Fix the ZStd checksum (#12005)

Summary:
Somehow we had the wrong checksum when validating the ZStd 1.5.5 download for RocksJava in the previous Pull Request - https://github.com/facebook/rocksdb/pull/9304. This PR fixes that.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12005

Reviewed By: jaykorean

Differential Revision: D50840338

Pulled By: cbi42

fbshipit-source-id: 8a92779d3bef013d812eecb89aaaf33fc73991ec

.circleci/config.yml

@@ -0,0 +1,896 @@
+version: 2.1
+
+orbs:
+  win: circleci/windows@5.0.0
+
+commands:
+  install-cmake-on-macos:
+    steps:
+      - run:
+          name: Install cmake on macos
+          command: |
+            HOMEBREW_NO_AUTO_UPDATE=1 brew install cmake
+
+  install-jdk8-on-macos:
+    steps:
+      - run:
+          name: Install JDK 8 on macos
+          command: |
+            HOMEBREW_NO_AUTO_UPDATE=1 brew tap bell-sw/liberica
+            HOMEBREW_NO_AUTO_UPDATE=1 brew install --cask liberica-jdk8
+
+  increase-max-open-files-on-macos:
+    steps:
+      - run:
+          name: Increase max open files
+          command: |
+            sudo sysctl -w kern.maxfiles=1048576
+            sudo sysctl -w kern.maxfilesperproc=1048576
+            sudo launchctl limit maxfiles 1048576
+
+  pre-steps:
+    steps:
+      - checkout
+      - run:
+          name: Setup Environment Variables
+          command: |
+            echo "export GTEST_THROW_ON_FAILURE=0" >> $BASH_ENV
+            echo "export GTEST_OUTPUT=\"xml:/tmp/test-results/\"" >> $BASH_ENV
+            echo "export SKIP_FORMAT_BUCK_CHECKS=1" >> $BASH_ENV
+            echo "export GTEST_COLOR=1" >> $BASH_ENV
+            echo "export CTEST_OUTPUT_ON_FAILURE=1" >> $BASH_ENV
+            echo "export CTEST_TEST_TIMEOUT=300" >> $BASH_ENV
+            echo "export ZLIB_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/zlib" >> $BASH_ENV
+            echo "export BZIP2_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/bzip2" >> $BASH_ENV
+            echo "export SNAPPY_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/snappy" >> $BASH_ENV
+            echo "export LZ4_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/lz4" >> $BASH_ENV
+            echo "export ZSTD_DOWNLOAD_BASE=https://rocksdb-deps.s3.us-west-2.amazonaws.com/pkgs/zstd" >> $BASH_ENV
+
+  windows-build-steps:
+    steps:
+      - checkout
+      - run:
+          name: "Install thirdparty dependencies"
+          command: |
+            echo "Installing CMake..."
+            choco install cmake --installargs 'ADD_CMAKE_TO_PATH=System' -y
+            mkdir $Env:THIRDPARTY_HOME
+            cd $Env:THIRDPARTY_HOME
+            echo "Building Snappy dependency..."
+            curl https://github.com/google/snappy/archive/refs/tags/1.1.8.zip -O snappy-1.1.8.zip
+            unzip -q snappy-1.1.8.zip
+            cd snappy-1.1.8
+            mkdir build
+            cd build
+            & $Env:CMAKE_BIN -G "$Env:CMAKE_GENERATOR" ..
+            msbuild.exe Snappy.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
+      - run:
+          name: "Build RocksDB"
+          command: |
+            mkdir build
+            cd build
+            & $Env:CMAKE_BIN -G "$Env:CMAKE_GENERATOR" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DJNI=1 ..
+            cd ..
+            echo "Building with VS version: $Env:CMAKE_GENERATOR"
+            msbuild.exe build/rocksdb.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
+      - run:
+          name: "Test RocksDB"
+          shell: powershell.exe
+          command: |
+            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
+  pre-steps-macos:
+      steps:
+        - pre-steps
+
+  post-steps:
+    steps:
+      - store_test_results: # store test result if there's any
+          path: /tmp/test-results
+      - store_artifacts: # store LOG for debugging if there's any
+          path: LOG
+      - run: # on fail, compress Test Logs for diagnosing the issue
+          name: Compress Test Logs
+          command: tar -cvzf t.tar.gz t
+          when: on_fail
+      - store_artifacts: # on fail, store Test Logs for diagnosing the issue
+          path: t.tar.gz
+          destination: test_logs
+          when: on_fail
+      - run: # store core dumps if there's any
+          command: |
+            mkdir -p /tmp/core_dumps
+            cp core.* /tmp/core_dumps
+          when: on_fail
+      - store_artifacts:
+          path: /tmp/core_dumps
+          when: on_fail
+
+  upgrade-cmake:
+    steps:
+      - run:
+          name: Upgrade cmake
+          command: |
+            sudo apt remove --purge cmake
+            sudo snap install cmake --classic
+
+  install-gflags:
+    steps:
+      - run:
+          name: Install gflags
+          command: |
+            sudo apt-get update -y && sudo apt-get install -y libgflags-dev
+
+  install-gflags-on-macos:
+    steps:
+      - run:
+          name: Install gflags on macos
+          command: |
+            HOMEBREW_NO_AUTO_UPDATE=1 brew install gflags
+
+  setup-folly:
+    steps:
+      - run:
+          name: Checkout folly sources
+          command: |
+            make checkout_folly
+
+  build-folly:
+    steps:
+      - run:
+          name: Build folly and dependencies
+          command: |
+            make build_folly
+
+  build-for-benchmarks:
+    steps:
+      - pre-steps
+      - run:
+          name: "Linux build for benchmarks"
+          command: #sized for the resource-class rocksdb-benchmark-sys1
+            make V=1 J=8 -j8 release
+
+  perform-benchmarks:
+    steps:
+      - run:
+          name: "Test low-variance benchmarks"
+          command: ./tools/benchmark_ci.py --db_dir /tmp/rocksdb-benchmark-datadir --output_dir /tmp/benchmark-results --num_keys 20000000
+          environment:
+            LD_LIBRARY_PATH: /usr/local/lib
+            # How long to run parts of the test(s)
+            DURATION_RO: 300
+            DURATION_RW: 500
+            # Keep threads within physical capacity of server (much lower than default)
+            NUM_THREADS: 1
+            MAX_BACKGROUND_JOBS: 4
+            # Don't run a couple of "optional" initial tests
+            CI_TESTS_ONLY: "true"
+            # Reduce configured size of levels to ensure more levels in the leveled compaction LSM tree
+            WRITE_BUFFER_SIZE_MB: 16
+            TARGET_FILE_SIZE_BASE_MB: 16
+            MAX_BYTES_FOR_LEVEL_BASE_MB: 64
+            # The benchmark host has 32GB memory
+            # The following values are tailored to work with that
+            # Note, tests may not exercise the targeted issues if the memory is increased on new test hosts.
+            COMPRESSION_TYPE: "none"
+            CACHE_INDEX_AND_FILTER_BLOCKS: 1
+            MIN_LEVEL_TO_COMPRESS: 3
+            CACHE_SIZE_MB: 10240
+            MB_WRITE_PER_SEC: 2
+
+  post-benchmarks:
+    steps:
+      - store_artifacts: # store the benchmark output
+          path: /tmp/benchmark-results
+          destination: test_logs
+      - run:
+          name: Send benchmark report to visualisation
+          command: |
+            set +e
+            set +o pipefail
+            ./build_tools/benchmark_log_tool.py --tsvfile /tmp/benchmark-results/report.tsv --esdocument https://search-rocksdb-bench-k2izhptfeap2hjfxteolsgsynm.us-west-2.es.amazonaws.com/bench_test3_rix/_doc
+            true
+
+executors:
+  linux-docker:
+    docker:
+      # The image configuration is build_tools/ubuntu20_image/Dockerfile
+      # To update and build the image:
+      #  $ cd build_tools/ubuntu20_image
+      #  $ docker build -t zjay437/rocksdb:0.5 .
+      #  $ docker push zjay437/rocksdb:0.5
+      # `zjay437` is the account name for zjay@meta.com which readwrite token is shared internally. To login:
+      #  $ docker login --username zjay437
+      # Or please feel free to change it to your docker hub account for hosting the image, meta employee should already have the account and able to login with SSO.
+      # To avoid impacting the existing CI runs, please bump the version every time creating a new image
+      # to run the CI image environment locally:
+      #  $ docker run --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -it zjay437/rocksdb:0.5 bash
+      # option `--cap-add=SYS_PTRACE --security-opt seccomp=unconfined` is used to enable gdb to attach an existing process
+      - image: zjay437/rocksdb:0.6
+  linux-java-docker:
+    docker:
+      - image: evolvedbinary/rocksjava:centos6_x64-be
+
+jobs:
+  build-macos:
+    macos:
+      xcode: 14.3.1
+    resource_class: macos.m1.medium.gen1
+    environment:
+      ROCKSDB_DISABLE_JEMALLOC: 1 # jemalloc cause env_test hang, disable it for now
+    steps:
+      - increase-max-open-files-on-macos
+      - install-gflags-on-macos
+      - pre-steps-macos
+      - run: ulimit -S -n `ulimit -H -n` && OPT=-DCIRCLECI make V=1 J=16 -j16 all
+      - post-steps
+
+  build-macos-cmake:
+    macos:
+      xcode: 14.3.1
+    resource_class: macos.m1.medium.gen1
+    parameters:
+      run_even_tests:
+        description: run even or odd tests, used to split tests to 2 groups
+        type: boolean
+        default: true
+    steps:
+      - increase-max-open-files-on-macos
+      - install-cmake-on-macos
+      - install-gflags-on-macos
+      - pre-steps-macos
+      - run:
+          name: "cmake generate project file"
+          command: ulimit -S -n `ulimit -H -n` && mkdir build && cd build && cmake -DWITH_GFLAGS=1 ..
+      - run:
+          name: "Build tests"
+          command: cd build && make V=1 -j16
+      - when:
+          condition: << parameters.run_even_tests >>
+          steps:
+            - run:
+                name: "Run even tests"
+                command: ulimit -S -n `ulimit -H -n` && cd build && ctest -j16 -I 0,,2
+      - when:
+          condition:
+            not: << parameters.run_even_tests >>
+          steps:
+            - run:
+                name: "Run odd tests"
+                command: ulimit -S -n `ulimit -H -n` && cd build && ctest -j16 -I 1,,2
+      - post-steps
+
+  build-linux:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: make V=1 J=32 -j32 check
+      - post-steps
+
+  build-linux-encrypted_env-no_compression:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - 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
+      - post-steps
+
+  build-linux-static_lib-alt_namespace-status_checked:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - 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
+      - post-steps
+
+  build-linux-release:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - checkout # check out the code in the project directory
+      - run: make V=1 -j32 LIB_MODE=shared release
+      - run: ls librocksdb.so # ensure shared lib built
+      - run: ./db_stress --version # ensure with gflags
+      - run: make clean
+      - run: make V=1 -j32 release
+      - run: ls librocksdb.a # ensure static lib built
+      - run: ./db_stress --version # ensure with gflags
+      - run: make clean
+      - run: apt-get remove -y libgflags-dev
+      - run: make V=1 -j32 LIB_MODE=shared release
+      - run: ls librocksdb.so # ensure shared lib built
+      - run: if ./db_stress --version; then false; else true; fi # ensure without gflags
+      - run: make clean
+      - run: make V=1 -j32 release
+      - run: ls librocksdb.a # ensure static lib built
+      - run: if ./db_stress --version; then false; else true; fi # ensure without gflags
+      - post-steps
+
+  build-linux-release-rtti:
+    executor: linux-docker
+    resource_class: xlarge
+    steps:
+      - checkout # check out the code in the project directory
+      - run: USE_RTTI=1 DEBUG_LEVEL=0 make V=1 -j16 static_lib tools db_bench
+      - run: ./db_stress --version # ensure with gflags
+      - 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 # ensure without gflags
+
+  build-linux-clang-no_test_run:
+    executor: linux-docker
+    resource_class: xlarge
+    steps:
+      - checkout # check out the code in the project directory
+      - run: CC=clang CXX=clang++ USE_CLANG=1 PORTABLE=1 make V=1 -j16 all
+      - post-steps
+
+  build-linux-clang10-asan:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - 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 # aligned new doesn't work for reason we haven't figured out
+      - post-steps
+
+  build-linux-clang10-mini-tsan:
+    executor: linux-docker
+    resource_class: 2xlarge+
+    steps:
+      - 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
+      - post-steps
+
+  build-linux-clang10-ubsan:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - 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 # aligned new doesn't work for reason we haven't figured out
+      - post-steps
+
+  build-linux-valgrind:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: PORTABLE=1 make V=1 -j32 valgrind_test
+      - post-steps
+
+  build-linux-clang10-clang-analyze:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - 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 # aligned new doesn't work for reason we haven't figured out. For unknown, reason passing "clang++-10" as CLANG_ANALYZER doesn't work, and we need a full path.
+      - post-steps
+      - run:
+          name: "compress test report"
+          command: tar -cvzf scan_build_report.tar.gz scan_build_report
+          when: on_fail
+      - store_artifacts:
+          path: scan_build_report.tar.gz
+          destination: scan_build_report
+          when: on_fail
+
+  build-linux-runner:
+    machine: true
+    resource_class: facebook/rocksdb-benchmark-sys1
+    steps:
+      - pre-steps
+      - run:
+          name: "Checked Linux build (Runner)"
+          command: make V=1 J=8 -j8 check
+          environment:
+            LD_LIBRARY_PATH: /usr/local/lib
+      - post-steps
+
+  build-linux-cmake-with-folly:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - setup-folly
+      - build-folly
+      - run: (mkdir build && cd build && cmake -DUSE_FOLLY=1 -DWITH_GFLAGS=1 -DROCKSDB_BUILD_SHARED=0 .. && make V=1 -j20 && ctest -j20)
+      - post-steps
+
+  build-linux-cmake-with-folly-lite-no-test:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - setup-folly
+      - run: (mkdir build && cd build && cmake -DUSE_FOLLY_LITE=1 -DWITH_GFLAGS=1 .. && make V=1 -j20)
+      - post-steps
+
+  build-linux-cmake-with-benchmark:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: mkdir build && cd build && cmake -DWITH_GFLAGS=1 -DWITH_BENCHMARK=1 .. && make V=1 -j20 && ctest -j20
+      - post-steps
+
+  build-linux-unity-and-headers:
+    docker: # executor type
+      - image: gcc:latest
+    environment:
+      EXTRA_CXXFLAGS: -mno-avx512f # Warnings-as-error in avx512fintrin.h, would be used on newer hardware
+    resource_class: large
+    steps:
+      - checkout # check out the code in the project directory
+      - run: apt-get update -y && apt-get install -y libgflags-dev
+      - run:
+          name: "Unity build"
+          command: make V=1 -j8 unity_test
+          no_output_timeout: 20m
+      - run: make V=1 -j8 -k check-headers # could be moved to a different build
+      - post-steps
+
+  build-linux-gcc-7-with-folly:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - setup-folly
+      - build-folly
+      - run: USE_FOLLY=1 LIB_MODE=static CC=gcc-7 CXX=g++-7 V=1 make -j32 check # TODO: LIB_MODE only to work around unresolved linker failures
+      - post-steps
+
+  build-linux-gcc-7-with-folly-lite-no-test:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - setup-folly
+      - run: USE_FOLLY_LITE=1 CC=gcc-7 CXX=g++-7 V=1 make -j32 all
+      - post-steps
+
+  build-linux-gcc-8-no_test_run:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: CC=gcc-8 CXX=g++-8 V=1 make -j32 all
+      - post-steps
+
+  build-linux-cmake-with-folly-coroutines:
+    executor: linux-docker
+    resource_class: 2xlarge
+    environment:
+      CC: gcc-10
+      CXX: g++-10
+    steps:
+      - pre-steps
+      - setup-folly
+      - build-folly
+      - run: (mkdir build && cd build && cmake -DUSE_COROUTINES=1 -DWITH_GFLAGS=1 -DROCKSDB_BUILD_SHARED=0 .. && make V=1 -j20 && ctest -j20)
+      - post-steps
+
+  build-linux-gcc-10-cxx20-no_test_run:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: CC=gcc-10 CXX=g++-10 V=1 ROCKSDB_CXX_STANDARD=c++20 make -j32 all
+      - post-steps
+
+  build-linux-gcc-11-no_test_run:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: LIB_MODE=static CC=gcc-11 CXX=g++-11 V=1 make -j32 all microbench # TODO: LIB_MODE only to work around unresolved linker failures
+      - post-steps
+
+  build-linux-clang-13-no_test_run:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: CC=clang-13 CXX=clang++-13 USE_CLANG=1 make -j32 all microbench
+      - post-steps
+
+  # Ensure ASAN+UBSAN with folly, and full testsuite with clang 13
+  build-linux-clang-13-asan-ubsan-with-folly:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - setup-folly
+      - build-folly
+      - run: CC=clang-13 CXX=clang++-13 LIB_MODE=static USE_CLANG=1 USE_FOLLY=1 COMPILE_WITH_UBSAN=1 COMPILE_WITH_ASAN=1 make -j32 check # TODO: LIB_MODE only to work around unresolved linker failures
+      - post-steps
+
+  # This job is only to make sure the microbench tests are able to run, the benchmark result is not meaningful as the CI host is changing.
+  build-linux-run-microbench:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run: DEBUG_LEVEL=0 make -j32 run_microbench
+      - post-steps
+
+  build-linux-mini-crashtest:
+    executor: linux-docker
+    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 --use_io_uring=0' blackbox_crash_test_with_atomic_flush
+      - post-steps
+
+  build-linux-crashtest-tiered-storage-bb:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run:
+          name: "run crashtest"
+          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
+
+  build-linux-crashtest-tiered-storage-wb:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run:
+          name: "run crashtest"
+          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
+
+  build-windows-vs2022:
+    executor:
+      name: win/server-2022
+      size: 2xlarge
+    environment:
+      THIRDPARTY_HOME: C:/Users/circleci/thirdparty
+      CMAKE_HOME: C:/Program Files/CMake
+      CMAKE_BIN: C:/Program Files/CMake/bin/cmake.exe
+      SNAPPY_HOME: C:/Users/circleci/thirdparty/snappy-1.1.8
+      SNAPPY_INCLUDE: C:/Users/circleci/thirdparty/snappy-1.1.8;C:/Users/circleci/thirdparty/snappy-1.1.8/build
+      SNAPPY_LIB_DEBUG: C:/Users/circleci/thirdparty/snappy-1.1.8/build/Debug/snappy.lib
+      CMAKE_GENERATOR: Visual Studio 17 2022
+    steps:
+      - windows-build-steps
+
+  build-windows-vs2019:
+    executor:
+      name: win/server-2019
+      size: 2xlarge
+    environment:
+      THIRDPARTY_HOME: C:/Users/circleci/thirdparty
+      CMAKE_HOME: C:/Program Files/CMake
+      CMAKE_BIN: C:/Program Files/CMake/bin/cmake.exe
+      SNAPPY_HOME: C:/Users/circleci/thirdparty/snappy-1.1.8
+      SNAPPY_INCLUDE: C:/Users/circleci/thirdparty/snappy-1.1.8;C:/Users/circleci/thirdparty/snappy-1.1.8/build
+      SNAPPY_LIB_DEBUG: C:/Users/circleci/thirdparty/snappy-1.1.8/build/Debug/snappy.lib
+      CMAKE_GENERATOR: Visual Studio 16 2019
+    steps:
+      - windows-build-steps
+
+  build-linux-java:
+    executor: linux-docker
+    resource_class: large
+    steps:
+      - pre-steps
+      - run:
+          name: "Set Java Environment"
+          command: |
+            echo "JAVA_HOME=${JAVA_HOME}"
+            echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
+            which java && java -version
+            which javac && javac -version
+      - run:
+          name: "Test RocksDBJava"
+          command: make V=1 J=8 -j8 jtest
+      - post-steps
+
+  build-linux-java-static:
+    executor: linux-java-docker
+    resource_class: large
+    steps:
+      - pre-steps
+      - run:
+          name: "Set Java Environment"
+          command: |
+            echo "JAVA_HOME=${JAVA_HOME}"
+            echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
+            which java && java -version
+            which javac && javac -version
+      - run:
+          name: "Build RocksDBJava Static Library"
+          command: scl enable devtoolset-7 'make V=1 J=8 -j8 rocksdbjavastatic'
+      - post-steps
+
+  build-macos-java:
+    macos:
+      xcode: 14.3.1
+    resource_class: macos.m1.medium.gen1
+    environment:
+      JAVA_HOME: /Library/Java/JavaVirtualMachines/liberica-jdk-8.jdk/Contents/Home
+      ROCKSDB_DISABLE_JEMALLOC: 1 # jemalloc causes java 8 crash
+    steps:
+      - increase-max-open-files-on-macos
+      - install-gflags-on-macos
+      - install-jdk8-on-macos
+      - pre-steps-macos
+      - run:
+          name: "Set Java Environment"
+          command: |
+            echo "JAVA_HOME=${JAVA_HOME}"
+            echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
+            which java && java -version
+            which javac && javac -version
+      - run:
+          name: "Test RocksDBJava"
+          command: make V=1 J=16 -j16 jtest
+          no_output_timeout: 20m
+      - post-steps
+
+  build-macos-java-static:
+    macos:
+      xcode: 14.3.1
+    resource_class: macos.m1.medium.gen1
+    environment:
+      JAVA_HOME: /Library/Java/JavaVirtualMachines/liberica-jdk-8.jdk/Contents/Home
+    steps:
+      - increase-max-open-files-on-macos
+      - install-gflags-on-macos
+      - install-cmake-on-macos
+      - install-jdk8-on-macos
+      - pre-steps-macos
+      - run:
+          name: "Set Java Environment"
+          command: |
+            echo "JAVA_HOME=${JAVA_HOME}"
+            echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
+            which java && java -version
+            which javac && javac -version
+      - run:
+          name: "Build RocksDBJava x86 and ARM Static Libraries"
+          command: make V=1 J=16 -j16 rocksdbjavastaticosx
+          no_output_timeout: 20m
+      - post-steps
+
+  build-macos-java-static-universal:
+    macos:
+      xcode: 14.3.1
+    resource_class: macos.m1.medium.gen1
+    environment:
+      JAVA_HOME: /Library/Java/JavaVirtualMachines/liberica-jdk-8.jdk/Contents/Home
+    steps:
+      - increase-max-open-files-on-macos
+      - install-gflags-on-macos
+      - install-cmake-on-macos
+      - install-jdk8-on-macos
+      - pre-steps-macos
+      - run:
+          name: "Set Java Environment"
+          command: |
+            echo "JAVA_HOME=${JAVA_HOME}"
+            echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
+            which java && java -version
+            which javac && javac -version
+      - run:
+          name: "Build RocksDBJava Universal Binary Static Library"
+          command: make V=1 J=16 -j16 rocksdbjavastaticosx_ub
+          no_output_timeout: 20m
+      - post-steps
+
+  build-examples:
+    executor: linux-docker
+    resource_class: large
+    steps:
+      - pre-steps
+      - run:
+          name: "Build examples"
+          command: |
+            make V=1 -j4 static_lib && cd examples && make V=1 -j4
+      - post-steps
+
+  build-cmake-mingw:
+    executor: linux-docker
+    resource_class: large
+    steps:
+      - pre-steps
+      - run: update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix
+      - run:
+          name: "Build cmake-mingw"
+          command: |
+            export PATH=$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
+      - post-steps
+
+  build-linux-non-shm:
+    executor: linux-docker
+    resource_class: 2xlarge
+    environment:
+      TEST_TMPDIR: /tmp/rocksdb_test_tmp
+    steps:
+      - pre-steps
+      - run: make V=1 -j32 check
+      - post-steps
+
+  build-linux-arm-test-full:
+    machine:
+      image: ubuntu-2004:202111-02
+    resource_class: arm.large
+    steps:
+      - pre-steps
+      - install-gflags
+      - run: make V=1 J=4 -j4 check
+      - post-steps
+
+  build-linux-arm:
+    machine:
+      image: ubuntu-2004:202111-02
+    resource_class: arm.large
+    steps:
+      - pre-steps
+      - install-gflags
+      - run: ROCKSDBTESTS_PLATFORM_DEPENDENT=only make V=1 J=4 -j4 all_but_some_tests check_some
+      - post-steps
+
+  build-linux-arm-cmake-no_test_run:
+    machine:
+      image: ubuntu-2004:202111-02
+    resource_class: arm.large
+    environment:
+      JAVA_HOME: /usr/lib/jvm/java-8-openjdk-arm64
+    steps:
+      - pre-steps
+      - install-gflags
+      - run:
+          name: "Set Java Environment"
+          command: |
+            echo "JAVA_HOME=${JAVA_HOME}"
+            echo 'export PATH=$JAVA_HOME/bin:$PATH' >> $BASH_ENV
+            which java && java -version
+            which javac && javac -version
+      - run:
+          name: "Build with cmake"
+          command: |
+            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
+      - run:
+          name: "Build Java with cmake"
+          command: |
+            rm -rf build
+            mkdir build
+            cd build
+            cmake -DJNI=1 -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 ..
+            make -j4 rocksdb rocksdbjni
+      - post-steps
+
+  build-format-compatible:
+    executor: linux-docker
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - run:
+          name: "test"
+          command: |
+            export TEST_TMPDIR=/dev/shm/rocksdb
+            rm -rf /dev/shm/rocksdb
+            mkdir /dev/shm/rocksdb
+            tools/check_format_compatible.sh
+      - post-steps
+
+  build-fuzzers:
+    executor: linux-docker
+    resource_class: large
+    steps:
+      - pre-steps
+      - run:
+          name: "Build rocksdb lib"
+          command: CC=clang-13 CXX=clang++-13 USE_CLANG=1 make -j4 static_lib
+      - run:
+          name: "Build fuzzers"
+          command: cd fuzz && make sst_file_writer_fuzzer db_fuzzer db_map_fuzzer
+      - post-steps
+
+  benchmark-linux: #use a private Circle CI runner (resource_class) to run the job
+    machine: true
+    resource_class: facebook/rocksdb-benchmark-sys1
+    steps:
+      - build-for-benchmarks
+      - perform-benchmarks
+      - post-benchmarks
+
+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-vs2022
+      - 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
+  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:
+          cron: "0 * * * *"
+          filters:
+            branches:
+              only:
+                - main
+    jobs:
+      - benchmark-linux
+  nightly:
+    triggers:
+      - schedule:
+          cron: "0 9 * * *"
+          filters:
+            branches:
+              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

