Fix WriteBatchBase::DeleteRange API comment

The `DeleteRange` end key is exclusive, not inclusive. Updated API comment accordingly.

.circleci/config.yml

@@ -1,56 +0,0 @@
-version: 2.1
-
-orbs:
-  win: circleci/windows@2.4.0
-
-executors:
-  windows-2xlarge:
-    machine:
-      image: 'windows-server-2019-vs2019:stable'
-      resource_class: windows.2xlarge
-      shell: bash.exe
-
-jobs:
-  build:
-    executor: windows-2xlarge
-    
-    environment:
-      THIRDPARTY_HOME: C:/Users/circleci/thirdparty
-      CMAKE_HOME: C:/Users/circleci/thirdparty/cmake-3.16.4-win64-x64
-      CMAKE_BIN: C:/Users/circleci/thirdparty/cmake-3.16.4-win64-x64/bin/cmake.exe
-      CMAKE_GENERATOR: Visual Studio 16 2019
-      SNAPPY_HOME: C:/Users/circleci/thirdparty/snappy-1.1.7
-      SNAPPY_INCLUDE: C:/Users/circleci/thirdparty/snappy-1.1.7;C:/Users/circleci/thirdparty/snappy-1.1.7/build
-      SNAPPY_LIB_DEBUG: C:/Users/circleci/thirdparty/snappy-1.1.7/build/Debug/snappy.lib
-
-    steps:
-      - checkout
-      - run:
-          name: "Install thirdparty dependencies"
-          command: |
-            mkdir ${THIRDPARTY_HOME}
-            cd ${THIRDPARTY_HOME}
-            echo "Installing CMake..."
-            curl --fail --silent --show-error --output cmake-3.16.4-win64-x64.zip --location https://github.com/Kitware/CMake/releases/download/v3.16.4/cmake-3.16.4-win64-x64.zip
-            unzip -q cmake-3.16.4-win64-x64.zip
-            echo "Building Snappy dependency..."
-            curl --fail --silent --show-error --output snappy-1.1.7.zip --location https://github.com/google/snappy/archive/1.1.7.zip
-            unzip -q snappy-1.1.7.zip
-            cd snappy-1.1.7
-            mkdir build
-            cd build
-            ${CMAKE_BIN} -G "${CMAKE_GENERATOR}" ..
-            msbuild.exe Snappy.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
-      - run:
-          name: "Build RocksDB"
-          command: |
-            mkdir build
-            cd build
-            ${CMAKE_BIN} -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DJNI=1 ..
-            cd ..
-            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 db_basic_test,db_test,db_test2,env_basic_test,env_test,db_merge_operand_test -Concurrency 16

.gitignore

@@ -24,7 +24,6 @@ make_config.mk
 *.vcxproj.filters
 *.sln
 *.cmake
-.watchmanconfig
 CMakeCache.txt
 CMakeFiles/
 build/
@@ -33,9 +32,6 @@ ldb
 manifest_dump
 sst_dump
 blob_dump
-block_cache_trace_analyzer
-db_with_timestamp_basic_test
-tools/block_cache_analyzer/*.pyc
 column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
@@ -51,10 +47,6 @@ rocksdb_undump
 db_test2
 trace_analyzer
 trace_analyzer_test
-block_cache_trace_analyzer
-.DS_Store
-.vs
-.vscode
 
 java/out
 java/target
@@ -82,6 +74,3 @@ tp2/
 fbcode/
 fbcode
 buckifier/*.pyc
-buckifier/__pycache__
-
-compile_commands.json

.travis.yml

@@ -1,41 +1,31 @@
-dist: xenial
+sudo: false
+dist: trusty
 language: cpp
 os:
   - linux
   - osx
-arch:
-  - amd64
-  - arm64
-  - ppc64le
 compiler:
   - clang
   - gcc
-osx_image: xcode9.4
+osx_image: xcode8.3
+jdk:
+  - oraclejdk7
 cache:
   - ccache
+  - apt
 
 addons:
   apt:
     sources:
       - ubuntu-toolchain-r-test
     packages:
-      - libgflags-dev
+      - curl
+      - g++-8
       - libbz2-dev
-      - liblz4-dev
+      - libgflags-dev
       - libsnappy-dev
-      - liblzma-dev  # xv
-      - libzstd-dev
+      - mingw-w64
       - zlib1g-dev
-  homebrew:
-    update: true
-    packages:
-      - ccache
-      - gflags
-      - lz4
-      - snappy
-      - xz
-      - zstd
-
 env:
   - TEST_GROUP=platform_dependent # 16-18 minutes
   - TEST_GROUP=1 # 33-35 minutes
@@ -54,135 +44,34 @@ env:
 
 matrix:
   exclude:
+  - os: osx
+    env: TEST_GROUP=1
+  - os: osx
+    env: TEST_GROUP=2
+  - os: osx
+    env: TEST_GROUP=3
+  - os: osx
+    env: TEST_GROUP=4
   - os: osx
     env: JOB_NAME=cmake-gcc8
-  - os: osx
+  - os : osx
     env: JOB_NAME=cmake-mingw
-  - os: osx
-    arch: ppc64le
-  - os: osx
-    compiler: gcc
   - os : linux
-    arch: arm64
-    env: JOB_NAME=cmake-mingw
-  - os: linux
-    arch: ppc64le
-    env: JOB_NAME=cmake-mingw
-  - os: linux
     compiler: clang
-  # Exclude most osx, arm64 and ppc64le tests for pull requests, but build in branches
-  - if: type != pull_request
-    os: osx
-    env: TEST_GROUP=1
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=1
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=1
-  - if: type != pull_request
-    os: osx
-    env: TEST_GROUP=2
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=2
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=2
-  - if: type != pull_request
-    os: osx
-    env: TEST_GROUP=3
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=3
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=3
-  - if: type != pull_request
-    os: osx
-    env: TEST_GROUP=4
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=4
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=4
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=java-test
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=java-test
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=lite-build
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=lite-build
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=examples
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=examples
-  - if: type != pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=cmake-gcc8
-  - if: type != pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=cmake-gcc8
+  - os : osx
+    compiler: gcc
 
+# https://docs.travis-ci.com/user/caching/#ccache-cache
 install:
   - if [ "${TRAVIS_OS_NAME}" == osx ]; then
+      brew install ccache zstd lz4 snappy xz;
       PATH=$PATH:/usr/local/opt/ccache/libexec;
     fi
   - if [ "${JOB_NAME}" == cmake-gcc8 ]; then
-      sudo apt-get install -y g++-8;
       CC=gcc-8 && CXX=g++-8;
     fi
-  - if [ "${JOB_NAME}" == cmake-mingw ]; then
-      sudo apt-get install -y mingw-w64 ;
-    fi
   - if [[ "${JOB_NAME}" == cmake* ]] && [ "${TRAVIS_OS_NAME}" == linux ]; then
-      CMAKE_DIST_URL="https://rocksdb-deps.s3-us-west-2.amazonaws.com/cmake/cmake-3.14.5-Linux-$(uname -m).tar.bz2";
-      TAR_OPT="--strip-components=1 -xj";
-      if [ "aarch64" == "$(uname -m)" ]; then
-        sudo apt-get install -y libuv1 librhash0;
-        sudo apt-get upgrade -y libstdc++6;
-      fi;
-      mkdir cmake-dist && curl --silent --fail --show-error --location "${CMAKE_DIST_URL}" | tar -C cmake-dist ${TAR_OPT} && export PATH=$PWD/cmake-dist/bin:$PATH;
-    fi
-  - |
-    if [[ "${JOB_NAME}" == java_test || "${JOB_NAME}" == cmake* ]]; then
-      # Ensure JDK 8
-      if [ "${TRAVIS_OS_NAME}" == osx ]; then
-        brew tap AdoptOpenJDK/openjdk
-        brew cask install adoptopenjdk8
-        export JAVA_HOME=$(/usr/libexec/java_home)
-      else
-        sudo apt-get install -y openjdk-8-jdk
-        export PATH=/usr/lib/jvm/java-8-openjdk-$(dpkg --print-architecture)/bin:$PATH
-        export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-$(dpkg --print-architecture)
-      fi
-      echo "JAVA_HOME=${JAVA_HOME}"
-      which java && java -version
-      which javac && javac -version
+      mkdir cmake-dist && curl -sfSL https://cmake.org/files/v3.8/cmake-3.8.1-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
     fi
 
 before_script:
@@ -191,20 +80,20 @@ before_script:
   - ulimit -n 8192
 
 script:
-  - date; ${CXX} --version
+  - ${CXX} --version
   - if [ `command -v ccache` ]; then ccache -C; fi
   - case $TEST_GROUP in
     platform_dependent)
       OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=db_block_cache_test make -j4 all_but_some_tests check_some
       ;;
     1)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=db_iter_test make -j4 check_some
+      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=full_filter_block_test make -j4 check_some
       ;;
     2)
-      OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" V=1 make -j4 tools && OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" V=1 ROCKSDBTESTS_START=db_iter_test ROCKSDBTESTS_END=options_file_test make -j4 check_some
+      OPT=-DTRAVIS V=1 make -j4 tools && OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=full_filter_block_test ROCKSDBTESTS_END=write_batch_with_index_test make -j4 check_some
       ;;
     3)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=options_file_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some
+      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_batch_with_index_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some
       ;;
     4)
       OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_prepared_transaction_test make -j4 check_some
@@ -212,7 +101,7 @@ script:
     esac
   - case $JOB_NAME in
     java_test)
-      OPT=-DTRAVIS V=1 make rocksdbjava jtest
+      OPT=-DTRAVIS V=1 make clean jclean && make rocksdbjava jtest
       ;;
     lite_build)
       OPT='-DTRAVIS -DROCKSDB_LITE' V=1 make -j4 static_lib tools
@@ -221,8 +110,7 @@ script:
       OPT=-DTRAVIS V=1 make -j4 static_lib && cd examples && make -j4
       ;;
     cmake-mingw)
-      sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
-      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
+      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
       ;;
     cmake*)
       mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release && make -j4 rocksdb rocksdbjni
@@ -231,3 +119,5 @@ script:
 notifications:
     email:
       - leveldb@fb.com
+    webhooks:
+      - https://buildtimetrend.herokuapp.com/travis

.watchmanconfig

@@ -1,6 +0,0 @@
-{
-  "content_hash_warming": true,
-  "content_hash_max_items": 333333,
-  "hint_num_files_per_dir": 8,
-  "fsevents_latency": 0.05
-}

CMakeLists.txt

@@ -14,7 +14,7 @@
 #        cd build
 # 3. Run cmake to generate project files for Windows, add more options to enable required third-party libraries.
 #    See thirdparty.inc for more information.
-#        sample command: cmake -G "Visual Studio 15 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
+#        sample command: cmake -G "Visual Studio 15 Win64" -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
 # 4. Then build the project in debug mode (you may want to add /m[:<N>] flag to run msbuild in <N> parallel threads
 #                                          or simply /m to use all avail cores)
 #        msbuild rocksdb.sln
@@ -32,34 +32,17 @@
 # 3. cmake ..
 # 4. make -j
 
-cmake_minimum_required(VERSION 3.5.1)
-
-list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
-include(ReadVersion)
-get_rocksdb_version(rocksdb_VERSION)
-project(rocksdb
-  VERSION ${rocksdb_VERSION}
-  LANGUAGES CXX C ASM)
+cmake_minimum_required(VERSION 2.8.12)
+project(rocksdb)
+enable_language(CXX)
+enable_language(C)
+enable_language(ASM)
 
 if(POLICY CMP0042)
   cmake_policy(SET CMP0042 NEW)
 endif()
 
-if(NOT CMAKE_BUILD_TYPE)
-  if(EXISTS "${CMAKE_SOURCE_DIR}/.git")
-    set(default_build_type "Debug")
-  else()
-    set(default_build_type "RelWithDebInfo")
-  endif()
-  set(CMAKE_BUILD_TYPE "${default_build_type}" CACHE STRING
-    "Default BUILD_TYPE is ${default_build_type}" FORCE)
-endif()
-
-find_program(CCACHE_FOUND ccache)
-if(CCACHE_FOUND)
-  set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
-  set_property(GLOBAL PROPERTY RULE_LAUNCH_LINK ccache)
-endif(CCACHE_FOUND)
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
 
 option(WITH_JEMALLOC "build with JeMalloc" OFF)
 option(WITH_SNAPPY "build with SNAPPY" OFF)
@@ -70,24 +53,10 @@ option(WITH_WINDOWS_UTF8_FILENAMES "use UTF8 as characterset for opening files,
 if (WITH_WINDOWS_UTF8_FILENAMES)
   add_definitions(-DROCKSDB_WINDOWS_UTF8_FILENAMES)
 endif()
-# third-party/folly is only validated to work on Linux and Windows for now.
-# So only turn it on there by default.
-if(CMAKE_SYSTEM_NAME MATCHES "Linux|Windows")
-  if(MSVC AND MSVC_VERSION LESS 1910)
-    # Folly does not compile with MSVC older than VS2017
-    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
-  else()
-    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
-  endif()
-else()
-  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
-endif()
-
-include(CMakeDependentOption)
-CMAKE_DEPENDENT_OPTION(WITH_GFLAGS "build with GFlags" ON
-  "NOT MSVC;NOT MINGW" OFF)
-
 if(MSVC)
+  # Defaults currently different for GFLAGS.
+  #  We will address find_package work a little later
+  option(WITH_GFLAGS "build with GFlags" OFF)
   option(WITH_XPRESS "build with windows built in compression" OFF)
   include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
 else()
@@ -99,58 +68,66 @@ else()
     if(WITH_JEMALLOC)
       find_package(JeMalloc REQUIRED)
       add_definitions(-DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE)
-      list(APPEND THIRDPARTY_LIBS JeMalloc::JeMalloc)
+      include_directories(${JEMALLOC_INCLUDE_DIR})
+      list(APPEND THIRDPARTY_LIBS ${JEMALLOC_LIBRARIES})
     endif()
   endif()
 
   # No config file for this
+  option(WITH_GFLAGS "build with GFlags" ON)
   if(WITH_GFLAGS)
-    find_package(gflags REQUIRED)
-    add_definitions(-DGFLAGS=1)
-    include_directories(${gflags_INCLUDE_DIR})
-    list(APPEND THIRDPARTY_LIBS gflags::gflags)
+    find_package(gflags)
+    if(gflags_FOUND)
+      add_definitions(-DGFLAGS=1)
+      include_directories(${gflags_INCLUDE_DIR})
+      list(APPEND THIRDPARTY_LIBS ${gflags_LIBRARIES})
+    endif()
   endif()
 
   if(WITH_SNAPPY)
     find_package(snappy REQUIRED)
     add_definitions(-DSNAPPY)
-    list(APPEND THIRDPARTY_LIBS snappy::snappy)
+    include_directories(${SNAPPY_INCLUDE_DIR})
+    list(APPEND THIRDPARTY_LIBS ${SNAPPY_LIBRARIES})
   endif()
 
   if(WITH_ZLIB)
-    find_package(ZLIB REQUIRED)
+    find_package(zlib REQUIRED)
     add_definitions(-DZLIB)
-    list(APPEND THIRDPARTY_LIBS ZLIB::ZLIB)
+    if(ZLIB_INCLUDE_DIRS)
+      # CMake 3
+      include_directories(${ZLIB_INCLUDE_DIRS})
+    else()
+      # CMake 2
+      include_directories(${ZLIB_INCLUDE_DIR})
+    endif()
+    list(APPEND THIRDPARTY_LIBS ${ZLIB_LIBRARIES})
   endif()
 
   option(WITH_BZ2 "build with bzip2" OFF)
   if(WITH_BZ2)
-    find_package(BZip2 REQUIRED)
+    find_package(bzip2 REQUIRED)
     add_definitions(-DBZIP2)
-    if(BZIP2_INCLUDE_DIRS)
-      include_directories(${BZIP2_INCLUDE_DIRS})
-    else()
-      include_directories(${BZIP2_INCLUDE_DIR})
-    endif()
+    include_directories(${BZIP2_INCLUDE_DIR})
     list(APPEND THIRDPARTY_LIBS ${BZIP2_LIBRARIES})
   endif()
 
   if(WITH_LZ4)
     find_package(lz4 REQUIRED)
     add_definitions(-DLZ4)
-    list(APPEND THIRDPARTY_LIBS lz4::lz4)
+    include_directories(${LZ4_INCLUDE_DIR})
+    list(APPEND THIRDPARTY_LIBS ${LZ4_LIBRARIES})
   endif()
 
   if(WITH_ZSTD)
     find_package(zstd REQUIRED)
     add_definitions(-DZSTD)
     include_directories(${ZSTD_INCLUDE_DIR})
-    list(APPEND THIRDPARTY_LIBS zstd::zstd)
+    list(APPEND THIRDPARTY_LIBS ${ZSTD_LIBRARIES})
   endif()
 endif()
 
-string(TIMESTAMP TS "%Y/%m/%d %H:%M:%S" UTC)
-set(GIT_DATE_TIME "${TS}" CACHE STRING "the time we first built rocksdb")
+string(TIMESTAMP GIT_DATE_TIME "%Y/%m/%d %H:%M:%S" UTC)
 
 find_package(Git)
 
@@ -167,6 +144,17 @@ endif()
 string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA "${GIT_SHA}")
 
