->output_compression())
           .c_str());
@@ -1089,7 +1082,6 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     }
     // fallback to local compaction
     assert(comp_status == CompactionServiceJobStatus::kUseLocal);
-    sub_compact->compaction_job_stats.is_remote_compaction = false;
   }
 
   uint64_t prev_cpu_micros = db_options_.clock->CPUMicros();
@@ -1138,9 +1130,6 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // (b) CompactionFilter::Decision::kRemoveAndSkipUntil.
   read_options.total_order_seek = true;
 
-  const WriteOptions write_options(Env::IOPriority::IO_LOW,
-                                   Env::IOActivity::kCompaction);
-
   // Remove the timestamps from boundaries because boundaries created in
   // GenSubcompactionBoundaries doesn't strip away the timestamp.
   size_t ts_sz = cfd->user_comparator()->timestamp_size();
@@ -1275,17 +1264,18 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
           ? new BlobFileBuilder(
                 versions_, fs_.get(),
                 sub_compact->compaction->immutable_options(),
-                mutable_cf_options, &file_options_, &write_options, db_id_,
-                db_session_id_, job_id_, cfd->GetID(), cfd->GetName(),
+                mutable_cf_options, &file_options_, db_id_, db_session_id_,
+                job_id_, cfd->GetID(), cfd->GetName(), Env::IOPriority::IO_LOW,
                 write_hint_, io_tracer_, blob_callback_,
                 BlobFileCreationReason::kCompaction, &blob_file_paths,
                 sub_compact->Current().GetBlobFileAdditionsPtr())
           : nullptr);
 
   TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
-  TEST_SYNC_POINT_CALLBACK("CompactionJob::Run():PausingManualCompaction:1",
-                           static_cast<void*>(const_cast<std::atomic<bool>*>(
-                               &manual_compaction_canceled_)));
+  TEST_SYNC_POINT_CALLBACK(
+      "CompactionJob::Run():PausingManualCompaction:1",
+      reinterpret_cast<void*>(
+          const_cast<std::atomic<bool>*>(&manual_compaction_canceled_)));
 
   const std::string* const full_history_ts_low =
       full_history_ts_low_.empty() ? nullptr : &full_history_ts_low_;
@@ -1295,9 +1285,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
 
   auto c_iter = std::make_unique<CompactionIterator>(
       input, cfd->user_comparator(), &merge, versions_->LastSequence(),
-      &existing_snapshots_, earliest_snapshot_,
-      earliest_write_conflict_snapshot_, job_snapshot_seq, snapshot_checker_,
-      env_, ShouldReportDetailedTime(env_, stats_),
+      &existing_snapshots_, earliest_write_conflict_snapshot_, job_snapshot_seq,
+      snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_),
       /*expect_valid_internal_key=*/true, range_del_agg.get(),
       blob_file_builder.get(), db_options_.allow_data_in_errors,
       db_options_.enforce_single_del_contracts, manual_compaction_canceled_,
@@ -1334,7 +1323,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   Status status;
   TEST_SYNC_POINT_CALLBACK(
       "CompactionJob::ProcessKeyValueCompaction()::Processing",
-      static_cast<void*>(const_cast<Compaction*>(sub_compact->compaction)));
+      reinterpret_cast<void*>(
+          const_cast<Compaction*>(sub_compact->compaction)));
   uint64_t last_cpu_micros = prev_cpu_micros;
   while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
     // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
@@ -1365,9 +1355,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       break;
     }
 
-    TEST_SYNC_POINT_CALLBACK("CompactionJob::Run():PausingManualCompaction:2",
-                             static_cast<void*>(const_cast<std::atomic<bool>*>(
-                                 &manual_compaction_canceled_)));
+    TEST_SYNC_POINT_CALLBACK(
+        "CompactionJob::Run():PausingManualCompaction:2",
+        reinterpret_cast<void*>(
+            const_cast<std::atomic<bool>*>(&manual_compaction_canceled_)));
     c_iter->Next();
     if (c_iter->status().IsManualCompactionPaused()) {
       break;
@@ -1586,8 +1577,6 @@ Status CompactionJob::FinishCompactionOutputFile(
   const uint64_t current_entries = outputs.NumEntries();
 
   s = outputs.Finish(s, seqno_to_time_mapping_);
-  TEST_SYNC_POINT_CALLBACK(
-      "CompactionJob::FinishCompactionOutputFile()::AfterFinish", &s);
 
   if (s.ok()) {
     // With accurate smallest and largest key, we can get a slightly more
@@ -1721,8 +1710,6 @@ Status CompactionJob::InstallCompactionResults(
   db_mutex_->AssertHeld();
 
   const ReadOptions read_options(Env::IOActivity::kCompaction);
-  const WriteOptions write_options(Env::IOActivity::kCompaction);
-
   auto* compaction = compact_->compaction;
   assert(compaction);
 