.circleci/ubsan_suppression_list.txt

@@ -0,0 +1,6 @@
+# Supress UBSAN warnings related to stl_tree.h, e.g.
+# UndefinedBehaviorSanitizer: undefined-behavior /usr/bin/../lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/c++/5.4.0/bits/stl_tree.h:1505:43 in 
+# /usr/bin/../lib/gcc/x86_64-linux-gnu/5.4.0/../../../../include/c++/5.4.0/bits/stl_tree.h:1505:43:
+# runtime error: upcast of address 0x000001fa8820 with insufficient space for an object of type
+# 'std::_Rb_tree_node<std::pair<const std::__cxx11::basic_string<char>, rocksdb::(anonymous namespace)::LockHoldingInfo> >'
+src:*bits/stl_tree.h

.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-24.04
-    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://rocksdb-deps.s3.us-west-2.amazonaws.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 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-clang13-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
@@ -91,7 +88,6 @@ buckifier/__pycache__
 .arcconfig
 
 compile_commands.json
-meta_gen_cpp_compile_commands.json
 clang-format-diff.py
 .py3/
 

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
@@ -799,7 +772,6 @@ set(SOURCES
         options/configurable.cc
         options/customizable.cc
         options/db_options.cc
-        options/offpeak_time_info.cc
         options/options.cc
         options/options_helper.cc
         options/options_parser.cc
@@ -835,7 +807,6 @@ set(SOURCES
         table/cuckoo/cuckoo_table_builder.cc
         table/cuckoo/cuckoo_table_factory.cc
         table/cuckoo/cuckoo_table_reader.cc
-        table/external_table.cc
         table/format.cc
         table/get_context.cc
         table/iterator.cc
@@ -940,11 +911,8 @@ set(SOURCES
         utilities/persistent_cache/block_cache_tier_metadata.cc
         utilities/persistent_cache/persistent_cache_tier.cc
         utilities/persistent_cache/volatile_tier_impl.cc
-        utilities/secondary_index/secondary_index_iterator.cc
-        utilities/secondary_index/simple_secondary_index.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
@@ -965,7 +933,6 @@ 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
@@ -1057,7 +1024,6 @@ 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
@@ -1065,12 +1031,6 @@ 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()
@@ -1145,15 +1105,11 @@ set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
 configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
 
 add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES} ${BUILD_VERSION_CC})
-target_include_directories(${ROCKSDB_STATIC_LIB} PUBLIC
-  $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>)
 target_link_libraries(${ROCKSDB_STATIC_LIB} PRIVATE
   ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 
 if(ROCKSDB_BUILD_SHARED)
   add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES} ${BUILD_VERSION_CC})
-  target_include_directories(${ROCKSDB_SHARED_LIB} PUBLIC
-    $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>)
   target_link_libraries(${ROCKSDB_SHARED_LIB} PRIVATE
     ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 
@@ -1380,7 +1336,6 @@ 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
@@ -1388,7 +1343,6 @@ 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
@@ -1469,7 +1423,6 @@ 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
@@ -1494,7 +1447,6 @@ 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
@@ -1505,7 +1457,6 @@ 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}
@@ -1521,7 +1472,7 @@ 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} ${FOLLY_LIBS})
@@ -1546,7 +1497,7 @@ if(WITH_TESTS)
       target_link_libraries(${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})
 
@@ -1566,7 +1517,7 @@ 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()
 
@@ -1574,7 +1525,6 @@ if(WITH_BENCHMARK_TOOLS)
   add_executable(db_bench${ARTIFACT_SUFFIX}
     tools/simulated_hybrid_file_system.cc
     tools/db_bench.cc
-    tools/tool_hooks.cc
     tools/db_bench_tool.cc)
   target_link_libraries(db_bench${ARTIFACT_SUFFIX}
     ${ROCKSDB_LIB} ${THIRDPARTY_LIBS})
@@ -1646,3 +1596,6 @@ option(WITH_BENCHMARK "build benchmark tests" OFF)
 if(WITH_BENCHMARK)
   add_subdirectory(${PROJECT_SOURCE_DIR}/microbench/)
 endif()
+
+target_include_directories(${PROJECT_NAME} PUBLIC
+  $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>)

HISTORY.md

@@ -1,468 +1,22 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
-## 10.1.0 (03/24/2025)
-### New Features
-* Added a new `DBOptions.calculate_sst_write_lifetime_hint_set` setting that allows to customize which compaction styles SST write lifetime hint calculation is allowed on. Today RocksDB supports only two modes `kCompactionStyleLevel` and `kCompactionStyleUniversal`.
-* Add a new field `num_l0_files` in `CompactionJobInfo` about the number of L0 files in the CF right before and after the compaction
-* Added per-key-placement feature in Remote Compaction
-* Implemented API DB::GetPropertiesOfTablesByLevel that retrieves table properties for files in each LSM tree level
+## 8.7.3 (10/30/2023)
+### Behavior Changes
+* Deleting stale files upon recovery are delegated to SstFileManger if available so they can be rate limited.
 
+## 8.7.2 (10/25/2023)
 ### Public API Changes
-* `GetAllKeyVersions()` now interprets empty slices literally, as valid keys, and uses new `OptSlice` type default value for extreme upper and lower range limits.
-* `DeleteFilesInRanges()` now takes `RangeOpt` which is based on `OptSlice`. The overload taking `RangePtr` is deprecated.
-* Add an unordered map of name/value pairs, ReadOptions::property_bag, to pass opaque options through to an external table when creating an Iterator.
-* Introduced CompactionServiceJobStatus::kAborted to allow handling aborted scenario in Schedule(), Wait() or OnInstallation() APIs in Remote Compactions.
-* format\_version < 2 in BlockBasedTableOptions is no longer supported for writing new files. Support for reading such files is deprecated and might be removed in the future. `CompressedSecondaryCacheOptions::compress_format_version == 1` is also deprecated.
-
-### Behavior Changes
-* `ldb` now returns an error if the specified `--compression_type` is not supported in the build.
-* MultiGet with snapshot and ReadOptions::read_tier = kPersistedTier will now read a consistent view across CFs (instead of potentially reading some CF before and some CF after a flush).
-* CreateColumnFamily() is no longer allowed on a read-only DB (OpenForReadOnly())
-
-### Bug Fixes
-* Fixed stats for Tiered Storage with preclude_last_level feature
-
-## 10.0.0 (02/21/2025)
-### New Features
-* Introduced new `auto_refresh_iterator_with_snapshot` opt-in knob that (when enabled) will periodically release obsolete memory and storage resources for as long as the iterator is making progress and its supplied `read_options.snapshot` was initialized with non-nullptr value.
-* Added the ability to plug-in a custom table reader implementation. See include/rocksdb/external_table_reader.h for more details.
-* Experimental feature: RocksDB now supports FAISS inverted file based indices via the secondary indexing framework. Applications can use FAISS secondary indices to automatically quantize embeddings and perform K-nearest-neighbors similarity searches. See `FaissIVFIndex` and `SecondaryIndex` for more details. Note: the FAISS integration currently requires using the BUCK build.
-* Add new DB property `num_running_compaction_sorted_runs` that tracks the number of sorted runs being processed by currently running compactions
-* Experimental feature: added support for simple secondary indices that index the specified column as-is. See `SimpleSecondaryIndex` and `SecondaryIndex` for more details.
-* Added new `TransactionDBOptions::txn_commit_bypass_memtable_threshold`, which enables optimized transaction commit (see `TransactionOptions::commit_bypass_memtable`) when the transaction size exceeds a configured threshold.
-
-### Public API Changes
-* Updated the query API of the experimental secondary indexing feature by removing the earlier `SecondaryIndex::NewIterator` virtual and adding a `SecondaryIndexIterator` class that can be utilized by applications to find the primary keys for a given search target.
-* Added back the ability to leverage the primary key when building secondary index entries. This involved changes to the signatures of `SecondaryIndex::GetSecondary{KeyPrefix,Value}` as well as the addition of a new method `SecondaryIndex::FinalizeSecondaryKeyPrefix`. See the API comments for more details.
-* Minimum supported version of ZSTD is now 1.4.0, for code simplification. Obsolete `CompressionType` `kZSTDNotFinalCompression` is also removed.
-
-### Behavior Changes
-* `VerifyBackup` in `verify_with_checksum`=`true` mode will now evaluate checksums in parallel. As a result, unlike in case of original implementation, the API won't bail out on a very first corruption / mismatch and instead will iterate over all the backup files logging success / _degree_of_failure_ for each.
-* Reversed the order of updates to the same key in WriteBatchWithIndex. This means if there are multiple updates to the same key, the most recent update is ordered first. This affects the output of WBWIIterator. When WriteBatchWithIndex is created with `overwrite_key=true`, this affects the output only if Merge is used (#13387).
-* Added support for Merge operations in transactions using option `TransactionOptions::commit_bypass_memtable`.
-
-### Bug Fixes
-* Fixed GetMergeOperands() API in ReadOnlyDB and SecondaryDB
-* Fix a bug in `GetMergeOperands()` that can return incorrect status (MergeInProgress) and incorrect number of merge operands. This can happen when `GetMergeOperandsOptions::continue_cb` is set, both active and immutable memtables have merge operands and the callback stops the look up at the immutable memtable.
-
-## 9.11.0 (01/17/2025)
-### New Features
-* Introduce CancelAwaitingJobs() in CompactionService interface which will allow users to implement cancellation of running remote compactions from the primary instance
-* Experimental feature: RocksDB now supports defining secondary indices, which are automatically maintained by the storage engine. Secondary indices provide a new customization point: applications can provide their own by implementing the new `SecondaryIndex` interface. See the `SecondaryIndex` API comments for more details. Note: this feature is currently only available in conjunction with write-committed pessimistic transactions, and `Merge` is not yet supported.
-* Provide a new option `track_and_verify_wals` to track and verify various information about WAL during WAL recovery. This is intended to be a better replacement to `track_and_verify_wals_in_manifest`.
-
-### Public API Changes
-* Add `io_buffer_size` to BackupEngineOptions to enable optimal configuration of IO size
-* Clean up all the references to `random_access_max_buffer_size`, related rules and all the clients wrappers. This option has been officially deprecated in 5.4.0.
-* Add `file_ingestion_nanos` and `file_ingestion_blocking_live_writes_nanos` in PerfContext to observe file ingestions
-* Offer new DB::Open and variants that use `std::unique_ptr<DB>*` output parameters and deprecate the old versions that use `DB**` output parameters.
-* The DB::DeleteFile API is officially deprecated.
-
-### Behavior Changes
-* For leveled compaction, manual compaction (CompactRange()) will be more strict about keeping compaction size under `max_compaction_bytes`. This prevents overly large compactions in some cases (#13306).
-* Experimental tiering options `preclude_last_level_data_seconds` and `preserve_internal_time_seconds` are now mutable with `SetOptions()`. Some changes to handling of these features along with long-lived snapshots and range deletes made this possible.
-
-### Bug Fixes
-* Fix a longstanding major bug with SetOptions() in which setting changes can be quietly reverted.
-
-## 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.
-
-### 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
-* Provide support for async_io to trim readahead_size by doing block cache lookup
-* Added initial wide-column support in `WriteBatchWithIndex`. This includes the `PutEntity` API and support for wide columns in the existing read APIs (`GetFromBatch`, `GetFromBatchAndDB`, `MultiGetFromBatchAndDB`, and `BaseDeltaIterator`).
-
-### Public API Changes
-* Custom implementations of `TablePropertiesCollectorFactory` may now return a `nullptr` collector to decline processing a file, reducing callback overheads in such cases.
-
-### Behavior Changes
-* Make ReadOptions.auto_readahead_size default true which does prefetching optimizations for forward scans if iterate_upper_bound and block_cache is also specified.
-* Compactions can be scheduled in parallel in an additional scenario: high compaction debt relative to the data size
-* HyperClockCache now has built-in protection against excessive CPU consumption under the extreme stress condition of no (or very few) evictable cache entries, which can slightly increase memory usage such conditions. New option `HyperClockCacheOptions::eviction_effort_cap` controls the space-time trade-off of the response. The default should be generally well-balanced, with no measurable affect on normal operation.
-
-### Bug Fixes
-* Fix a corner case with auto_readahead_size where Prev Operation returns NOT SUPPORTED error when scans direction is changed from forward to backward.
-* Avoid destroying the periodic task scheduler's default timer in order to prevent static destruction order issues.
-* Fix double counting of BYTES_WRITTEN ticker when doing writes with transactions.
-* Fix a WRITE_STALL counter that was reporting wrong value in few cases.
-* A lookup by MultiGet in a TieredCache that goes to the local flash cache and finishes with very low latency, i.e before the subsequent call to WaitAll, is ignored, resulting in a false negative and a memory leak.
-
-### Performance Improvements
-* Java API extensions to improve consistency and completeness of APIs
-1 Extended `RocksDB.get([ColumnFamilyHandle columnFamilyHandle,] ReadOptions opt, ByteBuffer key, ByteBuffer value)` which now accepts indirect buffer parameters as well as direct buffer parameters
-2 Extended `RocksDB.put( [ColumnFamilyHandle columnFamilyHandle,] WriteOptions writeOpts, final ByteBuffer key, final ByteBuffer value)` which now accepts indirect buffer parameters as well as direct buffer parameters
-3 Added `RocksDB.merge([ColumnFamilyHandle columnFamilyHandle,] WriteOptions writeOptions, ByteBuffer key, ByteBuffer value)` methods with the same parameter options as `put(...)` - direct and indirect buffers are supported
-4 Added `RocksIterator.key( byte[] key [, int offset, int len])` methods which retrieve the iterator key into the supplied buffer
-5 Added `RocksIterator.value( byte[] value [, int offset, int len])` methods which retrieve the iterator value into the supplied buffer
-6 Deprecated `get(final ColumnFamilyHandle columnFamilyHandle, final ReadOptions readOptions, byte[])` in favour of `get(final ReadOptions readOptions, final ColumnFamilyHandle columnFamilyHandle, byte[])` which has consistent parameter ordering with other methods in the same class
-7 Added `Transaction.get( ReadOptions opt, [ColumnFamilyHandle columnFamilyHandle, ] byte[] key, byte[] value)` methods which retrieve the requested value into the supplied buffer
-8 Added `Transaction.get( ReadOptions opt, [ColumnFamilyHandle columnFamilyHandle, ] ByteBuffer key, ByteBuffer value)` methods which retrieve the requested value into the supplied buffer
-9 Added `Transaction.getForUpdate( ReadOptions readOptions, [ColumnFamilyHandle columnFamilyHandle, ] byte[] key, byte[] value, boolean exclusive [, boolean doValidate])` methods which retrieve the requested value into the supplied buffer
-10 Added `Transaction.getForUpdate( ReadOptions readOptions, [ColumnFamilyHandle columnFamilyHandle, ] ByteBuffer key, ByteBuffer value, boolean exclusive [, boolean doValidate])` methods which retrieve the requested value into the supplied buffer
-11 Added `Transaction.getIterator()` method as a convenience which defaults the `ReadOptions` value supplied to existing `Transaction.iterator()` methods. This mirrors the existing `RocksDB.iterator()` method.
-12 Added `Transaction.put([ColumnFamilyHandle columnFamilyHandle, ]  ByteBuffer key, ByteBuffer value [, boolean assumeTracked])` methods which supply the key, and the value to be written in a `ByteBuffer` parameter
-13 Added `Transaction.merge([ColumnFamilyHandle columnFamilyHandle, ] ByteBuffer key, ByteBuffer value [,  boolean assumeTracked])` methods which supply the key, and the value to be written/merged in a `ByteBuffer` parameter
-14 Added `Transaction.mergeUntracked([ColumnFamilyHandle columnFamilyHandle, ] ByteBuffer key, ByteBuffer value)` methods which supply the key, and the value to be written/merged in a `ByteBuffer` parameter
-
-
-## 8.9.0 (11/17/2023)
-### New Features
-* Add GetEntity() and PutEntity() API implementation for Attribute Group support. Through the use of Column Families, AttributeGroup enables users to logically group wide-column entities.
-
-### Public API Changes
-* Added rocksdb_ratelimiter_create_auto_tuned API to create an auto-tuned GenericRateLimiter.
-* Added clipColumnFamily() to the Java API to clip the entries in the CF according to the range [begin_key, end_key).
-* Make the `EnableFileDeletion` API not default to force enabling. For users that rely on this default behavior and still
-want to continue to use force enabling, they need to explicitly pass a `true` to `EnableFileDeletion`.
 * Add new Cache APIs GetSecondaryCacheCapacity() and GetSecondaryCachePinnedUsage() to return the configured capacity, and cache reservation charged to the secondary cache.
 
-### Behavior Changes
-* During off-peak hours defined by `daily_offpeak_time_utc`, the compaction picker will select a larger number of files for periodic compaction. This selection will include files that are projected to expire by the next off-peak start time, ensuring that these files are not chosen for periodic compaction outside of off-peak hours.
-* If an error occurs when writing to a trace file after `DB::StartTrace()`, the subsequent trace writes are skipped to avoid writing to a file that has previously seen error. In this case, `DB::EndTrace()` will also return a non-ok status with info about the error occured previously in its status message.
-* Deleting stale files upon recovery are delegated to SstFileManger if available so they can be rate limited.
-* Make RocksDB only call `TablePropertiesCollector::Finish()` once.
-* When `WAL_ttl_seconds > 0`, we now process archived WALs for deletion at least every `WAL_ttl_seconds / 2` seconds. Previously it could be less frequent in case of small `WAL_ttl_seconds` values when size-based expiration (`WAL_size_limit_MB > 0 `) was simultaneously enabled.
-
 ### Bug Fixes
-* Fixed a crash or assertion failure bug in experimental new HyperClockCache variant, especially when running with a SecondaryCache.
-* Fix a race between flush error recovery and db destruction that can lead to db crashing.
-* Fixed some bugs in the index builder/reader path for user-defined timestamps in Memtable only feature.
-
-## 8.8.0 (10/23/2023)
-### New Features
-* Introduce AttributeGroup by adding the first AttributeGroup support API, MultiGetEntity(). Through the use of Column Families, AttributeGroup enables users to logically group wide-column entities. More APIs to support AttributeGroup will come soon, including GetEntity, PutEntity, and others.
-* Added new tickers `rocksdb.fifo.{max.size|ttl}.compactions` to count FIFO compactions that drop files for different reasons
-* Add an experimental offpeak duration awareness by setting `DBOptions::daily_offpeak_time_utc` in "HH:mm-HH:mm" format. This information will be used for resource optimization in the future
-* Users can now change the max bytes granted in a single refill period (i.e, burst) during runtime by `SetSingleBurstBytes()` for RocksDB rate limiter
-
-### Public API Changes
-* The default value of `DBOptions::fail_if_options_file_error` changed from `false` to `true`. Operations that set in-memory options (e.g., `DB::Open*()`, `DB::SetOptions()`, `DB::CreateColumnFamily*()`, and `DB::DropColumnFamily()`) but fail to persist the change will now return a non-OK `Status` by default.
-
-### Behavior Changes
-* For non direct IO, eliminate the file system prefetching attempt for compaction read when `Options::compaction_readahead_size` is 0
-* During a write stop, writes now block on in-progress recovery attempts
+* Fixed a possible underflow when computing the compressed secondary cache share of memory reservations while updating the compressed secondary to total block cache ratio.
+* Fix an assertion failure when UpdeteTieredCache() is called in an idempotent manner.
 
+## 8.7.1 (10/20/2023)
 ### Bug Fixes
 * Fix a bug in auto_readahead_size where first_internal_key of index blocks wasn't copied properly resulting in corruption error when first_internal_key was used for comparison.
-* Fixed a bug where compaction read under non direct IO still falls back to RocksDB internal prefetching after file system's prefetching returns non-OK status other than `Status::NotSupported()`
 * Add bounds check in WBWIIteratorImpl and make BaseDeltaIterator, WriteUnpreparedTxn and WritePreparedTxn respect the upper bound and lower bound in ReadOption. See 11680.
-* Fixed the handling of wide-column base values in the `max_successive_merges` logic.
-* Fixed a rare race bug involving a concurrent combination of Create/DropColumnFamily and/or Set(DB)Options that could lead to inconsistency between (a) the DB's reported options state, (b) the DB options in effect, and (c) the latest persisted OPTIONS file.
-* Fixed a possible underflow when computing the compressed secondary cache share of memory reservations while updating the compressed secondary to total block cache ratio.
-
-### Performance Improvements
-* Improved the I/O efficiency of DB::Open a new DB with `create_missing_column_families=true` and many column families.
 
 ## 8.7.0 (09/22/2023)
 ### New Features
@@ -487,6 +41,7 @@ want to continue to use force enabling, they need to explicitly pass a `true` to
 * Compaction read performance will regress when `Options::compaction_readahead_size` is explicitly set to 0
 * Universal size amp compaction will conditionally exclude some of the newest L0 files when selecting input with a small negative impact to size amp. This is to prevent a large number of L0 files from being locked by a size amp compaction, potentially leading to write stop with a few more flushes.
 * Change ldb scan command delimiter from ':' to '==>'.
+* For non direct IO, eliminate the file system prefetching attempt for compaction read when `Options::compaction_readahead_size` is 0
 
 ### Bug Fixes
 * Fix a bug where if there is an error reading from offset 0 of a file from L1+ and that the file is not the first file in the sorted run, data can be lost in compaction and read/scan can return incorrect results.
@@ -504,9 +59,10 @@ want to continue to use force enabling, they need to explicitly pass a `true` to
 * Fix an issue in sst dump tool to handle bounds specified for data with user-defined timestamps.
 * When auto_readahead_size is enabled, update readahead upper bound during readahead trimming when reseek changes iterate_upper_bound dynamically.
 * Fixed a bug where `rocksdb.file.read.verify.file.checksums.micros` is not populated
+* Fixed a bug where compaction read under non direct IO still falls back to RocksDB internal prefetching after file system's prefetching returns non-OK status other than `Status::NotSupported()`
 
 ### Performance Improvements
-* Added additional improvements in tuning readahead_size during Scans when auto_readahead_size is enabled. However it's not supported with Iterator::Prev operation and will return NotSupported error.
+* Added additional improvements in tuning readahead_size during Scans when auto_readahead_size is enabled. However it's not recommended for backward scans and might impact the performance. More details in options.h.
 * During async_io, the Seek happens in 2 phases. Phase 1 starts an asynchronous read on a block cache miss, and phase 2 waits for it to complete and finishes the seek. In both phases, it tries to lookup the block cache for the data block first before looking in the prefetch buffer. It's optimized by doing the block cache lookup only in the first phase that would save some CPU.
 
 ## 8.6.0 (08/18/2023)

INSTALL.md

@@ -17,7 +17,7 @@ There are few options when compiling RocksDB:
 * `make check` will compile and run all the unit tests. `make check` will compile RocksDB in debug mode.
 
 * `make all` will compile our static library, and all our tools and unit tests. Our tools
-depend on gflags 2.2.0 or newer. You will need to have gflags installed to run `make all`. This will compile RocksDB in debug mode. Don't
+depend on gflags. You will need to have gflags installed to run `make all`. This will compile RocksDB in debug mode. Don't
 use binaries compiled by `make all` in production.
 
 * By default the binary we produce is optimized for the CPU you're compiling on
@@ -77,7 +77,7 @@ most processors made since roughly 2013.
 
               git clone https://github.com/gflags/gflags.git
               cd gflags
-              git checkout v2.2.0
+              git checkout v2.0
               ./configure && make && sudo make install
 
       **Notice**: Once installed, please add the include path for gflags to your `CPATH` environment variable and the
@@ -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`.

LANGUAGE-BINDINGS.md

@@ -2,8 +2,7 @@ This is the list of all known third-party language bindings for RocksDB. If some
 
 * Java - https://github.com/facebook/rocksdb/tree/main/java
 * Python
-    * https://github.com/rocksdict/RocksDict
-    * http://python-rocksdb.readthedocs.io/en/latest/ (unmaintained) 
+    * http://python-rocksdb.readthedocs.io/en/latest/
     * http://pyrocksdb.readthedocs.org/en/latest/ (unmaintained)
 * Perl - https://metacpan.org/pod/RocksDB
 * Node.js - https://npmjs.org/package/rocksdb

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
 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)
 
@@ -1023,7 +994,7 @@ endif
 
 .PHONY: check_0
 check_0:
-	@printf '%s\n' ''						\
+	printf '%s\n' ''						\
 	  'To monitor subtest <duration,pass/fail,name>,'		\
 	  '  run "make watch-log" in a separate window' '';		\
 	{ \
@@ -1045,7 +1016,7 @@ valgrind-exclude-regexp = InlineSkipTest.ConcurrentInsert|TransactionStressTest.
 .PHONY: valgrind_check_0
 valgrind_check_0: test_log_prefix := valgrind_
 valgrind_check_0:
-	@printf '%s\n' ''						\
+	printf '%s\n' ''						\
 	  'To monitor subtest <duration,pass/fail,name>,'		\
 	  '  run "make watch-log" in a separate window' '';		\
 	{								\
@@ -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)
 
@@ -2104,7 +2060,7 @@ JAVA_INCLUDE = -I$(JAVA_HOME)/include/ -I$(JAVA_HOME)/include/linux
 ifeq ($(PLATFORM), OS_SOLARIS)
 	ARCH := $(shell isainfo -b)
 else ifeq ($(PLATFORM), OS_OPENBSD)
-	ifneq (,$(filter amd64 ppc64 ppc64le s390x arm64 aarch64 riscv64 sparc64 loongarch64, $(MACHINE)))
+	ifneq (,$(filter amd64 ppc64 ppc64le s390x arm64 aarch64 sparc64 loongarch64, $(MACHINE)))
 		ARCH := 64
 	else
 		ARCH := 32
@@ -2125,7 +2081,7 @@ ifneq ($(origin JNI_LIBC), undefined)
 endif
 
 ifeq (,$(ROCKSDBJNILIB))
-ifneq (,$(filter ppc% s390x arm64 aarch64 riscv64 sparc64 loongarch64, $(MACHINE)))
+ifneq (,$(filter ppc% s390x arm64 aarch64 sparc64 loongarch64, $(MACHINE)))
 	ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE)$(JNI_LIBC_POSTFIX).so
 else
 	ROCKSDBJNILIB = librocksdbjni-linux$(ARCH)$(JNI_LIBC_POSTFIX).so
@@ -2138,14 +2094,14 @@ ROCKSDB_JAVADOCS_JAR = rocksdbjni-$(ROCKSDB_JAVA_VERSION)-javadoc.jar
 ROCKSDB_SOURCES_JAR = rocksdbjni-$(ROCKSDB_JAVA_VERSION)-sources.jar
 SHA256_CMD = sha256sum
 
-ZLIB_VER ?= 1.3.1
-ZLIB_SHA256 ?= 9a93b2b7dfdac77ceba5a558a580e74667dd6fede4585b91eefb60f03b72df23
+ZLIB_VER ?= 1.3
+ZLIB_SHA256 ?= ff0ba4c292013dbc27530b3a81e1f9a813cd39de01ca5e0f8bf355702efa593e
 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 +2328,43 @@ 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
-
-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_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
 
 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
 
@@ -2467,9 +2419,6 @@ jtest_run:
 jtest: rocksdbjava
 	cd java;$(MAKE) sample test
 
-jpmd: rocksdbjava rocksdbjavageneratepom
-	cd java;$(MAKE) pmd
-
 jdb_bench:
 	cd java;$(MAKE) db_bench;
 
@@ -2489,13 +2438,14 @@ 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 78286282478e1ae05b2e8cbcf0e2139eab283bea
+	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 +2457,8 @@ 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
 

PLUGINS.md

@@ -5,5 +5,4 @@ This is the list of all known third-party plugins for RocksDB. If something is m
 * [ZenFS](https://github.com/westerndigitalcorporation/zenfs): a file system for zoned block devices
 * [RADOS](https://github.com/riversand963/rocksdb-rados-env): an Env used for interacting with RADOS. Migrated from RocksDB main repo.
 * [PMEM](https://github.com/pmem/pmem-rocksdb-plugin): a collection of plugins to enable Persistent Memory on RocksDB.
-* [IPPCP](https://github.com/intel/ippcp-plugin-rocksdb): a plugin to enable encryption on RocksDB based on Intel optimized open source IPP-Crypto library.
-* [encfs](https://github.com/pegasus-kv/encfs): a plugin to enable encryption on RocksDB based on OpenSSL library.
+* [IPPCP](https://github.com/intel/ippcp-plugin-rocksdb): a plugin to enable encryption on RocksDB based on Intel optimized open source IPP-Crypto library.