 
+# Read rocksdb version from version.h header file.
+file(READ include/rocksdb/version.h version_header_file)
+string(REGEX MATCH "#define ROCKSDB_MAJOR ([0-9]+)" _ ${version_header_file})
+set(ROCKSDB_VERSION_MAJOR ${CMAKE_MATCH_1})
+string(REGEX MATCH "#define ROCKSDB_MINOR ([0-9]+)" _ ${version_header_file})
+set(ROCKSDB_VERSION_MINOR ${CMAKE_MATCH_1})
+string(REGEX MATCH "#define ROCKSDB_PATCH ([0-9]+)" _ ${version_header_file})
+set(ROCKSDB_VERSION_PATCH ${CMAKE_MATCH_1})
+set(ROCKSDB_VERSION ${ROCKSDB_VERSION_MAJOR}.${ROCKSDB_VERSION_MINOR}.${ROCKSDB_VERSION_PATCH})
+
+
 option(WITH_MD_LIBRARY "build with MD" ON)
 if(WIN32 AND MSVC)
   if(WITH_MD_LIBRARY)
@@ -188,8 +176,7 @@ else()
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
   if(MINGW)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format -fno-asynchronous-unwind-tables")
-    add_definitions(-D_POSIX_C_SOURCE=1)
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
   endif()
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
   if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
@@ -203,34 +190,16 @@ else()
 endif()
 
 include(CheckCCompilerFlag)
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
-  CHECK_C_COMPILER_FLAG("-mcpu=power9" HAS_POWER9)
-  if(HAS_POWER9)
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power9 -mtune=power9")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power9 -mtune=power9")
-  else()
-    CHECK_C_COMPILER_FLAG("-mcpu=power8" HAS_POWER8)
-    if(HAS_POWER8)
-      set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power8 -mtune=power8")
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power8 -mtune=power8")
-    endif(HAS_POWER8)
-  endif(HAS_POWER9)
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
   CHECK_C_COMPILER_FLAG("-maltivec" HAS_ALTIVEC)
   if(HAS_ALTIVEC)
     message(STATUS " HAS_ALTIVEC yes")
     set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maltivec")
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maltivec")
+    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power8")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power8")
   endif(HAS_ALTIVEC)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
-
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
-        CHECK_C_COMPILER_FLAG("-march=armv8-a+crc+crypto" HAS_ARMV8_CRC)
-  if(HAS_ARMV8_CRC)
-    message(STATUS " HAS_ARMV8_CRC yes")
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
-  endif(HAS_ARMV8_CRC)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
+endif(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
 
 option(PORTABLE "build a portable binary" OFF)
 option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
@@ -244,7 +213,7 @@ else()
   if(MSVC)
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
   else()
-    if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64" AND NOT HAS_ARMV8_CRC)
+    if(NOT HAVE_POWER8)
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
     endif()
   endif()
@@ -331,14 +300,15 @@ if(WITH_NUMA)
   find_package(NUMA REQUIRED)
   add_definitions(-DNUMA)
   include_directories(${NUMA_INCLUDE_DIR})
-  list(APPEND THIRDPARTY_LIBS NUMA::NUMA)
+  list(APPEND THIRDPARTY_LIBS ${NUMA_LIBRARIES})
 endif()
 
 option(WITH_TBB "build with Threading Building Blocks (TBB)" OFF)
 if(WITH_TBB)
   find_package(TBB REQUIRED)
   add_definitions(-DTBB)
-  list(APPEND THIRDPARTY_LIBS TBB::TBB)
+  include_directories(${TBB_INCLUDE_DIR})
+  list(APPEND THIRDPARTY_LIBS ${TBB_LIBRARIES})
 endif()
 
 # Stall notifications eat some performance from inserts
@@ -347,10 +317,6 @@ if(DISABLE_STALL_NOTIF)
   add_definitions(-DROCKSDB_DISABLE_STALL_NOTIFICATION)
 endif()
 
-option(WITH_DYNAMIC_EXTENSION "build with dynamic extension support" OFF)
-if(NOT WITH_DYNAMIC_EXTENSION)
-  add_definitions(-DROCKSDB_NO_DYNAMIC_EXTENSION)
-endif()
 
 if(DEFINED USE_RTTI)
   if(USE_RTTI)
@@ -450,7 +416,7 @@ if(WITH_FALLOCATE)
 #include <linux/falloc.h>
 int main() {
  int fd = open(\"/dev/null\", 0);
- fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, 1024);
+ fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
 }
 " HAVE_FALLOCATE)
   if(HAVE_FALLOCATE)
@@ -490,50 +456,39 @@ if(HAVE_SCHED_GETCPU)
   add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
 endif()
 
-check_cxx_symbol_exists(getauxval auvx.h HAVE_AUXV_GETAUXVAL)
-if(HAVE_AUXV_GETAUXVAL)
-  add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
-endif()
-
 include_directories(${PROJECT_SOURCE_DIR})
 include_directories(${PROJECT_SOURCE_DIR}/include)
-include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.8.1/fused-src)
-if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-  include_directories(${PROJECT_SOURCE_DIR}/third-party/folly)
-endif()
+include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
 find_package(Threads REQUIRED)
 
+add_subdirectory(third-party/gtest-1.7.0/fused-src/gtest)
+
 # Main library source code
 
 set(SOURCES
         cache/clock_cache.cc
         cache/lru_cache.cc
         cache/sharded_cache.cc
-        db/arena_wrapped_db_iter.cc
-        db/blob/blob_file_addition.cc
-        db/blob/blob_file_garbage.cc
         db/builder.cc
         db/c.cc
         db/column_family.cc
         db/compacted_db_impl.cc
-        db/compaction/compaction.cc
-        db/compaction/compaction_iterator.cc
-        db/compaction/compaction_picker.cc
-        db/compaction/compaction_job.cc
-        db/compaction/compaction_picker_fifo.cc
-        db/compaction/compaction_picker_level.cc
-        db/compaction/compaction_picker_universal.cc
+        db/compaction.cc
+        db/compaction_iterator.cc
+        db/compaction_job.cc
+        db/compaction_picker.cc
+        db/compaction_picker_fifo.cc
+        db/compaction_picker_universal.cc
         db/convenience.cc
         db/db_filesnapshot.cc
-        db/db_impl/db_impl.cc
-        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_open.cc
-        db/db_impl/db_impl_debug.cc
-        db/db_impl/db_impl_experimental.cc
-        db/db_impl/db_impl_readonly.cc
-        db/db_impl/db_impl_secondary.cc
+        db/db_impl.cc
+        db/db_impl_write.cc
+        db/db_impl_compaction_flush.cc
+        db/db_impl_files.cc
+        db/db_impl_open.cc
+        db/db_impl_debug.cc
+        db/db_impl_experimental.cc
+        db/db_impl_readonly.cc
         db/db_info_dumper.cc
         db/db_iter.cc
         db/dbformat.cc
@@ -545,7 +500,6 @@ set(SOURCES
         db/flush_job.cc
         db/flush_scheduler.cc
         db/forward_iterator.cc
-        db/import_column_family_job.cc
         db/internal_stats.cc
         db/logs_with_prep_tracker.cc
         db/log_reader.cc
@@ -562,7 +516,6 @@ set(SOURCES
         db/table_cache.cc
         db/table_properties_collector.cc
         db/transaction_log_impl.cc
-        db/trim_history_scheduler.cc
         db/version_builder.cc
         db/version_edit.cc
         db/version_set.cc
@@ -575,25 +528,9 @@ set(SOURCES
         env/env_chroot.cc
         env/env_encryption.cc
         env/env_hdfs.cc
-        env/file_system.cc
         env/mock_env.cc
-        file/delete_scheduler.cc
-        file/file_prefetch_buffer.cc
-        file/file_util.cc
-        file/filename.cc
-        file/random_access_file_reader.cc
-        file/read_write_util.cc
-        file/readahead_raf.cc
-        file/sequence_file_reader.cc
-        file/sst_file_manager_impl.cc
-        file/writable_file_writer.cc
-        logging/auto_roll_logger.cc
-        logging/event_logger.cc
-        logging/log_buffer.cc
-        memory/arena.cc
-        memory/concurrent_arena.cc
-        memory/jemalloc_nodump_allocator.cc
         memtable/alloc_tracker.cc
+        memtable/hash_cuckoo_rep.cc
         memtable/hash_linklist_rep.cc
         memtable/hash_skiplist_rep.cc
         memtable/skiplistrep.cc
@@ -601,12 +538,10 @@ set(SOURCES
         memtable/write_buffer_manager.cc
         monitoring/histogram.cc
         monitoring/histogram_windowing.cc
-        monitoring/in_memory_stats_history.cc
         monitoring/instrumented_mutex.cc
         monitoring/iostats_context.cc
         monitoring/perf_context.cc
         monitoring/perf_level.cc
-        monitoring/persistent_stats_history.cc
         monitoring/statistics.cc
         monitoring/thread_status_impl.cc
         monitoring/thread_status_updater.cc
@@ -619,81 +554,80 @@ set(SOURCES
         options/options_parser.cc
         options/options_sanity_check.cc
         port/stack_trace.cc
-        table/adaptive/adaptive_table_factory.cc
-        table/block_based/binary_search_index_reader.cc
-        table/block_based/block.cc
-        table/block_based/block_based_filter_block.cc
-        table/block_based/block_based_table_builder.cc
-        table/block_based/block_based_table_factory.cc
-        table/block_based/block_based_table_iterator.cc
-        table/block_based/block_based_table_reader.cc
-        table/block_based/block_builder.cc
-        table/block_based/block_prefetcher.cc
-        table/block_based/block_prefix_index.cc
-        table/block_based/data_block_hash_index.cc
-        table/block_based/data_block_footer.cc
-        table/block_based/filter_block_reader_common.cc
-        table/block_based/filter_policy.cc
-        table/block_based/flush_block_policy.cc
-        table/block_based/full_filter_block.cc
-        table/block_based/hash_index_reader.cc
-        table/block_based/index_builder.cc
-        table/block_based/index_reader_common.cc
-        table/block_based/parsed_full_filter_block.cc
-        table/block_based/partitioned_filter_block.cc
-        table/block_based/partitioned_index_iterator.cc
-        table/block_based/partitioned_index_reader.cc
-        table/block_based/reader_common.cc
-        table/block_based/uncompression_dict_reader.cc
+        table/adaptive_table_factory.cc
+        table/block.cc
+        table/block_based_filter_block.cc
+        table/block_based_table_builder.cc
+        table/block_based_table_factory.cc
+        table/block_based_table_reader.cc
+        table/block_builder.cc
         table/block_fetcher.cc
-        table/cuckoo/cuckoo_table_builder.cc
-        table/cuckoo/cuckoo_table_factory.cc
-        table/cuckoo/cuckoo_table_reader.cc
+        table/block_prefix_index.cc
+        table/bloom_block.cc
+        table/cuckoo_table_builder.cc
+        table/cuckoo_table_factory.cc
+        table/cuckoo_table_reader.cc
+        table/data_block_hash_index.cc
+        table/data_block_footer.cc
+        table/flush_block_policy.cc
         table/format.cc
+        table/full_filter_block.cc
         table/get_context.cc
+        table/index_builder.cc
         table/iterator.cc
         table/merging_iterator.cc
         table/meta_blocks.cc
+        table/partitioned_filter_block.cc
         table/persistent_cache_helper.cc
-        table/plain/plain_table_bloom.cc
-        table/plain/plain_table_builder.cc
-        table/plain/plain_table_factory.cc
-        table/plain/plain_table_index.cc
-        table/plain/plain_table_key_coding.cc
-        table/plain/plain_table_reader.cc
+        table/plain_table_builder.cc
+        table/plain_table_factory.cc
+        table/plain_table_index.cc
+        table/plain_table_key_coding.cc
+        table/plain_table_reader.cc
         table/sst_file_reader.cc
         table/sst_file_writer.cc
         table/table_properties.cc
         table/two_level_iterator.cc
-        test_util/sync_point.cc
-        test_util/sync_point_impl.cc
-        test_util/testutil.cc
-        test_util/transaction_test_util.cc
-        tools/block_cache_analyzer/block_cache_trace_analyzer.cc
+        tools/db_bench_tool.cc
         tools/dump/db_dump_tool.cc
         tools/ldb_cmd.cc
         tools/ldb_tool.cc
         tools/sst_dump_tool.cc
         tools/trace_analyzer_tool.cc
-        trace_replay/trace_replay.cc
-        trace_replay/block_cache_tracer.cc
+        util/arena.cc
+        util/auto_roll_logger.cc
+        util/bloom.cc
         util/coding.cc
         util/compaction_job_stats_impl.cc
         util/comparator.cc
         util/compression_context_cache.cc
+        util/concurrent_arena.cc
         util/concurrent_task_limiter_impl.cc
         util/crc32c.cc
+        util/delete_scheduler.cc
         util/dynamic_bloom.cc
+        util/event_logger.cc
+        util/file_reader_writer.cc
+        util/file_util.cc
+        util/filename.cc
+        util/filter_policy.cc
         util/hash.cc
+        util/jemalloc_nodump_allocator.cc
+        util/log_buffer.cc
         util/murmurhash.cc
         util/random.cc
         util/rate_limiter.cc
         util/slice.cc
-        util/file_checksum_helper.cc
+        util/sst_file_manager_impl.cc
         util/status.cc
         util/string_util.cc
+        util/sync_point.cc
+        util/sync_point_impl.cc
+        util/testutil.cc
         util/thread_local.cc
         util/threadpool_imp.cc
+        util/trace_replay.cc
+        util/transaction_test_util.cc
         util/xxhash.cc
         utilities/backupable/backupable_db.cc
         utilities/blob_db/blob_compaction_filter.cc
@@ -714,15 +648,14 @@ set(SOURCES
         utilities/env_mirror.cc
         utilities/env_timed.cc
         utilities/leveldb_options/leveldb_options.cc
+        utilities/lua/rocks_lua_compaction_filter.cc
         utilities/memory/memory_util.cc
         utilities/merge_operators/bytesxor.cc
         utilities/merge_operators/max.cc
         utilities/merge_operators/put.cc
-        utilities/merge_operators/sortlist.cc
         utilities/merge_operators/string_append/stringappend.cc
         utilities/merge_operators/string_append/stringappend2.cc
         utilities/merge_operators/uint64add.cc
-        utilities/object_registry.cc
         utilities/option_change_migration/option_change_migration.cc
         utilities/options/options_util.cc
         utilities/persistent_cache/block_cache_tier.cc
@@ -730,7 +663,6 @@ 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/simulator_cache/cache_simulator.cc
         utilities/simulator_cache/sim_cache.cc
         utilities/table_properties_collectors/compact_on_deletion_collector.cc
         utilities/trace/file_trace_reader_writer.cc
@@ -758,16 +690,11 @@ if(HAVE_SSE42 AND NOT MSVC)
     PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
 endif()
 
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
+if(HAVE_POWER8)
   list(APPEND SOURCES
     util/crc32c_ppc.c
     util/crc32c_ppc_asm.S)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
-
-if(HAS_ARMV8_CRC)
-  list(APPEND SOURCES
-    util/crc32c_arm64.cc)
-endif(HAS_ARMV8_CRC)
+endif(HAVE_POWER8)
 
 if(WIN32)
   list(APPEND SOURCES
@@ -792,23 +719,12 @@ else()
   list(APPEND SOURCES
     port/port_posix.cc
     env/env_posix.cc
-    env/fs_posix.cc
     env/io_posix.cc)
 endif()
 
-if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-  list(APPEND SOURCES
-    third-party/folly/folly/detail/Futex.cpp
-    third-party/folly/folly/synchronization/AtomicNotification.cpp
-    third-party/folly/folly/synchronization/DistributedMutex.cpp
-    third-party/folly/folly/synchronization/ParkingLot.cpp
-    third-party/folly/folly/synchronization/WaitOptions.cpp)
-endif()
-
 set(ROCKSDB_STATIC_LIB rocksdb${ARTIFACT_SUFFIX})
 set(ROCKSDB_SHARED_LIB rocksdb-shared${ARTIFACT_SUFFIX})
-
-option(ROCKSDB_BUILD_SHARED "Build shared versions of the RocksDB libraries" ON)
+set(ROCKSDB_IMPORT_LIB ${ROCKSDB_SHARED_LIB})
 
 option(WITH_LIBRADOS "Build with librados" OFF)
 if(WITH_LIBRADOS)
@@ -818,45 +734,41 @@ if(WITH_LIBRADOS)
 endif()
 
 if(WIN32)
-  set(SYSTEM_LIBS ${SYSTEM_LIBS} shlwapi.lib rpcrt4.lib)
+  set(SYSTEM_LIBS ${SYSTEM_LIBS} Shlwapi.lib Rpcrt4.lib)
+  set(LIBS ${ROCKSDB_STATIC_LIB} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 else()
   set(SYSTEM_LIBS ${CMAKE_THREAD_LIBS_INIT})
+  set(LIBS ${ROCKSDB_SHARED_LIB} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+
+  add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES})
+  target_link_libraries(${ROCKSDB_SHARED_LIB}
+    ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+  set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
+                        LINKER_LANGUAGE CXX
+                        VERSION ${ROCKSDB_VERSION}
+                        SOVERSION ${ROCKSDB_VERSION_MAJOR}
+                        CXX_STANDARD 11
+                        OUTPUT_NAME "rocksdb")
 endif()
 
 add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES})
 target_link_libraries(${ROCKSDB_STATIC_LIB}
   ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 
-if(ROCKSDB_BUILD_SHARED)
-  add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES})
-  target_link_libraries(${ROCKSDB_SHARED_LIB}
+if(WIN32)
+  add_library(${ROCKSDB_IMPORT_LIB} SHARED ${SOURCES})
+  target_link_libraries(${ROCKSDB_IMPORT_LIB}
     ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
-
-  if(WIN32)
-    set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
-      COMPILE_DEFINITIONS "ROCKSDB_DLL;ROCKSDB_LIBRARY_EXPORTS")
-    if(MSVC)
-      set_target_properties(${ROCKSDB_STATIC_LIB} PROPERTIES
-        COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_STATIC_LIB}.pdb")
-      set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
-        COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_SHARED_LIB}.pdb")
-    endif()
-  else()
-    set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
-                          LINKER_LANGUAGE CXX
-                          VERSION ${rocksdb_VERSION}
-                          SOVERSION ${rocksdb_VERSION_MAJOR}
-                          CXX_STANDARD 11
-                          OUTPUT_NAME "rocksdb")
+  set_target_properties(${ROCKSDB_IMPORT_LIB} PROPERTIES
+    COMPILE_DEFINITIONS "ROCKSDB_DLL;ROCKSDB_LIBRARY_EXPORTS")
+  if(MSVC)
+    set_target_properties(${ROCKSDB_STATIC_LIB} PROPERTIES
+      COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_STATIC_LIB}.pdb")
+    set_target_properties(${ROCKSDB_IMPORT_LIB} PROPERTIES
+      COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_IMPORT_LIB}.pdb")
   endif()
 endif()
 
-if(ROCKSDB_BUILD_SHARED AND NOT WIN32)
-  set(ROCKSDB_LIB ${ROCKSDB_SHARED_LIB})
-else()
-  set(ROCKSDB_LIB ${ROCKSDB_STATIC_LIB})
-endif()
-
 option(WITH_JNI "build with JNI" OFF)
 if(WITH_JNI OR JNI)
   message(STATUS "JNI library is enabled")
@@ -889,7 +801,7 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
 
   write_basic_package_version_file(
     RocksDBConfigVersion.cmake
-    VERSION ${rocksdb_VERSION}
+    VERSION ${ROCKSDB_VERSION}
     COMPATIBILITY SameMajorVersion
   )
 
@@ -903,17 +815,15 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
     INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
   )
 
-  if(ROCKSDB_BUILD_SHARED)
-    install(
-      TARGETS ${ROCKSDB_SHARED_LIB}
-      EXPORT RocksDBTargets
-      COMPONENT runtime
-      ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
-      RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
-      LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
-      INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
-    )
-  endif()
+  install(
+    TARGETS ${ROCKSDB_SHARED_LIB}
+    EXPORT RocksDBTargets
+    COMPONENT runtime
+    ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
+    RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
+    LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
+    INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
+  )
 
   install(
     EXPORT RocksDBTargets
@@ -931,32 +841,22 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
   )
 endif()
 