@@ -1805,9 +1792,8 @@ Status CompactionJob::InstallCompactionResults(
   };
 
   return versions_->LogAndApply(
-      compaction->column_family_data(), mutable_cf_options, read_options,
-      write_options, edit, db_mutex_, db_directory_,
-      /*new_descriptor_log=*/false,
+      compaction->column_family_data(), mutable_cf_options, read_options, edit,
+      db_mutex_, db_directory_, /*new_descriptor_log=*/false,
       /*column_family_options=*/nullptr, manifest_wcb);
 }
 
@@ -1857,14 +1843,13 @@ Status CompactionJob::OpenCompactionOutputFile(SubcompactionState* sub_compact,
   // Pass temperature of the last level files to FileSystem.
   FileOptions fo_copy = file_options_;
   Temperature temperature = sub_compact->compaction->output_temperature();
-  Temperature last_level_temp =
-      sub_compact->compaction->mutable_cf_options()->last_level_temperature;
-  // Here last_level_temperature supersedes default_write_temperature, when
-  // enabled and applicable
-  if (last_level_temp != Temperature::kUnknown &&
+  // only set for the last level compaction and also it's not output to
+  // penultimate level (when preclude_last_level feature is enabled)
+  if (temperature == Temperature::kUnknown &&
       sub_compact->compaction->is_last_level() &&
       !sub_compact->IsCurrentPenultimateLevel()) {
-    temperature = last_level_temp;
+    temperature =
+        sub_compact->compaction->mutable_cf_options()->last_level_temperature;
   }
   fo_copy.temperature = temperature;
 
@@ -1920,10 +1905,6 @@ Status CompactionJob::OpenCompactionOutputFile(SubcompactionState* sub_compact,
     oldest_ancester_time = current_time;
   }
 
-  uint64_t newest_key_time = sub_compact->compaction->MaxInputFileNewestKeyTime(
-      sub_compact->start.has_value() ? &tmp_start : nullptr,
-      sub_compact->end.has_value() ? &tmp_end : nullptr);
-
   // Initialize a SubcompactionState::Output and add it to sub_compact->outputs
   uint64_t epoch_number = sub_compact->compaction->MinInputFileEpochNumber();
   {
@@ -1948,6 +1929,8 @@ Status CompactionJob::OpenCompactionOutputFile(SubcompactionState* sub_compact,
     }
 
     outputs.AddOutput(std::move(meta), cfd->internal_comparator(),
+                      sub_compact->compaction->mutable_cf_options()
+                          ->check_flush_compaction_key_order,
                       paranoid_file_checks_);
   }
 
@@ -1960,26 +1943,19 @@ Status CompactionJob::OpenCompactionOutputFile(SubcompactionState* sub_compact,
       sub_compact->compaction->immutable_options()->listeners;
   outputs.AssignFileWriter(new WritableFileWriter(
       std::move(writable_file), fname, fo_copy, db_options_.clock, io_tracer_,
-      db_options_.stats, Histograms::SST_WRITE_MICROS, listeners,
-      db_options_.file_checksum_gen_factory.get(),
+      db_options_.stats, listeners, db_options_.file_checksum_gen_factory.get(),
       tmp_set.Contains(FileType::kTableFile), false));
 
   // TODO(hx235): pass in the correct `oldest_key_time` instead of `0`
-  const ReadOptions read_options(Env::IOActivity::kCompaction);
-  const WriteOptions write_options(Env::IOActivity::kCompaction);
   TableBuilderOptions tboptions(
       *cfd->ioptions(), *(sub_compact->compaction->mutable_cf_options()),
-      read_options, write_options, cfd->internal_comparator(),
-      cfd->internal_tbl_prop_coll_factories(),
+      cfd->internal_comparator(), cfd->int_tbl_prop_collector_factories(),
       sub_compact->compaction->output_compression(),
       sub_compact->compaction->output_compression_opts(), cfd->GetID(),
-      cfd->GetName(), sub_compact->compaction->output_level(), newest_key_time,
+      cfd->GetName(), sub_compact->compaction->output_level(),
       bottommost_level_, TableFileCreationReason::kCompaction,
       0 /* oldest_key_time */, current_time, db_id_, db_session_id_,
-      sub_compact->compaction->max_output_file_size(), file_number,
-      preclude_last_level_min_seqno_ == kMaxSequenceNumber
-          ? preclude_last_level_min_seqno_
-          : std::min(earliest_snapshot_, preclude_last_level_min_seqno_));
+      sub_compact->compaction->max_output_file_size(), file_number);
 
   outputs.NewBuilder(tboptions);
 