TARGETS

@@ -3,8 +3,9 @@
 # --> DO NOT EDIT MANUALLY <--
 # This file is a Facebook-specific integration for buck builds, so can
 # only be validated by Facebook employees.
+#
+# @noautodeps @nocodemods
 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 +23,6 @@ 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 +39,6 @@ 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 +60,6 @@ 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 +81,6 @@ 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 +117,6 @@ 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 +146,6 @@ 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",
@@ -170,7 +165,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "options/configurable.cc",
         "options/customizable.cc",
         "options/db_options.cc",
-        "options/offpeak_time_info.cc",
         "options/options.cc",
         "options/options_helper.cc",
         "options/options_parser.cc",
@@ -214,7 +208,6 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "table/cuckoo/cuckoo_table_builder.cc",
         "table/cuckoo/cuckoo_table_factory.cc",
         "table/cuckoo/cuckoo_table_reader.cc",
-        "table/external_table.cc",
         "table/format.cc",
         "table/get_context.cc",
         "table/iterator.cc",
@@ -318,11 +311,8 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "utilities/persistent_cache/block_cache_tier_metadata.cc",
         "utilities/persistent_cache/persistent_cache_tier.cc",
         "utilities/persistent_cache/volatile_tier_impl.cc",
-        "utilities/secondary_index/secondary_index_iterator.cc",
-        "utilities/secondary_index/simple_secondary_index.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",
@@ -356,7 +346,6 @@ 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",
@@ -367,14 +356,9 @@ 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",
@@ -388,46 +372,29 @@ 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",
         "tools/block_cache_analyzer/block_cache_trace_analyzer.cc",
         "tools/db_bench_tool.cc",
         "tools/simulated_hybrid_file_system.cc",
-        "tools/tool_hooks.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",
         "db_stress_tool/db_stress_stat.cc",
         "db_stress_tool/db_stress_test_base.cc",
         "db_stress_tool/db_stress_tool.cc",
-        "db_stress_tool/db_stress_wide_merge_operator.cc",
         "db_stress_tool/expected_state.cc",
         "db_stress_tool/expected_value.cc",
         "db_stress_tool/multi_ops_txns_stress.cc",
@@ -435,17 +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)
 
 cpp_binary_wrapper(name="db_basic_bench", srcs=["microbench/db_basic_bench.cc"], deps=[], extra_preprocessor_flags=[], extra_bench_libs=True)
@@ -4655,12 +4616,6 @@ 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"],
@@ -4835,12 +4790,6 @@ 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"],
@@ -5051,7 +5000,7 @@ 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"],
@@ -5101,12 +5050,6 @@ 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"],
@@ -5281,12 +5224,6 @@ 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"],
@@ -5581,12 +5518,6 @@ 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"],
@@ -5688,5 +5619,3 @@ cpp_unittest_wrapper(name="write_unprepared_transaction_test",
             deps=[":rocksdb_test_lib"],
             extra_compiler_flags=[])
 
-
-export_file(name = "tools/db_crashtest.py")

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
@@ -151,9 +152,6 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 ## ArangoDB
 [ArangoDB](https://www.arangodb.com/) is a native multi-model database with flexible data models for documents, graphs, and key-values, for building high performance applications using a convenient SQL-like query language or JavaScript extensions. It uses RocksDB as its storage engine.
 
-## Qdrant
-[Qdrant](https://qdrant.tech/) is an open source vector database, it [uses](https://qdrant.tech/documentation/concepts/storage/) RocksDB as its persistent storage.
-
 ## Milvus
 [Milvus](https://milvus.io/) is an open source vector database for unstructured data. It uses RocksDB not only as one of the supported kv storage engines, but also as a message queue.
 

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 +181,39 @@ 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(
-        "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 +228,7 @@ 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 +250,7 @@ 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 +263,15 @@ 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 +280,30 @@ 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"]),
+                )
 
-    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 +323,10 @@ 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(
@@ -162,9 +148,3 @@ add_c_test_wrapper()
                 ).encode("utf-8")
             )
         self.total_test = self.total_test + 1
-
-    def export_file(self, name):
-        with open(self.path, "a") as targets_file:
-            targets_file.write(
-                targets_cfg.export_file_template.format(name=name)
-            )

buckifier/targets_cfg.py

@@ -1,12 +1,14 @@
 # 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}
 # --> DO NOT EDIT MANUALLY <--
 # This file is a Facebook-specific integration for buck builds, so can
 # only be validated by Facebook employees.
+#
+# @noautodeps @nocodemods
 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")
 
 """
 
@@ -37,7 +39,3 @@ fancy_bench_template = """
 fancy_bench_wrapper(suite_name="{name}", binary_to_bench_to_metric_list_map={bench_config}, slow={slow}, expected_runtime={expected_runtime}, sl_iterations={sl_iterations}, regression_threshold={regression_threshold})
 
 """
-
-export_file_template = """
-export_file(name = "{name}")
-"""

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)
@@ -360,13 +378,9 @@ EOF
     fi
 
     if ! test $ROCKSDB_DISABLE_ZSTD; then
-        # Test whether zstd library is installed with minimum version
-        # (Keep in sync with compression.h)
+        # Test whether zstd library is installed
         $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
           #include <zstd.h>
-          #if ZSTD_VERSION_NUMBER < 10400
-          #error "ZSTD support requires version >= 1.4.0 (libzstd-devel)"
-          #endif  // ZSTD_VERSION_NUMBER
           int main() {}
 EOF
         if [ "$?" = 0 ]; then
@@ -589,7 +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>
@@ -600,29 +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 $PLATFORM_CXXFLAGS -x c++ - -o test.o -Wshorten-64-to-32 2>/dev/null  <<EOF
     int main() {}
@@ -651,10 +647,8 @@ if [ "$PORTABLE" == "" ] || [ "$PORTABLE" == 0 ]; then
     fi
     COMMON_FLAGS="$COMMON_FLAGS"
   elif test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
-    RISC_ISA=$(cat /proc/cpuinfo | grep -E '^isa\s*:' | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
-    if [ -n "${RISCV_ISA}" ]; then
-      COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
-    fi
+    RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
+    COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
   elif [ "$TARGET_OS" == "IOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS"
   else
@@ -666,7 +660,8 @@ else
     if test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
       COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
     elif test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
-      COMMON_FLAGS="$COMMON_FLAGS -march=rv64gc"
+      RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
+      COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
     elif test "$USE_SSE"; then
       # USE_SSE is DEPRECATED
       # This is a rough approximation of the old USE_SSE behavior
@@ -755,11 +750,6 @@ 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 $COMMON_FLAGS"
@@ -801,7 +791,6 @@ echo "PROFILING_FLAGS=$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

@@ -59,7 +59,7 @@ fi
 if ! test $ROCKSDB_DISABLE_ZSTD; then
   ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
   ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd${MAYBE_PIC}.a"
-  CFLAGS+=" -DZSTD -DZSTD_STATIC_LINKING_ONLY"
+  CFLAGS+=" -DZSTD"
 fi
 
 # location of gflags headers and libraries
@@ -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

@@ -118,6 +118,7 @@ Status SecondaryCache::CreateFromString(
       sec_cache = NewCompressedSecondaryCache(sec_cache_opts);
     }
 
+
     if (status.ok()) {
       result->swap(sec_cache);
     }
@@ -132,25 +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

@@ -48,10 +48,6 @@ DEFINE_uint64(cache_size, 1 * GiB,
               "Number of bytes to use as a cache of uncompressed data.");
 DEFINE_int32(num_shard_bits, -1,
              "ShardedCacheOptions::shard_bits. Default = auto");
-DEFINE_int32(
-    eviction_effort_cap,
-    ROCKSDB_NAMESPACE::HyperClockCacheOptions(1, 1).eviction_effort_cap,
-    "HyperClockCacheOptions::eviction_effort_cap");
 
 DEFINE_double(resident_ratio, 0.25,
               "Ratio of keys fitting in cache to keyspace.");
@@ -67,22 +63,11 @@ DEFINE_int32(
 DEFINE_uint32(skew, 5, "Degree of skew in key selection. 0 = no skew");
 DEFINE_bool(populate_cache, true, "Populate cache before operations");
 
-DEFINE_double(pinned_ratio, 0.25,
-              "Keep roughly this portion of entries pinned in cache.");
-DEFINE_double(
-    vary_capacity_ratio, 0.0,
-    "If greater than 0.0, will periodically vary the capacity between this "
-    "ratio less than full size and full size. If vary_capacity_ratio + "
-    "pinned_ratio is close to or exceeds 1.0, the cache might thrash.");
-
-DEFINE_uint32(lookup_insert_percent, 82,
+DEFINE_uint32(lookup_insert_percent, 87,
               "Ratio of lookup (+ insert on not found) to total workload "
               "(expressed as a percentage)");
 DEFINE_uint32(insert_percent, 2,
               "Ratio of insert to total workload (expressed as a percentage)");
-DEFINE_uint32(blind_insert_percent, 5,
-              "Ratio of insert without keeping handle to total workload "
-              "(expressed as a percentage)");
 DEFINE_uint32(lookup_percent, 10,
               "Ratio of lookup to total workload (expressed as a percentage)");
 DEFINE_uint32(erase_percent, 1,
@@ -116,6 +101,7 @@ DEFINE_uint32(seed, 0, "Hashing/random seed to use. 0 = choose at random");
 
 DEFINE_string(secondary_cache_uri, "",
               "Full URI for creating a custom secondary cache object");
+static class std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache> secondary_cache;
 
 DEFINE_string(cache_type, "lru_cache", "Type of block cache.");
 
@@ -191,9 +177,10 @@ namespace {
 class SharedState {
  public:
   explicit SharedState(CacheBench* cache_bench)
-      : cv_(&mu_), cache_bench_(cache_bench) {}
+      : cv_(&mu_),
+        cache_bench_(cache_bench) {}
 
-  ~SharedState() = default;
+  ~SharedState() {}
 
   port::Mutex* GetMutex() { return &mu_; }
 
@@ -213,19 +200,16 @@ class SharedState {
 
   bool Started() const { return start_; }
 
-  void AddLookupStats(uint64_t hits, uint64_t misses, size_t pinned_count) {
+  void AddLookupStats(uint64_t hits, uint64_t misses) {
     MutexLock l(&mu_);
     lookup_count_ += hits + misses;
     lookup_hits_ += hits;
-    pinned_count_ += pinned_count;
   }
 
   double GetLookupHitRatio() const {
     return 1.0 * lookup_hits_ / lookup_count_;
   }
 
-  size_t GetPinnedCount() const { return pinned_count_; }
-
  private:
   port::Mutex mu_;
   port::CondVar cv_;
@@ -237,7 +221,6 @@ class SharedState {
   uint64_t num_done_ = 0;
   uint64_t lookup_count_ = 0;
   uint64_t lookup_hits_ = 0;
-  size_t pinned_count_ = 0;
 };
 
 // Per-thread state for concurrent executions of the same benchmark.
@@ -330,28 +313,6 @@ Cache::CacheItemHelper helper2(CacheEntryRole::kIndexBlock, DeleteFn, SizeFn,
 Cache::CacheItemHelper helper3_wos(CacheEntryRole::kFilterBlock, DeleteFn);
 Cache::CacheItemHelper helper3(CacheEntryRole::kFilterBlock, DeleteFn, SizeFn,
                                SaveToFn, CreateFn, &helper3_wos);
-
-void ConfigureSecondaryCache(ShardedCacheOptions& opts) {
-  if (!FLAGS_secondary_cache_uri.empty()) {
-    std::shared_ptr<SecondaryCache> secondary_cache;
-    Status s = SecondaryCache::CreateFromString(
-        ConfigOptions(), FLAGS_secondary_cache_uri, &secondary_cache);
-    if (secondary_cache == nullptr) {
-      fprintf(stderr,
-              "No secondary cache registered matching string: %s status=%s\n",
-              FLAGS_secondary_cache_uri.c_str(), s.ToString().c_str());
-      exit(1);
-    }
-    opts.secondary_cache = secondary_cache;
-  }
-}
-
-ShardedCacheBase* AsShardedCache(Cache* c) {
-  if (!FLAGS_secondary_cache_uri.empty()) {
-    c = static_cast_with_check<CacheWrapper>(c)->GetTarget().get();
-  }
-  return static_cast_with_check<ShardedCacheBase>(c);
-}
 }  // namespace
 
 class CacheBench {
@@ -366,9 +327,7 @@ class CacheBench {
                                  FLAGS_lookup_insert_percent),
         insert_threshold_(lookup_insert_threshold_ +
                           kHundredthUint64 * FLAGS_insert_percent),
-        blind_insert_threshold_(insert_threshold_ +
-                                kHundredthUint64 * FLAGS_blind_insert_percent),
-        lookup_threshold_(blind_insert_threshold_ +
+        lookup_threshold_(insert_threshold_ +
                           kHundredthUint64 * FLAGS_lookup_percent),
         erase_threshold_(lookup_threshold_ +
                          kHundredthUint64 * FLAGS_erase_percent) {
@@ -394,7 +353,6 @@ class CacheBench {
           FLAGS_cache_size, /*estimated_entry_charge=*/0, FLAGS_num_shard_bits);
       opts.hash_seed = BitwiseAnd(FLAGS_seed, INT32_MAX);
       opts.memory_allocator = allocator;
-      opts.eviction_effort_cap = FLAGS_eviction_effort_cap;
       if (FLAGS_cache_type == "fixed_hyper_clock_cache" ||
           FLAGS_cache_type == "hyper_clock_cache") {
         opts.estimated_entry_charge = FLAGS_value_bytes_estimate > 0
@@ -408,7 +366,6 @@ class CacheBench {
         fprintf(stderr, "Cache type not supported.\n");
         exit(1);
       }
-      ConfigureSecondaryCache(opts);
       cache_ = opts.MakeSharedCache();
     } else if (FLAGS_cache_type == "lru_cache") {
       LRUCacheOptions opts(FLAGS_cache_size, FLAGS_num_shard_bits,
@@ -416,7 +373,19 @@ class CacheBench {
                            0.5 /* high_pri_pool_ratio */);
       opts.hash_seed = BitwiseAnd(FLAGS_seed, INT32_MAX);
       opts.memory_allocator = allocator;
-      ConfigureSecondaryCache(opts);
+      if (!FLAGS_secondary_cache_uri.empty()) {
+        Status s = SecondaryCache::CreateFromString(
+            ConfigOptions(), FLAGS_secondary_cache_uri, &secondary_cache);
+        if (secondary_cache == nullptr) {
+          fprintf(
+              stderr,
+              "No secondary cache registered matching string: %s status=%s\n",
+              FLAGS_secondary_cache_uri.c_str(), s.ToString().c_str());
+          exit(1);
+        }
+        opts.secondary_cache = secondary_cache;
+      }
+
       cache_ = NewLRUCache(opts);
     } else {
       fprintf(stderr, "Cache type not supported.\n");
@@ -424,7 +393,7 @@ class CacheBench {
     }
   }
 
-  ~CacheBench() = default;
+  ~CacheBench() {}
 
   void PopulateCache() {
     Random64 rnd(FLAGS_seed);
@@ -536,8 +505,6 @@ class CacheBench {
     size_t slot = cache_->GetTableAddressCount();
     printf("Final load factor: %g (%zu / %zu)\n", 1.0 * occ / slot, occ, slot);
 
-    printf("Final pinned count: %zu\n", shared.GetPinnedCount());
-
     if (FLAGS_histograms) {
       printf("\nOperation latency (ns):\n");
       HistogramImpl combined;
@@ -569,7 +536,6 @@ class CacheBench {
   // Cumulative thresholds in the space of a random uint64_t
   const uint64_t lookup_insert_threshold_;
   const uint64_t insert_threshold_;
-  const uint64_t blind_insert_threshold_;
   const uint64_t lookup_threshold_;
   const uint64_t erase_threshold_;
 
@@ -685,44 +651,29 @@ class CacheBench {
     uint64_t lookup_misses = 0;
     uint64_t lookup_hits = 0;
     // To hold handles for a non-trivial amount of time
-    std::deque<Cache::Handle*> pinned;
-    size_t total_pin_count = static_cast<size_t>(
-        (FLAGS_cache_size * FLAGS_pinned_ratio) / FLAGS_value_bytes + 0.999999);
-    // For this thread. Some round up, some round down, as appropriate
-    size_t pin_count = (total_pin_count + thread->tid) / FLAGS_threads;
-
+    Cache::Handle* handle = nullptr;
     KeyGen gen;
     const auto clock = SystemClock::Default().get();
     uint64_t start_time = clock->NowMicros();
     StopWatchNano timer(clock);
     auto system_clock = SystemClock::Default();
-    size_t steps_to_next_capacity_change = 0;
 
     for (uint64_t i = 0; i < FLAGS_ops_per_thread; i++) {
       Slice key = gen.GetRand(thread->rnd, max_key_, FLAGS_skew);
       uint64_t random_op = thread->rnd.Next();
 
-      if (FLAGS_vary_capacity_ratio > 0.0 && thread->tid == 0) {
-        if (steps_to_next_capacity_change == 0) {
-          double cut_ratio = static_cast<double>(thread->rnd.Next()) /
-                             static_cast<double>(UINT64_MAX) *
-                             FLAGS_vary_capacity_ratio;
-          cache_->SetCapacity(FLAGS_cache_size * (1.0 - cut_ratio));
-          steps_to_next_capacity_change =
-              static_cast<size_t>(FLAGS_ops_per_thread / 100);
-        } else {
-          --steps_to_next_capacity_change;
-        }
-      }
-
       if (FLAGS_histograms) {
         timer.Start();
       }
 
       if (random_op < lookup_insert_threshold_) {
+        if (handle) {
+          cache_->Release(handle);
+          handle = nullptr;
+        }
         // do lookup
-        auto handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
-                                     Cache::Priority::LOW);
+        handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
+                                Cache::Priority::LOW);
         if (handle) {
           ++lookup_hits;
           if (!FLAGS_lean) {
@@ -730,31 +681,32 @@ class CacheBench {
             result += NPHash64(static_cast<char*>(cache_->Value(handle)),
                                FLAGS_value_bytes);
           }
-          pinned.push_back(handle);
         } else {
           ++lookup_misses;
           // do insert
           Status s = cache_->Insert(
               key, createValue(thread->rnd, cache_->memory_allocator()),
-              &helper2, FLAGS_value_bytes, &pinned.emplace_back());
+              &helper2, FLAGS_value_bytes, &handle);
           assert(s.ok());
         }
       } else if (random_op < insert_threshold_) {
+        if (handle) {
+          cache_->Release(handle);
+          handle = nullptr;
+        }
         // do insert
         Status s = cache_->Insert(
             key, createValue(thread->rnd, cache_->memory_allocator()), &helper3,
-            FLAGS_value_bytes, &pinned.emplace_back());
-        assert(s.ok());
-      } else if (random_op < blind_insert_threshold_) {
-        // insert without keeping a handle
-        Status s = cache_->Insert(
-            key, createValue(thread->rnd, cache_->memory_allocator()), &helper3,
-            FLAGS_value_bytes);
+            FLAGS_value_bytes, &handle);
         assert(s.ok());
       } else if (random_op < lookup_threshold_) {
+        if (handle) {
+          cache_->Release(handle);
+          handle = nullptr;
+        }
         // do lookup
-        auto handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
-                                     Cache::Priority::LOW);
+        handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
+                                Cache::Priority::LOW);
         if (handle) {
           ++lookup_hits;
           if (!FLAGS_lean) {
@@ -762,7 +714,6 @@ class CacheBench {
             result += NPHash64(static_cast<char*>(cache_->Value(handle)),
                                FLAGS_value_bytes);
           }
-          pinned.push_back(handle);
         } else {
           ++lookup_misses;
         }
@@ -776,6 +727,7 @@ class CacheBench {
       if (FLAGS_histograms) {
         thread->latency_ns_hist.Add(timer.ElapsedNanos());
       }
+      thread->shared->AddLookupStats(lookup_hits, lookup_misses);
       if (FLAGS_usleep > 0) {
         unsigned us =
             static_cast<unsigned>(thread->rnd.Uniform(FLAGS_usleep + 1));
@@ -783,17 +735,12 @@ class CacheBench {
           system_clock->SleepForMicroseconds(us);
         }
       }
-      while (pinned.size() > pin_count) {
-        cache_->Release(pinned.front());
-        pinned.pop_front();
-      }
     }
     if (FLAGS_early_exit) {
       MutexLock l(thread->shared->GetMutex());
       exit(0);
     }
-    thread->shared->AddLookupStats(lookup_hits, lookup_misses, pinned.size());
-    for (auto handle : pinned) {
+    if (handle) {
       cache_->Release(handle);
       handle = nullptr;
     }
@@ -822,7 +769,8 @@ class CacheBench {
     printf("Cache size          : %s\n",
            BytesToHumanString(FLAGS_cache_size).c_str());
     printf("Num shard bits      : %d\n",
-           AsShardedCache(cache_.get())->GetNumShardBits());
+           static_cast_with_check<ShardedCacheBase>(cache_.get())
+               ->GetNumShardBits());
     printf("Max key             : %" PRIu64 "\n", max_key_);
     printf("Resident ratio      : %g\n", FLAGS_resident_ratio);
     printf("Skew degree         : %u\n", FLAGS_skew);

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.h

@@ -11,7 +11,6 @@
 
 #include <array>
 #include <atomic>
-#include <climits>
 #include <cstddef>
 #include <cstdint>
 #include <memory>
@@ -25,7 +24,6 @@
 #include "port/port.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/secondary_cache.h"
-#include "util/atomic.h"
 #include "util/autovector.h"
 #include "util/math.h"
 
@@ -298,7 +296,7 @@ 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
@@ -370,19 +368,11 @@ struct ClockHandle : public ClockHandleBasicData {
   // TODO: make these coundown values tuning parameters for eviction?
 
   // See above. Mutable for read reference counting.
-  mutable AcqRelAtomic<uint64_t> meta{};
+  mutable std::atomic<uint64_t> meta{};
 };  // struct ClockHandle
 
 class BaseClockTable {
  public:
-  struct BaseOpts {
-    explicit BaseOpts(int _eviction_effort_cap)
-        : eviction_effort_cap(_eviction_effort_cap) {}
-    explicit BaseOpts(const HyperClockCacheOptions& opts)
-        : BaseOpts(opts.eviction_effort_cap) {}
-    int eviction_effort_cap;
-  };
-
   BaseClockTable(CacheMetadataChargePolicy metadata_charge_policy,
                  MemoryAllocator* allocator,
                  const Cache::EvictionCallback* eviction_callback,
@@ -395,37 +385,36 @@ class BaseClockTable {
   template <class Table>
   typename Table::HandleImpl* CreateStandalone(ClockHandleBasicData& proto,
                                                size_t capacity,
-                                               uint32_t eec_and_scl,
+                                               bool strict_capacity_limit,
                                                bool allow_uncharged);
 
   template <class Table>
   Status Insert(const ClockHandleBasicData& proto,
                 typename Table::HandleImpl** handle, Cache::Priority priority,
-                size_t capacity, uint32_t eec_and_scl);
+                size_t capacity, bool strict_capacity_limit);
 
   void Ref(ClockHandle& handle);
 
-  size_t GetOccupancy() const { return occupancy_.LoadRelaxed(); }
+  size_t GetOccupancy() const {
+    return occupancy_.load(std::memory_order_relaxed);
+  }
 
-  size_t GetUsage() const { return usage_.LoadRelaxed(); }
+  size_t GetUsage() const { return usage_.load(std::memory_order_relaxed); }
 
-  size_t GetStandaloneUsage() const { return standalone_usage_.LoadRelaxed(); }
+  size_t GetStandaloneUsage() const {
+    return standalone_usage_.load(std::memory_order_relaxed);
+  }
 
   uint32_t GetHashSeed() const { return hash_seed_; }
 
-  uint64_t GetYieldCount() const { return yield_count_.LoadRelaxed(); }
-
-  uint64_t GetEvictionEffortExceededCount() const {
-    return eviction_effort_exceeded_count_.LoadRelaxed();
-  }
+  uint64_t GetYieldCount() const { return yield_count_.load(); }
 
   struct EvictionData {
     size_t freed_charge = 0;
     size_t freed_count = 0;
-    size_t seen_pinned_count = 0;
   };
 
-  void TrackAndReleaseEvictedEntry(ClockHandle* h);
+  void TrackAndReleaseEvictedEntry(ClockHandle* h, EvictionData* data);
 
 #ifndef NDEBUG
   // Acquire N references
@@ -450,7 +439,6 @@ class BaseClockTable {
   template <class Table>
   Status ChargeUsageMaybeEvictStrict(size_t total_charge, size_t capacity,
                                      bool need_evict_for_occupancy,
-                                     uint32_t eviction_effort_cap,
                                      typename Table::InsertState& state);
 
   // Helper for updating `usage_` for new entry with given `total_charge`
@@ -464,7 +452,6 @@ class BaseClockTable {
   template <class Table>
   bool ChargeUsageMaybeEvictNonStrict(size_t total_charge, size_t capacity,
                                       bool need_evict_for_occupancy,
-                                      uint32_t eviction_effort_cap,
                                       typename Table::InsertState& state);
 
  protected:  // data
@@ -473,29 +460,21 @@ class BaseClockTable {
   // operations in ClockCacheShard.
 