-# Tests are excluded from Release builds
-CMAKE_DEPENDENT_OPTION(WITH_TESTS "build with tests" ON
-  "CMAKE_BUILD_TYPE STREQUAL Debug" OFF)
+option(WITH_TESTS "build with tests" ON)
 if(WITH_TESTS)
-  add_subdirectory(third-party/gtest-1.8.1/fused-src/gtest)
-  add_library(testharness STATIC
-  test_util/testharness.cc)
-  target_link_libraries(testharness gtest)
-
   set(TESTS
         cache/cache_test.cc
         cache/lru_cache_test.cc
-        db/blob/blob_file_addition_test.cc
-        db/blob/blob_file_garbage_test.cc
-        db/blob/db_blob_index_test.cc
         db/column_family_test.cc
         db/compact_files_test.cc
-        db/compaction/compaction_job_stats_test.cc
-        db/compaction/compaction_job_test.cc
-        db/compaction/compaction_iterator_test.cc
-        db/compaction/compaction_picker_test.cc
+        db/compaction_iterator_test.cc
+        db/compaction_job_stats_test.cc
+        db/compaction_job_test.cc
+        db/compaction_picker_test.cc
         db/comparator_db_test.cc
         db/corruption_test.cc
         db/cuckoo_table_db_test.cc
         db/db_basic_test.cc
-        db/db_with_timestamp_basic_test.cc
+        db/db_blob_index_test.cc
         db/db_block_cache_test.cc
         db/db_bloom_filter_test.cc
         db/db_compaction_filter_test.cc
@@ -971,24 +871,21 @@ if(WITH_TESTS)
         db/db_log_iter_test.cc
         db/db_memtable_test.cc
         db/db_merge_operator_test.cc
-        db/db_merge_operand_test.cc
         db/db_options_test.cc
         db/db_properties_test.cc
         db/db_range_del_test.cc
-        db/db_impl/db_secondary_test.cc
         db/db_sst_test.cc
         db/db_statistics_test.cc
         db/db_table_properties_test.cc
         db/db_tailing_iter_test.cc
         db/db_test.cc
         db/db_test2.cc
-        db/db_logical_block_size_cache_test.cc
         db/db_universal_compaction_test.cc
         db/db_wal_test.cc
         db/db_write_test.cc
         db/dbformat_test.cc
         db/deletefile_test.cc
-        db/error_handler_fs_test.cc
+        db/error_handler_test.cc
         db/obsolete_files_test.cc
         db/external_sst_file_basic_test.cc
         db/external_sst_file_test.cc
@@ -1019,52 +916,44 @@ if(WITH_TESTS)
         db/write_controller_test.cc
         env/env_basic_test.cc
         env/env_test.cc
-        env/io_posix_test.cc
         env/mock_env_test.cc
-        file/delete_scheduler_test.cc
-        logging/auto_roll_logger_test.cc
-        logging/env_logger_test.cc
-        logging/event_logger_test.cc
-        memory/arena_test.cc
         memtable/inlineskiplist_test.cc
         memtable/skiplist_test.cc
         memtable/write_buffer_manager_test.cc
         monitoring/histogram_test.cc
         monitoring/iostats_context_test.cc
         monitoring/statistics_test.cc
-        monitoring/stats_history_test.cc
         options/options_settable_test.cc
         options/options_test.cc
-        table/block_based/block_based_filter_block_test.cc
-        table/block_based/block_test.cc
-        table/block_based/data_block_hash_index_test.cc
-        table/block_based/full_filter_block_test.cc
-        table/block_based/partitioned_filter_block_test.cc
+        table/block_based_filter_block_test.cc
+        table/block_test.cc
         table/cleanable_test.cc
-        table/cuckoo/cuckoo_table_builder_test.cc
-        table/cuckoo/cuckoo_table_reader_test.cc
+        table/cuckoo_table_builder_test.cc
+        table/cuckoo_table_reader_test.cc
+        table/data_block_hash_index_test.cc
+        table/full_filter_block_test.cc
         table/merger_test.cc
         table/sst_file_reader_test.cc
         table/table_test.cc
-        tools/block_cache_analyzer/block_cache_trace_analyzer_test.cc
         tools/ldb_cmd_test.cc
         tools/reduce_levels_test.cc
         tools/sst_dump_test.cc
         tools/trace_analyzer_test.cc
+        util/arena_test.cc
+        util/auto_roll_logger_test.cc
         util/autovector_test.cc
         util/bloom_test.cc
         util/coding_test.cc
         util/crc32c_test.cc
-        util/defer_test.cc
+        util/delete_scheduler_test.cc
         util/dynamic_bloom_test.cc
+        util/event_logger_test.cc
         util/file_reader_writer_test.cc
         util/filelock_test.cc
         util/hash_test.cc
         util/heap_test.cc
-        util/random_test.cc
         util/rate_limiter_test.cc
         util/repeatable_thread_test.cc
-        util/slice_test.cc
         util/slice_transform_test.cc
         util/timer_queue_test.cc
         util/thread_list_test.cc
@@ -1076,6 +965,7 @@ if(WITH_TESTS)
         utilities/cassandra/cassandra_row_merge_test.cc
         utilities/cassandra/cassandra_serialize_test.cc
         utilities/checkpoint/checkpoint_test.cc
+        utilities/lua/rocks_lua_test.cc
         utilities/memory/memory_test.cc
         utilities/merge_operators/string_append/stringappend_test.cc
         utilities/object_registry_test.cc
@@ -1083,7 +973,6 @@ if(WITH_TESTS)
         utilities/options/options_util_test.cc
         utilities/persistent_cache/hash_table_test.cc
         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_on_deletion_collector_test.cc
         utilities/transactions/optimistic_transaction_test.cc
@@ -1097,23 +986,35 @@ if(WITH_TESTS)
     list(APPEND TESTS utilities/env_librados_test.cc)
   endif()
 
-  if(WITH_FOLLY_DISTRIBUTED_MUTEX)
-    list(APPEND TESTS third-party/folly/folly/synchronization/test/DistributedMutexTest.cpp)
-  endif()
+  set(BENCHMARKS
+    cache/cache_bench.cc
+    memtable/memtablerep_bench.cc
+    db/range_del_aggregator_bench.cc
+    tools/db_bench.cc
+    table/table_reader_bench.cc
+    utilities/persistent_cache/hash_table_bench.cc)
+  add_library(testharness OBJECT util/testharness.cc)
+  foreach(sourcefile ${BENCHMARKS})
+    get_filename_component(exename ${sourcefile} NAME_WE)
+    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
+      $<TARGET_OBJECTS:testharness>)
+    target_link_libraries(${exename}${ARTIFACT_SUFFIX} gtest ${LIBS})
+  endforeach(sourcefile ${BENCHMARKS})
 
+  # For test util library that is build only in DEBUG mode
+  # and linked to tests. Add test only code that is not #ifdefed for Release here.
   set(TESTUTIL_SOURCE
       db/db_test_util.cc
       monitoring/thread_status_updater_debug.cc
       table/mock_table.cc
-      test_util/fault_injection_test_env.cc
-      test_util/fault_injection_test_fs.cc
+      util/fault_injection_test_env.cc
       utilities/cassandra/test_utils.cc
   )
+  # test utilities are only build in debug
   enable_testing()
   add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND})
   set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
   add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
-  target_link_libraries(${TESTUTILLIB} ${ROCKSDB_LIB})
   if(MSVC)
     set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
   endif()
@@ -1123,92 +1024,46 @@ if(WITH_TESTS)
         EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
         )
 
-  foreach(sourcefile ${TESTS})
+  # Tests are excluded from Release builds
+  set(TEST_EXES ${TESTS})
+
+  foreach(sourcefile ${TEST_EXES})
       get_filename_component(exename ${sourcefile} NAME_WE)
-      add_executable(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+      add_executable(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} ${sourcefile}
+        $<TARGET_OBJECTS:testharness>)
       set_target_properties(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX}
         PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
         EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
         EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
         OUTPUT_NAME ${exename}${ARTIFACT_SUFFIX}
         )
-      target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} testharness gtest ${ROCKSDB_LIB})
+      target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} gtest ${LIBS})
       if(NOT "${exename}" MATCHES "db_sanity_test")
         add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
         add_dependencies(check ${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX})
       endif()
-  endforeach(sourcefile ${TESTS})
+  endforeach(sourcefile ${TEST_EXES})
 
-  if(WIN32)
-    # C executables must link to a shared object
-    if(ROCKSDB_BUILD_SHARED)
-      set(ROCKSDB_LIB_FOR_C ${ROCKSDB_SHARED_LIB})
-    else()
-      set(ROCKSDB_LIB_FOR_C OFF)
-    endif()
-  else()
-    set(ROCKSDB_LIB_FOR_C ${ROCKSDB_LIB})
-  endif()
+  # C executables must link to a shared object
+  set(C_TESTS db/c_test.c)
+  set(C_TEST_EXES ${C_TESTS})
 
-  if(ROCKSDB_LIB_FOR_C)
-    set(C_TESTS db/c_test.c)
-    # C executables must link to a shared object
-    add_executable(c_test db/c_test.c)
-    target_link_libraries(c_test ${ROCKSDB_SHARED_LIB} testharness)
-    add_test(NAME c_test COMMAND c_test${ARTIFACT_SUFFIX})
-    add_dependencies(check c_test)
-  endif()
+  foreach(sourcefile ${C_TEST_EXES})
+      string(REPLACE ".c" "" exename ${sourcefile})
+      string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
+      add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+      set_target_properties(${exename}${ARTIFACT_SUFFIX}
+        PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
+        EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
+        EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
+        )
+      target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${ROCKSDB_IMPORT_LIB} testutillib${ARTIFACT_SUFFIX})
+      add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
+      add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
+  endforeach(sourcefile ${C_TEST_EXES})
 endif()
 
-option(WITH_BENCHMARK_TOOLS "build with benchmarks" ON)
-if(WITH_BENCHMARK_TOOLS)
-  add_executable(db_bench
-    tools/db_bench.cc
-    tools/db_bench_tool.cc)
-  target_link_libraries(db_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(cache_bench
-    cache/cache_bench.cc)
-  target_link_libraries(cache_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(memtablerep_bench
-    memtable/memtablerep_bench.cc)
-  target_link_libraries(memtablerep_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(range_del_aggregator_bench
-    db/range_del_aggregator_bench.cc)
-  target_link_libraries(range_del_aggregator_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(table_reader_bench
-    table/table_reader_bench.cc)
-  target_link_libraries(table_reader_bench
-    ${ROCKSDB_LIB} testharness)
-
-  add_executable(filter_bench
-    util/filter_bench.cc)
-  target_link_libraries(filter_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(hash_table_bench
-    utilities/persistent_cache/hash_table_bench.cc)
-  target_link_libraries(hash_table_bench
-    ${ROCKSDB_LIB})
-endif()
-
-option(WITH_CORE_TOOLS "build with ldb and sst_dump" ON)
 option(WITH_TOOLS "build with tools" ON)
-if(WITH_CORE_TOOLS OR WITH_TOOLS)
-  add_subdirectory(tools)
-  add_custom_target(core_tools
-    DEPENDS ${core_tool_deps})
-endif()
-
 if(WITH_TOOLS)
-  add_subdirectory(db_stress_tool)
-  add_custom_target(tools
-    DEPENDS ${tool_deps})
+  add_subdirectory(tools)
 endif()

CODE_OF_CONDUCT.md

@@ -1,77 +1,3 @@
 # Code of Conduct
 
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to make participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, sex characteristics, gender identity and expression,
-level of experience, education, socio-economic status, nationality, personal
-appearance, race, religion, or sexual identity and orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-  advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-  address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies within all project spaces, and it also applies when
-an individual is representing the project or its community in public spaces.
-Examples of representing a project or community include using an official
-project e-mail address, posting via an official social media account, or acting
-as an appointed representative at an online or offline event. Representation of
-a project may be further defined and clarified by project maintainers.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at <opensource-conduct@fb.com>. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
-
+Facebook has adopted a Code of Conduct that we expect project participants to adhere to. Please [read the full text](https://code.facebook.com/codeofconduct) so that you can understand what actions will and will not be tolerated.