@@ -2016,8 +1992,7 @@ bool CompactionJob::UpdateCompactionStats(uint64_t* num_input_range_del) {
   for (int input_level = 0;
        input_level < static_cast<int>(compaction->num_input_levels());
        ++input_level) {
-    const LevelFilesBrief* flevel = compaction->input_levels(input_level);
-    size_t num_input_files = flevel->num_files;
+    size_t num_input_files = compaction->num_input_files(input_level);
     uint64_t* bytes_read;
     if (compaction->level(input_level) != compaction->output_level()) {
       compaction_stats_.stats.num_input_files_in_non_output_levels +=
@@ -2029,7 +2004,7 @@ bool CompactionJob::UpdateCompactionStats(uint64_t* num_input_range_del) {
       bytes_read = &compaction_stats_.stats.bytes_read_output_level;
     }
     for (size_t i = 0; i < num_input_files; ++i) {
-      const FileMetaData* file_meta = flevel->files[i].file_metadata;
+      const FileMetaData* file_meta = compaction->input(input_level, i);
       *bytes_read += file_meta->fd.GetFileSize();
       uint64_t file_input_entries = file_meta->num_entries;
       uint64_t file_num_range_del = file_meta->num_range_deletions;
@@ -2052,23 +2027,6 @@ bool CompactionJob::UpdateCompactionStats(uint64_t* num_input_range_del) {
         *num_input_range_del += file_num_range_del;
       }
     }
-
-    const std::vector<FileMetaData*>& filtered_flevel =
-        compaction->filtered_input_levels(input_level);
-    size_t num_filtered_input_files = filtered_flevel.size();
-    uint64_t* bytes_skipped;
-    if (compaction->level(input_level) != compaction->output_level()) {
-      compaction_stats_.stats.num_filtered_input_files_in_non_output_levels +=
-          static_cast<int>(num_filtered_input_files);
-      bytes_skipped = &compaction_stats_.stats.bytes_skipped_non_output_levels;
-    } else {
-      compaction_stats_.stats.num_filtered_input_files_in_output_level +=
-          static_cast<int>(num_filtered_input_files);
-      bytes_skipped = &compaction_stats_.stats.bytes_skipped_output_level;
-    }
-    for (const FileMetaData* filtered_file_meta : filtered_flevel) {
-      *bytes_skipped += filtered_file_meta->fd.GetFileSize();
-    }
   }
 
   assert(compaction_job_stats_);
@@ -2093,13 +2051,6 @@ void CompactionJob::UpdateCompactionJobStats(
       stats.num_input_files_in_output_level;
   compaction_job_stats_->num_input_files_at_output_level =
       stats.num_input_files_in_output_level;
-  compaction_job_stats_->num_filtered_input_files =
-      stats.num_filtered_input_files_in_non_output_levels +
-      stats.num_filtered_input_files_in_output_level;
-  compaction_job_stats_->num_filtered_input_files_at_output_level =
-      stats.num_filtered_input_files_in_output_level;
-  compaction_job_stats_->total_skipped_input_bytes =
-      stats.bytes_skipped_non_output_levels + stats.bytes_skipped_output_level;
 
   // output information
   compaction_job_stats_->total_output_bytes = stats.bytes_written;

db/compaction/compaction_job.h

@@ -41,6 +41,7 @@
 #include "rocksdb/env.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/transaction_log.h"
+#include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
@@ -209,13 +210,12 @@ class CompactionJob {
   // Returns true iff compaction_stats_.stats.num_input_records and
   // num_input_range_del are calculated successfully.
   bool UpdateCompactionStats(uint64_t* num_input_range_del = nullptr);
-  virtual void UpdateCompactionJobStats(
-      const InternalStats::CompactionStats& stats) const;
   void LogCompaction();
   virtual void RecordCompactionIOStats();
   void CleanupCompaction();
 
-  // Iterate through input and compact the kv-pairs.
+  // Call compaction filter. Then iterate through input and compact the
+  // kv-pairs
   void ProcessKeyValueCompaction(SubcompactionState* sub_compact);
 
   CompactionState* compact_;
@@ -280,7 +280,8 @@ class CompactionJob {
                                   bool* compaction_released);
   Status OpenCompactionOutputFile(SubcompactionState* sub_compact,
                                   CompactionOutputs& outputs);
-
+  void UpdateCompactionJobStats(
+      const InternalStats::CompactionStats& stats) const;
   void RecordDroppedKeys(const CompactionIterationStats& c_iter_stats,
                          CompactionJobStats* compaction_job_stats = nullptr);
 
@@ -314,8 +315,6 @@ class CompactionJob {
   // deleted because that version is not visible in any snapshot.
   std::vector<SequenceNumber> existing_snapshots_;
 