   // Clock algorithm sweep pointer.
-  // (Relaxed: only needs to be consistent with itself.)
-  RelaxedAtomic<uint64_t> clock_pointer_{};
+  std::atomic<uint64_t> clock_pointer_{};
 
   // Counter for number of times we yield to wait on another thread.
-  // It is normal for this to occur rarely in normal operation.
-  // (Relaxed: a simple stat counter.)
-  RelaxedAtomic<uint64_t> yield_count_{};
-
-  // Counter for number of times eviction effort cap is exceeded.
-  // It is normal for this to occur rarely in normal operation.
-  // (Relaxed: a simple stat counter.)
-  RelaxedAtomic<uint64_t> eviction_effort_exceeded_count_{};
+  std::atomic<uint64_t> yield_count_{};
 
   // TODO: is this separation needed if we don't do background evictions?
   ALIGN_AS(CACHE_LINE_SIZE)
   // Number of elements in the table.
-  AcqRelAtomic<size_t> occupancy_{};
+  std::atomic<size_t> occupancy_{};
 
   // Memory usage by entries tracked by the cache (including standalone)
-  AcqRelAtomic<size_t> usage_{};
+  std::atomic<size_t> usage_{};
 
   // Part of usage by standalone entries (not in table)
-  AcqRelAtomic<size_t> standalone_usage_{};
+  std::atomic<size_t> standalone_usage_{};
 
   ALIGN_AS(CACHE_LINE_SIZE)
   const CacheMetadataChargePolicy metadata_charge_policy_;
@@ -521,11 +500,7 @@ class FixedHyperClockTable : public BaseClockTable {
   struct ALIGN_AS(64U) HandleImpl : public ClockHandle {
     // The number of elements that hash to this slot or a lower one, but wind
     // up in this slot or a higher one.
-    // (Relaxed: within a Cache op, does not need consistency with entries
-    // inserted/removed during that op. For example, a Lookup() that
-    // happens-after an Insert() will see an appropriate displacements value
-    // for the entry to be in a published state.)
-    RelaxedAtomic<uint32_t> displacements{};
+    std::atomic<uint32_t> displacements{};
 
     // Whether this is a "deteched" handle that is independently allocated
     // with `new` (so must be deleted with `delete`).
@@ -539,19 +514,17 @@ class FixedHyperClockTable : public BaseClockTable {
     inline void SetStandalone() { standalone = true; }
   };  // struct HandleImpl
 
-  struct Opts : public BaseOpts {
-    explicit Opts(size_t _estimated_value_size, int _eviction_effort_cap)
-        : BaseOpts(_eviction_effort_cap),
-          estimated_value_size(_estimated_value_size) {}
-    explicit Opts(const HyperClockCacheOptions& opts)
-        : BaseOpts(opts.eviction_effort_cap) {
+  struct Opts {
+    explicit Opts(size_t _estimated_value_size)
+        : estimated_value_size(_estimated_value_size) {}
+    explicit Opts(const HyperClockCacheOptions& opts) {
       assert(opts.estimated_entry_charge > 0);
       estimated_value_size = opts.estimated_entry_charge;
     }
     size_t estimated_value_size;
   };
 
-  FixedHyperClockTable(size_t capacity,
+  FixedHyperClockTable(size_t capacity, bool strict_capacity_limit,
                        CacheMetadataChargePolicy metadata_charge_policy,
                        MemoryAllocator* allocator,
                        const Cache::EvictionCallback* eviction_callback,
@@ -573,8 +546,7 @@ class FixedHyperClockTable : public BaseClockTable {
   // Runs the clock eviction algorithm trying to reclaim at least
   // requested_charge. Returns how much is evicted, which could be less
   // if it appears impossible to evict the requested amount without blocking.
-  void Evict(size_t requested_charge, InsertState& state, EvictionData* data,
-             uint32_t eviction_effort_cap);
+  void Evict(size_t requested_charge, InsertState& state, EvictionData* data);
 
   HandleImpl* Lookup(const UniqueId64x2& hashed_key);
 
@@ -815,33 +787,32 @@ class AutoHyperClockTable : public BaseClockTable {
 
     // See above. The head pointer is logically independent of the rest of
     // the entry, including the chain next pointer.
-    AcqRelAtomic<uint64_t> head_next_with_shift{kUnusedMarker};
-    AcqRelAtomic<uint64_t> chain_next_with_shift{kUnusedMarker};
+    std::atomic<uint64_t> head_next_with_shift{kUnusedMarker};
+    std::atomic<uint64_t> chain_next_with_shift{kUnusedMarker};
 
     // For supporting CreateStandalone and some fallback cases.
     inline bool IsStandalone() const {
-      return head_next_with_shift.Load() == kStandaloneMarker;
+      return head_next_with_shift.load(std::memory_order_acquire) ==
+             kStandaloneMarker;
     }
 
     inline void SetStandalone() {
-      head_next_with_shift.Store(kStandaloneMarker);
+      head_next_with_shift.store(kStandaloneMarker, std::memory_order_release);
     }
   };  // struct HandleImpl
 
-  struct Opts : public BaseOpts {
-    explicit Opts(size_t _min_avg_value_size, int _eviction_effort_cap)
-        : BaseOpts(_eviction_effort_cap),
-          min_avg_value_size(_min_avg_value_size) {}
+  struct Opts {
+    explicit Opts(size_t _min_avg_value_size)
+        : min_avg_value_size(_min_avg_value_size) {}
 
-    explicit Opts(const HyperClockCacheOptions& opts)
-        : BaseOpts(opts.eviction_effort_cap) {
+    explicit Opts(const HyperClockCacheOptions& opts) {
       assert(opts.estimated_entry_charge == 0);
       min_avg_value_size = opts.min_avg_entry_charge;
     }
     size_t min_avg_value_size;
   };
 
-  AutoHyperClockTable(size_t capacity,
+  AutoHyperClockTable(size_t capacity, bool strict_capacity_limit,
                       CacheMetadataChargePolicy metadata_charge_policy,
                       MemoryAllocator* allocator,
                       const Cache::EvictionCallback* eviction_callback,
@@ -868,8 +839,7 @@ class AutoHyperClockTable : public BaseClockTable {
   // Runs the clock eviction algorithm trying to reclaim at least
   // requested_charge. Returns how much is evicted, which could be less
   // if it appears impossible to evict the requested amount without blocking.
-  void Evict(size_t requested_charge, InsertState& state, EvictionData* data,
-             uint32_t eviction_effort_cap);
+  void Evict(size_t requested_charge, InsertState& state, EvictionData* data);
 
   HandleImpl* Lookup(const UniqueId64x2& hashed_key);
 
@@ -934,8 +904,7 @@ class AutoHyperClockTable : public BaseClockTable {
   // with proper handling to ensure all existing data is seen even in the
   // presence of concurrent insertions, etc. (See implementation.)
   template <class OpData>
-  void PurgeImpl(OpData* op_data, size_t home = SIZE_MAX,
-                 EvictionData* data = nullptr);
+  void PurgeImpl(OpData* op_data, size_t home = SIZE_MAX);
 
   // An RAII wrapper for locking a chain of entries for removals. See
   // implementation.
@@ -945,7 +914,7 @@ class AutoHyperClockTable : public BaseClockTable {
   // implementation.
   template <class OpData>
   void PurgeImplLocked(OpData* op_data, ChainRewriteLock& rewrite_lock,
-                       size_t home, EvictionData* data);
+                       size_t home);
 
   // Update length_info_ as much as possible without waiting, given a known
   // usable (ready for inserts and lookups) grow_home. (Previous grow_homes
@@ -970,25 +939,22 @@ class AutoHyperClockTable : public BaseClockTable {
   // log time to find the correct chain, but normally this value enables
   // readers to find the correct chain on the first try.
   //
-  // To maximize parallelization of Grow() operations, this field is only
-  // updated opportunistically after Grow() operations and in DoInsert() where
-  // it is found to be out-of-date. See CatchUpLengthInfoNoWait().
-  AcqRelAtomic<uint64_t> length_info_;
+  // NOTES: length_info_ is only updated at the end of a Grow operation,
+  // so that waiting in Grow operations isn't done while entries are pinned
+  // for internal operation purposes. Thus, Lookup and Insert have to
+  // detect and support cases where length_info hasn't caught up to updated
+  // chains. Winning grow thread is the one that transitions
+  // head_next_with_shift from zeros. Grow threads can spin/yield wait for
+  // preconditions and postconditions to be met.
+  std::atomic<uint64_t> length_info_;
 
   // An already-computed version of the usable length times the max load
   // factor. Could be slightly out of date but GrowIfNeeded()/Grow() handle
   // that internally.
-  // (Relaxed: allowed to lag behind length_info_ by a little)
-  RelaxedAtomic<size_t> occupancy_limit_;
-
-  // The next index to use from array_ upon the next Grow(). Might be ahead of
-  // length_info_.
-  // (Relaxed: self-contained source of truth for next grow home)
-  RelaxedAtomic<size_t> grow_frontier_;
+  std::atomic<size_t> occupancy_limit_;
 
   // See explanation in AutoHyperClockTable::Evict
-  // (Relaxed: allowed to lag behind clock_pointer_ and length_info_ state)
-  RelaxedAtomic<size_t> clock_pointer_mask_;
+  std::atomic<size_t> clock_pointer_mask_;
 };  // class AutoHyperClockTable
 
 // A single shard of sharded cache.
@@ -1104,13 +1070,10 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
   Table table_;
 
   // Maximum total charge of all elements stored in the table.
-  // (Relaxed: eventual consistency/update is OK)
-  RelaxedAtomic<size_t> capacity_;
+  std::atomic<size_t> capacity_;
 
-  // Encodes eviction_effort_cap (bottom 31 bits) and strict_capacity_limit
-  // (top bit). See HyperClockCacheOptions::eviction_effort_cap etc.
-  // (Relaxed: eventual consistency/update is OK)
-  RelaxedAtomic<uint32_t> eec_and_scl_;
+  // Whether to reject insertion if cache reaches its full capacity.
+  std::atomic<bool> strict_capacity_limit_;
 };  // class ClockCacheShard
 
 template <class Table>
@@ -1128,12 +1091,6 @@ 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

@@ -26,20 +26,16 @@ 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,
     Cache::CreateContext* create_context, bool /*wait*/, bool advise_erase,
-    Statistics* stats, bool& kept_in_sec_cache) {
+    bool& kept_in_sec_cache) {
   assert(helper);
-  // This is a minor optimization. Its ok to skip it in TSAN in order to
-  // avoid a false positive.
-#ifndef __SANITIZE_THREAD__
   if (disable_cache_) {
     return nullptr;
   }
-#endif
 
   std::unique_ptr<SecondaryCacheResultHandle> handle;
   kept_in_sec_cache = false;
@@ -51,7 +47,6 @@ std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
   void* handle_value = cache_->Value(lru_handle);
   if (handle_value == nullptr) {
     cache_->Release(lru_handle, /*erase_if_last_ref=*/false);
-    RecordTick(stats, COMPRESSED_SECONDARY_CACHE_DUMMY_HITS);
     return nullptr;
   }
 
@@ -79,11 +74,7 @@ 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();
 
@@ -142,7 +133,6 @@ std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
     cache_->Release(lru_handle, /*erase_if_last_ref=*/false);
   }
   handle.reset(new CompressedSecondaryCacheResultHandle(value, charge));
-  RecordTick(stats, COMPRESSED_SECONDARY_CACHE_HITS);
   return handle;
 }
 
@@ -173,15 +163,13 @@ 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 +186,13 @@ 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 +204,6 @@ 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 +216,14 @@ 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 +285,6 @@ 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 +373,7 @@ const Cache::CacheItemHelper* CompressedSecondaryCache::GetHelper(
             chunks_head = chunks_head->next;
             tmp_chunk->Free();
             obj = nullptr;
-          }
+          };
         }};
     return &kHelper;
   } else {
@@ -413,21 +387,6 @@ 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

@@ -86,7 +86,7 @@ class CompressedSecondaryCache : public SecondaryCache {
   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;
+      bool& kept_in_sec_cache) override;
 
   bool SupportForceErase() const override { return true; }
 
@@ -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

@@ -33,20 +33,18 @@ 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.
     std::unique_ptr<SecondaryCacheResultHandle> handle0 =
         sec_cache->Lookup(key0, GetHelper(), this, true, /*advise_erase=*/true,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle0, nullptr);
 
     Random rnd(301);
@@ -61,18 +59,16 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 
     std::unique_ptr<SecondaryCacheResultHandle> handle1_1 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/false,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle1_1, nullptr);
 
     // Insert and Lookup the item k1 for the second time and advise erasing it.
     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);
+                          kept_in_sec_cache);
     ASSERT_NE(handle1_2, nullptr);
     ASSERT_FALSE(kept_in_sec_cache);
     if (sec_cache_is_compressed) {
@@ -93,7 +89,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     // Lookup the item k1 again.
     std::unique_ptr<SecondaryCacheResultHandle> handle1_3 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/true,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle1_3, nullptr);
 
     // Insert and Lookup the item k2.
@@ -103,7 +99,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_dummy_count, 2);
     std::unique_ptr<SecondaryCacheResultHandle> handle2_1 =
         sec_cache->Lookup(key2, GetHelper(), this, true, /*advise_erase=*/false,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle2_1, nullptr);
 
     ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper(), false));
@@ -119,7 +115,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     }
     std::unique_ptr<SecondaryCacheResultHandle> handle2_2 =
         sec_cache->Lookup(key2, GetHelper(), this, true, /*advise_erase=*/false,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_NE(handle2_2, nullptr);
     std::unique_ptr<TestItem> val2 =
         std::unique_ptr<TestItem>(static_cast<TestItem*>(handle2_2->Value()));
@@ -200,14 +196,14 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     bool kept_in_sec_cache{false};
     std::unique_ptr<SecondaryCacheResultHandle> handle1 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/false,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle1, nullptr);
 
     // Insert k2 and k1 is evicted.
     ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper(), false));
     std::unique_ptr<SecondaryCacheResultHandle> handle2 =
         sec_cache->Lookup(key2, GetHelper(), this, true, /*advise_erase=*/false,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_NE(handle2, nullptr);
     std::unique_ptr<TestItem> val2 =
         std::unique_ptr<TestItem>(static_cast<TestItem*>(handle2->Value()));
@@ -219,14 +215,14 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 
     std::unique_ptr<SecondaryCacheResultHandle> handle1_1 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/false,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle1_1, nullptr);
 
     // Create Fails.
     SetFailCreate(true);
     std::unique_ptr<SecondaryCacheResultHandle> handle2_1 =
         sec_cache->Lookup(key2, GetHelper(), this, true, /*advise_erase=*/true,
-                          /*stats=*/nullptr, kept_in_sec_cache);
+                          kept_in_sec_cache);
     ASSERT_EQ(handle2_1, nullptr);
 
     // Save Fails.
@@ -845,6 +841,7 @@ TEST_P(CompressedSecondaryCacheTestWithCompressionParam,
   BasicTestHelper(sec_cache, sec_cache_is_compressed_);
 }
 
+
 TEST_P(CompressedSecondaryCacheTestWithCompressionParam, FailsTest) {
   FailsTest(sec_cache_is_compressed_);
 }
@@ -915,9 +912,9 @@ TEST_P(CompressedSecondaryCacheTestWithCompressionParam, EntryRoles) {
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_real_count, 1U);
 
     bool kept_in_sec_cache{true};
-    std::unique_ptr<SecondaryCacheResultHandle> handle = sec_cache->Lookup(
-        ith_key, GetHelper(role), this, true,
-        /*advise_erase=*/true, /*stats=*/nullptr, kept_in_sec_cache);
+    std::unique_ptr<SecondaryCacheResultHandle> handle =
+        sec_cache->Lookup(ith_key, GetHelper(role), this, true,
+                          /*advise_erase=*/true, kept_in_sec_cache);
     ASSERT_NE(handle, nullptr);
 
     // Lookup returns the right data
@@ -995,8 +992,6 @@ class CompressedSecCacheTestWithTiered
         /*_capacity=*/0,
         /*_estimated_entry_charge=*/256 << 10,
         /*_num_shard_bits=*/0);
-    // eviction_effort_cap setting simply to avoid churn in existing test
-    hcc_opts.eviction_effort_cap = 100;
     TieredCacheOptions opts;
     lru_opts.capacity = 0;
     lru_opts.num_shard_bits = 0;
@@ -1065,7 +1060,7 @@ 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
@@ -1088,7 +1083,7 @@ 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));
@@ -1174,7 +1169,7 @@ 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
@@ -1229,16 +1224,18 @@ TEST_P(CompressedSecCacheTestWithTiered, DynamicUpdate) {
   ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
   ASSERT_EQ(sec_capacity, 0);
 
-  ASSERT_OK(UpdateTieredCache(tiered_cache, -1, 0.3));
-  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
-               GetPercent(30 << 20, 1));
+  ASSERT_NOK(UpdateTieredCache(tiered_cache, -1, 0.3));
+  // Only check usage for LRU cache. HCC shows a 64KB usage for some reason
+  if (std::get<0>(GetParam()) == PrimaryCacheType::kCacheTypeLRU) {
+    ASSERT_EQ(GetCache()->GetUsage(), 0);
+  }
   ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
-  ASSERT_EQ(sec_capacity, (30 << 20));
+  ASSERT_EQ(sec_capacity, 0);
 }
 
 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));
@@ -1319,50 +1316,28 @@ TEST_P(CompressedSecCacheTestWithTiered, DynamicUpdateWithReservation) {
   ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
   ASSERT_EQ(sec_capacity, 0);
 
-  ASSERT_OK(UpdateTieredCache(tiered_cache, -1, 0.3));
-  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (37 << 20),
-               GetPercent(37 << 20, 1));
-  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (3 << 20),
-               GetPercent(3 << 20, 1));
-  ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
-  ASSERT_EQ(sec_capacity, 30 << 20);
-
   ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(0));
 }
 
-TEST_P(CompressedSecCacheTestWithTiered, ReservationOverCapacity) {
-  CompressedSecondaryCache* sec_cache =
-      static_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+TEST_P(CompressedSecCacheTestWithTiered,
+       DynamicUpdateWithReservationUnderflow) {
   std::shared_ptr<Cache> tiered_cache = GetTieredCache();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"CacheWithSecondaryAdapter::Release:ChargeSecCache1",
+        "CacheWithSecondaryAdapter::UpdateCacheReservationRatio:Begin"},
+       {"CacheWithSecondaryAdapter::UpdateCacheReservationRatio:End",
+        "CacheWithSecondaryAdapter::Release:ChargeSecCache2"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
-  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(110 << 20));
-  // Use EXPECT_PRED3 instead of EXPECT_NEAR to void too many size_t to
-  // double explicit casts
-  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (110 << 20),
-               GetPercent(110 << 20, 1));
-  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (30 << 20),
-               GetPercent(30 << 20, 1));
-  size_t sec_capacity;
-  ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
-  ASSERT_EQ(sec_capacity, (30 << 20));
+  port::Thread reserve_release_thread([&]() {
+    EXPECT_EQ(cache_res_mgr()->UpdateCacheReservation(50), Status::OK());
+    EXPECT_EQ(cache_res_mgr()->UpdateCacheReservation(0), Status::OK());
+  });
+  ASSERT_OK(UpdateTieredCache(tiered_cache, 100 << 20, 0.01));
+  reserve_release_thread.join();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
 
-  ASSERT_OK(UpdateTieredCache(tiered_cache, -1, 0.39));
-  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (110 << 20),
-               GetPercent(110 << 20, 1));
-  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (39 << 20),
-               GetPercent(39 << 20, 1));
-  ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
-  ASSERT_EQ(sec_capacity, (39 << 20));
-
-  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(90 << 20));
-  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (94 << 20),
-               GetPercent(94 << 20, 1));
-  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (35 << 20),
-               GetPercent(35 << 20, 1));
-  ASSERT_OK(sec_cache->GetCapacity(sec_capacity));
-  ASSERT_EQ(sec_capacity, (39 << 20));
-
-  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(0));
+  ASSERT_OK(UpdateTieredCache(tiered_cache, 100 << 20, 0.3));
 }
 
 INSTANTIATE_TEST_CASE_P(

cache/lru_cache.cc

@@ -93,8 +93,9 @@ void LRUHandleTable::Resize() {
 
   uint32_t old_length = uint32_t{1} << length_bits_;
   int new_length_bits = length_bits_ + 1;
-  std::unique_ptr<LRUHandle*[]> new_list{
-      new LRUHandle* [size_t{1} << new_length_bits] {}};
+  std::unique_ptr<LRUHandle* []> new_list {
+    new LRUHandle* [size_t{1} << new_length_bits] {}
+  };
   [[maybe_unused]] uint32_t count = 0;
   for (uint32_t i = 0; i < old_length; i++) {
     LRUHandle* h = list_[i];
@@ -276,8 +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;
@@ -300,7 +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);
@@ -312,7 +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);
@@ -340,7 +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);
@@ -506,7 +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);
@@ -661,32 +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() {
@@ -392,12 +389,12 @@ class ClockCacheTest : public testing::Test {
     }
   }
 
-  void NewShard(size_t capacity, bool strict_capacity_limit = true,
-                int eviction_effort_cap = 30) {
+  void NewShard(size_t capacity, bool strict_capacity_limit = true) {
     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};
+    TableOpts opts{1 /*value_size*/};
     new (shard_)
         Shard(capacity, strict_capacity_limit, kDontChargeCacheMetadata,
               /*allocator*/ nullptr, &eviction_callback_, &hash_seed_, opts);
@@ -448,20 +445,12 @@ class ClockCacheTest : public testing::Test {
     return Slice(reinterpret_cast<const char*>(&hashed_key), 16U);
   }
 
-  // A bad hash function for testing / stressing collision handling
   static inline UniqueId64x2 TestHashedKey(char key) {
     // For testing hash near-collision behavior, put the variance in
     // hashed_key in bits that are unlikely to be used as hash bits.
     return {(static_cast<uint64_t>(key) << 56) + 1234U, 5678U};
   }
 
-  // A reasonable hash function, for testing "typical behavior" etc.
-  template <typename T>
-  static inline UniqueId64x2 CheapHash(T i) {
-    return {static_cast<uint64_t>(i) * uint64_t{0x85EBCA77C2B2AE63},
-            static_cast<uint64_t>(i) * uint64_t{0xC2B2AE3D27D4EB4F}};
-  }
-
   Shard* shard_ = nullptr;
 
  private:
@@ -546,7 +535,7 @@ TYPED_TEST(ClockCacheTest, Limits) {
     // verify usage tracking on detached entries.)
     {
       size_t n = kCapacity * 5 + 1;
-      std::unique_ptr<HandleImpl*[]> ha{new HandleImpl* [n] {}};
+      std::unique_ptr<HandleImpl* []> ha { new HandleImpl* [n] {} };
       Status s;
       for (size_t i = 0; i < n && s.ok(); ++i) {
         hkey[1] = i;
@@ -694,53 +683,6 @@ TYPED_TEST(ClockCacheTest, ClockEvictionTest) {
   }
 }
 
-TYPED_TEST(ClockCacheTest, ClockEvictionEffortCapTest) {
-  using HandleImpl = typename ClockCacheTest<TypeParam>::Shard::HandleImpl;
-  for (bool strict_capacity_limit : {true, false}) {
-    SCOPED_TRACE("strict_capacity_limit = " +
-                 std::to_string(strict_capacity_limit));
-    for (int eec : {-42, 0, 1, 10, 100, 1000}) {
-      SCOPED_TRACE("eviction_effort_cap = " + std::to_string(eec));
-      constexpr size_t kCapacity = 1000;
-      // Start with much larger capacity to ensure that we can go way over
-      // capacity without reaching table occupancy limit.
-      this->NewShard(3 * kCapacity, strict_capacity_limit, eec);
-      auto& shard = *this->shard_;
-      shard.SetCapacity(kCapacity);
-
-      // Nearly fill the cache with pinned entries, then add a bunch of
-      // non-pinned entries. eviction_effort_cap should affect how many
-      // evictable entries are present beyond the cache capacity, despite
-      // being evictable.
-      constexpr size_t kCount = kCapacity - 1;
-      std::unique_ptr<HandleImpl*[]> ha{new HandleImpl* [kCount] {}};
-      for (size_t i = 0; i < 2 * kCount; ++i) {
-        UniqueId64x2 hkey = this->CheapHash(i);
-        ASSERT_OK(shard.Insert(
-            this->TestKey(hkey), hkey, nullptr /*value*/, &kNoopCacheItemHelper,
-            1 /*charge*/, i < kCount ? &ha[i] : nullptr, Cache::Priority::LOW));
-      }
-
-      if (strict_capacity_limit) {
-        // If strict_capacity_limit is enabled, the cache will never exceed its
-        // capacity
-        EXPECT_EQ(shard.GetOccupancyCount(), kCapacity);
-      } else {
-        // Rough inverse relationship between cap and possible memory
-        // explosion, which shows up as increased table occupancy count.
-        int effective_eec = std::max(int{1}, eec) + 1;
-        EXPECT_NEAR(shard.GetOccupancyCount() * 1.0,
-                    kCount * (1 + 1.4 / effective_eec),
-                    kCount * (0.6 / effective_eec) + 1.0);
-      }
-
-      for (size_t i = 0; i < kCount; ++i) {
-        shard.Release(ha[i]);
-      }
-    }
-  }
-}
-
 namespace {
 struct DeleteCounter {
   int deleted = 0;
@@ -1093,8 +1035,7 @@ class TestSecondaryCache : public SecondaryCache {
   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 {
+      bool /*advise_erase*/, bool& kept_in_sec_cache) override {
     std::string key_str = key.ToString();
     TEST_SYNC_POINT_CALLBACK("TestSecondaryCache::Lookup", &key_str);
 
@@ -1979,7 +1920,7 @@ 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 +2647,6 @@ 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.cc