HISTORY.md

@@ -1,307 +1,5 @@
 # Rocksdb Change Log
 ## Unreleased
-### Public API Change
-* Fix spelling so that API now has correctly spelled transaction state name `COMMITTED`, while the old misspelled `COMMITED` is still available as an alias.
-
-### Bug Fixes
-* Fix a bug where range tombstone blocks in ingested files were cached incorrectly during ingestion. If range tombstones were read from those incorrectly cached blocks, the keys they covered would be exposed.
-* Fix a data race that might cause crash when calling DB::GetCreationTimeOfOldestFile() by a small chance. The bug was introduced in 6.6 Release.
-
-### Performance Improvements
-* In CompactRange, for levels starting from 0, if the level does not have any file with any key falling in the specified range, the level is skipped. So instead of always compacting from level 0, the compaction starts from the first level with keys in the specified range until the last such level.
-
-### New Features
-* Basic support for user timestamp in iterator. Seek/SeekToFirst/Next and lower/upper bounds are supported. Reverse iteration is not supported. Merge is not considered.
-* When file lock failure when the lock is held by the current process, return acquiring time and thread ID in the error message.
-
-## 6.8.0 (02/24/2020)
-### Java API Changes
-* Major breaking changes to Java comparators, toward standardizing on ByteBuffer for performant, locale-neutral operations on keys (#6252).
-* Added overloads of common API methods using direct ByteBuffers for keys and values (#2283).
-
-### Bug Fixes
-* Fix incorrect results while block-based table uses kHashSearch, together with Prev()/SeekForPrev().
-* Fix a bug that prevents opening a DB after two consecutive crash with TransactionDB, where the first crash recovers from a corrupted WAL with kPointInTimeRecovery but the second cannot.
-* Fixed issue #6316 that can cause a corruption of the MANIFEST file in the middle when writing to it fails due to no disk space.
-* Add DBOptions::skip_checking_sst_file_sizes_on_db_open. It disables potentially expensive checking of all sst file sizes in DB::Open().
-* BlobDB now ignores trivially moved files when updating the mapping between blob files and SSTs. This should mitigate issue #6338 where out of order flush/compaction notifications could trigger an assertion with the earlier code.
-* Batched MultiGet() ignores IO errors while reading data blocks, causing it to potentially continue looking for a key and returning stale results.
-* `WriteBatchWithIndex::DeleteRange` returns `Status::NotSupported`. Previously it returned success even though reads on the batch did not account for range tombstones. The corresponding language bindings now cannot be used. In C, that includes `rocksdb_writebatch_wi_delete_range`, `rocksdb_writebatch_wi_delete_range_cf`, `rocksdb_writebatch_wi_delete_rangev`, and `rocksdb_writebatch_wi_delete_rangev_cf`. In Java, that includes `WriteBatchWithIndex::deleteRange`.
-* Assign new MANIFEST file number when caller tries to create a new MANIFEST by calling LogAndApply(..., new_descriptor_log=true). This bug can cause MANIFEST being overwritten during recovery if options.write_dbid_to_manifest = true and there are WAL file(s).
-
-### Performance Improvements
-* Perfom readahead when reading from option files. Inside DB, options.log_readahead_size will be used as the readahead size. In other cases, a default 512KB is used.
-
-### Public API Change
-* The BlobDB garbage collector now emits the statistics `BLOB_DB_GC_NUM_FILES` (number of blob files obsoleted during GC), `BLOB_DB_GC_NUM_NEW_FILES` (number of new blob files generated during GC), `BLOB_DB_GC_FAILURES` (number of failed GC passes), `BLOB_DB_GC_NUM_KEYS_RELOCATED` (number of blobs relocated during GC), and `BLOB_DB_GC_BYTES_RELOCATED` (total size of blobs relocated during GC). On the other hand, the following statistics, which are not relevant for the new GC implementation, are now deprecated: `BLOB_DB_GC_NUM_KEYS_OVERWRITTEN`, `BLOB_DB_GC_NUM_KEYS_EXPIRED`, `BLOB_DB_GC_BYTES_OVERWRITTEN`, `BLOB_DB_GC_BYTES_EXPIRED`, and `BLOB_DB_GC_MICROS`.
-* Disable recycle_log_file_num when an inconsistent recovery modes are requested: kPointInTimeRecovery and kAbsoluteConsistency
-
-### New Features
-* Added the checksum for each SST file generated by Flush or Compaction. Added sst_file_checksum_func to Options such that user can plugin their own SST file checksum function via override the FileChecksumFunc class. If user does not set the sst_file_checksum_func, SST file checksum calculation will not be enabled. The checksum information inlcuding uint32_t checksum value and a checksum function name (string). The checksum information is stored in FileMetadata in version store and also logged to MANIFEST. A new tool is added to LDB such that user can dump out a list of file checksum information from MANIFEST (stored in an unordered_map).
-* `db_bench` now supports `value_size_distribution_type`, `value_size_min`, `value_size_max` options for generating random variable sized value. Added `blob_db_compression_type` option for BlobDB to enable blob compression.
-* Replace RocksDB namespace "rocksdb" with flag "ROCKSDB_NAMESPACE" which if is not defined, defined as "rocksdb" in header file rocksdb_namespace.h.
-
-## 6.7.0 (01/21/2020)
-### Public API Change
-* Added a rocksdb::FileSystem class in include/rocksdb/file_system.h to encapsulate file creation/read/write operations, and an option DBOptions::file_system to allow a user to pass in an instance of rocksdb::FileSystem. If its a non-null value, this will take precendence over DBOptions::env for file operations. A new API rocksdb::FileSystem::Default() returns a platform default object. The DBOptions::env option and Env::Default() API will continue to be used for threading and other OS related functions, and where DBOptions::file_system is not specified, for file operations. For storage developers who are accustomed to rocksdb::Env, the interface in rocksdb::FileSystem is new and will probably undergo some changes as more storage systems are ported to it from rocksdb::Env. As of now, no env other than Posix has been ported to the new interface.
-* A new rocksdb::NewSstFileManager() API that allows the caller to pass in separate Env and FileSystem objects.
-* Changed Java API for RocksDB.keyMayExist functions to use Holder<byte[]> instead of StringBuilder, so that retrieved values need not decode to Strings.
-* A new `OptimisticTransactionDBOptions` Option that allows users to configure occ validation policy. The default policy changes from kValidateSerial to kValidateParallel to reduce mutex contention.
-
-### Bug Fixes
-* Fix a bug that can cause unnecessary bg thread to be scheduled(#6104).
-* Fix crash caused by concurrent CF iterations and drops(#6147).
-* Fix a race condition for cfd->log_number_ between manifest switch and memtable switch (PR 6249) when number of column families is greater than 1.
-* Fix a bug on fractional cascading index when multiple files at the same level contain the same smallest user key, and those user keys are for merge operands. In this case, Get() the exact key may miss some merge operands.
-* Delcare kHashSearch index type feature-incompatible with index_block_restart_interval larger than 1.
-* Fixed an issue where the thread pools were not resized upon setting `max_background_jobs` dynamically through the `SetDBOptions` interface.
-* Fix a bug that can cause write threads to hang when a slowdown/stall happens and there is a mix of writers with WriteOptions::no_slowdown set/unset.
-* Fixed an issue where an incorrect "number of input records" value was used to compute the "records dropped" statistics for compactions.
-* Fix a regression bug that causes segfault when hash is used, max_open_files != -1 and total order seek is used and switched back.
-
-### New Features
-* It is now possible to enable periodic compactions for the base DB when using BlobDB.
-* BlobDB now garbage collects non-TTL blobs when `enable_garbage_collection` is set to `true` in `BlobDBOptions`. Garbage collection is performed during compaction: any valid blobs located in the oldest N files (where N is the number of non-TTL blob files multiplied by the value of `BlobDBOptions::garbage_collection_cutoff`) encountered during compaction get relocated to new blob files, and old blob files are dropped once they are no longer needed. Note: we recommend enabling periodic compactions for the base DB when using this feature to deal with the case when some old blob files are kept alive by SSTs that otherwise do not get picked for compaction.
-* `db_bench` now supports the `garbage_collection_cutoff` option for BlobDB.
-* Introduce ReadOptions.auto_prefix_mode. When set to true, iterator will return the same result as total order seek, but may choose to use prefix seek internally based on seek key and iterator upper bound.
-* MultiGet() can use IO Uring to parallelize read from the same SST file. This featuer is by default disabled. It can be enabled with environment variable ROCKSDB_USE_IO_URING.
-
-## 6.6.2 (01/13/2020)
-### Bug Fixes
-* Fixed a bug where non-L0 compaction input files were not considered to compute the `creation_time` of new compaction outputs.
-
-## 6.6.1 (01/02/2020)
-### Bug Fixes
-* Fix a bug in WriteBatchWithIndex::MultiGetFromBatchAndDB, which is called by Transaction::MultiGet, that causes due to stale pointer access when the number of keys is > 32
-* Fixed two performance issues related to memtable history trimming. First, a new SuperVersion is now created only if some memtables were actually trimmed. Second, trimming is only scheduled if there is at least one flushed memtable that is kept in memory for the purposes of transaction conflict checking.
-* BlobDB no longer updates the SST to blob file mapping upon failed compactions.
-* Fix a bug in which a snapshot read through an iterator could be affected by a DeleteRange after the snapshot (#6062).
-* Fixed a bug where BlobDB was comparing the `ColumnFamilyHandle` pointers themselves instead of only the column family IDs when checking whether an API call uses the default column family or not.
-* Delete superversions in BackgroundCallPurge.
-* Fix use-after-free and double-deleting files in BackgroundCallPurge().
-
-## 6.6.0 (11/25/2019)
-### Bug Fixes
-* Fix data corruption caused by output of intra-L0 compaction on ingested file not being placed in correct order in L0.
-* Fix a data race between Version::GetColumnFamilyMetaData() and Compaction::MarkFilesBeingCompacted() for access to being_compacted (#6056). The current fix acquires the db mutex during Version::GetColumnFamilyMetaData(), which may cause regression.
-* Fix a bug in DBIter that is_blob_ state isn't updated when iterating backward using seek.
-* Fix a bug when format_version=3, partitioned filters, and prefix search are used in conjunction. The bug could result into Seek::(prefix) returning NotFound for an existing prefix.
-* Revert the feature "Merging iterator to avoid child iterator reseek for some cases (#5286)" since it might cause strong results when reseek happens with a different iterator upper bound.
-* Fix a bug causing a crash during ingest external file when background compaction cause severe error (file not found).
-* Fix a bug when partitioned filters and prefix search are used in conjunction, ::SeekForPrev could return invalid for an existing prefix. ::SeekForPrev might be called by the user, or internally on ::Prev, or within ::Seek if the return value involves Delete or a Merge operand.
-* Fix OnFlushCompleted fired before flush result persisted in MANIFEST when there's concurrent flush job. The bug exists since OnFlushCompleted was introduced in rocksdb 3.8.
-* Fixed an sst_dump crash on some plain table SST files.
-* Fixed a memory leak in some error cases of opening plain table SST files.
-* Fix a bug when a crash happens while calling WriteLevel0TableForRecovery for multiple column families, leading to a column family's log number greater than the first corrutped log number when the DB is being opened in PointInTime recovery mode during next recovery attempt (#5856).
-
-### New Features
-* Universal compaction to support options.periodic_compaction_seconds. A full compaction will be triggered if any file is over the threshold.
-* `GetLiveFilesMetaData` and `GetColumnFamilyMetaData` now expose the file number of SST files as well as the oldest blob file referenced by each SST.
-* A batched MultiGet API (DB::MultiGet()) that supports retrieving keys from multiple column families.
-* Full and partitioned filters in the block-based table use an improved Bloom filter implementation, enabled with format_version 5 (or above) because previous releases cannot read this filter. This replacement is faster and more accurate, especially for high bits per key or millions of keys in a single (full) filter. For example, the new Bloom filter has the same false positive rate at 9.55 bits per key as the old one at 10 bits per key, and a lower false positive rate at 16 bits per key than the old one at 100 bits per key.
-* Added AVX2 instructions to USE_SSE builds to accelerate the new Bloom filter and XXH3-based hash function on compatible x86_64 platforms (Haswell and later, ~2014).
-* Support options.ttl or options.periodic_compaction_seconds with options.max_open_files = -1. File's oldest ancester time and file creation time will be written to manifest. If it is availalbe, this information will be used instead of creation_time and file_creation_time in table properties.
-* Setting options.ttl for universal compaction now has the same meaning as setting periodic_compaction_seconds.
-* SstFileMetaData also returns file creation time and oldest ancester time.
-* The `sst_dump` command line tool `recompress` command now displays how many blocks were compressed and how many were not, in particular how many were not compressed because the compression ratio was not met (12.5% threshold for GoodCompressionRatio), as seen in the `number.block.not_compressed` counter stat since version 6.0.0.
-* The block cache usage is now takes into account the overhead of metadata per each entry. This results into more accurate management of memory. A side-effect of this feature is that less items are fit into the block cache of the same size, which would result to higher cache miss rates. This can be remedied by increasing the block cache size or passing kDontChargeCacheMetadata to its constuctor to restore the old behavior.
-* When using BlobDB, a mapping is maintained and persisted in the MANIFEST between each SST file and the oldest non-TTL blob file it references.
-* `db_bench` now supports and by default issues non-TTL Puts to BlobDB. TTL Puts can be enabled by specifying a non-zero value for the `blob_db_max_ttl_range` command line parameter explicitly.
-* `sst_dump` now supports printing BlobDB blob indexes in a human-readable format. This can be enabled by specifying the `decode_blob_index` flag on the command line.
-* A number of new information elements are now exposed through the EventListener interface. For flushes, the file numbers of the new SST file and the oldest blob file referenced by the SST are propagated. For compactions, the level, file number, and the oldest blob file referenced are passed to the client for each compaction input and output file.
-
-### Public API Change
-* RocksDB release 4.1 or older will not be able to open DB generated by the new release. 4.2 was released on Feb 23, 2016.
-* TTL Compactions in Level compaction style now initiate successive cascading compactions on a key range so that it reaches the bottom level quickly on TTL expiry. `creation_time` table property for compaction output files is now set to the minimum of the creation times of all compaction inputs.
-* With FIFO compaction style, options.periodic_compaction_seconds will have the same meaning as options.ttl. Whichever stricter will be used. With the default options.periodic_compaction_seconds value with options.ttl's default of 0, RocksDB will give a default of 30 days.
-* Added an API GetCreationTimeOfOldestFile(uint64_t* creation_time) to get the file_creation_time of the oldest SST file in the DB.
-* FilterPolicy now exposes additional API to make it possible to choose filter configurations based on context, such as table level and compaction style. See `LevelAndStyleCustomFilterPolicy` in db_bloom_filter_test.cc. While most existing custom implementations of FilterPolicy should continue to work as before, those wrapping the return of NewBloomFilterPolicy will require overriding new function `GetBuilderWithContext()`, because calling `GetFilterBitsBuilder()` on the FilterPolicy returned by NewBloomFilterPolicy is no longer supported.
-* An unlikely usage of FilterPolicy is no longer supported. Calling GetFilterBitsBuilder() on the FilterPolicy returned by NewBloomFilterPolicy will now cause an assertion violation in debug builds, because RocksDB has internally migrated to a more elaborate interface that is expected to evolve further. Custom implementations of FilterPolicy should work as before, except those wrapping the return of NewBloomFilterPolicy, which will require a new override of a protected function in FilterPolicy.
-* NewBloomFilterPolicy now takes bits_per_key as a double instead of an int. This permits finer control over the memory vs. accuracy trade-off in the new Bloom filter implementation and should not change source code compatibility.
-* The option BackupableDBOptions::max_valid_backups_to_open is now only used when opening BackupEngineReadOnly. When opening a read/write BackupEngine, anything but the default value logs a warning and is treated as the default. This change ensures that backup deletion has proper accounting of shared files to ensure they are deleted when no longer referenced by a backup.
-* Deprecate `snap_refresh_nanos` option.
-* Added DisableManualCompaction/EnableManualCompaction to stop and resume manual compaction.
-* Add TryCatchUpWithPrimary() to StackableDB in non-LITE mode.
-* Add a new Env::LoadEnv() overloaded function to return a shared_ptr to Env.
-* Flush sets file name to "(nil)" for OnTableFileCreationCompleted() if the flush does not produce any L0. This can happen if the file is empty thus delete by RocksDB.
-
-### Default Option Changes
-* Changed the default value of periodic_compaction_seconds to `UINT64_MAX - 1` which allows RocksDB to auto-tune periodic compaction scheduling. When using the default value, periodic compactions are now auto-enabled if a compaction filter is used. A value of `0` will turn off the feature completely.
-* Changed the default value of ttl to `UINT64_MAX - 1` which allows RocksDB to auto-tune ttl value. When using the default value, TTL will be auto-enabled to 30 days, when the feature is supported. To revert the old behavior, you can explicitly set it to 0.
-
-### Performance Improvements
-* For 64-bit hashing, RocksDB is standardizing on a slightly modified preview version of XXH3. This function is now used for many non-persisted hashes, along with fastrange64() in place of the modulus operator, and some benchmarks show a slight improvement.
-* Level iterator to invlidate the iterator more often in prefix seek and the level is filtered out by prefix bloom.
-
-## 6.5.2 (11/15/2019)
-### Bug Fixes
-* Fix a assertion failure in MultiGet() when BlockBasedTableOptions::no_block_cache is true and there is no compressed block cache
-* Fix a buffer overrun problem in BlockBasedTable::MultiGet() when compression is enabled and no compressed block cache is configured.
-* If a call to BackupEngine::PurgeOldBackups or BackupEngine::DeleteBackup suffered a crash, power failure, or I/O error, files could be left over from old backups that could only be purged with a call to GarbageCollect. Any call to PurgeOldBackups, DeleteBackup, or GarbageCollect should now suffice to purge such files.
-
-## 6.5.1 (10/16/2019)
-### Bug Fixes
-* Revert the feature "Merging iterator to avoid child iterator reseek for some cases (#5286)" since it might cause strange results when reseek happens with a different iterator upper bound.
-* Fix a bug in BlockBasedTableIterator that might return incorrect results when reseek happens with a different iterator upper bound.
-* Fix a bug when partitioned filters and prefix search are used in conjunction, ::SeekForPrev could return invalid for an existing prefix. ::SeekForPrev might be called by the user, or internally on ::Prev, or within ::Seek if the return value involves Delete or a Merge operand.
-
-## 6.5.0 (9/13/2019)
-### Bug Fixes
-* Fixed a number of data races in BlobDB.
-* Fix a bug where the compaction snapshot refresh feature is not disabled as advertised when `snap_refresh_nanos` is set to 0..
-* Fix bloom filter lookups by the MultiGet batching API when BlockBasedTableOptions::whole_key_filtering is false, by checking that a key is in the perfix_extractor domain and extracting the prefix before looking up.
-* Fix a bug in file ingestion caused by incorrect file number allocation when the number of column families involved in the ingestion exceeds 2.
-
-### New Features
-* Introduced DBOptions::max_write_batch_group_size_bytes to configure maximum limit on number of bytes that are written in a single batch of WAL or memtable write. It is followed when the leader write size is larger than 1/8 of this limit.
-* VerifyChecksum() by default will issue readahead. Allow ReadOptions to be passed in to those functions to override the readhead size. For checksum verifying before external SST file ingestion, a new option IngestExternalFileOptions.verify_checksums_readahead_size, is added for this readahead setting.
-* When user uses options.force_consistency_check in RocksDb, instead of crashing the process, we now pass the error back to the users without killing the process.
-* Add an option `memtable_insert_hint_per_batch` to WriteOptions. If it is true, each WriteBatch will maintain its own insert hints for each memtable in concurrent write. See include/rocksdb/options.h for more details.
-
-### Public API Change
-* Added max_write_buffer_size_to_maintain option to better control memory usage of immutable memtables.
-* Added a lightweight API GetCurrentWalFile() to get last live WAL filename and size. Meant to be used as a helper for backup/restore tooling in a larger ecosystem such as MySQL with a MyRocks storage engine.
-* The MemTable Bloom filter, when enabled, now always uses cache locality. Options::bloom_locality now only affects the PlainTable SST format.
-
-### Performance Improvements
-* Improve the speed of the MemTable Bloom filter, reducing the write overhead of enabling it by 1/3 to 1/2, with similar benefit to read performance.
-
-## 6.4.0 (7/30/2019)
-### Default Option Change
-* LRUCacheOptions.high_pri_pool_ratio is set to 0.5 (previously 0.0) by default, which means that by default midpoint insertion is enabled. The same change is made for the default value of high_pri_pool_ratio argument in NewLRUCache(). When block cache is not explicitly created, the small block cache created by BlockBasedTable will still has this option to be 0.0.
-* Change BlockBasedTableOptions.cache_index_and_filter_blocks_with_high_priority's default value from false to true.
-
-### Public API Change
-* Filter and compression dictionary blocks are now handled similarly to data blocks with regards to the block cache: instead of storing objects in the cache, only the blocks themselves are cached. In addition, filter and compression dictionary blocks (as well as filter partitions) no longer get evicted from the cache when a table is closed.
-* Due to the above refactoring, block cache eviction statistics for filter and compression dictionary blocks are temporarily broken. We plan to reintroduce them in a later phase.
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-* Errors related to the retrieval of the compression dictionary are now propagated to the user.
-* db_bench adds a "benchmark" stats_history, which prints out the whole stats history.
-* Overload GetAllKeyVersions() to support non-default column family.
-* Added new APIs ExportColumnFamily() and CreateColumnFamilyWithImport() to support export and import of a Column Family. https://github.com/facebook/rocksdb/issues/3469
-* ldb sometimes uses a string-append merge operator if no merge operator is passed in. This is to allow users to print keys from a DB with a merge operator.
-* Replaces old Registra with ObjectRegistry to allow user to create custom object from string, also add LoadEnv() to Env.
-* Added new overload of GetApproximateSizes which gets SizeApproximationOptions object and returns a Status. The older overloads are redirecting their calls to this new method and no longer assert if the include_flags doesn't have either of INCLUDE_MEMTABLES or INCLUDE_FILES bits set. It's recommended to use the new method only, as it is more type safe and returns a meaningful status in case of errors.
-* LDBCommandRunner::RunCommand() to return the status code as an integer, rather than call exit() using the code.
-
-### New Features
-* Add argument `--secondary_path` to ldb to open the database as the secondary instance. This would keep the original DB intact.
-* Compression dictionary blocks are now prefetched and pinned in the cache (based on the customer's settings) the same way as index and filter blocks.
-* Added DBOptions::log_readahead_size which specifies the number of bytes to prefetch when reading the log. This is mostly useful for reading a remotely located log, as it can save the number of round-trips. If 0 (default), then the prefetching is disabled.
-* Added new option in SizeApproximationOptions used with DB::GetApproximateSizes. When approximating the files total size that is used to store a keys range, allow approximation with an error margin of up to total_files_size * files_size_error_margin. This allows to take some shortcuts in files size approximation, resulting in better performance, while guaranteeing the resulting error is within a reasonable margin.
-* Support loading custom objects in unit tests. In the affected unit tests, RocksDB will create custom Env objects based on environment variable TEST_ENV_URI. Users need to make sure custom object types are properly registered. For example, a static library should expose a `RegisterCustomObjects` function. By linking the unit test binary with the static library, the unit test can execute this function.
-
-### Performance Improvements
-* Reduce iterator key comparison for upper/lower bound check.
-* Improve performance of row_cache: make reads with newer snapshots than data in an SST file share the same cache key, except in some transaction cases.
-* The compression dictionary is no longer copied to a new object upon retrieval.
-
-### Bug Fixes
-* Fix ingested file and directory not being fsync.
-* Return TryAgain status in place of Corruption when new tail is not visible to TransactionLogIterator.
-* Fixed a regression where the fill_cache read option also affected index blocks.
-* Fixed an issue where using cache_index_and_filter_blocks==false affected partitions of partitioned indexes/filters as well.
-
-## 6.3.2 (8/15/2019)
-### Public API Change
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-
-### Bug Fixes
-* Fixed a regression where the fill_cache read option also affected index blocks.
-* Fixed an issue where using cache_index_and_filter_blocks==false affected partitions of partitioned indexes as well.
-
-## 6.3.1 (7/24/2019)
-### Bug Fixes
-* Fix auto rolling bug introduced in 6.3.0, which causes segfault if log file creation fails.
-
-## 6.3.0 (6/18/2019)
-### Public API Change
-* Now DB::Close() will return Aborted() error when there is unreleased snapshot. Users can retry after all snapshots are released.
-* Index blocks are now handled similarly to data blocks with regards to the block cache: instead of storing objects in the cache, only the blocks themselves are cached. In addition, index blocks no longer get evicted from the cache when a table is closed, can now use the compressed block cache (if any), and can be shared among multiple table readers.
-* Partitions of partitioned indexes no longer affect the read amplification statistics.
-* Due to the above refactoring, block cache eviction statistics for indexes are temporarily broken. We plan to reintroduce them in a later phase.
-* options.keep_log_file_num will be enforced strictly all the time. File names of all log files will be tracked, which may take significantly amount of memory if options.keep_log_file_num is large and either of options.max_log_file_size or options.log_file_time_to_roll is set.
-* Add initial support for Get/Put with user timestamps. Users can specify timestamps via ReadOptions and WriteOptions when calling DB::Get and DB::Put.
-* Accessing a partition of a partitioned filter or index through a pinned reference is no longer considered a cache hit.
-* Add C bindings for secondary instance, i.e. DBImplSecondary.
-* Rate limited deletion of WALs is only enabled if DBOptions::wal_dir is not set, or explicitly set to db_name passed to DB::Open and DBOptions::db_paths is empty, or same as db_paths[0].path
-
-### New Features
-* Add an option `snap_refresh_nanos` (default to 0) to periodically refresh the snapshot list in compaction jobs. Assign to 0 to disable the feature.
-* Add an option `unordered_write` which trades snapshot guarantees with higher write throughput. When used with WRITE_PREPARED transactions with two_write_queues=true, it offers higher throughput with however no compromise on guarantees.
-* Allow DBImplSecondary to remove memtables with obsolete data after replaying MANIFEST and WAL.
-* Add an option `failed_move_fall_back_to_copy` (default is true) for external SST ingestion. When `move_files` is true and hard link fails, ingestion falls back to copy if `failed_move_fall_back_to_copy` is true. Otherwise, ingestion reports an error.
-* Add command `list_file_range_deletes` in ldb, which prints out tombstones in SST files.
-
-### Performance Improvements
-* Reduce binary search when iterator reseek into the same data block.
-* DBIter::Next() can skip user key checking if previous entry's seqnum is 0.
-* Merging iterator to avoid child iterator reseek for some cases
-* Log Writer will flush after finishing the whole record, rather than a fragment.
-* Lower MultiGet batching API latency by reading data blocks from disk in parallel
-
-### General Improvements
-* Added new status code kColumnFamilyDropped to distinguish between Column Family Dropped and DB Shutdown in progress.
-* Improve ColumnFamilyOptions validation when creating a new column family.
-
-### Bug Fixes
-* Fix a bug in WAL replay of secondary instance by skipping write batches with older sequence numbers than the current last sequence number.
-* Fix flush's/compaction's merge processing logic which allowed `Put`s covered by range tombstones to reappear. Note `Put`s may exist even if the user only ever called `Merge()` due to an internal conversion during compaction to the bottommost level.
-* Fix/improve memtable earliest sequence assignment and WAL replay so that WAL entries of unflushed column families will not be skipped after replaying the MANIFEST and increasing db sequence due to another flushed/compacted column family.
-* Fix a bug caused by secondary not skipping the beginning of new MANIFEST.
-* On DB open, delete WAL trash files left behind in wal_dir
-
-## 6.2.0 (4/30/2019)
-### New Features
-* Add an option `strict_bytes_per_sync` that causes a file-writing thread to block rather than exceed the limit on bytes pending writeback specified by `bytes_per_sync` or `wal_bytes_per_sync`.
-* Improve range scan performance by avoiding per-key upper bound check in BlockBasedTableIterator.
-* Introduce Periodic Compaction for Level style compaction. Files are re-compacted periodically and put in the same level.
-* Block-based table index now contains exact highest key in the file, rather than an upper bound. This may improve Get() and iterator Seek() performance in some situations, especially when direct IO is enabled and block cache is disabled. A setting BlockBasedTableOptions::index_shortening is introduced to control this behavior. Set it to kShortenSeparatorsAndSuccessor to get the old behavior.
-* When reading from option file/string/map, customized envs can be filled according to object registry.
-* Improve range scan performance when using explicit user readahead by not creating new table readers for every iterator.
-* Add index type BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey. It significantly reduces read amplification in some setups, especially for iterator seeks. It's not fully implemented yet: IO errors are not handled right.
-
-### Public API Change
-* Change the behavior of OptimizeForPointLookup(): move away from hash-based block-based-table index, and use whole key memtable filtering.
-* Change the behavior of OptimizeForSmallDb(): use a 16MB block cache, put index and filter blocks into it, and cost the memtable size to it. DBOptions.OptimizeForSmallDb() and ColumnFamilyOptions.OptimizeForSmallDb() start to take an optional cache object.
-* Added BottommostLevelCompaction::kForceOptimized to avoid double compacting newly compacted files in the bottommost level compaction of manual compaction. Note this option may prohibit the manual compaction to produce a single file in the bottommost level.
-
-### Bug Fixes
-* Adjust WriteBufferManager's dummy entry size to block cache from 1MB to 256KB.
-* Fix a race condition between WritePrepared::Get and ::Put with duplicate keys.
-* Fix crash when memtable prefix bloom is enabled and read/write a key out of domain of prefix extractor.
-* Close a WAL file before another thread deletes it.
-* Fix an assertion failure `IsFlushPending() == true` caused by one bg thread releasing the db mutex in ~ColumnFamilyData and another thread clearing `flush_requested_` flag.
-
-## 6.1.1 (4/9/2019)
-### New Features
-* When reading from option file/string/map, customized comparators and/or merge operators can be filled according to object registry.
-
-### Public API Change
-
-### Bug Fixes
-* Fix a bug in 2PC where a sequence of txn prepare, memtable flush, and crash could result in losing the prepared transaction.
-* Fix a bug in Encryption Env which could cause encrypted files to be read beyond file boundaries.
-
-## 6.1.0 (3/27/2019)
-### New Features
-* Introduce two more stats levels, kExceptHistogramOrTimers and kExceptTimers.
-* Added a feature to perform data-block sampling for compressibility, and report stats to user.
-* Add support for trace filtering.
-* Add DBOptions.avoid_unnecessary_blocking_io. If true, we avoid file deletion when destroying ColumnFamilyHandle and Iterator. Instead, a job is scheduled to delete the files in background.
-
-### Public API Change
-* Remove bundled fbson library.
-* statistics.stats_level_ becomes atomic. It is preferred to use statistics.set_stats_level() and statistics.get_stats_level() to access it.
-* Introduce a new IOError subcode, PathNotFound, to indicate trying to open a nonexistent file or directory for read.
-* Add initial support for multiple db instances sharing the same data in single-writer, multi-reader mode.
-* Removed some "using std::xxx" from public headers.
-
-### Bug Fixes
-* Fix JEMALLOC_CXX_THROW macro missing from older Jemalloc versions, causing build failures on some platforms.
-* Fix SstFileReader not able to open file ingested with write_glbal_seqno=true.
-
-## 6.0.0 (2/19/2019)
 ### New Features
 * Enabled checkpoint on readonly db (DBImplReadOnly).
 * Make DB ignore dropped column families while committing results of atomic flush.
@@ -309,16 +7,8 @@
 * For users of dictionary compression with ZSTD v0.7.0+, we now reuse the same digested dictionary when compressing each of an SST file's data blocks for faster compression speeds.
 * For all users of dictionary compression who set `cache_index_and_filter_blocks == true`, we now store dictionary data used for decompression in the block cache for better control over memory usage. For users of ZSTD v1.1.4+ who compile with -DZSTD_STATIC_LINKING_ONLY, this includes a digested dictionary, which is used to increase decompression speed.
 * Add support for block checksums verification for external SST files before ingestion.
-* Introduce stats history which periodically saves Statistics snapshots and added `GetStatsHistory` API to retrieve these snapshots.
-* Add a place holder in manifest which indicate a record from future that can be safely ignored.
-* Add support for trace sampling.
-* Enable properties block checksum verification for block-based tables.
-* For all users of dictionary compression, we now generate a separate dictionary for compressing each bottom-level SST file. Previously we reused a single dictionary for a whole compaction to bottom level. The new approach achieves better compression ratios; however, it uses more memory and CPU for buffering/sampling data blocks and training dictionaries.
-* Add whole key bloom filter support in memtable.
-* Files written by `SstFileWriter` will now use dictionary compression if it is configured in the file writer's `CompressionOptions`.
 