-  SequenceNumber earliest_snapshot_;
-
   // This is the earliest snapshot that could be used for write-conflict
   // checking by a transaction.  For any user-key newer than this snapshot, we
   // should make sure not to remove evidence that a write occurred.
@@ -377,7 +376,9 @@ class CompactionJob {
 // doesn't contain the LSM tree information, which is passed though MANIFEST
 // file.
 struct CompactionServiceInput {
-  std::string cf_name;
+  ColumnFamilyDescriptor column_family;
+
+  DBOptions db_options;
 
   std::vector<SequenceNumber> snapshots;
 
@@ -385,7 +386,7 @@ struct CompactionServiceInput {
   // files needed for this compaction, for both input level files and output
   // level files.
   std::vector<std::string> input_files;
-  int output_level = 0;
+  int output_level;
 
   // db_id is used to generate unique id of sst on the remote compactor
   std::string db_id;
@@ -396,12 +397,13 @@ struct CompactionServiceInput {
   bool has_end = false;
   std::string end;
 
-  uint64_t options_file_number = 0;
-
   // serialization interface to read and write the object
   static Status Read(const std::string& data_str, CompactionServiceInput* obj);
   Status Write(std::string* output);
 
+  // Initialize a dummy ColumnFamilyDescriptor
+  CompactionServiceInput() : column_family("", ColumnFamilyOptions()) {}
+
 #ifndef NDEBUG
   bool TEST_Equals(CompactionServiceInput* other);
   bool TEST_Equals(CompactionServiceInput* other, std::string* mismatch);
@@ -415,25 +417,20 @@ struct CompactionServiceOutputFile {
   SequenceNumber largest_seqno;
   std::string smallest_internal_key;
   std::string largest_internal_key;
-  uint64_t oldest_ancester_time = kUnknownOldestAncesterTime;
-  uint64_t file_creation_time = kUnknownFileCreationTime;
-  uint64_t epoch_number = kUnknownEpochNumber;
-  std::string file_checksum = kUnknownFileChecksum;
-  std::string file_checksum_func_name = kUnknownFileChecksumFuncName;
+  uint64_t oldest_ancester_time;
+  uint64_t file_creation_time;
+  uint64_t epoch_number;
   uint64_t paranoid_hash;
   bool marked_for_compaction;
-  UniqueId64x2 unique_id{};
-  TableProperties table_properties;
+  UniqueId64x2 unique_id;
 
   CompactionServiceOutputFile() = default;
   CompactionServiceOutputFile(
       const std::string& name, SequenceNumber smallest, SequenceNumber largest,
       std::string _smallest_internal_key, std::string _largest_internal_key,
       uint64_t _oldest_ancester_time, uint64_t _file_creation_time,
-      uint64_t _epoch_number, const std::string& _file_checksum,
-      const std::string& _file_checksum_func_name, uint64_t _paranoid_hash,
-      bool _marked_for_compaction, UniqueId64x2 _unique_id,
-      const TableProperties& _table_properties)
+      uint64_t _epoch_number, uint64_t _paranoid_hash,
+      bool _marked_for_compaction, UniqueId64x2 _unique_id)
       : file_name(name),
         smallest_seqno(smallest),
         largest_seqno(largest),
@@ -442,12 +439,9 @@ struct CompactionServiceOutputFile {
         oldest_ancester_time(_oldest_ancester_time),
         file_creation_time(_file_creation_time),
         epoch_number(_epoch_number),
-        file_checksum(_file_checksum),
-        file_checksum_func_name(_file_checksum_func_name),
         paranoid_hash(_paranoid_hash),
         marked_for_compaction(_marked_for_compaction),
-        unique_id(std::move(_unique_id)),
-        table_properties(_table_properties) {}
+        unique_id(std::move(_unique_id)) {}
 };
 
 // CompactionServiceResult contains the compaction result from a different db
@@ -456,11 +450,14 @@ struct CompactionServiceOutputFile {
 struct CompactionServiceResult {
   Status status;
   std::vector<CompactionServiceOutputFile> output_files;
-  int output_level = 0;
+  int output_level;
 
   // location of the output files
   std::string output_path;
 
+  // some statistics about the compaction
+  uint64_t num_output_records = 0;
+  uint64_t total_bytes = 0;
   uint64_t bytes_read = 0;
   uint64_t bytes_written = 0;
   CompactionJobStats stats;
@@ -506,9 +503,6 @@ class CompactionServiceCompactionJob : private CompactionJob {
  protected:
   void RecordCompactionIOStats() override;
 
-  void UpdateCompactionJobStats(
-      const InternalStats::CompactionStats& stats) const override;
-
  private:
   // Get table file name in output_path
   std::string GetTableFileName(uint64_t file_number) override;