@@ -7,4 +7,6 @@
 
 #include "cache/cache_entry_roles.h"
 
-namespace ROCKSDB_NAMESPACE {}  // namespace ROCKSDB_NAMESPACE
+namespace ROCKSDB_NAMESPACE {
+
+}  // namespace ROCKSDB_NAMESPACE

cache/secondary_cache_adapter.cc

@@ -83,10 +83,7 @@ CacheWithSecondaryAdapter::CacheWithSecondaryAdapter(
     : CacheWrapper(std::move(target)),
       secondary_cache_(std::move(secondary_cache)),
       adm_policy_(adm_policy),
-      distribute_cache_res_(distribute_cache_res),
-      placeholder_usage_(0),
-      reserved_usage_(0),
-      sec_reserved_(0) {
+      distribute_cache_res_(distribute_cache_res) {
   target_->SetEvictionCallback(
       [this](const Slice& key, Handle* handle, bool was_hit) {
         return EvictionHandler(key, handle, was_hit);
@@ -106,7 +103,8 @@ CacheWithSecondaryAdapter::CacheWithSecondaryAdapter(
     // secondary cache is freed from the reservation.
     s = pri_cache_res_->UpdateCacheReservation(sec_capacity);
     assert(s.ok());
-    sec_cache_res_ratio_ = (double)sec_capacity / target_->GetCapacity();
+    sec_cache_res_ratio_.store((double)sec_capacity / target_->GetCapacity(),
+                               std::memory_order_relaxed);
   }
 }
 
@@ -115,12 +113,10 @@ CacheWithSecondaryAdapter::~CacheWithSecondaryAdapter() {
   // use after free
   target_->SetEvictionCallback({});
 #ifndef NDEBUG
-  if (distribute_cache_res_) {
+  if (distribute_cache_res_ && !ratio_changed_) {
     size_t sec_capacity = 0;
     Status s = secondary_cache_->GetCapacity(sec_capacity);
     assert(s.ok());
-    assert(placeholder_usage_ == 0);
-    assert(reserved_usage_ == 0);
     assert(pri_cache_res_->GetTotalMemoryUsed() == sec_capacity);
   }
 #endif  // NDEBUG
@@ -134,14 +130,12 @@ 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
@@ -242,37 +236,18 @@ Status CacheWithSecondaryAdapter::Insert(const Slice& key, ObjectPtr value,
                                          const Slice& compressed_value,
                                          CompressionType type) {
   Status s = target_->Insert(key, value, helper, charge, handle, priority);
-  if (s.ok() && value == nullptr && distribute_cache_res_ && handle) {
-    charge = target_->GetCharge(*handle);
-
-    MutexLock l(&cache_res_mutex_);
-    placeholder_usage_ += charge;
-    // Check if total placeholder reservation is more than the overall
-    // cache capacity. If it is, then we don't try to charge the
-    // secondary cache because we don't want to overcharge it (beyond
-    // its capacity).
-    // In order to make this a bit more lightweight, we also check if
-    // the difference between placeholder_usage_ and reserved_usage_ is
-    // atleast kReservationChunkSize and avoid any adjustments if not.
-    if ((placeholder_usage_ <= target_->GetCapacity()) &&
-        ((placeholder_usage_ - reserved_usage_) >= kReservationChunkSize)) {
-      reserved_usage_ = placeholder_usage_ & ~(kReservationChunkSize - 1);
-      size_t new_sec_reserved =
-          static_cast<size_t>(reserved_usage_ * sec_cache_res_ratio_);
-      size_t sec_charge = new_sec_reserved - sec_reserved_;
-      s = secondary_cache_->Deflate(sec_charge);
-      assert(s.ok());
-      s = pri_cache_res_->UpdateCacheReservation(sec_charge,
-                                                 /*increase=*/false);
-      assert(s.ok());
-      sec_reserved_ += sec_charge;
-    }
+  if (s.ok() && value == nullptr && distribute_cache_res_) {
+    size_t sec_charge = static_cast<size_t>(
+        charge * (sec_cache_res_ratio_.load(std::memory_order_relaxed)));
+    s = secondary_cache_->Deflate(sec_charge);
+    assert(s.ok());
+    s = pri_cache_res_->UpdateCacheReservation(sec_charge, /*increase=*/false);
+    assert(s.ok());
   }
   // 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());
   }
@@ -297,8 +272,7 @@ Cache::Handle* CacheWithSecondaryAdapter::Lookup(const Slice& key,
     bool kept_in_sec_cache = false;
     std::unique_ptr<SecondaryCacheResultHandle> secondary_handle =
         secondary_cache_->Lookup(key, helper, create_context, /*wait*/ true,
-                                 found_dummy_entry, stats,
-                                 /*out*/ kept_in_sec_cache);
+                                 found_dummy_entry, /*out*/ kept_in_sec_cache);
     if (secondary_handle) {
       result = Promote(std::move(secondary_handle), key, helper, priority,
                        stats, found_dummy_entry, kept_in_sec_cache);
@@ -313,27 +287,14 @@ bool CacheWithSecondaryAdapter::Release(Handle* handle,
     ObjectPtr v = target_->Value(handle);
     if (v == nullptr && distribute_cache_res_) {
       size_t charge = target_->GetCharge(handle);
-
-      MutexLock l(&cache_res_mutex_);
-      placeholder_usage_ -= charge;
-      // Check if total placeholder reservation is more than the overall
-      // cache capacity. If it is, then we do nothing as reserved_usage_ must
-      // be already maxed out
-      if ((placeholder_usage_ <= target_->GetCapacity()) &&
-          (placeholder_usage_ < reserved_usage_)) {
-        // Adjust reserved_usage_ in chunks of kReservationChunkSize, so
-        // we don't hit this slow path too often.
-        reserved_usage_ = placeholder_usage_ & ~(kReservationChunkSize - 1);
-        size_t new_sec_reserved =
-            static_cast<size_t>(reserved_usage_ * sec_cache_res_ratio_);
-        size_t sec_charge = sec_reserved_ - new_sec_reserved;
-        Status s = secondary_cache_->Inflate(sec_charge);
-        assert(s.ok());
-        s = pri_cache_res_->UpdateCacheReservation(sec_charge,
-                                                   /*increase=*/true);
-        assert(s.ok());
-        sec_reserved_ -= sec_charge;
-      }
+      size_t sec_charge = static_cast<size_t>(
+          charge * (sec_cache_res_ratio_.load(std::memory_order_relaxed)));
+      TEST_SYNC_POINT("CacheWithSecondaryAdapter::Release:ChargeSecCache1");
+      TEST_SYNC_POINT("CacheWithSecondaryAdapter::Release:ChargeSecCache2");
+      Status s = secondary_cache_->Inflate(sec_charge);
+      assert(s.ok());
+      s = pri_cache_res_->UpdateCacheReservation(sec_charge, /*increase=*/true);
+      assert(s.ok());
     }
   }
   return target_->Release(handle, erase_if_last_ref);
@@ -352,10 +313,10 @@ void CacheWithSecondaryAdapter::StartAsyncLookupOnMySecondary(
   assert(async_handle.result_handle == nullptr);
 
   std::unique_ptr<SecondaryCacheResultHandle> secondary_handle =
-      secondary_cache_->Lookup(
-          async_handle.key, async_handle.helper, async_handle.create_context,
-          /*wait*/ false, async_handle.found_dummy_entry, async_handle.stats,
-          /*out*/ async_handle.kept_in_sec_cache);
+      secondary_cache_->Lookup(async_handle.key, async_handle.helper,
+                               async_handle.create_context, /*wait*/ false,
+                               async_handle.found_dummy_entry,
+                               /*out*/ async_handle.kept_in_sec_cache);
   if (secondary_handle) {
     // TODO with stacked secondaries: Check & process if already ready?
     async_handle.pending_handle = secondary_handle.release();
@@ -480,11 +441,13 @@ const char* CacheWithSecondaryAdapter::Name() const {
 // where the new capacity < total cache reservations.
 void CacheWithSecondaryAdapter::SetCapacity(size_t capacity) {
   size_t sec_capacity = static_cast<size_t>(
-      capacity * (distribute_cache_res_ ? sec_cache_res_ratio_ : 0.0));
+      capacity * (distribute_cache_res_
+                      ? sec_cache_res_ratio_.load(std::memory_order_relaxed)
+                      : 0.0));
   size_t old_sec_capacity = 0;
 
   if (distribute_cache_res_) {
-    MutexLock m(&cache_res_mutex_);
+    MutexLock m(&mutex_);
 
     Status s = secondary_cache_->GetCapacity(old_sec_capacity);
     if (!s.ok()) {
@@ -499,17 +462,9 @@ void CacheWithSecondaryAdapter::SetCapacity(size_t capacity) {
       // 3. Decrease the primary cache capacity to the total budget
       s = secondary_cache_->SetCapacity(sec_capacity);
       if (s.ok()) {
-        if (placeholder_usage_ > capacity) {
-          // Adjust reserved_usage_ down
-          reserved_usage_ = capacity & ~(kReservationChunkSize - 1);
-        }
-        size_t new_sec_reserved =
-            static_cast<size_t>(reserved_usage_ * sec_cache_res_ratio_);
         s = pri_cache_res_->UpdateCacheReservation(
-            (old_sec_capacity - sec_capacity) -
-                (sec_reserved_ - new_sec_reserved),
+            old_sec_capacity - sec_capacity,
             /*increase=*/false);
-        sec_reserved_ = new_sec_reserved;
         assert(s.ok());
         target_->SetCapacity(capacity);
       }
@@ -543,7 +498,7 @@ Status CacheWithSecondaryAdapter::GetSecondaryCachePinnedUsage(
     size_t& size) const {
   Status s;
   if (distribute_cache_res_) {
-    MutexLock m(&cache_res_mutex_);
+    MutexLock m(&mutex_);
     size_t capacity = 0;
     s = secondary_cache_->GetCapacity(capacity);
     if (s.ok()) {
@@ -571,11 +526,12 @@ Status CacheWithSecondaryAdapter::GetSecondaryCachePinnedUsage(
 // in the future.
 Status CacheWithSecondaryAdapter::UpdateCacheReservationRatio(
     double compressed_secondary_ratio) {
-  if (!distribute_cache_res_) {
+  if (!distribute_cache_res_ ||
+      sec_cache_res_ratio_.load(std::memory_order_relaxed) == 0.0) {
     return Status::NotSupported();
   }
 
-  MutexLock m(&cache_res_mutex_);
+  MutexLock m(&mutex_);
   size_t pri_capacity = target_->GetCapacity();
   size_t sec_capacity =
       static_cast<size_t>(pri_capacity * compressed_secondary_ratio);
@@ -585,17 +541,38 @@ Status CacheWithSecondaryAdapter::UpdateCacheReservationRatio(
     return s;
   }
 
+  TEST_SYNC_POINT(
+      "CacheWithSecondaryAdapter::UpdateCacheReservationRatio:Begin");
+
+  // There's a possible race condition here. Since the read of pri_cache_res_
+  // memory used (secondary cache usage charged to primary cache), and the
+  // change to sec_cache_res_ratio_ are not guarded by a mutex, its possible
+  // that an Insert/Release in another thread might decrease/increase the
+  // pri_cache_res_ reservation by the wrong amount. This should not be a
+  // problem because updating the sec/pri ratio is a rare operation, and
+  // the worst that can happen is we may over/under charge the secondary
+  // cache usage by a little bit. But we do need to protect against
+  // underflow of old_sec_reserved.
+  // TODO: Make the accounting more accurate by tracking the total memory
+  // reservation on the primary cache. This will also allow us to remove
+  // the restriction of not being able to change the sec/pri ratio from
+  // 0.0 to higher.
+  size_t sec_charge_to_pri = pri_cache_res_->GetTotalMemoryUsed();
+  size_t old_sec_reserved = (old_sec_capacity > sec_charge_to_pri)
+                                ? (old_sec_capacity - sec_charge_to_pri)
+                                : 0;
   // Calculate the new secondary cache reservation
-  // reserved_usage_ will never be > the cache capacity, so we don't
-  // have to worry about adjusting it here.
-  sec_cache_res_ratio_ = compressed_secondary_ratio;
-  size_t new_sec_reserved =
-      static_cast<size_t>(reserved_usage_ * sec_cache_res_ratio_);
+  size_t sec_reserved = static_cast<size_t>(
+      old_sec_reserved *
+      (double)(compressed_secondary_ratio /
+               sec_cache_res_ratio_.load(std::memory_order_relaxed)));
+  sec_cache_res_ratio_.store(compressed_secondary_ratio,
+                             std::memory_order_relaxed);
   if (sec_capacity > old_sec_capacity) {
     // We're increasing the ratio, thus ending up with a larger secondary
     // cache and a smaller usable primary cache capacity. Similar to
     // SetCapacity(), we try to avoid a temporary increase in total usage
-    // beyond the configured capacity -
+    // beyond teh configured capacity -
     // 1. A higher secondary cache ratio means it gets a higher share of
     //    cache reservations. So first account for that by deflating the
     //    secondary cache
@@ -603,13 +580,12 @@ Status CacheWithSecondaryAdapter::UpdateCacheReservationRatio(
     //    cache utilization (increase in capacity - increase in share of cache
     //    reservation)
     // 3. Increase secondary cache capacity
-    s = secondary_cache_->Deflate(new_sec_reserved - sec_reserved_);
+    s = secondary_cache_->Deflate(sec_reserved - old_sec_reserved);
     assert(s.ok());
     s = pri_cache_res_->UpdateCacheReservation(
-        (sec_capacity - old_sec_capacity) - (new_sec_reserved - sec_reserved_),
+        (sec_capacity - old_sec_capacity) - (sec_reserved - old_sec_reserved),
         /*increase=*/true);
     assert(s.ok());
-    sec_reserved_ = new_sec_reserved;
     s = secondary_cache_->SetCapacity(sec_capacity);
     assert(s.ok());
   } else {
@@ -623,16 +599,21 @@ Status CacheWithSecondaryAdapter::UpdateCacheReservationRatio(
     s = secondary_cache_->SetCapacity(sec_capacity);
     if (s.ok()) {
       s = pri_cache_res_->UpdateCacheReservation(
-          (old_sec_capacity - sec_capacity) -
-              (sec_reserved_ - new_sec_reserved),
+          (old_sec_capacity - sec_capacity) - (old_sec_reserved - sec_reserved),
           /*increase=*/false);
       assert(s.ok());
-      s = secondary_cache_->Inflate(sec_reserved_ - new_sec_reserved);
+      s = secondary_cache_->Inflate(old_sec_reserved - sec_reserved);
       assert(s.ok());
-      sec_reserved_ = new_sec_reserved;
     }
   }
 
+  TEST_SYNC_POINT("CacheWithSecondaryAdapter::UpdateCacheReservationRatio:End");
+#ifndef NDEBUG
+  // As mentioned in the function comments, we may accumulate some erros when
+  // the ratio is changed. We set a flag here which disables some assertions
+  // in the destructor
+  ratio_changed_ = true;
+#endif
   return s;
 }
 
@@ -664,7 +645,6 @@ 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;
         }
@@ -688,14 +668,12 @@ std::shared_ptr<Cache> NewTieredCache(const TieredCacheOptions& _opts) {
         *(static_cast_with_check<LRUCacheOptions, ShardedCacheOptions>(
             opts.cache_opts));
     cache_opts.capacity = opts.total_capacity;
-    cache_opts.secondary_cache = nullptr;
     cache = cache_opts.MakeSharedCache();
   } else if (opts.cache_type == PrimaryCacheType::kCacheTypeHCC) {
     HyperClockCacheOptions cache_opts =
         *(static_cast_with_check<HyperClockCacheOptions, ShardedCacheOptions>(
             opts.cache_opts));
     cache_opts.capacity = opts.total_capacity;
-    cache_opts.secondary_cache = nullptr;
     cache = cache_opts.MakeSharedCache();
   } else {
     return nullptr;

cache/secondary_cache_adapter.h

@@ -60,8 +60,6 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
   SecondaryCache* TEST_GetSecondaryCache() { return secondary_cache_.get(); }
 
  private:
-  static constexpr size_t kReservationChunkSize = 1 << 20;
-
   bool EvictionHandler(const Slice& key, Handle* handle, bool was_hit);
 
   void StartAsyncLookupOnMySecondary(AsyncLookupHandle& async_handle);
@@ -86,18 +84,11 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
   std::shared_ptr<ConcurrentCacheReservationManager> pri_cache_res_;
   // Fraction of a cache memory reservation to be assigned to the secondary
   // cache
-  double sec_cache_res_ratio_;
-  // Mutex for use when managing cache memory reservations. Should not be used
-  // for other purposes, as it may risk causing deadlocks.
-  mutable port::Mutex cache_res_mutex_;
-  // Total memory reserved by placeholder entriesin the cache
-  size_t placeholder_usage_;
-  // Total placeholoder memory charged to both the primary and secondary
-  // caches. Will be <= placeholder_usage_.
-  size_t reserved_usage_;
-  // Amount of memory reserved in the secondary cache. This should be
-  // reserved_usage_ * sec_cache_res_ratio_ in steady state.
-  size_t sec_reserved_;
+  std::atomic<double> sec_cache_res_ratio_;
+  mutable port::Mutex mutex_;
+#ifndef NDEBUG
+  bool ratio_changed_ = false;
+#endif
 };
 
 }  // namespace ROCKSDB_NAMESPACE

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.cc

@@ -5,8 +5,6 @@
 
 #include "cache/tiered_secondary_cache.h"
 
-#include "monitoring/statistics_impl.h"
-
 namespace ROCKSDB_NAMESPACE {
 
 // Creation callback for use in the lookup path. It calls the upper layer
@@ -31,9 +29,6 @@ Status TieredSecondaryCache::MaybeInsertAndCreate(
     // TODO: Don't hardcode the source
     context->comp_sec_cache->InsertSaved(*context->key, data, type, source)
         .PermitUncheckedError();
-    RecordTick(context->stats, COMPRESSED_SECONDARY_CACHE_PROMOTIONS);
-  } else {
-    RecordTick(context->stats, COMPRESSED_SECONDARY_CACHE_PROMOTION_SKIPS);
   }
   // Primary cache will accept the object, so call its helper to create
   // the object
@@ -48,10 +43,10 @@ Status TieredSecondaryCache::MaybeInsertAndCreate(
 std::unique_ptr<SecondaryCacheResultHandle> TieredSecondaryCache::Lookup(
     const Slice& key, const Cache::CacheItemHelper* helper,
     Cache::CreateContext* create_context, bool wait, bool advise_erase,
-    Statistics* stats, bool& kept_in_sec_cache) {
+    bool& kept_in_sec_cache) {
   bool dummy = false;
   std::unique_ptr<SecondaryCacheResultHandle> result =
-      target()->Lookup(key, helper, create_context, wait, advise_erase, stats,
+      target()->Lookup(key, helper, create_context, wait, advise_erase,
                        /*kept_in_sec_cache=*/dummy);
   // We never want the item to spill back into the secondary cache
   kept_in_sec_cache = true;
@@ -71,10 +66,9 @@ std::unique_ptr<SecondaryCacheResultHandle> TieredSecondaryCache::Lookup(
     ctx.helper = helper;
     ctx.inner_ctx = create_context;
     ctx.comp_sec_cache = target();
-    ctx.stats = stats;
 
     return nvm_sec_cache_->Lookup(key, outer_helper, &ctx, wait, advise_erase,
-                                  stats, kept_in_sec_cache);
+                                  kept_in_sec_cache);
   }
 
   // If wait is false, i.e its an async lookup, we have to allocate a result
@@ -86,10 +80,8 @@ std::unique_ptr<SecondaryCacheResultHandle> TieredSecondaryCache::Lookup(
   handle->ctx()->helper = helper;
   handle->ctx()->inner_ctx = create_context;
   handle->ctx()->comp_sec_cache = target();
-  handle->ctx()->stats = stats;
-  handle->SetInnerHandle(
-      nvm_sec_cache_->Lookup(key, outer_helper, handle->ctx(), wait,
-                             advise_erase, stats, kept_in_sec_cache));
+  handle->SetInnerHandle(nvm_sec_cache_->Lookup(
+      key, outer_helper, handle->ctx(), wait, advise_erase, kept_in_sec_cache));
   if (!handle->inner_handle()) {
     handle.reset();
   } else {
@@ -117,8 +109,10 @@ void TieredSecondaryCache::WaitAll(
   }
   nvm_sec_cache_->WaitAll(nvm_handles);
   for (auto handle : my_handles) {
-    assert(handle->inner_handle()->IsReady());
-    handle->Complete();
+    assert(handle->IsReady());
+    auto nvm_handle = handle->inner_handle();
+    handle->SetSize(nvm_handle->Size());
+    handle->SetValue(nvm_handle->Value());
   }
 }
 

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;
+      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 {
@@ -70,7 +72,6 @@ class TieredSecondaryCache : public SecondaryCacheWrapper {
     Cache::CreateContext* inner_ctx;
     std::shared_ptr<SecondaryCacheResultHandle> inner_handle;
     SecondaryCache* comp_sec_cache;
-    Statistics* stats;
   };
 
   class ResultHandle : public SecondaryCacheResultHandle {
@@ -78,10 +79,7 @@ class TieredSecondaryCache : public SecondaryCacheWrapper {
     ~ResultHandle() override {}
 
     bool IsReady() override {
-      if (inner_handle_ && inner_handle_->IsReady()) {
-        Complete();
-      }
-      return ready_;
+      return !inner_handle_ || inner_handle_->IsReady();
     }
 
     void Wait() override {
@@ -94,10 +92,10 @@ class TieredSecondaryCache : public SecondaryCacheWrapper {
     Cache::ObjectPtr Value() override { return value_; }
 
     void Complete() {
+      assert(IsReady());
       size_ = inner_handle_->Size();
       value_ = inner_handle_->Value();
       inner_handle_.reset();
-      ready_ = true;
     }
 
     void SetInnerHandle(std::unique_ptr<SecondaryCacheResultHandle>&& handle) {
@@ -117,7 +115,6 @@ class TieredSecondaryCache : public SecondaryCacheWrapper {
     CreateContext ctx_;
     size_t size_;
     Cache::ObjectPtr value_;
-    bool ready_ = false;
   };
 
   static void NoopDelete(Cache::ObjectPtr /*obj*/,

cache/tiered_secondary_cache_test.cc

@@ -15,11 +15,10 @@ namespace ROCKSDB_NAMESPACE {
 
 class TestSecondaryCache : public SecondaryCache {
  public:
-  explicit TestSecondaryCache(size_t capacity, bool ready_before_wait)
+  explicit TestSecondaryCache(size_t capacity)
       : cache_(NewLRUCache(capacity, 0, false, 0.5 /* high_pri_pool_ratio */,
                            nullptr, kDefaultToAdaptiveMutex,
                            kDontChargeCacheMetadata)),
-        ready_before_wait_(ready_before_wait),
         num_insert_saved_(0),
         num_hits_(0),
         num_misses_(0) {}
@@ -62,7 +61,7 @@ class TestSecondaryCache : public SecondaryCache {
   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 {
+      bool& kept_in_sec_cache) override {
     std::string key_str = key.ToString();
     TEST_SYNC_POINT_CALLBACK("TestSecondaryCache::Lookup", &key_str);
 
@@ -89,8 +88,7 @@ class TestSecondaryCache : public SecondaryCache {
                             /*alloc*/ nullptr, &value, &charge);
       if (s.ok()) {
         secondary_handle.reset(new TestSecondaryCacheResultHandle(
-            cache_.get(), handle, value, charge,
-            /*ready=*/wait || ready_before_wait_));
+            cache_.get(), handle, value, charge, /*ready=*/wait));
         kept_in_sec_cache = true;
       } else {
         cache_.Release(handle);
@@ -170,7 +168,6 @@ class TestSecondaryCache : public SecondaryCache {
       BasicTypedSharedCacheInterface<char[], CacheEntryRole::kMisc>;
   using TypedHandle = SharedCache::TypedHandle;
   SharedCache cache_;
-  bool ready_before_wait_;
   uint32_t num_insert_saved_;
   uint32_t num_hits_;
   uint32_t num_misses_;
@@ -182,10 +179,11 @@ class DBTieredSecondaryCacheTest : public DBTestBase {
   DBTieredSecondaryCacheTest()
       : DBTestBase("db_tiered_secondary_cache_test", /*env_do_fsync=*/true) {}
 
-  std::shared_ptr<Cache> NewCache(
-      size_t pri_capacity, size_t compressed_capacity, size_t nvm_capacity,
-      TieredAdmissionPolicy adm_policy = TieredAdmissionPolicy::kAdmPolicyAuto,
-      bool ready_before_wait = false) {
+  std::shared_ptr<Cache> NewCache(size_t pri_capacity,
+                                  size_t compressed_capacity,
+                                  size_t nvm_capacity,
+                                  TieredAdmissionPolicy adm_policy =
+                                      TieredAdmissionPolicy::kAdmPolicyAuto) {
     LRUCacheOptions lru_opts;
     TieredCacheOptions opts;
     lru_opts.capacity = 0;
@@ -196,11 +194,10 @@ class DBTieredSecondaryCacheTest : public DBTestBase {
     opts.comp_cache_opts.capacity = 0;
     opts.comp_cache_opts.num_shard_bits = 0;
     opts.total_capacity = pri_capacity + compressed_capacity;
-    opts.compressed_secondary_ratio = compressed_secondary_ratio_ =
+    opts.compressed_secondary_ratio =
         (double)compressed_capacity / opts.total_capacity;
     if (nvm_capacity > 0) {
-      nvm_sec_cache_.reset(
-          new TestSecondaryCache(nvm_capacity, ready_before_wait));
+      nvm_sec_cache_.reset(new TestSecondaryCache(nvm_capacity));
       opts.nvm_sec_cache = nvm_sec_cache_;
     }
     opts.adm_policy = adm_policy;
@@ -210,12 +207,6 @@ class DBTieredSecondaryCacheTest : public DBTestBase {
     return cache_;
   }
 
-  void ClearPrimaryCache() {
-    ASSERT_EQ(UpdateTieredCache(cache_, -1, 1.0), Status::OK());
-    ASSERT_EQ(UpdateTieredCache(cache_, -1, compressed_secondary_ratio_),
-              Status::OK());
-  }
-
   TestSecondaryCache* nvm_sec_cache() { return nvm_sec_cache_.get(); }
 
   CompressedSecondaryCache* compressed_secondary_cache() {
@@ -227,7 +218,6 @@ class DBTieredSecondaryCacheTest : public DBTestBase {
  private:
   std::shared_ptr<Cache> cache_;
   std::shared_ptr<TestSecondaryCache> nvm_sec_cache_;
-  double compressed_secondary_ratio_;
 };
 