 ### Public API Change
-* Disallow CompactionFilter::IgnoreSnapshots() = false, because it is not very useful and the behavior is confusing. The filter will filter everything if there is no snapshot declared by the time the compaction starts. However, users can define a snapshot after the compaction starts and before it finishes and this new snapshot won't be repeatable, because after the compaction finishes, some keys may be dropped.
 * CompactionPri = kMinOverlappingRatio also uses compensated file size, which boosts file with lots of tombstones to be compacted first.
 * Transaction::GetForUpdate is extended with a do_validate parameter with default value of true. If false it skips validating the snapshot before doing the read. Similarly ::Merge, ::Put, ::Delete, and ::SingleDelete are extended with assume_tracked with default value of false. If true it indicates that call is assumed to be after a ::GetForUpdate.
 * `TableProperties::num_entries` and `TableProperties::num_deletions` now also account for number of range tombstones.
@@ -326,11 +16,7 @@
 * With "ldb ----try_load_options", when wal_dir specified by the option file doesn't exist, ignore it.
 * Change time resolution in FileOperationInfo.
 * Deleting Blob files also go through SStFileManager.
-* Remove CuckooHash memtable.
-* The counter stat `number.block.not_compressed` now also counts blocks not compressed due to poor compression ratio.
-* Remove ttl option from `CompactionOptionsFIFO`. The option has been deprecated and ttl in `ColumnFamilyOptions` is used instead.
-* Support SST file ingestion across multiple column families via DB::IngestExternalFiles. See the function's comment about atomicity.
-* Remove Lua compaction filter.
+* Remove PlainTable's store_index_in_file feature. When opening an existing DB with index in SST files, the index and bloom filter will still be rebuild while SST files are opened, in the same way as there is no index in the file.
 
 ### Bug Fixes
 * Fix a deadlock caused by compaction and file ingestion waiting for each other in the event of write stalls.
@@ -667,7 +353,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 
 ## 5.2.0 (02/08/2017)
 ### Public API Change
-* NewLRUCache() will determine number of shard bits automatically based on capacity, if the user doesn't pass one. This also impacts the default block cache when the user doesn't explicit provide one.
+* NewLRUCache() will determine number of shard bits automatically based on capacity, if the user doesn't pass one. This also impacts the default block cache when the user doesn't explict provide one.
 * Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files.
 * Options::use_direct_writes and Options::use_direct_reads are now ready to use.
 * (Experimental) Two-level indexing that partition the index and creates a 2nd level index on the partitions. The feature can be enabled by setting kTwoLevelIndexSearch as IndexType and configuring index_per_partition.
@@ -738,7 +424,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 
 ### New Features
 * A tool to migrate DB after options change. See include/rocksdb/utilities/option_change_migration.h.
-* Add ReadOptions.background_purge_on_iterator_cleanup. If true, we avoid file deletion when destroying iterators.
+* Add ReadOptions.background_purge_on_iterator_cleanup. If true, we avoid file deletion when destorying iterators.
 
 ## 4.10.0 (7/5/2016)
 ### Public API Change

LANGUAGE-BINDINGS.md

@@ -1,9 +1,7 @@
 This is the list of all known third-party language bindings for RocksDB. If something is missing, please open a pull request to add it.
 
 * Java - https://github.com/facebook/rocksdb/tree/master/java
-* Python
-    * http://python-rocksdb.readthedocs.io/en/latest/
-    * http://pyrocksdb.readthedocs.org/en/latest/ (unmaintained)
+* Python - http://pyrocksdb.readthedocs.org/en/latest/
 * Perl - https://metacpan.org/pod/RocksDB
 * Node.js - https://npmjs.org/package/rocksdb
 * Go - https://github.com/tecbot/gorocksdb

Makefile

@@ -82,23 +82,17 @@ ifeq ($(MAKECMDGOALS),rocksdbjavastatic)
 endif
 
 ifeq ($(MAKECMDGOALS),rocksdbjavastaticrelease)
-	ifneq ($(DEBUG_LEVEL),2)
-		DEBUG_LEVEL=0
-	endif
+	DEBUG_LEVEL=0
 endif
 
 ifeq ($(MAKECMDGOALS),rocksdbjavastaticreleasedocker)
-	ifneq ($(DEBUG_LEVEL),2)
-		DEBUG_LEVEL=0
-	endif
+        DEBUG_LEVEL=0
 endif
 
 ifeq ($(MAKECMDGOALS),rocksdbjavastaticpublish)
 	DEBUG_LEVEL=0
 endif
 
-$(info $$DEBUG_LEVEL is ${DEBUG_LEVEL})
-
 # Lite build flag.
 LITE ?= 0
 ifeq ($(LITE), 0)
@@ -143,12 +137,6 @@ CFLAGS +=  -DHAVE_POWER8
 HAVE_POWER8=1
 endif
 
-ifeq (,$(shell $(CXX) -fsyntax-only -march=armv8-a+crc+crypto -xc /dev/null 2>&1))
-CXXFLAGS += -march=armv8-a+crc+crypto
-CFLAGS += -march=armv8-a+crc+crypto
-ARMCRC_SOURCE=1
-endif
-
 # if we're compiling for release, compile without debug code (-DNDEBUG)
 ifeq ($(DEBUG_LEVEL),0)
 OPT += -DNDEBUG
@@ -207,7 +195,6 @@ AM_LINK = $(AM_V_CCLD)$(CXX) $^ $(EXEC_LDFLAGS) -o $@ $(LDFLAGS) $(COVERAGEFLAGS
 dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; export PORTABLE="$(PORTABLE)"; "$(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
-export JAVAC_ARGS
 CLEAN_FILES += make_config.mk
 
 missing_make_config_paths := $(shell				\
@@ -217,7 +204,7 @@ missing_make_config_paths := $(shell				\
 	done | sort | uniq)
 
 $(foreach path, $(missing_make_config_paths), \
-	$(warning Warning: $(path) does not exist))
+	$(warning Warning: $(path) dont exist))
 
 ifeq ($(PLATFORM), OS_AIX)
 # no debug info
@@ -257,8 +244,8 @@ endif
 ifdef COMPILE_WITH_TSAN
 	DISABLE_JEMALLOC=1
 	EXEC_LDFLAGS += -fsanitize=thread
-	PLATFORM_CCFLAGS += -fsanitize=thread -fPIC -DFOLLY_SANITIZE_THREAD
-	PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC -DFOLLY_SANITIZE_THREAD
+	PLATFORM_CCFLAGS += -fsanitize=thread -fPIC
+	PLATFORM_CXXFLAGS += -fsanitize=thread -fPIC
         # Turn off -pg when enabling TSAN testing, because that induces
         # a link failure.  TODO: find the root cause
 	PROFILING_FLAGS =
@@ -305,13 +292,9 @@ ifndef DISABLE_JEMALLOC
 	PLATFORM_CCFLAGS += $(JEMALLOC_INCLUDE)
 endif
 
-ifndef USE_FOLLY_DISTRIBUTED_MUTEX
-	USE_FOLLY_DISTRIBUTED_MUTEX=0
-endif
-
 export GTEST_THROW_ON_FAILURE=1
 export GTEST_HAS_EXCEPTIONS=1
-GTEST_DIR = ./third-party/gtest-1.8.1/fused-src
+GTEST_DIR = ./third-party/gtest-1.7.0/fused-src
 # AIX: pre-defined system headers are surrounded by an extern "C" block
 ifeq ($(PLATFORM), OS_AIX)
 	PLATFORM_CCFLAGS += -I$(GTEST_DIR)
@@ -321,23 +304,6 @@ else
 	PLATFORM_CXXFLAGS += -isystem $(GTEST_DIR)
 endif
 
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-	FOLLY_DIR = ./third-party/folly
-	# AIX: pre-defined system headers are surrounded by an extern "C" block
-	ifeq ($(PLATFORM), OS_AIX)
-		PLATFORM_CCFLAGS += -I$(FOLLY_DIR)
-		PLATFORM_CXXFLAGS += -I$(FOLLY_DIR)
-	else
-		PLATFORM_CCFLAGS += -isystem $(FOLLY_DIR)
-		PLATFORM_CXXFLAGS += -isystem $(FOLLY_DIR)
-	endif
-endif
-
-ifdef TEST_CACHE_LINE_SIZE
-  PLATFORM_CCFLAGS += -DTEST_CACHE_LINE_SIZE=$(TEST_CACHE_LINE_SIZE)
-  PLATFORM_CXXFLAGS += -DTEST_CACHE_LINE_SIZE=$(TEST_CACHE_LINE_SIZE)
-endif
-
 # This (the first rule) must depend on "all".
 default: all
 
@@ -424,13 +390,10 @@ endif
 
 LIBOBJECTS += $(TOOL_LIB_SOURCES:.cc=.o)
 MOCKOBJECTS = $(MOCK_LIB_SOURCES:.cc=.o)
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-  FOLLYOBJECTS = $(FOLLY_SOURCES:.cpp=.o)
-endif
 
 GTEST = $(GTEST_DIR)/gtest/gtest-all.o
-TESTUTIL = ./test_util/testutil.o
-TESTHARNESS = ./test_util/testharness.o $(TESTUTIL) $(MOCKOBJECTS) $(GTEST)
+TESTUTIL = ./util/testutil.o
+TESTHARNESS = ./util/testharness.o $(TESTUTIL) $(MOCKOBJECTS) $(GTEST)
 VALGRIND_ERROR = 2
 VALGRIND_VER := $(join $(VALGRIND_VER),valgrind)
 
@@ -440,13 +403,10 @@ BENCHTOOLOBJECTS = $(BENCH_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)
 
 ANALYZETOOLOBJECTS = $(ANALYZER_LIB_SOURCES:.cc=.o)
 
-STRESSTOOLOBJECTS = $(STRESS_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)
-
 EXPOBJECTS = $(LIBOBJECTS) $(TESTUTIL)
 
 TESTS = \
 	db_basic_test \
-	db_with_timestamp_basic_test \
 	db_encryption_test \
 	db_test2 \
 	external_sst_file_basic_test \
@@ -460,10 +420,7 @@ TESTS = \
 	inlineskiplist_test \
 	env_basic_test \
 	env_test \
-	env_logger_test \
-	io_posix_test \
 	hash_test \
-	random_test \
 	thread_local_test \
 	rate_limiter_test \
 	perf_context_test \
@@ -471,12 +428,11 @@ TESTS = \
 	db_wal_test \
 	db_block_cache_test \
 	db_test \
-	db_logical_block_size_cache_test \
 	db_blob_index_test \
+	db_bloom_filter_test \
 	db_iter_test \
 	db_iter_stress_test \
 	db_log_iter_test \
-	db_bloom_filter_test \
 	db_compaction_filter_test \
 	db_compaction_test \
 	db_dynamic_level_test \
@@ -485,10 +441,8 @@ TESTS = \
 	db_iterator_test \
 	db_memtable_test \
 	db_merge_operator_test \
-	db_merge_operand_test \
 	db_options_test \
 	db_range_del_test \
-	db_secondary_test \
 	db_sst_test \
 	db_tailing_iter_test \
 	db_io_failure_test \
@@ -496,7 +450,7 @@ TESTS = \
 	db_table_properties_test \
 	db_statistics_test \
 	db_write_test \
-	error_handler_fs_test \
+	error_handler_test \
 	autovector_test \
 	blob_db_test \
 	cleanable_test \
@@ -507,7 +461,6 @@ TESTS = \
 	data_block_hash_index_test \
 	cache_test \
 	corruption_test \
-	slice_test \
 	slice_transform_test \
 	dbformat_test \
 	fault_injection_test \
@@ -533,7 +486,6 @@ TESTS = \
 	plain_table_db_test \
 	comparator_db_test \
 	external_sst_file_test \
-	import_column_family_test \
 	prefix_test \
 	skiplist_test \
 	write_buffer_manager_test \
@@ -544,7 +496,6 @@ TESTS = \
 	cassandra_serialize_test \
 	ttl_test \
 	backupable_db_test \
-	cache_simulator_test \
 	sim_cache_test \
 	version_edit_test \
 	version_set_test \
@@ -584,7 +535,7 @@ TESTS = \
 	ldb_cmd_test \
 	persistent_cache_test \
 	statistics_test \
-	stats_history_test \
+	lua_test \
 	lru_cache_test \
 	object_registry_test \
 	repair_test \
@@ -597,20 +548,9 @@ TESTS = \
 	range_tombstone_fragmenter_test \
 	range_del_aggregator_test \
 	sst_file_reader_test \
-	db_secondary_test \
-	block_cache_tracer_test \
-	block_cache_trace_analyzer_test \
-	defer_test \
-	blob_file_addition_test \
-	blob_file_garbage_test \
-
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-	TESTS += folly_synchronization_distributed_mutex_test
-endif
 