 // In this test, the block size is set to 4096. Each value is 1007 bytes, so
@@ -253,7 +243,6 @@ 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 +354,6 @@ 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 +376,7 @@ 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 +390,7 @@ 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 +404,7 @@ 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 +418,7 @@ 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 +432,7 @@ 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 +446,7 @@ 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 +460,7 @@ 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 +474,7 @@ 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 +496,6 @@ 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 +518,7 @@ 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 +532,7 @@ 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 +551,7 @@ 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 +572,7 @@ 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);
@@ -595,117 +582,6 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   Destroy(options);
 }
 
-TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
-  if (!LZ4_Supported()) {
-    ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-    return;
-  }
-
-  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.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);
-  ASSERT_EQ(options.statistics->getTickerCount(BLOCK_CACHE_MISS), 3u);
-
-  keys.clear();
-  values.clear();
-  keys.push_back(Key(12));
-  keys.push_back(Key(16));
-  keys.push_back(Key(20));
-  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(), 6u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 6u);
-  ASSERT_EQ(nvm_sec_cache()->num_hits(), 0u);
-  ASSERT_EQ(options.statistics->getTickerCount(BLOCK_CACHE_MISS), 6u);
-
-  keys.clear();
-  values.clear();
-  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(), 6u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 6u);
-  ASSERT_EQ(nvm_sec_cache()->num_hits(), 3u);
-  ASSERT_EQ(options.statistics->getTickerCount(BLOCK_CACHE_MISS), 6u);
-
-  ClearPrimaryCache();
-
-  keys.clear();
-  values.clear();
-  keys.push_back(Key(0));
-  keys.push_back(Key(32));
-  keys.push_back(Key(36));
-  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(), 8u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 8u);
-  ASSERT_EQ(nvm_sec_cache()->num_hits(), 4u);
-  ASSERT_EQ(options.statistics->getTickerCount(BLOCK_CACHE_MISS), 8u);
-
-  keys.clear();
-  values.clear();
-  keys.push_back(Key(0));
-  keys.push_back(Key(32));
-  keys.push_back(Key(36));
-  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(), 8u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 8u);
-  ASSERT_EQ(nvm_sec_cache()->num_hits(), 4u);
-  ASSERT_EQ(options.statistics->getTickerCount(BLOCK_CACHE_MISS), 8u);
-
-  Destroy(options);
-}
-
 // This test is for iteration. It iterates through a set of keys in two
 // passes. First pass loads the compressed blocks into the nvm tier, and
 // the second pass should hit all of those blocks.
@@ -721,7 +597,6 @@ 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 +640,6 @@ 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 +664,6 @@ 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();
@@ -870,184 +696,11 @@ 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];
-            // See https://github.com/facebook/rocksdb/pull/13195 for why we
-            // want to set up our test implementation for FSAllocationPtr this
-            // way.
-            char* internalData = new char[req.len];
-            req.status = Read(req.offset, req.len, options, &req.result,
-                              internalData, dbg);
-
-            Slice* internalSlice = new Slice(internalData, req.len);
-            FSAllocationPtr internalPtr(internalSlice, [](void* ptr) {
-              delete[] static_cast<const char*>(
-                  static_cast<Slice*>(ptr)->data_);
-              delete static_cast<Slice*>(ptr);
-            });
-            req.fs_scratch = std::move(internalPtr);
-          }
-          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

@@ -43,167 +43,74 @@ 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;
-}
-
-void ArenaWrappedDBIter::MaybeAutoRefresh(bool is_seek,
-                                          DBIter::Direction direction) {
-  if (cfh_ != nullptr && read_options_.snapshot != nullptr && allow_refresh_ &&
-      read_options_.auto_refresh_iterator_with_snapshot) {
-    // The intent here is to capture the superversion number change
-    // reasonably soon from the time it actually happened. As such,
-    // we're fine with weaker synchronization / ordering guarantees
-    // provided by relaxed atomic (in favor of less CPU / mem overhead).
-    uint64_t cur_sv_number = cfh_->cfd()->GetSuperVersionNumberRelaxed();
-    if ((sv_number_ != cur_sv_number) && status().ok()) {
-      // Changing iterators' direction is pretty heavy-weight operation and
-      // could have unintended consequences when it comes to prefix seek.
-      // Therefore, we need an efficient implementation that does not duplicate
-      // the effort by doing things like double seek(forprev).
-      //
-      // Auto refresh can be triggered on the following groups of operations:
-      //
-      //  1. [Seek]: Seek(), SeekForPrev()
-      //  2. [Non-Seek]: Next(), Prev()
-      //
-      // In case of 'Seek' group, procedure is fairly straightforward as we'll
-      // simply call refresh and then invoke the operation on intended target.
-      //
-      // In case of 'Non-Seek' group, we'll first advance the cursor by invoking
-      // intended user operation (Next() or Prev()), capture the target key T,
-      // refresh the iterator and then reconcile the refreshed iterator by
-      // explicitly calling [Seek(T) or SeekForPrev(T)]. Below is an example
-      // flow for Next(), but same principle applies to Prev():
-      //
-      //
-      //          T0: Before the operation     T1: Execute Next()
-      //                         |                      |
-      //                         |         -------------
-      //                         |        |   * capture the key (T)
-      //           DBIter(SV#A)  |        |
-      //          --------------\ /------\ /---------
-      //  SV #A  |     ... ->  [ X ] -> [ T ] -> ... |
-      //          -----------------------------------
-      //                                / |
-      //                               /  |
-      //                              /  T2: Refresh iterator
-      //                             /
-      //           DBIter(SV#A')    /
-      //          ----------------------------------
-      //  SV #A' |       ... ->  [ T ] -> ...       |
-      //          ----------------/ \---------------
-      //                           |
-      //                            ---- T3: Seek(T)
-      //
-      bool valid = false;
-      std::string key;
-      if (!is_seek && db_iter_->Valid()) {
-        // The key() Slice is valid until the iterator state changes.
-        // Given that refresh is heavy-weight operation it itself,
-        // we should copy the target key upfront to avoid reading bad value.
-        valid = true;
-        key = db_iter_->key().ToString();
-      }
-
-      // It's perfectly fine to unref the corresponding superversion
-      // as we rely on pinning behavior of snapshot for consistency.
-      DoRefresh(read_options_.snapshot, cur_sv_number);
-
-      if (!is_seek && valid) {  // Reconcile new iterator after Next() / Prev()
-        if (direction == DBIter::kForward) {
-          db_iter_->Seek(key);
-        } else {
-          assert(direction == DBIter::kReverse);
-          db_iter_->SeekForPrev(key);
-        }
-      }
-    }
-  }
 }
 
 Status ArenaWrappedDBIter::Refresh() { return Refresh(nullptr); }
 
-void ArenaWrappedDBIter::DoRefresh(const Snapshot* snapshot,
-                                   [[maybe_unused]] uint64_t sv_number) {
-  Env* env = db_iter_->env();
-
-  // NOTE:
-  //
-  // Errors like file deletion (as a part of SV cleanup in ~DBIter) will be
-  // present in the error log, but won't be reflected in the iterator status.
-  // This is by design as we expect compaction to clean up those obsolete files
-  // eventually.
-  db_iter_->~DBIter();
-
-  arena_.~Arena();
-  new (&arena_) Arena();
-
-  auto cfd = cfh_->cfd();
-  auto db_impl = cfh_->db();
-
-  SuperVersion* sv = cfd->GetReferencedSuperVersion(db_impl);
-  assert(sv->version_number >= sv_number);
-  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, sv->current,
-       read_seq, sv->mutable_cf_options.max_sequential_skip_in_iterations,
-       sv->version_number, read_callback_, cfh_, expose_blob_index_,
-       allow_refresh_);
-
-  InternalIterator* internal_iter = db_impl->NewInternalIterator(
-      read_options_, cfd, sv, &arena_, read_seq,
-      /* allow_unprepared_value */ true, /* db_iter */ this);
-  SetIterUnderDBIter(internal_iter);
-}
-
 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_);
+    assert(sv->version_number >= cur_sv_number);
+    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,
+         sv->current, read_seq,
+         sv->mutable_cf_options.max_sequential_skip_in_iterations,
+         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,
+        /* allow_unprepared_value */ true, /* db_iter */ this);
+    SetIterUnderDBIter(internal_iter);
+  };
   while (true) {
     if (sv_number_ != cur_sv_number) {
-      DoRefresh(snapshot, cur_sv_number);
+      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 */);
@@ -216,28 +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.
-            DoRefresh(snapshot, cur_sv_number);
+            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
@@ -256,14 +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;
   }
 
@@ -65,26 +64,12 @@ class ArenaWrappedDBIter : public Iterator {
   void SeekToLast() override { db_iter_->SeekToLast(); }
   // 'target' does not contain timestamp, even if user timestamp feature is
   // enabled.
-  void Seek(const Slice& target) override {
-    MaybeAutoRefresh(true /* is_seek */, DBIter::kForward);
-    db_iter_->Seek(target);
-  }
-
+  void Seek(const Slice& target) override { db_iter_->Seek(target); }
   void SeekForPrev(const Slice& target) override {
-    MaybeAutoRefresh(true /* is_seek */, DBIter::kReverse);
     db_iter_->SeekForPrev(target);
   }
-
-  void Next() override {
-    db_iter_->Next();
-    MaybeAutoRefresh(false /* is_seek */, DBIter::kForward);
-  }
-
-  void Prev() override {
-    db_iter_->Prev();
-    MaybeAutoRefresh(false /* is_seek */, DBIter::kReverse);
-  }
-
+  void Next() override { db_iter_->Next(); }
+  void Prev() override { db_iter_->Prev(); }
   Slice key() const override { return db_iter_->key(); }
   Slice value() const override { return db_iter_->value(); }
   const WideColumns& columns() const override { return db_iter_->columns(); }
@@ -97,51 +82,47 @@ 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;
   }
 
  private:
-  void DoRefresh(const Snapshot* snapshot, uint64_t sv_number);
-  void MaybeAutoRefresh(bool is_seek, DBIter::Direction direction);
-
   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_);
@@ -188,12 +187,10 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
   }
 
   std::unique_ptr<FSWritableFile> file;
-  FileOptions fo_copy;
+
   {
     assert(file_options_);
-    fo_copy = *file_options_;
-    fo_copy.write_hint = write_hint_;
-    Status s = NewWritableFile(fs_, blob_file_path, &file, fo_copy);
+    Status s = NewWritableFile(fs_, blob_file_path, &file, *file_options_);
 
     TEST_SYNC_POINT_CALLBACK(
         "BlobFileBuilder::OpenBlobFileIfNeeded:NewWritableFile", &s);
@@ -210,16 +207,14 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
   blob_file_paths_->emplace_back(std::move(blob_file_path));
 
   assert(file);
-  file->SetIOPriority(write_options_->rate_limiter_priority);
-  // Subsequent attempts to override the hint via SetWriteLifeTimeHint
-  // with the very same value will be ignored by the fs.
-  file->SetWriteLifeTimeHint(fo_copy.write_hint);
+  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));
 
@@ -236,7 +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);
@@ -301,8 +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);
 
@@ -327,8 +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)};
   }
 }
 
@@ -82,8 +81,8 @@ Status BlobSource::PutBlobIntoCache(
   assert(cached_blob->IsEmpty());
 
   TypedHandle* cache_handle = nullptr;
-  const Status s = InsertEntryIntoCache(cache_key, blob->get(), &cache_handle,
-                                        Cache::Priority::BOTTOM);
+  const Status s = InsertEntryIntoCache(cache_key, blob->get(),
+                                        &cache_handle, Cache::Priority::BOTTOM);
   if (s.ok()) {
     blob->release();
 

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]));
@@ -1226,7 +1220,7 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
       auto sec_handle0 = secondary_cache->Lookup(
           key0, BlobSource::SharedCacheInterface::GetFullHelper(),
           /*context*/ nullptr, true,
-          /*advise_erase=*/true, /*stats=*/nullptr, kept_in_sec_cache);
+          /*advise_erase=*/true, kept_in_sec_cache);
       ASSERT_FALSE(kept_in_sec_cache);
       ASSERT_NE(sec_handle0, nullptr);
       ASSERT_TRUE(sec_handle0->IsReady());
@@ -1254,7 +1248,7 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
       auto sec_handle1 = secondary_cache->Lookup(
           key1, BlobSource::SharedCacheInterface::GetFullHelper(),
           /*context*/ nullptr, true,
-          /*advise_erase=*/true, /*stats=*/nullptr, kept_in_sec_cache);
+          /*advise_erase=*/true, kept_in_sec_cache);
       ASSERT_FALSE(kept_in_sec_cache);
       ASSERT_EQ(sec_handle1, nullptr);
 
@@ -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

@@ -168,7 +168,6 @@ TEST_F(DBBlobBasicTest, IterateBlobsFromCache) {
       ASSERT_EQ(iter->value().ToString(), blobs[i]);
       ++i;
     }
-    ASSERT_OK(iter->status());
     ASSERT_EQ(i, num_blobs);
     ASSERT_EQ(options.statistics->getAndResetTickerCount(BLOB_DB_CACHE_ADD), 0);
   }
@@ -204,7 +203,6 @@ TEST_F(DBBlobBasicTest, IterateBlobsFromCache) {
       ASSERT_EQ(iter->value().ToString(), blobs[i]);
       ++i;
     }
-    ASSERT_OK(iter->status());
     ASSERT_EQ(i, num_blobs);
     ASSERT_EQ(options.statistics->getAndResetTickerCount(BLOB_DB_CACHE_ADD),
               num_blobs);
@@ -226,7 +224,6 @@ TEST_F(DBBlobBasicTest, IterateBlobsFromCache) {
       ASSERT_EQ(iter->value().ToString(), blobs[i]);
       ++i;
     }
-    ASSERT_OK(iter->status());
     ASSERT_EQ(i, num_blobs);
     ASSERT_EQ(options.statistics->getAndResetTickerCount(BLOB_DB_CACHE_ADD), 0);
   }
@@ -374,115 +371,6 @@ 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 +415,8 @@ 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 +438,8 @@ 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 +509,8 @@ 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 +531,8 @@ 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 +550,8 @@ 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 +571,8 @@ 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 +755,8 @@ 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 +826,8 @@ 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 +840,8 @@ 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 +855,8 @@ 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 +869,8 @@ 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 +1179,6 @@ 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 +1203,8 @@ 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 +1467,8 @@ 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 +1524,6 @@ 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 +1577,6 @@ 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 +1817,7 @@ 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 +1914,8 @@ 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 +1998,8 @@ 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");
@@ -2350,7 +2123,6 @@ TEST_F(DBBlobWithTimestampTest, IterateBlobs) {
                        /*key_is_internal*/ false);
       iter->Prev();
     }
-    ASSERT_OK(iter->status());
   }
 
   // Backward iteration, then reverse to forward.
@@ -2397,7 +2169,6 @@ TEST_F(DBBlobWithTimestampTest, IterateBlobs) {
         iter->Next();
       }
     }
-    ASSERT_OK(iter->status());
   }
 
   // Backward iterating multiple versions of the same key, get in this order:
@@ -2416,7 +2187,6 @@ TEST_F(DBBlobWithTimestampTest, IterateBlobs) {
         iter->Prev();
       }
     }
-    ASSERT_OK(iter->status());
   }
 
   int upper_bound_idx = num_blobs - 2;
@@ -2439,7 +2209,6 @@ TEST_F(DBBlobWithTimestampTest, IterateBlobs) {
         iter->Next();
       }
     }
-    ASSERT_OK(iter->status());
   }
 
   // Backward iteration with upper and lower bound.
@@ -2455,7 +2224,6 @@ TEST_F(DBBlobWithTimestampTest, IterateBlobs) {
         iter->Prev();
       }
     }
-    ASSERT_OK(iter->status());
   }
 }
 

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();
@@ -145,9 +147,7 @@ Status BuildTable(
       bool use_direct_writes = file_options.use_direct_writes;
       TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
 #endif  // !NDEBUG
-      FileOptions fo_copy = file_options;
-      fo_copy.write_hint = write_hint;
-      IOStatus io_s = NewWritableFile(fs, fname, &file, fo_copy);
+      IOStatus io_s = NewWritableFile(fs, fname, &file, file_options);
       assert(s.ok());
       s = io_s;
       if (io_status->ok()) {
@@ -164,13 +164,11 @@ Status BuildTable(
 
       table_file_created = true;
       FileTypeSet tmp_set = ioptions.checksum_handoff_file_types;
-      file->SetIOPriority(tboptions.write_options.rate_limiter_priority);
-      // Subsequent attempts to override the hint via SetWriteLifeTimeHint
-      // with the very same value will be ignored by the fs.
-      file->SetWriteLifeTimeHint(fo_copy.write_hint);
+      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));
 
@@ -190,16 +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(),
@@ -210,61 +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));
@@ -282,7 +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_,
@@ -294,7 +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);
           }
@@ -313,17 +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_time_mapping_str;
+      seqno_to_time_mapping.Encode(
+          seqno_time_mapping_str, meta->fd.smallest_seqno,
+          meta->fd.largest_seqno, meta->file_creation_time);
       builder->SetSeqnoTimeTableProperties(
-          relevant_mapping,
+          seqno_time_mapping_str,
           ioptions.compaction_style == CompactionStyle::kCompactionStyleFIFO
               ? meta->file_creation_time
               : meta->oldest_ancester_time);
@@ -370,16 +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.
@@ -423,8 +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,
@@ -432,10 +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
@@ -460,22 +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

@@ -45,8 +45,6 @@
 #include "rocksdb/utilities/transaction_db.h"
 #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 +114,6 @@ 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;
@@ -128,7 +125,6 @@ using ROCKSDB_NAMESPACE::WALRecoveryMode;
 using ROCKSDB_NAMESPACE::WritableFile;
 using ROCKSDB_NAMESPACE::WriteBatch;
 using ROCKSDB_NAMESPACE::WriteBatchWithIndex;
-using ROCKSDB_NAMESPACE::WriteBufferManager;
 using ROCKSDB_NAMESPACE::WriteOptions;
 
 using std::unordered_set;
@@ -223,15 +219,11 @@ struct rocksdb_memory_allocator_t {
 struct rocksdb_cache_t {
   std::shared_ptr<Cache> rep;
 };
-struct rocksdb_write_buffer_manager_t {
-  std::shared_ptr<WriteBufferManager> rep;
-};
 struct rocksdb_livefiles_t {
   std::vector<LiveFileMetaData> rep;
 };
 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 +439,7 @@ 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 +468,8 @@ 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 +523,6 @@ 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 +538,6 @@ 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 +879,9 @@ 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 +898,6 @@ 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 +912,9 @@ 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 +928,6 @@ 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 +946,9 @@ 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 +963,6 @@ 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 +978,9 @@ 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 +996,6 @@ 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 +1027,6 @@ 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 +1064,6 @@ 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 +1074,7 @@ 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 +1087,6 @@ 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 +1106,6 @@ 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 +1127,9 @@ 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 +1365,6 @@ 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 +1680,6 @@ 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)) {
@@ -1838,24 +1757,8 @@ 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);
 }
 
 const rocksdb_livefiles_t* rocksdb_livefiles(rocksdb_t* db) {
@@ -1964,8 +1867,9 @@ 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,
@@ -2031,10 +1935,6 @@ 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;
 }
@@ -2046,15 +1946,6 @@ 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(); }
@@ -2282,32 +2173,6 @@ 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),
@@ -2320,21 +2185,6 @@ 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();
@@ -2361,35 +2211,6 @@ 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;
@@ -2912,24 +2733,6 @@ 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;
 }
@@ -2974,9 +2777,7 @@ 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));
 }
 
@@ -2985,9 +2786,7 @@ 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));
 }
 
@@ -3105,42 +2904,6 @@ void rocksdb_options_set_db_paths(rocksdb_options_t* opt,
   opt->rep.db_paths = db_paths;
 }
 
-void rocksdb_options_set_cf_paths(rocksdb_options_t* opt,
-                                  const rocksdb_dbpath_t** dbpath_values,
-                                  size_t num_paths) {
-  std::vector<DbPath> cf_paths(num_paths);
-  for (size_t i = 0; i < num_paths; ++i) {
-    cf_paths[i] = dbpath_values[i]->rep;
-  }
-  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);
 }
@@ -3151,12 +2914,6 @@ 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);
 }
@@ -3178,11 +2935,6 @@ void rocksdb_options_set_write_buffer_size(rocksdb_options_t* opt, size_t s) {
   opt->rep.write_buffer_size = s;
 }
 
-void rocksdb_options_set_write_buffer_manager(
-    rocksdb_options_t* opt, rocksdb_write_buffer_manager_t* wbm) {
-  opt->rep.write_buffer_manager = wbm->rep;
-}
-
 size_t rocksdb_options_get_write_buffer_size(rocksdb_options_t* opt) {
   return opt->rep.write_buffer_size;
 }
@@ -3277,24 +3029,6 @@ 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;
-}
-
-uint64_t rocksdb_options_get_periodic_compaction_seconds(
-    rocksdb_options_t* opt) {
-  return opt->rep.periodic_compaction_seconds;
-}
-
 void rocksdb_options_enable_statistics(rocksdb_options_t* opt) {
   opt->rep.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
 }
@@ -3347,7 +3081,7 @@ 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;
 }
@@ -3719,6 +3453,35 @@ 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;
@@ -4061,36 +3824,6 @@ 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;
@@ -4154,14 +3887,6 @@ 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) {
@@ -4232,26 +3957,6 @@ rocksdb_ratelimiter_t* rocksdb_ratelimiter_create(int64_t rate_bytes_per_sec,
   return rate_limiter;
 }
 
-rocksdb_ratelimiter_t* rocksdb_ratelimiter_create_auto_tuned(
-    int64_t rate_bytes_per_sec, int64_t refill_period_us, int32_t fairness) {
-  rocksdb_ratelimiter_t* rate_limiter = new rocksdb_ratelimiter_t;
-  rate_limiter->rep.reset(NewGenericRateLimiter(rate_bytes_per_sec,
-                                                refill_period_us, fairness,
-                                                RateLimiter::Mode::kWritesOnly,
-                                                true));  // 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;
 }
@@ -4470,8 +4175,13 @@ 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
@@ -4843,7 +4553,7 @@ 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();
 }
@@ -4996,35 +4706,6 @@ int rocksdb_compactoptions_get_target_level(rocksdb_compactoptions_t* opt) {
   return opt->rep.target_level;
 }
 
-void rocksdb_compactoptions_set_target_path_id(rocksdb_compactoptions_t* opt,
-                                               int n) {
-  opt->rep.target_path_id = n;
-}
-
-int rocksdb_compactoptions_get_target_path_id(rocksdb_compactoptions_t* opt) {
-  return opt->rep.target_path_id;
-}
-
-void rocksdb_compactoptions_set_allow_write_stall(rocksdb_compactoptions_t* opt,
-                                                  unsigned char v) {
-  opt->rep.allow_write_stall = v;
-}
-
-unsigned char rocksdb_compactoptions_get_allow_write_stall(
-    rocksdb_compactoptions_t* opt) {
-  return opt->rep.allow_write_stall;
-}
-
-void rocksdb_compactoptions_set_max_subcompactions(
-    rocksdb_compactoptions_t* opt, int n) {
-  opt->rep.max_subcompactions = n;
-}
-
-int rocksdb_compactoptions_get_max_subcompactions(
-    rocksdb_compactoptions_t* opt) {
-  return opt->rep.max_subcompactions;
-}
-
 void rocksdb_compactoptions_set_full_history_ts_low(
     rocksdb_compactoptions_t* opt, char* ts, size_t tslen) {
   if (ts == nullptr) {
@@ -5185,60 +4866,6 @@ size_t rocksdb_cache_get_occupancy_count(const rocksdb_cache_t* cache) {
   return cache->rep->GetOccupancyCount();
 }
 
-rocksdb_write_buffer_manager_t* rocksdb_write_buffer_manager_create(
-    size_t buffer_size, bool allow_stall) {
-  rocksdb_write_buffer_manager_t* wbm = new rocksdb_write_buffer_manager_t;
-  wbm->rep.reset(new WriteBufferManager(buffer_size, {}, allow_stall));
-  return wbm;
-}
-
-rocksdb_write_buffer_manager_t* rocksdb_write_buffer_manager_create_with_cache(
-    size_t buffer_size, const rocksdb_cache_t* cache, bool allow_stall) {
-  rocksdb_write_buffer_manager_t* wbm = new rocksdb_write_buffer_manager_t;
-  wbm->rep.reset(new WriteBufferManager(buffer_size, cache->rep, allow_stall));
-  return wbm;
-}
-
-void rocksdb_write_buffer_manager_destroy(rocksdb_write_buffer_manager_t* wbm) {
-  delete wbm;
-}
-
-bool rocksdb_write_buffer_manager_enabled(rocksdb_write_buffer_manager_t* wbm) {
-  return wbm->rep->enabled();
-}
-
-bool rocksdb_write_buffer_manager_cost_to_cache(
-    rocksdb_write_buffer_manager_t* wbm) {
-  return wbm->rep->cost_to_cache();
-}
-
-size_t rocksdb_write_buffer_manager_memory_usage(
-    rocksdb_write_buffer_manager_t* wbm) {
-  return wbm->rep->memory_usage();
-}
-
-size_t rocksdb_write_buffer_manager_mutable_memtable_memory_usage(
-    rocksdb_write_buffer_manager_t* wbm) {
-  return wbm->rep->mutable_memtable_memory_usage();
-}
-
-size_t rocksdb_write_buffer_manager_dummy_entries_in_cache_usage(
-    rocksdb_write_buffer_manager_t* wbm) {
-  return wbm->rep->dummy_entries_in_cache_usage();
-}
-size_t rocksdb_write_buffer_manager_buffer_size(
-    rocksdb_write_buffer_manager_t* wbm) {
-  return wbm->rep->buffer_size();
-}
-void rocksdb_write_buffer_manager_set_buffer_size(
-    rocksdb_write_buffer_manager_t* wbm, size_t new_size) {
-  wbm->rep->SetBufferSize(new_size);
-}
-ROCKSDB_LIBRARY_API void rocksdb_write_buffer_manager_set_allow_stall(
-    rocksdb_write_buffer_manager_t* wbm, bool new_allow_stall) {
-  wbm->rep->SetAllowStall(new_allow_stall);
-}
-
 rocksdb_dbpath_t* rocksdb_dbpath_create(const char* path,
                                         uint64_t target_size) {
   rocksdb_dbpath_t* result = new rocksdb_dbpath_t;
@@ -5321,9 +4948,7 @@ 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;
 }
 
@@ -5707,7 +5332,9 @@ 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,
@@ -5787,7 +5414,7 @@ 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));
@@ -5837,11 +5464,6 @@ char* rocksdb_sst_file_metadata_get_relative_filename(
   return strdup(file_meta->rep->relative_filename.c_str());
 }
 
-char* rocksdb_sst_file_metadata_get_directory(
-    rocksdb_sst_file_metadata_t* file_meta) {
-  return strdup(file_meta->rep->directory.c_str());
-}
-
 uint64_t rocksdb_sst_file_metadata_get_size(
     rocksdb_sst_file_metadata_t* file_meta) {
   return file_meta->rep->size;
@@ -5977,7 +5599,6 @@ 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;
 }
 
@@ -6003,9 +5624,9 @@ 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;
@@ -6020,7 +5641,6 @@ 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;
@@ -6798,9 +6418,9 @@ 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;
@@ -6815,7 +6435,6 @@ 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);
@@ -794,16 +713,6 @@ int main(int argc, char** argv) {
   rocksdb_options_set_ratelimiter(options, rate_limiter);
   rocksdb_ratelimiter_destroy(rate_limiter);
 
-  rate_limiter =
-      rocksdb_ratelimiter_create_auto_tuned(1000 * 1024 * 1024, 100 * 1000, 10);
-  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 +782,6 @@ 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 +802,6 @@ 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 +817,6 @@ 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 +825,7 @@ 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 +836,6 @@ 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 +873,9 @@ 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 +934,7 @@ 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 +1308,6 @@ 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);
@@ -1668,20 +1474,10 @@ int main(int argc, char** argv) {
     CheckCondition(cflen == 2);
     rocksdb_list_column_families_destroy(column_fams, cflen);
 
-    rocksdb_options_t* cf_options_1 = rocksdb_options_create();
-    rocksdb_options_t* cf_options_2 = rocksdb_options_create();
-
-    // use dbpathname2 as the cf_path for "cf1"
-    rocksdb_dbpath_t* dbpath2;
-    char dbpathname2[200];
-    snprintf(dbpathname2, sizeof(dbpathname2), "%s/rocksdb_c_test-%d-dbpath2",
-             GetTempDir(), ((int)geteuid()));
-    dbpath2 = rocksdb_dbpath_create(dbpathname2, 1024 * 1024);
-    const rocksdb_dbpath_t* cf_paths[1] = {dbpath2};
-    rocksdb_options_set_cf_paths(cf_options_2, cf_paths, 1);
+    rocksdb_options_t* cf_options = rocksdb_options_create();
 
     const char* cf_names[2] = {"default", "cf1"};
-    const rocksdb_options_t* cf_opts[2] = {cf_options_1, cf_options_2};
+    const rocksdb_options_t* cf_opts[2] = {cf_options, cf_options};
     rocksdb_column_family_handle_t* handles[2];
 
     LoadAndCheckLatestOptions(dbname, env, false, cache, NULL, 2, cf_names,
@@ -1709,37 +1505,6 @@ int main(int argc, char** argv) {
     rocksdb_flushoptions_t* flush_options = rocksdb_flushoptions_create();
     rocksdb_flushoptions_set_wait(flush_options, 1);
     rocksdb_flush_cf(db, flush_options, handles[1], &err);
-
-    // make sure all files in "cf1" are under the specified cf path
-    {
-      rocksdb_column_family_metadata_t* cf_meta =
-          rocksdb_get_column_family_metadata_cf(db, handles[1]);
-      size_t cf_file_count = rocksdb_column_family_metadata_get_size(cf_meta);
-      assert(cf_file_count > 0);
-      size_t level_count =
-          rocksdb_column_family_metadata_get_level_count(cf_meta);
-      assert(level_count > 0);
-      for (size_t l = 0; l < level_count; ++l) {
-        rocksdb_level_metadata_t* level_meta =
-            rocksdb_column_family_metadata_get_level_metadata(cf_meta, l);
-        assert(level_meta);
-
-        size_t file_count = rocksdb_level_metadata_get_file_count(level_meta);
-        for (size_t f = 0; f < file_count; ++f) {
-          rocksdb_sst_file_metadata_t* file_meta =
-              rocksdb_level_metadata_get_sst_file_metadata(level_meta, f);
-          assert(file_meta);
-          char* file_path = rocksdb_sst_file_metadata_get_directory(file_meta);
-          assert(strcmp(file_path, dbpathname2) == 0);
-          Free(&file_path);
-          rocksdb_sst_file_metadata_destroy(file_meta);
-        }
-        rocksdb_level_metadata_destroy(level_meta);
-      }
-
-      rocksdb_column_family_metadata_destroy(cf_meta);
-    }
-
     CheckNoError(err) rocksdb_flushoptions_destroy(flush_options);
 
     CheckGetCF(db, roptions, handles[1], "foo", "hello");
@@ -1772,21 +1537,6 @@ 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);
@@ -1918,9 +1668,7 @@ int main(int argc, char** argv) {
     }
     rocksdb_destroy_db(options, dbname, &err);
     rocksdb_options_destroy(db_options);
-    rocksdb_options_destroy(cf_options_1);
-    rocksdb_options_destroy(cf_options_2);
-    rocksdb_dbpath_destroy(dbpath2);
+    rocksdb_options_destroy(cf_options);
   }
 
   StartPhase("prefix");
@@ -2125,13 +1873,6 @@ int main(int argc, char** argv) {
     CheckCondition(2.0 ==
                    rocksdb_options_get_max_bytes_for_level_multiplier(o));
 
-    rocksdb_options_set_periodic_compaction_seconds(o, 100000);
-    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 +1979,9 @@ 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 +2052,6 @@ 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 +2074,6 @@ 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 +2176,8 @@ 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));
@@ -2566,16 +2303,6 @@ int main(int argc, char** argv) {
     CheckCondition(2.0 ==
                    rocksdb_options_get_max_bytes_for_level_multiplier(o));
 
-    rocksdb_options_set_periodic_compaction_seconds(copy, 8000);
-    CheckCondition(8000 ==
-                   rocksdb_options_get_periodic_compaction_seconds(copy));
-    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 +2450,11 @@ 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 +2553,6 @@ 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));
@@ -2938,15 +2666,6 @@ int main(int argc, char** argv) {
     rocksdb_compactoptions_set_target_level(co, 1);
     CheckCondition(1 == rocksdb_compactoptions_get_target_level(co));
 
-    rocksdb_compactoptions_set_target_path_id(co, 1);
-    CheckCondition(1 == rocksdb_compactoptions_get_target_path_id(co));
-
-    rocksdb_compactoptions_set_allow_write_stall(co, 1);
-    CheckCondition(1 == rocksdb_compactoptions_get_allow_write_stall(co));
-
-    rocksdb_compactoptions_set_max_subcompactions(co, 1);
-    CheckCondition(1 == rocksdb_compactoptions_get_max_subcompactions(co));
-
     rocksdb_compactoptions_destroy(co);
   }
 
@@ -3004,30 +2723,6 @@ 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;
@@ -3934,7 +3629,7 @@ 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 =
@@ -4028,30 +3723,6 @@ int main(int argc, char** argv) {
     rocksdb_wait_for_compact_options_destroy(wco);
   }
 
-  StartPhase("write_buffer_manager");
-  {
-    rocksdb_cache_t* lru;
-    lru = rocksdb_cache_create_lru(100);
-
-    rocksdb_write_buffer_manager_t* write_buffer_manager;
-    write_buffer_manager =
-        rocksdb_write_buffer_manager_create_with_cache(200, lru, false);
-
-    CheckCondition(true ==
-                   rocksdb_write_buffer_manager_enabled(write_buffer_manager));
-    CheckCondition(true == rocksdb_write_buffer_manager_cost_to_cache(
-                               write_buffer_manager));
-    CheckCondition(
-        200 == rocksdb_write_buffer_manager_buffer_size(write_buffer_manager));
-
-    rocksdb_write_buffer_manager_set_buffer_size(write_buffer_manager, 300);
-    CheckCondition(
-        300 == rocksdb_write_buffer_manager_buffer_size(write_buffer_manager));
-
-    rocksdb_write_buffer_manager_destroy(write_buffer_manager);
-    rocksdb_cache_destroy(lru);
-  }
-
   StartPhase("cancel_all_background_work");
   rocksdb_cancel_all_background_work(db, 1);
 

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

@@ -53,7 +53,7 @@ ColumnFamilyHandleImpl::ColumnFamilyHandleImpl(
 
 ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
   if (cfd_ != nullptr) {
-    for (auto& listener : cfd_->ioptions().listeners) {
+    for (auto& listener : cfd_->ioptions()->listeners) {
       listener->OnColumnFamilyHandleDeletionStarted(this);
     }
     // Job id == 0 means that this is not our background process, but rather
@@ -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]));
   }
 }
@@ -168,8 +168,7 @@ Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options) {
   }
   if (!cf_options.memtable_factory->IsInsertConcurrentlySupported()) {
     return Status::InvalidArgument(
-        "Memtable doesn't allow concurrent writes "
-        "(allow_concurrent_memtable_write)");
+        "Memtable doesn't concurrent writes (allow_concurrent_memtable_write)");
   }
   return Status::OK();
 }
@@ -200,9 +199,8 @@ const uint64_t kDefaultTtl = 0xfffffffffffffffe;
 const uint64_t kDefaultPeriodicCompSecs = 0xfffffffffffffffe;
 }  // anonymous namespace
 
-ColumnFamilyOptions SanitizeCfOptions(const ImmutableDBOptions& db_options,
-                                      bool read_only,
-                                      const ColumnFamilyOptions& src) {
+ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
+                                    const ColumnFamilyOptions& src) {
   ColumnFamilyOptions result = src;
   size_t clamp_max = std::conditional<
       sizeof(size_t) == 4, std::integral_constant<size_t, 0xffffffff>,
@@ -241,10 +239,6 @@ ColumnFamilyOptions SanitizeCfOptions(const ImmutableDBOptions& db_options,
 
     result.min_write_buffer_number_to_merge = 1;
   }
-  if (result.disallow_memtable_writes) {
-    // A simple memtable that enforces MarkReadOnly (unlike skip list)
-    result.memtable_factory = std::make_shared<VectorRepFactory>();
-  }
 
   if (result.num_levels < 1) {
     result.num_levels = 1;
@@ -328,8 +322,8 @@ ColumnFamilyOptions SanitizeCfOptions(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,
@@ -364,16 +358,16 @@ ColumnFamilyOptions SanitizeCfOptions(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;
     }
@@ -417,13 +411,6 @@ ColumnFamilyOptions SanitizeCfOptions(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
@@ -441,18 +428,6 @@ ColumnFamilyOptions SanitizeCfOptions(const ImmutableDBOptions& db_options,
     result.periodic_compaction_seconds = 0;
   }
 
-  if (read_only && (result.preserve_internal_time_seconds > 0 ||
-                    result.preclude_last_level_data_seconds > 0)) {
-    // With no writes coming in, we don't need periodic SeqnoToTime entries.
-    // Existing SST files may or may not have that info associated with them.
-    ROCKS_LOG_WARN(
-        db_options.info_log.get(),
-        "preserve_internal_time_seconds and preclude_last_level_data_seconds "
-        "are ignored in read-only DB");
-    result.preserve_internal_time_seconds = 0;
-    result.preclude_last_level_data_seconds = 0;
-  }
-
   return result;
 }
 
@@ -484,7 +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());
@@ -495,32 +470,18 @@ 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();
   current->Ref();
   refs.store(1, std::memory_order_relaxed);
-
-  // There should be at least one mapping entry iff time tracking is enabled.
-#ifndef NDEBUG
-  MinAndMaxPreserveSeconds preserve_info{mutable_cf_options};
-  if (preserve_info.IsEnabled()) {
-    assert(seqno_to_time_mapping);
-    assert(!seqno_to_time_mapping->Empty());
-  } else {
-    assert(seqno_to_time_mapping == nullptr);
-  }
-#endif  // NDEBUG
 }
 
 namespace {
@@ -559,7 +520,7 @@ ColumnFamilyData::ColumnFamilyData(
     const FileOptions* file_options, ColumnFamilySet* column_family_set,
     BlockCacheTracer* const block_cache_tracer,
     const std::shared_ptr<IOTracer>& io_tracer, const std::string& db_id,
-    const std::string& db_session_id, bool read_only)
+    const std::string& db_session_id)
     : id_(id),
       name_(name),
       dummy_versions_(_dummy_versions),
@@ -567,9 +528,8 @@ ColumnFamilyData::ColumnFamilyData(
       refs_(0),
       initialized_(false),
       dropped_(false),
-      flush_skip_reschedule_(false),
       internal_comparator_(cf_options.comparator),
-      initial_cf_options_(SanitizeCfOptions(db_options, read_only, cf_options)),
+      initial_cf_options_(SanitizeOptions(db_options, cf_options)),
       ioptions_(db_options, initial_cf_options_),
       mutable_cf_options_(initial_cf_options_),
       is_delete_range_supported_(
@@ -612,7 +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) {
@@ -622,10 +582,10 @@ ColumnFamilyData::ColumnFamilyData(
                                       block_cache_tracer, io_tracer,
                                       db_session_id));
     blob_file_cache_.reset(
-        new BlobFileCache(_table_cache, &ioptions(), soptions(), id_,
+        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(
@@ -722,9 +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;
   }
 
@@ -873,8 +833,8 @@ std::unique_ptr<WriteControllerToken> SetupDelay(
   return write_controller->GetDelayToken(write_rate);
 }
 
-int GetL0FileCountForCompactionSpeedup(int level0_file_num_compaction_trigger,
-                                       int level0_slowdown_writes_trigger) {
+int GetL0ThresholdSpeedupCompaction(int level0_file_num_compaction_trigger,
+                                    int level0_slowdown_writes_trigger) {
   // SanitizeOptions() ensures it.
   assert(level0_file_num_compaction_trigger <= level0_slowdown_writes_trigger);
 
@@ -904,47 +864,6 @@ int GetL0FileCountForCompactionSpeedup(int level0_file_num_compaction_trigger,
     return static_cast<int>(res);
   }
 }
-
-uint64_t GetPendingCompactionBytesForCompactionSpeedup(
-    const MutableCFOptions& mutable_cf_options,
-    const VersionStorageInfo* vstorage) {
-  // Compaction debt relatively large compared to the stable (bottommost) data
-  // size indicates compaction fell behind.
-  const uint64_t kBottommostSizeDivisor = 8;
-  // Meaningful progress toward the slowdown trigger is another good indication.
-  const uint64_t kSlowdownTriggerDivisor = 4;
-
-  uint64_t bottommost_files_size = 0;
-  for (const auto& level_and_file : vstorage->BottommostFiles()) {
-    bottommost_files_size += level_and_file.second->fd.GetFileSize();
-  }
-
-  // Slowdown trigger might be zero but that means compaction speedup should
-  // always happen (undocumented/historical), so no special treatment is needed.
-  uint64_t slowdown_threshold =
-      mutable_cf_options.soft_pending_compaction_bytes_limit /
-      kSlowdownTriggerDivisor;
-
-  // Size of zero, however, should not be used to decide to speedup compaction.
-  if (bottommost_files_size == 0) {
-    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);
-  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>
@@ -997,7 +916,7 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
     auto write_stall_condition_and_cause = GetWriteStallConditionAndCause(
         imm()->NumNotFlushed(), vstorage->l0_delay_trigger_count(),
         vstorage->estimated_compaction_needed_bytes(), mutable_cf_options,
-        ioptions());
+        *ioptions());
     write_stall_condition = write_stall_condition_and_cause.first;
     auto write_stall_cause = write_stall_condition_and_cause.second;
 
@@ -1100,7 +1019,7 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
     } else {
       assert(write_stall_condition == WriteStallCondition::kNormal);
       if (vstorage->l0_delay_trigger_count() >=
-          GetL0FileCountForCompactionSpeedup(
+          GetL0ThresholdSpeedupCompaction(
               mutable_cf_options.level0_file_num_compaction_trigger,
               mutable_cf_options.level0_slowdown_writes_trigger)) {
         write_controller_token_ =
@@ -1110,32 +1029,22 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
             "[%s] Increasing compaction threads because we have %d level-0 "
             "files ",
             name_.c_str(), vstorage->l0_delay_trigger_count());
-      } else if (mutable_cf_options.soft_pending_compaction_bytes_limit == 0) {
+      } else if (vstorage->estimated_compaction_needed_bytes() >=
+                 mutable_cf_options.soft_pending_compaction_bytes_limit / 4) {
+        // Increase compaction threads if bytes needed for compaction exceeds
+        // 1/4 of threshold for slowing down.
         // If soft pending compaction byte limit is not set, always speed up
         // compaction.
         write_controller_token_ =
             write_controller->GetCompactionPressureToken();
-      } else if (vstorage->estimated_compaction_needed_bytes() >=
-                 GetPendingCompactionBytesForCompactionSpeedup(
-                     mutable_cf_options, vstorage)) {
-        write_controller_token_ =
-            write_controller->GetCompactionPressureToken();
-        ROCKS_LOG_INFO(
-            ioptions_.logger,
-            "[%s] Increasing compaction threads because of estimated pending "
-            "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()));
+        if (mutable_cf_options.soft_pending_compaction_bytes_limit > 0) {
+          ROCKS_LOG_INFO(
+              ioptions_.logger,
+              "[%s] Increasing compaction threads because of estimated pending "
+              "compaction "
+              "bytes %" PRIu64,
+              name_.c_str(), vstorage->estimated_compaction_needed_bytes());
+        }
       } else {
         write_controller_token_.reset();
       }
@@ -1189,13 +1098,12 @@ MemTable* ColumnFamilyData::ConstructNewMemtable(
                       write_buffer_manager_, earliest_seq, id_);
 }
 
-void ColumnFamilyData::CreateNewMemtable(SequenceNumber earliest_seq) {
+void ColumnFamilyData::CreateNewMemtable(
+    const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
   if (mem_ != nullptr) {
     delete mem_->Unref();
   }
-  // NOTE: db mutex must be locked for SetMemtable, so safe for
-  // GetLatestMutableCFOptions
-  SetMemtable(ConstructNewMemtable(GetLatestMutableCFOptions(), earliest_seq));
+  SetMemtable(ConstructNewMemtable(mutable_cf_options, earliest_seq));
   mem_->Ref();
 }
 
@@ -1206,12 +1114,10 @@ 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_);
   }
@@ -1226,24 +1132,21 @@ 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);
@@ -1273,8 +1176,7 @@ 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)) {
@@ -1368,20 +1270,18 @@ bool ColumnFamilyData::ReturnThreadLocalSuperVersion(SuperVersion* sv) {
   return false;
 }
 
-void ColumnFamilyData::InstallSuperVersion(
-    SuperVersionContext* sv_context, InstrumentedMutex* db_mutex,
-    std::optional<std::shared_ptr<SeqnoToTimeMapping>>
-        new_seqno_to_time_mapping) {
+void ColumnFamilyData::InstallSuperVersion(SuperVersionContext* sv_context,
+                                           InstrumentedMutex* db_mutex) {
   db_mutex->AssertHeld();
+  return InstallSuperVersion(sv_context, mutable_cf_options_);
+}
 
+void ColumnFamilyData::InstallSuperVersion(
+    SuperVersionContext* sv_context,
+    const MutableCFOptions& mutable_cf_options) {
   SuperVersion* new_superversion = sv_context->new_superversion.release();
-  new_superversion->mutable_cf_options = GetLatestMutableCFOptions();
-  new_superversion->Init(this, mem_, imm_.current(), current_,
-                         new_seqno_to_time_mapping.has_value()
-                             ? std::move(new_seqno_to_time_mapping.value())
-                         : super_version_
-                             ? super_version_->ShareSeqnoToTimeMapping()
-                             : nullptr);
+  new_superversion->mutable_cf_options = mutable_cf_options;
+  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() ||
@@ -1391,7 +1291,7 @@ void ColumnFamilyData::InstallSuperVersion(
     // currently RecalculateWriteStallConditions() treats it as further slowing
     // down is needed.
     super_version_->write_stall_condition =
-        RecalculateWriteStallConditions(new_superversion->mutable_cf_options);
+        RecalculateWriteStallConditions(mutable_cf_options);
   } else {
     super_version_->write_stall_condition =
         old_superversion->write_stall_condition;
@@ -1404,15 +1304,14 @@ void ColumnFamilyData::InstallSuperVersion(
     ResetThreadLocalSuperVersions();
 
     if (old_superversion->mutable_cf_options.write_buffer_size !=
-        new_superversion->mutable_cf_options.write_buffer_size) {
-      mem_->UpdateWriteBufferSize(
-          new_superversion->mutable_cf_options.write_buffer_size);
+        mutable_cf_options.write_buffer_size) {
+      mem_->UpdateWriteBufferSize(mutable_cf_options.write_buffer_size);
     }
     if (old_superversion->write_stall_condition !=
         new_superversion->write_stall_condition) {
       sv_context->PushWriteStallNotification(
           old_superversion->write_stall_condition,
-          new_superversion->write_stall_condition, GetName(), &ioptions());
+          new_superversion->write_stall_condition, GetName(), ioptions());
     }
     if (old_superversion->Unref()) {
       old_superversion->Cleanup();
@@ -1565,20 +1464,6 @@ 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;
 }
 
@@ -1589,11 +1474,6 @@ 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()) {
@@ -1606,6 +1486,28 @@ 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;
@@ -1641,19 +1543,6 @@ 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();
@@ -1671,9 +1560,6 @@ 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
@@ -1707,8 +1593,7 @@ ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
       dummy_cfd_(new ColumnFamilyData(
           ColumnFamilyData::kDummyColumnFamilyDataId, "", nullptr, nullptr,
           nullptr, ColumnFamilyOptions(), *db_options, &file_options_, nullptr,
-          block_cache_tracer, io_tracer, db_id, db_session_id,
-          /*read_only*/ true)),
+          block_cache_tracer, io_tracer, db_id, db_session_id)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
@@ -1780,12 +1665,12 @@ size_t ColumnFamilySet::NumberOfColumnFamilies() const {
 // under a DB mutex AND write thread
 ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
     const std::string& name, uint32_t id, Version* dummy_versions,
-    const ColumnFamilyOptions& options, bool read_only) {
+    const ColumnFamilyOptions& options) {
   assert(column_families_.find(name) == column_families_.end());
   ColumnFamilyData* new_cfd = new ColumnFamilyData(
       id, name, dummy_versions, table_cache_, write_buffer_manager_, options,
       *db_options_, &file_options_, this, block_cache_tracer_, io_tracer_,
-      db_id_, db_session_id_, read_only);
+      db_id_, db_session_id_);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   auto ucmp = new_cfd->user_comparator();
@@ -1863,17 +1748,4 @@ const Comparator* GetColumnFamilyUserComparator(
   return nullptr;
 }
 
-const ImmutableOptions& GetImmutableOptions(ColumnFamilyHandle* column_family) {
-  assert(column_family);
-
-  ColumnFamilyHandleImpl* const handle =
-      static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
-  assert(handle);
-
-  const ColumnFamilyData* const cfd = handle->cfd();
-  assert(cfd);
-
-  return cfd->ioptions();
-}
-
 }  // namespace ROCKSDB_NAMESPACE

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_;
@@ -207,10 +204,9 @@ 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;
-  // TODO: do we really need this in addition to what's in current Version?
   MutableCFOptions mutable_cf_options;
   // Version number of the current SuperVersion
   uint64_t version_number;
@@ -222,10 +218,6 @@ struct SuperVersion {
   // enable UDT feature, this is an empty string.
   std::string full_history_ts_low;
 
-  // An immutable snapshot of the DB's seqno to time mapping, usually shared
-  // between SuperVersions.
-  std::shared_ptr<const SeqnoToTimeMapping> seqno_to_time_mapping{nullptr};
-
   // should be called outside the mutex
   SuperVersion() = default;
   ~SuperVersion();
@@ -239,23 +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
@@ -271,25 +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 SanitizeCfOptions(const ImmutableDBOptions& db_options,
-                                      bool read_only,
-                                      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;
 
@@ -333,10 +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; }
 
@@ -345,17 +318,17 @@ class ColumnFamilyData {
 
   // thread-safe
   const FileOptions* soptions() const;
-  const ImmutableOptions& ioptions() const { return ioptions_; }
+  const ImmutableOptions* ioptions() const { return &ioptions_; }
   // REQUIRES: DB mutex held
   // This returns the MutableCFOptions used by current SuperVersion
   // You should use this API to reference MutableCFOptions most of the time.
-  const MutableCFOptions& GetCurrentMutableCFOptions() const {
-    return super_version_->mutable_cf_options;
+  const MutableCFOptions* GetCurrentMutableCFOptions() const {
+    return &(super_version_->mutable_cf_options);
   }
   // REQUIRES: DB mutex held
   // This returns the latest MutableCFOptions, which may be not in effect yet.
-  const MutableCFOptions& GetLatestMutableCFOptions() const {
-    return mutable_cf_options_;
+  const MutableCFOptions* GetLatestMutableCFOptions() const {
+    return &mutable_cf_options_;
   }
 
   // REQUIRES: DB mutex held
@@ -382,49 +355,38 @@ class ColumnFamilyData {
     return mem()->GetFirstSequenceNumber() == 0 && imm()->NumNotFlushed() == 0;
   }
 
+  Version* current() { return current_; }
   Version* dummy_versions() { return dummy_versions_; }
-  Version* current() { return current_; }  // REQUIRE: DB mutex held
-  void SetCurrent(Version* _current);      // REQUIRE: DB mutex held
-  uint64_t GetNumLiveVersions() const;     // REQUIRE: DB mutex held
-  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 SetCurrent(Version* _current);
+  uint64_t GetNumLiveVersions() const;    // REQUIRE: DB mutex held
+  uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
+  uint64_t GetLiveSstFilesSize() const;   // REQUIRE: DB mutex held
+  uint64_t GetTotalBlobFileSize() const;  // 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;
-    if (ioptions_.disallow_memtable_writes) {
-      mem_->MarkImmutable();
-    }
-  }
-
-  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();
 
   // See Memtable constructor for explanation of earliest_seq param.
-  // `mutable_cf_options` might need to be a saved copy if calling this without
-  // holding the DB mutex.
   MemTable* ConstructNewMemtable(const MutableCFOptions& mutable_cf_options,
                                  SequenceNumber earliest_seq);
-  void CreateNewMemtable(SequenceNumber earliest_seq);
+  void CreateNewMemtable(const MutableCFOptions& mutable_cf_options,
+                         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
@@ -439,7 +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);
 