 PARALLEL_TEST = \
 	backupable_db_test \
-	db_bloom_filter_test \
 	db_compaction_filter_test \
 	db_compaction_test \
 	db_merge_operator_test \
@@ -619,9 +559,7 @@ PARALLEL_TEST = \
 	db_universal_compaction_test \
 	db_wal_test \
 	external_sst_file_test \
-	import_column_family_test \
 	fault_injection_test \
-	file_reader_writer_test \
 	inlineskiplist_test \
 	manual_compaction_test \
 	persistent_cache_test \
@@ -654,13 +592,12 @@ TOOLS = \
 	rocksdb_undump \
 	blob_dump \
 	trace_analyzer \
-	block_cache_trace_analyzer \
 
 TEST_LIBS = \
 	librocksdb_env_basic_test.a
 
 # TODO: add back forward_iterator_bench, after making it build in all environemnts.
-BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench filter_bench persistent_cache_bench range_del_aggregator_bench
+BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench persistent_cache_bench range_del_aggregator_bench
 
 # if user didn't config LIBNAME, set the default
 ifeq ($(LIBNAME),)
@@ -673,7 +610,6 @@ endif
 endif
 LIBRARY = ${LIBNAME}.a
 TOOLS_LIBRARY = ${LIBNAME}_tools.a
-STRESS_LIBRARY = ${LIBNAME}_stress.a
 
 ROCKSDB_MAJOR = $(shell egrep "ROCKSDB_MAJOR.[0-9]" include/rocksdb/version.h | cut -d ' ' -f 3)
 ROCKSDB_MINOR = $(shell egrep "ROCKSDB_MINOR.[0-9]" include/rocksdb/version.h | cut -d ' ' -f 3)
@@ -751,9 +687,7 @@ endif  # PLATFORM_SHARED_EXT
 .PHONY: blackbox_crash_test check clean coverage crash_test ldb_tests package \
 	release tags tags0 valgrind_check whitebox_crash_test format static_lib shared_lib all \
 	dbg rocksdbjavastatic rocksdbjava install install-static install-shared uninstall \
-	analyze tools tools_lib \
-	blackbox_crash_test_with_atomic_flush whitebox_crash_test_with_atomic_flush  \
-	blackbox_crash_test_with_txn whitebox_crash_test_with_txn
+	analyze tools tools_lib
 
 
 all: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(TESTS)
@@ -764,8 +698,6 @@ static_lib: $(LIBRARY)
 
 shared_lib: $(SHARED)
 
-stress_lib: $(STRESS_LIBRARY)
-
 tools: $(TOOLS)
 
 tools_lib: $(TOOLS_LIBRARY)
@@ -943,11 +875,10 @@ check: all
 	    $(MAKE) T="$$t" TMPD=$(TMPD) check_0;                       \
 	else                                                            \
 	    for t in $(TESTS); do                                       \
-	      echo "===== Running $$t (`date`)"; ./$$t || exit 1; done;          \
+	      echo "===== Running $$t"; ./$$t || exit 1; done;          \
 	fi
 	rm -rf $(TMPD)
 ifneq ($(PLATFORM), OS_AIX)
-	python tools/check_all_python.py
 ifeq ($(filter -DROCKSDB_LITE,$(OPT)),)
 	python tools/ldb_test.py
 	sh tools/rocksdb_dump_test.sh
@@ -956,7 +887,7 @@ endif
 
 # TODO add ldb_tests
 check_some: $(SUBSET)
-	for t in $(SUBSET); do echo "===== Running $$t (`date`)"; ./$$t || exit 1; done
+	for t in $(SUBSET); do echo "===== Running $$t"; ./$$t || exit 1; done
 
 .PHONY: ldb_tests
 ldb_tests: ldb
@@ -964,38 +895,23 @@ ldb_tests: ldb
 
 crash_test: whitebox_crash_test blackbox_crash_test
 
-crash_test_with_atomic_flush: whitebox_crash_test_with_atomic_flush blackbox_crash_test_with_atomic_flush
-
-crash_test_with_txn: whitebox_crash_test_with_txn blackbox_crash_test_with_txn
-
 blackbox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --enable_atomic_flush blackbox $(CRASH_TEST_EXT_ARGS)
 	python -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)
 
-blackbox_crash_test_with_atomic_flush: db_stress
-	python -u tools/db_crashtest.py --cf_consistency blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_txn: db_stress
-	python -u tools/db_crashtest.py --txn blackbox $(CRASH_TEST_EXT_ARGS)
-
 ifeq ($(CRASH_TEST_KILL_ODD),)
   CRASH_TEST_KILL_ODD=888887
 endif
 
 whitebox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
+      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --enable_atomic_flush whitebox  --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
 	python -u tools/db_crashtest.py whitebox  --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
 
-whitebox_crash_test_with_atomic_flush: db_stress
-	python -u tools/db_crashtest.py --cf_consistency whitebox  --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
-whitebox_crash_test_with_txn: db_stress
-	python -u tools/db_crashtest.py --txn whitebox --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
 asan_check:
 	$(MAKE) clean
 	COMPILE_WITH_ASAN=1 $(MAKE) check -j32
@@ -1006,16 +922,6 @@ asan_crash_test:
 	COMPILE_WITH_ASAN=1 $(MAKE) crash_test
 	$(MAKE) clean
 
-asan_crash_test_with_atomic_flush:
-	$(MAKE) clean
-	COMPILE_WITH_ASAN=1 $(MAKE) crash_test_with_atomic_flush
-	$(MAKE) clean
-
-asan_crash_test_with_txn:
-	$(MAKE) clean
-	COMPILE_WITH_ASAN=1 $(MAKE) crash_test_with_txn
-	$(MAKE) clean
-
 ubsan_check:
 	$(MAKE) clean
 	COMPILE_WITH_UBSAN=1 $(MAKE) check -j32
@@ -1026,16 +932,6 @@ ubsan_crash_test:
 	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test
 	$(MAKE) clean
 
-ubsan_crash_test_with_atomic_flush:
-	$(MAKE) clean
-	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test_with_atomic_flush
-	$(MAKE) clean
-
-ubsan_crash_test_with_txn:
-	$(MAKE) clean
-	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test_with_txn
-	$(MAKE) clean
-
 valgrind_test:
 	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
@@ -1062,7 +958,7 @@ ifneq ($(PAR_TEST),)
 parloop:
 	ret_bad=0;							\
 	for t in $(PAR_TEST); do		\
-		echo "===== Running $$t in parallel $(NUM_PAR) (`date`)";\
+		echo "===== Running $$t in parallel $(NUM_PAR)";\
 		if [ $(db_test) -eq 1 ]; then \
 			seq $(J) | v="$$t" build_tools/gnu_parallel --gnu --plain 's=$(TMPD)/rdb-{};  export TEST_TMPDIR=$$s;' \
 				'timeout 2m ./db_test --gtest_filter=$$v >> $$s/log-{} 2>1'; \
@@ -1105,9 +1001,6 @@ parallel_check: $(TESTS)
 		TMPD=$(TMPD) J=$(J) db_test=0 parloop;
 
 analyze: clean
-	USE_CLANG=1 $(MAKE) analyze_incremental
-
-analyze_incremental:
 	$(CLANG_SCAN_BUILD) --use-analyzer=$(CLANG_ANALYZER) \
 		--use-c++=$(CXX) --use-cc=$(CC) --status-bugs \
 		-o $(CURDIR)/scan_build_report \
@@ -1136,27 +1029,13 @@ unity_test: db/db_test.o db/db_test_util.o $(TESTHARNESS) $(TOOLLIBOBJECTS) unit
 rocksdb.h rocksdb.cc: build_tools/amalgamate.py Makefile $(LIB_SOURCES) unity.cc
 	build_tools/amalgamate.py -I. -i./include unity.cc -x include/rocksdb/c.h -H rocksdb.h -o rocksdb.cc
 
-clean: clean-ext-libraries-all clean-rocks clean-rocksjava
-
-clean-not-downloaded: clean-ext-libraries-bin clean-rocks clean-not-downloaded-rocksjava
-
-clean-rocks:
-	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(LIBRARY) $(SHARED)
+clean:
+	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(LIBRARY) $(SHARED)
 	rm -rf $(CLEAN_FILES) ios-x86 ios-arm scan_build_report
 	$(FIND) . -name "*.[oda]" -exec rm -f {} \;
 	$(FIND) . -type f -regex ".*\.\(\(gcda\)\|\(gcno\)\)" -exec rm {} \;
-
-clean-rocksjava:
-	cd java && $(MAKE) clean
-
-clean-not-downloaded-rocksjava:
-	cd java && $(MAKE) clean-not-downloaded
-
-clean-ext-libraries-all:
 	rm -rf bzip2* snappy* zlib* lz4* zstd*
-
-clean-ext-libraries-bin:
-	find . -maxdepth 1 -type d \( -name bzip2\* -or -name snappy\* -or -name zlib\* -or -name lz4\* -or -name zstd\* \) -prune -exec rm -rf {} \;
+	cd java; $(MAKE) clean
 
 tags:
 	ctags -R .
@@ -1187,10 +1066,6 @@ $(TOOLS_LIBRARY): $(BENCH_LIB_SOURCES:.cc=.o) $(TOOL_LIB_SOURCES:.cc=.o) $(LIB_S
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
 
-$(STRESS_LIBRARY): $(LIB_SOURCES:.cc=.o) $(TESTUTIL) $(ANALYZER_LIB_SOURCES:.cc=.o) $(STRESS_LIB_SOURCES:.cc=.o)
-	$(AM_V_AR)rm -f $@
-	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
-
 librocksdb_env_basic_test.a: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
@@ -1201,14 +1076,6 @@ db_bench: tools/db_bench.o $(BENCHTOOLOBJECTS)
 trace_analyzer: tools/trace_analyzer.o $(ANALYZETOOLOBJECTS) $(LIBOBJECTS)
 	$(AM_LINK)
 
-block_cache_trace_analyzer: tools/block_cache_analyzer/block_cache_trace_analyzer_tool.o $(ANALYZETOOLOBJECTS) $(LIBOBJECTS)
-	$(AM_LINK)
-
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-folly_synchronization_distributed_mutex_test: $(LIBOBJECTS) $(TESTHARNESS) $(FOLLYOBJECTS) third-party/folly/folly/synchronization/test/DistributedMutexTest.o
-	$(AM_LINK)
-endif
-
 cache_bench: cache/cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
@@ -1218,10 +1085,7 @@ persistent_cache_bench: utilities/persistent_cache/persistent_cache_bench.o $(LI
 memtablerep_bench: memtable/memtablerep_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
-filter_bench: util/filter_bench.o $(LIBOBJECTS) $(TESTUTIL)
-	$(AM_LINK)
-
-db_stress: db_stress_tool/db_stress.o $(STRESSTOOLOBJECTS)
+db_stress: tools/db_stress.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
 write_stress: tools/write_stress.o $(LIBOBJECTS) $(TESTUTIL)
@@ -1233,7 +1097,7 @@ db_sanity_test: tools/db_sanity_test.o $(LIBOBJECTS) $(TESTUTIL)
 db_repl_stress: tools/db_repl_stress.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
-arena_test: memory/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
+arena_test: util/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 autovector_test: util/autovector_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1263,9 +1127,6 @@ coding_test: util/coding_test.o $(LIBOBJECTS) $(TESTHARNESS)
 hash_test: util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-random_test: util/random_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 option_change_migration_test: utilities/option_change_migration/option_change_migration_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1293,24 +1154,18 @@ histogram_test: monitoring/histogram_test.o $(LIBOBJECTS) $(TESTHARNESS)
 thread_local_test: util/thread_local_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-corruption_test: db/corruption_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+corruption_test: db/corruption_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 crc32c_test: util/crc32c_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-slice_test: util/slice_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 slice_transform_test: util/slice_transform_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 db_basic_test: db/db_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-db_with_timestamp_basic_test: db/db_with_timestamp_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 db_encryption_test: db/db_encryption_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1320,10 +1175,7 @@ db_test: db/db_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 db_test2: db/db_test2.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-db_logical_block_size_cache_test: db/db_logical_block_size_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-db_blob_index_test: db/blob/db_blob_index_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+db_blob_index_test: db/db_blob_index_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 db_block_cache_test: db/db_block_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1359,9 +1211,6 @@ db_memtable_test: db/db_memtable_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHA
 db_merge_operator_test: db/db_merge_operator_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-db_merge_operand_test: db/db_merge_operand_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 db_options_test: db/db_options_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1377,7 +1226,7 @@ db_statistics_test: db/db_statistics_test.o db/db_test_util.o $(LIBOBJECTS) $(TE
 db_write_test: db/db_write_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-error_handler_fs_test: db/error_handler_fs_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+error_handler_test: db/error_handler_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 external_sst_file_basic_test: db/external_sst_file_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1386,9 +1235,6 @@ external_sst_file_basic_test: db/external_sst_file_basic_test.o db/db_test_util.
 external_sst_file_test: db/external_sst_file_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-import_column_family_test: db/import_column_family_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 db_tailing_iter_test: db/db_tailing_iter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1437,9 +1283,6 @@ backupable_db_test: utilities/backupable/backupable_db_test.o $(LIBOBJECTS) $(TE
 checkpoint_test: utilities/checkpoint/checkpoint_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-cache_simulator_test: utilities/simulator_cache/cache_simulator_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 sim_cache_test: utilities/simulator_cache/sim_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1466,13 +1309,13 @@ write_batch_with_index_test: utilities/write_batch_with_index/write_batch_with_i
 flush_job_test: db/flush_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-compaction_iterator_test: db/compaction/compaction_iterator_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_iterator_test: db/compaction_iterator_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-compaction_job_test: db/compaction/compaction_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_job_test: db/compaction_job_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-compaction_job_stats_test: db/compaction/compaction_job_stats_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_job_stats_test: db/compaction_job_stats_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 compact_on_deletion_collector_test: utilities/table_properties_collectors/compact_on_deletion_collector_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1490,16 +1333,13 @@ env_basic_test: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 env_test: env/env_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-io_posix_test: env/io_posix_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 rate_limiter_test: util/rate_limiter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-delete_scheduler_test: file/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
+delete_scheduler_test: util/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1508,13 +1348,13 @@ filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
 file_reader_writer_test: util/file_reader_writer_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-block_based_filter_block_test: table/block_based/block_based_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+block_based_filter_block_test: table/block_based_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-full_filter_block_test: table/block_based/full_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+full_filter_block_test: table/full_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-partitioned_filter_block_test: table/block_based/partitioned_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+partitioned_filter_block_test: table/partitioned_filter_block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 log_test: db/log_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1526,10 +1366,10 @@ cleanable_test: table/cleanable_test.o $(LIBOBJECTS) $(TESTHARNESS)
 table_test: table/table_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-block_test: table/block_based/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
+block_test: table/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-data_block_hash_index_test: table/block_based/data_block_hash_index_test.o $(LIBOBJECTS) $(TESTHARNESS)
+data_block_hash_index_test: table/data_block_hash_index_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 inlineskiplist_test: memtable/inlineskiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1547,7 +1387,7 @@ version_edit_test: db/version_edit_test.o $(LIBOBJECTS) $(TESTHARNESS)
 version_set_test: db/version_set_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-compaction_picker_test: db/compaction/compaction_picker_test.o $(LIBOBJECTS) $(TESTHARNESS)
+compaction_picker_test: db/compaction_picker_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 version_builder_test: db/version_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1583,10 +1423,10 @@ util_merge_operators_test: utilities/util_merge_operators_test.o $(LIBOBJECTS) $
 options_file_test: db/options_file_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-deletefile_test: db/deletefile_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+deletefile_test: db/deletefile_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-obsolete_files_test: db/obsolete_files_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+obsolete_files_test: db/obsolete_files_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
@@ -1595,10 +1435,10 @@ rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
 rocksdb_undump: tools/dump/rocksdb_undump.o $(LIBOBJECTS)
 	$(AM_LINK)
 
-cuckoo_table_builder_test: table/cuckoo/cuckoo_table_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
+cuckoo_table_builder_test: table/cuckoo_table_builder_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-cuckoo_table_reader_test: table/cuckoo/cuckoo_table_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
+cuckoo_table_reader_test: table/cuckoo_table_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 cuckoo_table_db_test: db/cuckoo_table_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1628,7 +1468,7 @@ db_bench_tool_test: tools/db_bench_tool_test.o $(BENCHTOOLOBJECTS) $(TESTHARNESS
 trace_analyzer_test: tools/trace_analyzer_test.o $(LIBOBJECTS) $(ANALYZETOOLOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-event_logger_test: logging/event_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
+event_logger_test: util/event_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 timer_queue_test: util/timer_queue_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1649,10 +1489,7 @@ manual_compaction_test: db/manual_compaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 filelock_test: util/filelock_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-auto_roll_logger_test: logging/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-env_logger_test: logging/env_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
+auto_roll_logger_test: util/auto_roll_logger_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 memtable_list_test: db/memtable_list_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1697,10 +1534,10 @@ persistent_cache_test: utilities/persistent_cache/persistent_cache_test.o  db/db
 statistics_test: monitoring/statistics_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-stats_history_test: monitoring/stats_history_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+lru_cache_test: cache/lru_cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-lru_cache_test: cache/lru_cache_test.o $(LIBOBJECTS) $(TESTHARNESS)
+lua_test: utilities/lua/rocks_lua_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 range_del_aggregator_test: db/range_del_aggregator_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1721,24 +1558,6 @@ range_tombstone_fragmenter_test: db/range_tombstone_fragmenter_test.o db/db_test
 sst_file_reader_test: table/sst_file_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-db_secondary_test: db/db_impl/db_secondary_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-block_cache_tracer_test: trace_replay/block_cache_tracer_test.o trace_replay/block_cache_tracer.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-block_cache_trace_analyzer_test: tools/block_cache_analyzer/block_cache_trace_analyzer_test.o tools/block_cache_analyzer/block_cache_trace_analyzer.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-defer_test: util/defer_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-blob_file_addition_test: db/blob/blob_file_addition_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-blob_file_garbage_test: db/blob/blob_file_garbage_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1784,7 +1603,7 @@ JAVA_INCLUDE = -I$(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 arm64 aarch64 sparc64, $(MACHINE)))
+	ifneq (,$(filter $(MACHINE), amd64 arm64 sparc64))
 		ARCH := 64
 	else
 		ARCH := 32
@@ -1793,23 +1612,12 @@ else
 	ARCH := $(shell getconf LONG_BIT)
 endif
 