@@ -468,8 +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_; }
@@ -488,14 +450,15 @@ class ColumnFamilyData {
   uint64_t GetSuperVersionNumber() const {
     return super_version_number_.load();
   }
-  uint64_t GetSuperVersionNumberRelaxed() const {
-    return super_version_number_.load(std::memory_order_relaxed);
-  }
-  // Only intended for use by DBImpl::InstallSuperVersion() and variants
+  // will return a pointer to SuperVersion* if previous SuperVersion
+  // if its reference count is zero and needs deletion or nullptr if not
+  // As argument takes a pointer to allocated SuperVersion to enable
+  // the clients to allocate SuperVersion outside of mutex.
+  // IMPORTANT: Only call this from DBImpl::InstallSuperVersion()
   void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex,
-                           std::optional<std::shared_ptr<SeqnoToTimeMapping>>
-                               new_seqno_to_time_mapping = {});
+                           const MutableCFOptions& mutable_cf_options);
+  void InstallSuperVersion(SuperVersionContext* sv_context,
+                           InstrumentedMutex* db_mutex);
 
   void ResetThreadLocalSuperVersions();
 
@@ -525,6 +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(
@@ -584,20 +549,18 @@ 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, Version* dummy_versions,
-      Cache* table_cache, WriteBufferManager* write_buffer_manager,
-      const ColumnFamilyOptions& options, const ImmutableDBOptions& db_options,
-      const FileOptions* file_options, ColumnFamilySet* column_family_set,
-      BlockCacheTracer* const block_cache_tracer,
-      const std::shared_ptr<IOTracer>& io_tracer, const std::string& db_id,
-      const std::string& db_session_id, bool read_only);
+  ColumnFamilyData(uint32_t id, const std::string& name,
+                   Version* dummy_versions, Cache* table_cache,
+                   WriteBufferManager* write_buffer_manager,
+                   const ColumnFamilyOptions& options,
+                   const ImmutableDBOptions& db_options,
+                   const FileOptions* file_options,
+                   ColumnFamilySet* column_family_set,
+                   BlockCacheTracer* const block_cache_tracer,
+                   const std::shared_ptr<IOTracer>& io_tracer,
+                   const std::string& db_id, const std::string& db_session_id);
 
   std::vector<std::string> GetDbPaths() const;
 
@@ -610,17 +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_;
@@ -681,7 +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_;
@@ -759,8 +713,7 @@ class ColumnFamilySet {
 
   ColumnFamilyData* CreateColumnFamily(const std::string& name, uint32_t id,
                                        Version* dummy_version,
-                                       const ColumnFamilyOptions& options,
-                                       bool read_only);
+                                       const ColumnFamilyOptions& options);
 
   const UnorderedMap<uint32_t, size_t>& GetRunningColumnFamiliesTimestampSize()
       const {
@@ -901,17 +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_;
@@ -919,11 +872,9 @@ 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);
-
 }  // namespace ROCKSDB_NAMESPACE

db/compact_files_test.cc

@@ -3,6 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+
 #include <mutex>
 #include <string>
 #include <thread>
@@ -33,8 +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_);
@@ -44,7 +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;
@@ -158,9 +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);
     }
@@ -229,7 +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;
@@ -440,50 +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;
@@ -537,3 +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();
 
@@ -115,42 +115,6 @@ void Compaction::GetBoundaryKeys(
   }
 }
 
-void Compaction::GetBoundaryInternalKeys(
-    VersionStorageInfo* vstorage,
-    const std::vector<CompactionInputFiles>& inputs, InternalKey* smallest_key,
-    InternalKey* largest_key, int exclude_level) {
-  bool initialized = false;
-  const InternalKeyComparator* icmp = vstorage->InternalComparator();
-  for (size_t i = 0; i < inputs.size(); ++i) {
-    if (inputs[i].files.empty() || inputs[i].level == exclude_level) {
-      continue;
-    }
-    if (inputs[i].level == 0) {
-      // we need to consider all files on level 0
-      for (const auto* f : inputs[i].files) {
-        if (!initialized || icmp->Compare(f->smallest, *smallest_key) < 0) {
-          *smallest_key = f->smallest;
-        }
-        if (!initialized || icmp->Compare(f->largest, *largest_key) > 0) {
-          *largest_key = f->largest;
-        }
-        initialized = true;
-      }
-    } else {
-      // we only need to consider the first and last file
-      if (!initialized ||
-          icmp->Compare(inputs[i].files[0]->smallest, *smallest_key) < 0) {
-        *smallest_key = inputs[i].files[0]->smallest;
-      }
-      if (!initialized ||
-          icmp->Compare(inputs[i].files.back()->largest, *largest_key) > 0) {
-        *largest_key = inputs[i].files.back()->largest;
-      }
-      initialized = true;
-    }
-  }
-}
-
 std::vector<CompactionInputFiles> Compaction::PopulateWithAtomicBoundaries(
     VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs) {
   const Comparator* ucmp = vstorage->InternalComparator()->user_comparator();
@@ -162,9 +126,7 @@ 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 +245,9 @@ 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 +269,6 @@ 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"
@@ -332,22 +291,21 @@ Compaction::Compaction(
               : (_blob_garbage_collection_policy ==
                          BlobGarbageCollectionPolicy::kDisable
                      ? false
-                     : mutable_cf_options().enable_blob_garbage_collection)),
+                     : mutable_cf_options()->enable_blob_garbage_collection)),
       blob_garbage_collection_age_cutoff_(
           _blob_garbage_collection_age_cutoff < 0 ||
                   _blob_garbage_collection_age_cutoff > 1
-              ? mutable_cf_options().blob_garbage_collection_age_cutoff
+              ? mutable_cf_options()->blob_garbage_collection_age_cutoff
               : _blob_garbage_collection_age_cutoff),
-      proximal_level_(
-          // For simplicity, we don't support the concept of "proximal level"
+      penultimate_level_(
+          // For simplicity, we don't support the concept of "penultimate level"
           // with `CompactionReason::kExternalSstIngestion` and
           // `CompactionReason::kRefitLevel`
           _compaction_reason == CompactionReason::kExternalSstIngestion ||
                   _compaction_reason == CompactionReason::kRefitLevel
               ? Compaction::kInvalidLevel
-              : EvaluateProximalLevel(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 +316,11 @@ 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 +328,12 @@ 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_);
     }
   }
 
@@ -405,71 +360,48 @@ Compaction::Compaction(
     }
   }
 
-  PopulateProximalLevelOutputRange();
+  PopulatePenultimateLevelOutputRange();
 }
 
-void Compaction::PopulateProximalLevelOutputRange() {
+void Compaction::PopulatePenultimateLevelOutputRange() {
   if (!SupportsPerKeyPlacement()) {
-    assert(keep_in_last_level_through_seqno_ == kMaxSequenceNumber);
     return;
   }
 
   // exclude the last level, the range of all input levels is the safe range
   // of keys that can be moved up.
   int exclude_level = number_levels_ - 1;
-  proximal_output_range_type_ = ProximalOutputRangeType::kNonLastRange;
+  penultimate_output_range_type_ = PenultimateOutputRangeType::kNonLastRange;
 
-  // For universal compaction, the proximal_output_range could be extended if
-  // all proximal level files are included in the compaction (which includes
-  // the case that the proximal level is empty).
+  // For universal compaction, the penultimate_output_range could be extended if
+  // all penultimate level files are included in the compaction (which includes
+  // the case that the penultimate level is empty).
   if (immutable_options_.compaction_style == kCompactionStyleUniversal) {
     exclude_level = kInvalidLevel;
-    proximal_output_range_type_ = ProximalOutputRangeType::kFullRange;
-    std::set<uint64_t> proximal_inputs;
+    penultimate_output_range_type_ = PenultimateOutputRangeType::kFullRange;
+    std::set<uint64_t> penultimate_inputs;
     for (const auto& input_lvl : inputs_) {
-      if (input_lvl.level == proximal_level_) {
+      if (input_lvl.level == penultimate_level_) {
         for (const auto& file : input_lvl.files) {
-          proximal_inputs.emplace(file->fd.GetNumber());
+          penultimate_inputs.emplace(file->fd.GetNumber());
         }
       }
     }
-    auto proximal_files = input_vstorage_->LevelFiles(proximal_level_);
-    for (const auto& file : proximal_files) {
-      if (proximal_inputs.find(file->fd.GetNumber()) == proximal_inputs.end()) {
+    auto penultimate_files = input_vstorage_->LevelFiles(penultimate_level_);
+    for (const auto& file : penultimate_files) {
+      if (penultimate_inputs.find(file->fd.GetNumber()) ==
+          penultimate_inputs.end()) {
         exclude_level = number_levels_ - 1;
-        proximal_output_range_type_ = ProximalOutputRangeType::kNonLastRange;
+        penultimate_output_range_type_ =
+            PenultimateOutputRangeType::kNonLastRange;
         break;
       }
     }
   }
 
-  // FIXME: should make use of `proximal_output_range_type_`.
-  // FIXME: when last level's input range does not overlap with
-  //  proximal level, and proximal level input is empty,
-  //  this call will not set proximal_level_smallest_ or
-  //  proximal_level_largest_. No keys will be compacted up.
-  GetBoundaryInternalKeys(input_vstorage_, inputs_, &proximal_level_smallest_,
-                          &proximal_level_largest_, exclude_level);
-
-  if (proximal_output_range_type_ != ProximalOutputRangeType::kFullRange) {
-    // If not full range in proximal level, must keep everything already
-    // in the last level there, because moving it back up might cause
-    // overlap/placement issues that are difficult to resolve properly in the
-    // presence of range deletes
-    SequenceNumber max_last_level_seqno = 0;
-    for (const auto& input_lvl : inputs_) {
-      if (input_lvl.level == output_level_) {
-        for (const auto& file : input_lvl.files) {
-          max_last_level_seqno =
-              std::max(max_last_level_seqno, file->fd.largest_seqno);
-        }
-      }
-    }
-
-    keep_in_last_level_through_seqno_ = max_last_level_seqno;
-  } else {
-    keep_in_last_level_through_seqno_ = 0;
-  }
+  GetBoundaryKeys(input_vstorage_, inputs_,
+                  &penultimate_level_smallest_user_key_,
+                  &penultimate_level_largest_user_key_, exclude_level);
 }
 
 Compaction::~Compaction() {
@@ -482,23 +414,35 @@ Compaction::~Compaction() {
 }
 
 bool Compaction::SupportsPerKeyPlacement() const {
-  return proximal_level_ != kInvalidLevel;
+  return penultimate_level_ != kInvalidLevel;
 }
 
-int Compaction::GetProximalLevel() const { return proximal_level_; }
+int Compaction::GetPenultimateLevel() const { return penultimate_level_; }
 
 // smallest_key and largest_key include timestamps if user-defined timestamp is
 // enabled.
-bool Compaction::OverlapProximalLevelOutputRange(
+bool Compaction::OverlapPenultimateLevelOutputRange(
     const Slice& smallest_key, const Slice& largest_key) const {
   if (!SupportsPerKeyPlacement()) {
     return false;
   }
+  const Comparator* ucmp =
+      input_vstorage_->InternalComparator()->user_comparator();
 
-  // See FIXME in Compaction::PopulateProximalLevelOutputRange().
-  // We do not compact any key up in this case.
-  if (proximal_level_smallest_.size() == 0 ||
-      proximal_level_largest_.size() == 0) {
+  return ucmp->CompareWithoutTimestamp(
+             smallest_key, penultimate_level_largest_user_key_) <= 0 &&
+         ucmp->CompareWithoutTimestamp(
+             largest_key, penultimate_level_smallest_user_key_) >= 0;
+}
+
+// key includes timestamp if user-defined timestamp is enabled.
+bool Compaction::WithinPenultimateLevelOutputRange(const Slice& key) const {
+  if (!SupportsPerKeyPlacement()) {
+    return false;
+  }
+
+  if (penultimate_level_smallest_user_key_.empty() ||
+      penultimate_level_largest_user_key_.empty()) {
     return false;
   }
 
@@ -506,35 +450,9 @@ bool Compaction::OverlapProximalLevelOutputRange(
       input_vstorage_->InternalComparator()->user_comparator();
 
   return ucmp->CompareWithoutTimestamp(
-             smallest_key, proximal_level_largest_.user_key()) <= 0 &&
+             key, penultimate_level_smallest_user_key_) >= 0 &&
          ucmp->CompareWithoutTimestamp(
-             largest_key, proximal_level_smallest_.user_key()) >= 0;
-}
-
-// key includes timestamp if user-defined timestamp is enabled.
-void Compaction::TEST_AssertWithinProximalLevelOutputRange(
-    const Slice& user_key, bool expect_failure) const {
-#ifdef NDEBUG
-  (void)user_key;
-  (void)expect_failure;
-#else
-  assert(SupportsPerKeyPlacement());
-
-  assert(proximal_level_smallest_.size() > 0);
-  assert(proximal_level_largest_.size() > 0);
-
-  auto* cmp = input_vstorage_->user_comparator();
-
-  // op_type of a key can change during compaction, e.g. Merge -> Put.
-  if (!(cmp->Compare(user_key, proximal_level_smallest_.user_key()) >= 0)) {
-    assert(expect_failure);
-  } else if (!(cmp->Compare(user_key, proximal_level_largest_.user_key()) <=
-               0)) {
-    assert(expect_failure);
-  } else {
-    assert(!expect_failure);
-  }
-#endif
+             key, penultimate_level_largest_user_key_) <= 0;
 }
 
 bool Compaction::InputCompressionMatchesOutput() const {
@@ -588,7 +506,7 @@ bool Compaction::IsTrivialMove() const {
   // input files are non overlapping
   if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
       (output_level_ != 0) &&
-      (cfd_->ioptions().compaction_style == kCompactionStyleUniversal)) {
+      (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal)) {
     return is_trivial_move_;
   }
 
@@ -646,7 +564,7 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   if (bottommost_level_) {
     return true;
   } else if (output_level_ != 0 &&
-             cfd_->ioptions().compaction_style == kCompactionStyleLevel) {
+             cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
     // Maybe use binary search to find right entry instead of linear search?
     const Comparator* user_cmp = cfd_->user_comparator();
     for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
@@ -687,7 +605,7 @@ bool Compaction::KeyRangeNotExistsBeyondOutputLevel(
   if (bottommost_level_) {
     return true /* does not overlap */;
   } else if (output_level_ != 0 &&
-             cfd_->ioptions().compaction_style == kCompactionStyleLevel) {
+             cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
     const Comparator* user_cmp = cfd_->user_comparator();
     for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
       const std::vector<FileMetaData*>& files =
@@ -720,11 +638,12 @@ 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;
     }
   }
 }
@@ -768,7 +687,7 @@ 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);
 }
@@ -779,10 +698,8 @@ 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++) {
@@ -790,17 +707,9 @@ 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
@@ -823,15 +732,8 @@ 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;
     }
@@ -863,12 +765,12 @@ uint64_t Compaction::OutputFilePreallocationSize() const {
 }
 
 std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
-  if (!cfd_->ioptions().compaction_filter_factory) {
+  if (!cfd_->ioptions()->compaction_filter_factory) {
     return nullptr;
   }
 
   if (!cfd_->ioptions()
-           .compaction_filter_factory->ShouldFilterTableFileCreation(
+           ->compaction_filter_factory->ShouldFilterTableFileCreation(
                TableFileCreationReason::kCompaction)) {
     return nullptr;
   }
@@ -887,7 +789,7 @@ std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
         "for compaction.");
   }
 
-  return cfd_->ioptions().compaction_filter_factory->CreateCompactionFilter(
+  return cfd_->ioptions()->compaction_filter_factory->CreateCompactionFilter(
       context);
 }
 
@@ -914,15 +816,10 @@ 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 &&
-      cfd_->ioptions().compaction_style == kCompactionStyleLevel) {
+  if (cfd_->ioptions()->compaction_pri == kRoundRobin &&
+      cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
     return output_level_ > 0;
   }
 
@@ -930,9 +827,9 @@ bool Compaction::ShouldFormSubcompactions() const {
     return false;
   }
 
-  if (cfd_->ioptions().compaction_style == kCompactionStyleLevel) {
+  if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
     return (start_level_ == 0 || is_manual_compaction_) && output_level_ > 0;
-  } else if (cfd_->ioptions().compaction_style == kCompactionStyleUniversal) {
+  } else if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
     return number_levels_ > 1 && output_level_ > 0;
   } else {
     return false;
@@ -962,25 +859,6 @@ 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();
@@ -1014,9 +892,8 @@ uint64_t Compaction::MinInputFileEpochNumber() const {
   return min_epoch_number;
 }
 
-int Compaction::EvaluateProximalLevel(
+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
@@ -1029,26 +906,26 @@ int Compaction::EvaluateProximalLevel(
     return kInvalidLevel;
   }
 
-  int proximal_level = output_level - 1;
-  assert(proximal_level < immutable_options.num_levels);
-  if (proximal_level <= 0) {
+  int penultimate_level = output_level - 1;
+  assert(penultimate_level < immutable_options.num_levels);
+  if (penultimate_level <= 0) {
     return kInvalidLevel;
   }
 
-  // If the proximal level is not within input level -> output level range
-  // check if the proximal output level is empty, if it's empty, it could
-  // also be locked for the proximal output.
+  // If the penultimate level is not within input level -> output level range
+  // check if the penultimate output level is empty, if it's empty, it could
+  // also be locked for the penultimate output.
   // TODO: ideally, it only needs to check if there's a file within the
   //  compaction output key range. For simplicity, it just check if there's any
-  //  file on the proximal level.
+  //  file on the penultimate level.
   if (start_level == immutable_options.num_levels - 1 &&
       (immutable_options.compaction_style != kCompactionStyleUniversal ||
-       !vstorage->LevelFiles(proximal_level).empty())) {
+       !vstorage->LevelFiles(penultimate_level).empty())) {
     return kInvalidLevel;
   }
 
   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",
@@ -1057,73 +934,7 @@ int Compaction::EvaluateProximalLevel(
     return kInvalidLevel;
   }
 
-  return proximal_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_);
-  }
+  return penultimate_level;
 }
 
 }  // 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,
@@ -102,13 +98,13 @@ class Compaction {
                  BlobGarbageCollectionPolicy::kUseDefault,
              double blob_garbage_collection_age_cutoff = -1);
 
-  // The type of the proximal level output range
-  enum class ProximalOutputRangeType : int {
-    kNotSupported,  // it cannot output to the proximal level
-    kFullRange,     // any data could be output to the proximal level
+  // The type of the penultimate level output range
+  enum class PenultimateOutputRangeType : int {
+    kNotSupported,  // it cannot output to the penultimate level
+    kFullRange,     // any data could be output to the penultimate level
     kNonLastRange,  // only the keys within non_last_level compaction inputs can
-                    // be outputted to the proximal level
-    kDisabled,      // no data can be outputted to the proximal level
+                    // be outputted to the penultimate level
+    kDisabled,      // no data can be outputted to the penultimate level
   };
 
   // No copying allowed
@@ -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
@@ -288,14 +274,14 @@ class Compaction {
 
   // Return the ImmutableOptions that should be used throughout the compaction
   // procedure
-  const ImmutableOptions& immutable_options() const {
-    return immutable_options_;
+  const ImmutableOptions* immutable_options() const {
+    return &immutable_options_;
   }
 
   // Return the MutableCFOptions that should be used throughout the compaction
   // procedure
-  const MutableCFOptions& mutable_cf_options() const {
-    return mutable_cf_options_;
+  const MutableCFOptions* mutable_cf_options() const {
+    return &mutable_cf_options_;
   }
 
   // Returns the size in bytes that the output file should be preallocated to.
@@ -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_;
   }
@@ -370,30 +353,40 @@ class Compaction {
 
   Slice GetLargestUserKey() const { return largest_user_key_; }
 
-  ProximalOutputRangeType GetProximalOutputRangeType() const {
-    return proximal_output_range_type_;
+  Slice GetPenultimateLevelSmallestUserKey() const {
+    return penultimate_level_smallest_user_key_;
+  }
+
+  Slice GetPenultimateLevelLargestUserKey() const {
+    return penultimate_level_largest_user_key_;
+  }
+
+  PenultimateOutputRangeType GetPenultimateOutputRangeType() const {
+    return penultimate_output_range_type_;
   }
 
   // Return true if the compaction supports per_key_placement
   bool SupportsPerKeyPlacement() const;
 
-  // Get per_key_placement proximal output level, which is `last_level - 1`
+  // Get per_key_placement penultimate output level, which is `last_level - 1`
   // if per_key_placement feature is supported. Otherwise, return -1.
-  int GetProximalLevel() const;
+  int GetPenultimateLevel() const;
 
-  // Return true if the given range is overlap with proximal level output
+  // Return true if the given range is overlap with penultimate level output
   // range.
   // Both smallest_key and largest_key include timestamps if user-defined
   // timestamp is enabled.
-  bool OverlapProximalLevelOutputRange(const Slice& smallest_key,
-                                       const Slice& largest_key) const;
+  bool OverlapPenultimateLevelOutputRange(const Slice& smallest_key,
+                                          const Slice& largest_key) const;
 
-  // For testing purposes, check that a key is within proximal level
-  // output range for per_key_placement feature, which is safe to place the key
-  // to the proximal level. Different compaction strategies have different
-  // rules. `user_key` includes timestamp if user-defined timestamp is enabled.
-  void TEST_AssertWithinProximalLevelOutputRange(
-      const Slice& user_key, bool expect_failure = false) const;
+  // Return true if the key is within penultimate level output range for
+  // per_key_placement feature, which is safe to place the key to the
+  // penultimate level. different compaction strategy has different rules.
+  // If per_key_placement is not supported, always return false.
+  // TODO: currently it doesn't support moving data from the last level to the
+  //  penultimate level
+  //  key includes timestamp if user-defined timestamp is enabled.
+  bool WithinPenultimateLevelOutputRange(const Slice& key) const;
 
   CompactionReason compaction_reason() const { return compaction_reason_; }
 
@@ -415,12 +408,6 @@ 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,
@@ -441,58 +428,38 @@ class Compaction {
 
   static constexpr int kInvalidLevel = -1;
 
-  // Evaluate proximal output level. If the compaction supports
-  // per_key_placement feature, it returns the proximal level number.
+  // Evaluate penultimate output level. If the compaction supports
+  // per_key_placement feature, it returns the penultimate level number.
   // Otherwise, it's set to kInvalidLevel (-1), which means
-  // output_to_proximal_level is not supported.
-  // Note: even the proximal level output is supported (ProximalLevel !=
+  // output_to_penultimate_level is not supported.
+  // Note: even the penultimate level output is supported (PenultimateLevel !=
   // kInvalidLevel), some key range maybe unsafe to be outputted to the
-  // proximal level. The safe key range is populated by
-  // `PopulateProximalLevelOutputRange()`.
-  // Which could potentially disable all proximal level output.
-  static int EvaluateProximalLevel(const VersionStorageInfo* vstorage,
-                                   const MutableCFOptions& mutable_cf_options,
-                                   const ImmutableOptions& immutable_options,
-                                   const int start_level,
-                                   const int output_level);
-
-  // If some data cannot be safely migrated "up" the LSM tree due to a change
-  // in the preclude_last_level_data_seconds setting, this indicates a sequence
-  // number for the newest data that must be kept in the last level.
-  SequenceNumber GetKeepInLastLevelThroughSeqno() const {
-    return keep_in_last_level_through_seqno_;
-  }
-
-  // mark (or clear) all files that are being compacted
-  void MarkFilesBeingCompacted(bool being_compacted) const;
+  // 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 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,
                               Slice* smallest_key, Slice* largest_key,
                               int exclude_level = -1);
 
-  // get the smallest and largest internal key present in files to be compacted
-  static void GetBoundaryInternalKeys(
-      VersionStorageInfo* vstorage,
-      const std::vector<CompactionInputFiles>& inputs,
-      InternalKey* smallest_key, InternalKey* largest_key,
-      int exclude_level = -1);
-
-  // populate proximal level output range, which will be used to determine if
-  // a key is safe to output to the proximal level (details see
-  // `Compaction::WithinProximalLevelOutputRange()`.
-  void PopulateProximalLevelOutputRange();
-
-  // 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();
+  // populate penultimate level output range, which will be used to determine if
+  // a key is safe to output to the penultimate level (details see
+  // `Compaction::WithinPenultimateLevelOutputRange()`.
+  void PopulatePenultimateLevelOutputRange();
 
   // Get the atomic file boundaries for all files in the compaction. Necessary
   // in order to avoid the scenario described in
@@ -544,30 +511,12 @@ 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?
@@ -612,24 +561,22 @@ class Compaction {
   // Blob garbage collection age cutoff.
   double blob_garbage_collection_age_cutoff_;
 
-  SequenceNumber keep_in_last_level_through_seqno_ = kMaxSequenceNumber;
-
   // only set when per_key_placement feature is enabled, -1 (kInvalidLevel)
   // means not supported.
-  const int proximal_level_;
+  const int penultimate_level_;
 
-  // Key range for proximal level output
+  // Key range for penultimate level output
   // includes timestamp if user-defined timestamp is enabled.
-  // proximal_output_range_type_ shows the range type
-  InternalKey proximal_level_smallest_;
-  InternalKey proximal_level_largest_;
-  ProximalOutputRangeType proximal_output_range_type_ =
-      ProximalOutputRangeType::kNotSupported;
+  // penultimate_output_range_type_ shows the range type
+  Slice penultimate_level_smallest_user_key_;
+  Slice penultimate_level_largest_user_key_;
+  PenultimateOutputRangeType penultimate_output_range_type_ =
+      PenultimateOutputRangeType::kNotSupported;
 };
 
 #ifndef NDEBUG
 // Helper struct only for tests, which contains the data to decide if a key
-// should be output to the proximal level.
+// should be output to the penultimate level.
 // TODO: remove this when the public feature knob is available
 struct PerKeyPlacementContext {
   const int level;
@@ -637,20 +584,20 @@ struct PerKeyPlacementContext {
   const Slice value;
   const SequenceNumber seq_num;
 
-  bool& output_to_proximal_level;
+  bool& output_to_penultimate_level;
 
   PerKeyPlacementContext(int _level, Slice _key, Slice _value,
                          SequenceNumber _seq_num,
-                         bool& _output_to_proximal_level)
+                         bool& _output_to_penultimate_level)
       : level(_level),
         key(_key),
         value(_value),
         seq_num(_seq_num),
-        output_to_proximal_level(_output_to_proximal_level) {}
+        output_to_penultimate_level(_output_to_penultimate_level) {}
 };
 #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