-ifeq ($(shell ldd /usr/bin/env 2>/dev/null | grep -q musl; echo $$?),0)
-        JNI_LIBC = musl
-# GNU LibC (or glibc) is so pervasive we can assume it is the default
-# else
-#        JNI_LIBC = glibc
-endif
-
-ifneq ($(origin JNI_LIBC), undefined)
-  JNI_LIBC_POSTFIX = -$(JNI_LIBC)
-endif
-
-ifneq (,$(filter ppc% arm64 aarch64 sparc64, $(MACHINE)))
-	ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE)$(JNI_LIBC_POSTFIX).so
+ifeq (,$(findstring ppc,$(MACHINE)))
+        ROCKSDBJNILIB = librocksdbjni-linux$(ARCH).so
 else
-	ROCKSDBJNILIB = librocksdbjni-linux$(ARCH)$(JNI_LIBC_POSTFIX).so
+        ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE).so
 endif
-ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux$(ARCH)$(JNI_LIBC_POSTFIX).jar
+ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux$(ARCH).jar
 ROCKSDB_JAR_ALL = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH).jar
 ROCKSDB_JAVADOCS_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-javadoc.jar
 ROCKSDB_SOURCES_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-sources.jar
@@ -1820,15 +1628,15 @@ ZLIB_SHA256 ?= c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1
 ZLIB_DOWNLOAD_BASE ?= http://zlib.net
 BZIP2_VER ?= 1.0.6
 BZIP2_SHA256 ?= a2848f34fcd5d6cf47def00461fcb528a0484d8edef8208d6d2e2909dc61d9cd
-BZIP2_DOWNLOAD_BASE ?= https://downloads.sourceforge.net/project/bzip2
-SNAPPY_VER ?= 1.1.8
-SNAPPY_SHA256 ?= 16b677f07832a612b0836178db7f374e414f94657c138e6993cbfc5dcc58651f
+BZIP2_DOWNLOAD_BASE ?= https://web.archive.org/web/20180624184835/http://www.bzip.org
+SNAPPY_VER ?= 1.1.7
+SNAPPY_SHA256 ?= 3dfa02e873ff51a11ee02b9ca391807f0c8ea0529a4924afa645fbf97163f9d4
 SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/archive
-LZ4_VER ?= 1.9.2
-LZ4_SHA256 ?= 658ba6191fa44c92280d4aa2c271b0f4fbc0e34d249578dd05e50e76d0e5efcc
+LZ4_VER ?= 1.8.3
+LZ4_SHA256 ?= 33af5936ac06536805f9745e0b6d61da606a1f8b4cc5c04dd3cbaca3b9b4fc43
 LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
-ZSTD_VER ?= 1.4.4
-ZSTD_SHA256 ?= a364f5162c7d1a455cc915e8e3cf5f4bd8b75d09bc0f53965b0c9ca1383c52c8
+ZSTD_VER ?= 1.3.7
+ZSTD_SHA256 ?= 5dd1e90eb16c25425880c8a91327f63de22891ffed082fcc17e5ae84fce0d5fb
 ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
 CURL_SSL_OPTS ?= --tlsv1
 
@@ -1868,7 +1676,7 @@ endif
 libz.a:
 	-rm -rf zlib-$(ZLIB_VER)
 ifeq (,$(wildcard ./zlib-$(ZLIB_VER).tar.gz))
-	curl --fail --output zlib-$(ZLIB_VER).tar.gz --location ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
+	curl --output zlib-$(ZLIB_VER).tar.gz -L ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
 endif
 	ZLIB_SHA256_ACTUAL=`$(SHA256_CMD) zlib-$(ZLIB_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZLIB_SHA256)" != "$$ZLIB_SHA256_ACTUAL" ]; then \
@@ -1882,7 +1690,7 @@ endif
 libbz2.a:
 	-rm -rf bzip2-$(BZIP2_VER)
 ifeq (,$(wildcard ./bzip2-$(BZIP2_VER).tar.gz))
-	curl --fail --output bzip2-$(BZIP2_VER).tar.gz --location ${CURL_SSL_OPTS} ${BZIP2_DOWNLOAD_BASE}/bzip2-$(BZIP2_VER).tar.gz
+	curl --output bzip2-$(BZIP2_VER).tar.gz -L ${BZIP2_DOWNLOAD_BASE}/$(BZIP2_VER)/bzip2-$(BZIP2_VER).tar.gz
 endif
 	BZIP2_SHA256_ACTUAL=`$(SHA256_CMD) bzip2-$(BZIP2_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(BZIP2_SHA256)" != "$$BZIP2_SHA256_ACTUAL" ]; then \
@@ -1896,7 +1704,7 @@ endif
 libsnappy.a:
 	-rm -rf snappy-$(SNAPPY_VER)
 ifeq (,$(wildcard ./snappy-$(SNAPPY_VER).tar.gz))
-	curl --fail --output snappy-$(SNAPPY_VER).tar.gz --location ${CURL_SSL_OPTS} ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER).tar.gz
+	curl --output snappy-$(SNAPPY_VER).tar.gz -L ${CURL_SSL_OPTS} ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER).tar.gz
 endif
 	SNAPPY_SHA256_ACTUAL=`$(SHA256_CMD) snappy-$(SNAPPY_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(SNAPPY_SHA256)" != "$$SNAPPY_SHA256_ACTUAL" ]; then \
@@ -1905,13 +1713,13 @@ endif
 	fi
 	tar xvzf snappy-$(SNAPPY_VER).tar.gz
 	mkdir snappy-$(SNAPPY_VER)/build
-	cd snappy-$(SNAPPY_VER)/build && CFLAGS='${EXTRA_CFLAGS}' CXXFLAGS='${EXTRA_CXXFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
+	cd snappy-$(SNAPPY_VER)/build && CFLAGS='${EXTRA_CFLAGS}' CXXFLAGS='${EXTRA_CXXFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' cmake .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
 	cp snappy-$(SNAPPY_VER)/build/libsnappy.a .
 
 liblz4.a:
 	-rm -rf lz4-$(LZ4_VER)
 ifeq (,$(wildcard ./lz4-$(LZ4_VER).tar.gz))
-	curl --fail --output lz4-$(LZ4_VER).tar.gz --location ${CURL_SSL_OPTS} ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
+	curl --output lz4-$(LZ4_VER).tar.gz -L ${CURL_SSL_OPTS} ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
 endif
 	LZ4_SHA256_ACTUAL=`$(SHA256_CMD) lz4-$(LZ4_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(LZ4_SHA256)" != "$$LZ4_SHA256_ACTUAL" ]; then \
@@ -1925,7 +1733,7 @@ endif
 libzstd.a:
 	-rm -rf zstd-$(ZSTD_VER)
 ifeq (,$(wildcard ./zstd-$(ZSTD_VER).tar.gz))
-	curl --fail --output zstd-$(ZSTD_VER).tar.gz --location ${CURL_SSL_OPTS} ${ZSTD_DOWNLOAD_BASE}/v$(ZSTD_VER).tar.gz
+	curl --output zstd-$(ZSTD_VER).tar.gz -L ${CURL_SSL_OPTS} ${ZSTD_DOWNLOAD_BASE}/v$(ZSTD_VER).tar.gz
 endif
 	ZSTD_SHA256_ACTUAL=`$(SHA256_CMD) zstd-$(ZSTD_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZSTD_SHA256)" != "$$ZSTD_SHA256_ACTUAL" ]; then \
@@ -1983,47 +1791,39 @@ rocksdbjavastatic: $(java_static_all_libobjects)
 	cd java/src/main/java;jar -cf ../../../target/$(ROCKSDB_SOURCES_JAR) org
 
 rocksdbjavastaticrelease: rocksdbjavastatic
-	cd java/crossbuild && (vagrant destroy -f || true) && vagrant up linux32 && vagrant halt linux32 && vagrant up linux64 && vagrant halt linux64 && vagrant up linux64-musl && vagrant halt linux64-musl
+	cd java/crossbuild && vagrant destroy -f && vagrant up linux32 && vagrant halt linux32 && vagrant up linux64 && vagrant halt linux64
 	cd java;jar -cf target/$(ROCKSDB_JAR_ALL) HISTORY*.md
 	cd java/target;jar -uf $(ROCKSDB_JAR_ALL) librocksdbjni-*.so librocksdbjni-*.jnilib
 	cd java/target/classes;jar -uf ../$(ROCKSDB_JAR_ALL) org/rocksdb/*.class org/rocksdb/util/*.class
 
-rocksdbjavastaticreleasedocker: rocksdbjavastatic rocksdbjavastaticdockerx86 rocksdbjavastaticdockerx86_64 rocksdbjavastaticdockerx86musl rocksdbjavastaticdockerx86_64musl
+rocksdbjavastaticreleasedocker: rocksdbjavastatic rocksdbjavastaticdockerx86 rocksdbjavastaticdockerx86_64
 	cd java;jar -cf target/$(ROCKSDB_JAR_ALL) HISTORY*.md
 	cd java/target;jar -uf $(ROCKSDB_JAR_ALL) librocksdbjni-*.so librocksdbjni-*.jnilib
 	cd java/target/classes;jar -uf ../$(ROCKSDB_JAR_ALL) org/rocksdb/*.class org/rocksdb/util/*.class
 
 rocksdbjavastaticdockerx86:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-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_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	DOCKER_LINUX_X86_CONTAINER=`docker ps -aqf name=rocksdb_linux_x86-be`; \
+	if [ -z "$$DOCKER_LINUX_X86_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x86-be evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_x86-be
 
 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) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	DOCKER_LINUX_X64_CONTAINER=`docker ps -aqf name=rocksdb_linux_x64-be`; \
+	if [ -z "$$DOCKER_LINUX_X64_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_x64-be
 
 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) 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) evolvedbinary/rocksjava:centos7_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerx86musl:
-	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-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_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.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) evolvedbinary/rocksjava:alpine3_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.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) evolvedbinary/rocksjava:alpine3_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.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) evolvedbinary/rocksjava:alpine3_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	DOCKER_LINUX_PPC64LE_CONTAINER=`docker ps -aqf name=rocksdb_linux_ppc64le-be`; \
+	if [ -z "$$DOCKER_LINUX_PPC64LE_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_ppc64le-be evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_ppc64le-be
 
 rocksdbjavastaticpublish: rocksdbjavastaticrelease rocksdbjavastaticpublishcentral
 
@@ -2034,8 +1834,6 @@ rocksdbjavastaticpublishcentral:
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-sources.jar -Dclassifier=sources
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux64.jar -Dclassifier=linux64
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux32.jar -Dclassifier=linux32
-	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux64-musl.jar -Dclassifier=linux64-musl
-	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux32-musl.jar -Dclassifier=linux32-musl
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-osx.jar -Dclassifier=osx
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-win64.jar -Dclassifier=win64
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH).jar
@@ -2089,7 +1887,6 @@ jtest_run:
 
 jtest: rocksdbjava
 	cd java;$(MAKE) sample;$(MAKE) test;
-	python tools/check_all_python.py # TODO peterd: find a better place for this check in CI targets
 
 jdb_bench:
 	cd java;$(MAKE) db_bench;
@@ -2137,9 +1934,6 @@ endif
 .cc.o:
 	$(AM_V_CC)$(CXX) $(CXXFLAGS) -c $< -o $@ $(COVERAGEFLAGS)
 
-.cpp.o:
-	$(AM_V_CC)$(CXX) $(CXXFLAGS) -c $< -o $@ $(COVERAGEFLAGS)
-
 .c.o:
 	$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
 endif
@@ -2147,13 +1941,9 @@ endif
 #  	Source files dependencies detection
 # ---------------------------------------------------------------------------
 
-all_sources = $(LIB_SOURCES) $(MAIN_SOURCES) $(MOCK_LIB_SOURCES) $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(TEST_LIB_SOURCES) $(ANALYZER_LIB_SOURCES) $(STRESS_LIB_SOURCES)
+all_sources = $(LIB_SOURCES) $(MAIN_SOURCES) $(MOCK_LIB_SOURCES) $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(TEST_LIB_SOURCES) $(ANALYZER_LIB_SOURCES)
 DEPFILES = $(all_sources:.cc=.cc.d)
 
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-  DEPFILES += $(FOLLY_SOURCES:.cpp=.cpp.d)
-endif
-
 # Add proper dependency support so changing a .h file forces a .cc file to
 # rebuild.
 
@@ -2163,10 +1953,6 @@ endif
 	@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
 	  -MM -MT'$@' -MT'$(<:.cc=.o)' "$<" -o '$@'
 
-%.cpp.d: %.cpp
-	@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
-	  -MM -MT'$@' -MT'$(<:.cpp=.o)' "$<" -o '$@'
-
 ifeq ($(HAVE_POWER8),1)
 DEPFILES_C = $(LIB_SOURCES_C:.c=.c.d)
 DEPFILES_ASM = $(LIB_SOURCES_ASM:.S=.S.d)

README.md

@@ -5,15 +5,15 @@
 [![PPC64le Build Status](http://140.211.168.68:8080/buildStatus/icon?job=Rocksdb)](http://140.211.168.68:8080/job/Rocksdb)
 
 RocksDB is developed and maintained by Facebook Database Engineering Team.
-It is built on earlier work on [LevelDB](https://github.com/google/leveldb) by Sanjay Ghemawat (sanjay@google.com)
+It is built on earlier work on LevelDB by Sanjay Ghemawat (sanjay@google.com)
 and Jeff Dean (jeff@google.com)
 
 This code is a library that forms the core building block for a fast
-key-value server, especially suited for storing data on flash drives.
+key value server, especially suited for storing data on flash drives.
 It has a Log-Structured-Merge-Database (LSM) design with flexible tradeoffs
 between Write-Amplification-Factor (WAF), Read-Amplification-Factor (RAF)
 and Space-Amplification-Factor (SAF). It has multi-threaded compactions,
-making it especially suitable for storing multiple terabytes of data in a
+making it specially suitable for storing multiple terabytes of data in a
 single database.
 
 Start with example usage here: https://github.com/facebook/rocksdb/tree/master/examples

USERS.md

@@ -50,10 +50,6 @@ Check out their blog post: http://blog.cloudera.com/blog/2015/08/inside-santande
 ## Airbnb
 Airbnb is using RocksDB as a storage engine for their personalized search service. You can learn more about it here: https://www.youtube.com/watch?v=ASQ6XMtogMs
 
-## Alluxio
-[Alluxio](https://www.alluxio.io) uses RocksDB to serve and scale file system metadata to beyond 1 Billion files. The detailed design and implementation is described in this engineering blog:
-https://www.alluxio.io/blog/scalable-metadata-service-in-alluxio-storing-billions-of-files/
-
 ## Pinterest
 Pinterest's Object Retrieval System uses RocksDB for storage: https://www.youtube.com/watch?v=MtFEVEs_2Vo
 
@@ -95,14 +91,4 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 [ProfaneDB](https://profanedb.gitlab.io/) is a database for Protocol Buffers, and uses RocksDB for storage. It is accessible via gRPC, and the schema is defined using directly `.proto` files.
 
 ## IOTA Foundation
- [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
- 
-## Avrio Project
- [Avrio Project](http://avrio-project.github.io/avrio.network/) is using RocksDB in [Avrio ](https://github.com/avrio-project/avrio) to store blocks, account balances and data and other blockchain-releated data. Avrio is a multiblockchain decentralized cryptocurrency empowering monetary transactions.
- 
-## Crux
-[Crux](https://github.com/juxt/crux) is a document database that uses RocksDB for local [EAV](https://en.wikipedia.org/wiki/Entity%E2%80%93attribute%E2%80%93value_model) index storage to enable point-in-time bitemporal Datalog queries. The "unbundled" architecture uses Kafka to provide horizontal scalability.
-
-## Nebula Graph
-
-[Nebula Graph](https://github.com/vesoft-inc/nebula) is a distributed, scalable, lightning-fast, open source graph database capable of hosting super large scale graphs with dozens of billions of vertices (nodes) and trillions of edges, with milliseconds of latency.
+ [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.

WINDOWS_PORT.md

@@ -43,7 +43,7 @@ We plan to use this port for our business purposes here at Bing and this provide
 
 * Certain headers that are not present and not necessary on Windows were simply `#ifndef OS_WIN` in a few places (`unistd.h`)
 * All posix specific headers were replaced to port/port.h which worked well
-* Replaced `dirent.h` for `port/port_dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
+* Replaced `dirent.h` for `port/dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
 * Replaced `sys/time.h` to `port/sys_time.h` (few places) implemented equivalents within `rocksdb::port`
 * `printf %z` specification is not supported on Windows. To imitate existing standards we came up with a string macro `ROCKSDB_PRIszt` which expands to `zu` on posix systems and to `Iu` on windows.
 * in class member initialization were moved to a __ctors in some cases

appveyor.yml

@@ -1,75 +1,15 @@
 version: 1.0.{build}
-
 image: Visual Studio 2017
-
-environment:
-  JAVA_HOME: C:\Program Files\Java\jdk1.8.0
-  THIRDPARTY_HOME: $(APPVEYOR_BUILD_FOLDER)\thirdparty
-  SNAPPY_HOME: $(THIRDPARTY_HOME)\snappy-1.1.7
-  SNAPPY_INCLUDE: $(SNAPPY_HOME);$(SNAPPY_HOME)\build
-  SNAPPY_LIB_DEBUG: $(SNAPPY_HOME)\build\Debug\snappy.lib
-  SNAPPY_LIB_RELEASE: $(SNAPPY_HOME)\build\Release\snappy.lib
-  LZ4_HOME: $(THIRDPARTY_HOME)\lz4-1.8.3
-  LZ4_INCLUDE: $(LZ4_HOME)\lib
-  LZ4_LIB_DEBUG: $(LZ4_HOME)\visual\VS2010\bin\x64_Debug\liblz4_static.lib
-  LZ4_LIB_RELEASE: $(LZ4_HOME)\visual\VS2010\bin\x64_Release\liblz4_static.lib
-  ZSTD_HOME: $(THIRDPARTY_HOME)\zstd-1.4.0
-  ZSTD_INCLUDE: $(ZSTD_HOME)\lib;$(ZSTD_HOME)\lib\dictBuilder
-  ZSTD_LIB_DEBUG: $(ZSTD_HOME)\build\VS2010\bin\x64_Debug\libzstd_static.lib
-  ZSTD_LIB_RELEASE: $(ZSTD_HOME)\build\VS2010\bin\x64_Release\libzstd_static.lib
-  matrix:
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015
-      CMAKE_GENERATOR: Visual Studio 14 Win64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio 14.0\Common7\IDE\devenv.com
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2017
-      CMAKE_GENERATOR: Visual Studio 15 Win64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com
-
-install:
-  - md %THIRDPARTY_HOME%
-  - echo "Building Snappy dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl --fail --silent --show-error --output snappy-1.1.7.zip --location https://github.com/google/snappy/archive/1.1.7.zip
-  - unzip snappy-1.1.7.zip
-  - cd snappy-1.1.7
-  - mkdir build
-  - cd build
-  - cmake -G "%CMAKE_GENERATOR%" ..
-  - msbuild Snappy.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild Snappy.sln /p:Configuration=Release /p:Platform=x64
-  - echo "Building LZ4 dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl --fail --silent --show-error --output lz4-1.8.3.zip --location https://github.com/lz4/lz4/archive/v1.8.3.zip
-  - unzip lz4-1.8.3.zip
-  - cd lz4-1.8.3\visual\VS2010
-  - ps: $CMD="$Env:DEV_ENV"; & $CMD lz4.sln /upgrade
-  - msbuild lz4.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild lz4.sln /p:Configuration=Release /p:Platform=x64
-  - echo "Building ZStd dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl --fail --silent --show-error --output zstd-1.4.0.zip --location https://github.com/facebook/zstd/archive/v1.4.0.zip
-  - unzip zstd-1.4.0.zip
-  - cd zstd-1.4.0\build\VS2010
-  - ps: $CMD="$Env:DEV_ENV"; & $CMD zstd.sln /upgrade
-  - msbuild zstd.sln /p:Configuration=Debug /p:Platform=x64
-  - msbuild zstd.sln /p:Configuration=Release /p:Platform=x64
-
 before_build:
-  - md %APPVEYOR_BUILD_FOLDER%\build
-  - cd %APPVEYOR_BUILD_FOLDER%\build
-  - cmake -G "%CMAKE_GENERATOR%" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1 ..
-  - cd ..
-
+- md %APPVEYOR_BUILD_FOLDER%\build
+- cd %APPVEYOR_BUILD_FOLDER%\build
+- cmake -G "Visual Studio 15 Win64" -DOPTDBG=1 -DWITH_XPRESS=1 -DPORTABLE=1 -DJNI=1 ..
+- cd ..
 build:
   project: build\rocksdb.sln
   parallel: true
   verbosity: normal
-
 test:
-
 test_script:
-  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_with_timestamp_basic_test,db_test2,db_test,env_basic_test,env_test,db_merge_operand_test -Concurrency 8
-
-on_failure:
-  - cmd: 7z a build-failed.zip %APPVEYOR_BUILD_FOLDER%\build\ && appveyor PushArtifact build-failed.zip
+- ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test -Concurrency 8
 

buckifier/buckify_rocksdb.py

@@ -1,38 +1,14 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import str
-except ImportError:
-    from __builtin__ import str
 from targets_builder import TARGETSBuilder
-import json
 import os
 import fnmatch
 import sys
 
 from util import ColorString
 
-# 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 TARGETS file.
-# Usage:
-# $python buckifier/buckify_rocksdb.py
-# (This generates a TARGET file without user-specified dependency for unit
-# tests.)
-# $python buckifier/buckify_rocksdb.py \
-#        '{"fake": { \
-#                      "extra_deps": [":test_dep", "//fakes/module:mock1"],  \
-#                      "extra_compiler_flags": ["-DROCKSDB_LITE", "-Os"], \
-#                  } \
-#         }'
-# (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.)
-
 # tests to export as libraries for inclusion in other projects
 _EXPORTED_TEST_LIBS = ["env_basic_test"]
 
@@ -105,36 +81,12 @@ def get_tests(repo_path):
             else:
                 # we consumed all the parallel tests
                 break
-
+    
     return tests
 
 
-# Parse extra dependencies passed by user from command line
-def get_dependencies():
-    deps_map = {
-        '': {
-            'extra_deps': [],
-            'extra_compiler_flags': []
-        }
-    }
-    if len(sys.argv) < 2:
-        return deps_map
-
-    def encode_dict(data):
-        rv = {}
-        for k, v in data.items():
-            if isinstance(v, dict):
-                v = encode_dict(v)
-            rv[k] = v
-        return rv
-    extra_deps = json.loads(sys.argv[1], object_hook=encode_dict)
-    for target_alias, deps in extra_deps.items():
-        deps_map[target_alias] = deps
-    return deps_map
-
-
 # Prepare TARGETS file for buck
-def generate_targets(repo_path, deps_map):
+def generate_targets(repo_path):
     print(ColorString.info("Generating TARGETS"))
     # parsed src.mk file
     src_mk = parse_src_mk(repo_path)
@@ -165,43 +117,27 @@ def generate_targets(repo_path, deps_map):
         "rocksdb_tools_lib",
         src_mk.get("BENCH_LIB_SOURCES", []) +
         src_mk.get("ANALYZER_LIB_SOURCES", []) +
-        ["test_util/testutil.cc"],
-        [":rocksdb_lib"])
-    # rocksdb_stress_lib
-    TARGETS.add_library(
-        "rocksdb_stress_lib",
-        src_mk.get("ANALYZER_LIB_SOURCES", [])
-        + src_mk.get('STRESS_LIB_SOURCES', [])
-        + ["test_util/testutil.cc"],
+        ["util/testutil.cc"],
         [":rocksdb_lib"])
 
-    print("Extra dependencies:\n{0}".format(str(deps_map)))
     # test for every test we found in the Makefile
-    for target_alias, deps in deps_map.items():
-        for test in sorted(tests):
-            match_src = [src for src in cc_files if ("/%s.c" % test) in src]
-            if len(match_src) == 0:
-                print(ColorString.warning("Cannot find .cc file for %s" % test))
-                continue
-            elif len(match_src) > 1:
-                print(ColorString.warning("Found more than one .cc for %s" % test))
-                print(match_src)
-                continue
+    for test in sorted(tests):
+        match_src = [src for src in cc_files if ("/%s.c" % test) in src]
+        if len(match_src) == 0:
+            print(ColorString.warning("Cannot find .cc file for %s" % test))
+            continue
+        elif len(match_src) > 1:
+            print(ColorString.warning("Found more than one .cc for %s" % test))
+            print(match_src)
+            continue
 
-            assert(len(match_src) == 1)
-            is_parallel = tests[test]
-            test_target_name = \
-                test if not target_alias else test + "_" + target_alias
-            TARGETS.register_test(
-                test_target_name,
-                match_src[0],
-                is_parallel,
-                deps['extra_deps'],
-                deps['extra_compiler_flags'])
+        assert(len(match_src) == 1)
+        is_parallel = tests[test]
+        TARGETS.register_test(test, match_src[0], is_parallel)
 
-            if test in _EXPORTED_TEST_LIBS:
-                test_library = "%s_lib" % test_target_name
-                TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
+        if test in _EXPORTED_TEST_LIBS:
+            test_library = "%s_lib" % test
+            TARGETS.add_library(test_library, match_src, [":rocksdb_test_lib"])
     TARGETS.flush_tests()
 
     print(ColorString.info("Generated TARGETS Summary:"))
@@ -226,9 +162,8 @@ def exit_with_error(msg):
 
 
 def main():
-    deps_map = get_dependencies()
     # Generate TARGETS file for buck
-    ok = generate_targets(get_rocksdb_path(), deps_map)
+    ok = generate_targets(get_rocksdb_path())
     if not ok:
         exit_with_error("Failed to generate TARGETS files")
 

buckifier/rocks_test_runner.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # Create a tmp directory for the test to use
 TEST_DIR=$(mktemp -d /dev/shm/fbcode_rocksdb_XXXXXXX)
 # shellcheck disable=SC2068

buckifier/targets_builder.py

@@ -1,14 +1,7 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import object
-    from builtins import str
-except ImportError:
-    from __builtin__ import object
-    from __builtin__ import str
 import targets_cfg
 
 def pretty_list(lst, indent=8):
@@ -24,7 +17,7 @@ def pretty_list(lst, indent=8):
     return res
 
 
-class TARGETSBuilder(object):
+class TARGETSBuilder:
     def __init__(self, path):
         self.path = path
         self.targets_file = open(path, 'w')
@@ -57,21 +50,14 @@ class TARGETSBuilder(object):
             pretty_list(deps)))
         self.total_bin = self.total_bin + 1
 
-    def register_test(self,
-                      test_name,
-                      src,
-                      is_parallel,
-                      extra_deps,
-                      extra_compiler_flags):
+    def register_test(self, test_name, src, is_parallel):
         exec_mode = "serial"
         if is_parallel:
             exec_mode = "parallel"
         self.tests_cfg += targets_cfg.test_cfg_template % (
             test_name,
             str(src),
-            str(exec_mode),
-            extra_deps,
-            extra_compiler_flags)
+            str(exec_mode))
 
         self.total_test = self.total_test + 1
 

buckifier/targets_cfg.py

@@ -1,27 +1,37 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-
-rocksdb_target_header = """# This file \100generated by `python buckifier/buckify_rocksdb.py`
-# --> DO NOT EDIT MANUALLY <--
-# This file is a Facebook-specific integration for buck builds, so can
-# only be validated by Facebook employees.
-#
-load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
-load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
+rocksdb_target_header = """load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
 load(":defs.bzl", "test_binary")
 
 REPO_PATH = package_name() + "/"
 
 ROCKSDB_COMPILER_FLAGS = [
     "-fno-builtin-memcmp",
+    "-DROCKSDB_PLATFORM_POSIX",
+    "-DROCKSDB_LIB_IO_POSIX",
+    "-DROCKSDB_FALLOCATE_PRESENT",
+    "-DROCKSDB_MALLOC_USABLE_SIZE",
+    "-DROCKSDB_RANGESYNC_PRESENT",
+    "-DROCKSDB_SCHED_GETCPU_PRESENT",
+    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
+    "-DOS_LINUX",
+    # Flags to enable libs we include
+    "-DSNAPPY",
+    "-DZLIB",
+    "-DBZIP2",
+    "-DLZ4",
+    "-DZSTD",
+    "-DGFLAGS=gflags",
+    "-DNUMA",
+    "-DTBB",
     # Needed to compile in fbcode
     "-Wno-expansion-to-defined",
     # Added missing flags from output of build_detect_platform
+    "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
+    "-DROCKSDB_BACKTRACE",
     "-Wnarrowing",
-    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
 ]
 
 ROCKSDB_EXTERNAL_DEPS = [
@@ -32,56 +42,11 @@ ROCKSDB_EXTERNAL_DEPS = [
     ("lz4", None, "lz4"),
     ("zstd", None),
     ("tbb", None),
+    ("numa", None, "numa"),
     ("googletest", None, "gtest"),
 ]
 
-ROCKSDB_OS_DEPS = [
-    (
-        "linux",
-        ["third-party//numa:numa", "third-party//liburing:uring"],
-    ),
-]
-
-ROCKSDB_OS_PREPROCESSOR_FLAGS = [
-    (
-        "linux",
-        [
-            "-DOS_LINUX",
-            "-DROCKSDB_FALLOCATE_PRESENT",
-            "-DROCKSDB_MALLOC_USABLE_SIZE",
-            "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
-            "-DROCKSDB_RANGESYNC_PRESENT",
-            "-DROCKSDB_SCHED_GETCPU_PRESENT",
-            "-DROCKSDB_IOURING_PRESENT",
-            "-DHAVE_SSE42",
-            "-DLIBURING",
-            "-DNUMA",
-        ],
-    ),
-    (
-        "macos",
-        ["-DOS_MACOSX"],
-    ),
-]
-
 ROCKSDB_PREPROCESSOR_FLAGS = [
-    "-DROCKSDB_PLATFORM_POSIX",
-    "-DROCKSDB_LIB_IO_POSIX",
-    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
-
-    # Flags to enable libs we include
-    "-DSNAPPY",
-    "-DZLIB",
-    "-DBZIP2",
-    "-DLZ4",
-    "-DZSTD",
-    "-DZSTD_STATIC_LINKING_ONLY",
-    "-DGFLAGS=gflags",
-    "-DTBB",
-
-    # Added missing flags from output of build_detect_platform
-    "-DROCKSDB_BACKTRACE",
-
     # Directories with files for #include
     "-I" + REPO_PATH + "include/",
     "-I" + REPO_PATH,
@@ -89,6 +54,7 @@ ROCKSDB_PREPROCESSOR_FLAGS = [
 
 ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
     "x86_64": [
+        "-DHAVE_SSE42",
         "-DHAVE_PCLMUL",
     ],
 }
@@ -105,15 +71,9 @@ sanitizer = read_config("fbcode", "sanitizer")
 
 # Do not enable jemalloc if sanitizer presents. RocksDB will further detect
 # whether the binary is linked with jemalloc at runtime.
-ROCKSDB_OS_PREPROCESSOR_FLAGS += ([(
-    "linux",
-    ["-DROCKSDB_JEMALLOC"],
-)] if sanitizer == "" else [])
+ROCKSDB_COMPILER_FLAGS += (["-DROCKSDB_JEMALLOC"] if sanitizer == "" else [])
 
-ROCKSDB_OS_DEPS += ([(
-    "linux",
-    ["third-party//jemalloc:headers"],
-)] if sanitizer == "" else [])
+ROCKSDB_EXTERNAL_DEPS += ([("jemalloc", None, "headers")] if sanitizer == "" else [])
 """
 
 
@@ -124,8 +84,6 @@ cpp_library(
     {headers_attr_prefix}headers = {headers},
     arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
     compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    os_deps = ROCKSDB_OS_DEPS,
-    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
     preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
     deps = [{deps}],
     external_deps = ROCKSDB_EXTERNAL_DEPS,
@@ -148,13 +106,11 @@ test_cfg_template = """    [
         "%s",
         "%s",
         "%s",
-        %s,
-        %s,
     ],
 """
 
 unittests_template = """
-# [test_name, test_src, test_type, extra_deps, extra_compiler_flags]
+# [test_name, test_src, test_type]
 ROCKS_TESTS = [
 %s]
 
@@ -163,19 +119,15 @@ ROCKS_TESTS = [
 # will not be included.
 [
     test_binary(
-        extra_compiler_flags = extra_compiler_flags,
-        extra_deps = extra_deps,
         parallelism = parallelism,
         rocksdb_arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
         rocksdb_compiler_flags = ROCKSDB_COMPILER_FLAGS,
         rocksdb_external_deps = ROCKSDB_EXTERNAL_DEPS,
-        rocksdb_os_deps = ROCKSDB_OS_DEPS,
-        rocksdb_os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
         rocksdb_preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
         test_cc = test_cc,
         test_name = test_name,
     )
-    for test_name, test_cc, parallelism, extra_deps, extra_compiler_flags in ROCKS_TESTS
+    for test_name, test_cc, parallelism in ROCKS_TESTS
     if not is_opt_mode
 ]
 """

buckifier/util.py

@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 """
 This module keeps commonly used components.
 """
@@ -6,16 +5,11 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import object
-except ImportError:
-    from __builtin__ import object
 import subprocess
-import sys
 import os
 import time
 
-class ColorString(object):
+class ColorString:
     """ Generate colorful strings on terminal """
     HEADER = '\033[95m'
     BLUE = '\033[94m'
@@ -26,13 +20,7 @@ class ColorString(object):
 
     @staticmethod
     def _make_color_str(text, color):
-        # In Python2, default encoding for unicode string is ASCII
-        if sys.version_info.major <= 2:
-            return "".join(
-                [color, text.encode('utf-8'), ColorString.ENDC])
-        # From Python3, default encoding for unicode string is UTF-8
-        return "".join(
-            [color, text, ColorString.ENDC])
+        return "".join([color, text.encode('utf-8'), ColorString.ENDC])
 
     @staticmethod
     def ok(text):

build_tools/RocksDBCommonHelper.php

@@ -0,0 +1,377 @@
+<?php
+// Copyright 2004-present Facebook. All Rights Reserved.
+//  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).
+
+// Name of the environment variables which need to be set by the entity which
+// triggers continuous runs so that code at the end of the file gets executed
+// and Sandcastle run starts.
+const ENV_POST_RECEIVE_HOOK = "POST_RECEIVE_HOOK";
+const ENV_HTTPS_APP_VALUE = "HTTPS_APP_VALUE";
+const ENV_HTTPS_TOKEN_VALUE = "HTTPS_TOKEN_VALUE";
+
+const PRIMARY_TOKEN_FILE = '/home/krad/.sandcastle';
+const CONT_RUN_ALIAS = "leveldb";
+
+//////////////////////////////////////////////////////////////////////
+/*  Run tests in sandcastle */
+function postURL($diffID, $url) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($url) > 0);
+
+  $cmd_args = array(
+    'diff_id' => (int)$diffID,
+    'name' => sprintf(
+      'click here for sandcastle tests for D%d',
+      (int)$diffID
+    ),
+    'link' => $url
+  );
+  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
+         . ' | arc call-conduit differential.updateunitresults';
+
+  shell_exec($cmd);
+}
+
+function buildUpdateTestStatusCmd($diffID, $test, $status) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($test) > 0);
+  assert(strlen($status) > 0);
+
+  $cmd_args = array(
+    'diff_id' => (int)$diffID,
+    'name' => $test,
+    'result' => $status
+  );
+
+  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
+         . ' | arc call-conduit differential.updateunitresults';
+
+  return $cmd;
+}
+
+function updateTestStatus($diffID, $test) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($test) > 0);
+
+  shell_exec(buildUpdateTestStatusCmd($diffID, $test, "waiting"));
+}
+
+function getSteps($applyDiff, $diffID, $username, $test) {
+  assert(strlen($username) > 0);
+  assert(strlen($test) > 0);
+
+  if ($applyDiff) {
+    assert(strlen($diffID) > 0);
+    assert(is_numeric($diffID));
+
+    $arcrc_content = (PHP_OS == "Darwin" ?
+        exec("cat ~/.arcrc | gzip -f | base64") :
+            exec("cat ~/.arcrc | gzip -f | base64 -w0"));
+    assert(strlen($arcrc_content) > 0);
+
+    // Sandcastle machines don't have arc setup. We copy the user certificate
+    // and authenticate using that in Sandcastle.
+    $setup = array(
+      "name" => "Setup arcrc",
+      "shell" => "echo " . escapeshellarg($arcrc_content) . " | base64 --decode"
+                 . " | gzip -d > ~/.arcrc",
+      "user" => "root"
+    );
+
+    // arc demands certain permission on its config.
+    // also fix the sticky bit issue in sandcastle
+    $fix_permission = array(
+      "name" => "Fix environment",
+      "shell" => "chmod 600 ~/.arcrc && chmod +t /dev/shm",
+      "user" => "root"
+    );
+
+    // Construct the steps in the order of execution.
+    $steps[] = $setup;
+    $steps[] = $fix_permission;
+  }
+
+  // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
+  // Git thinks it is an uncommitted change.
+  $fix_git_ignore = array(
+    "name" => "Fix git ignore",
+    "shell" => "echo fbcode >> .git/info/exclude",
+    "user" => "root"
+  );
+
+  // This fixes "FATAL: ThreadSanitizer can not mmap the shadow memory"
+  // Source:
+  // https://github.com/google/sanitizers/wiki/ThreadSanitizerCppManual#FAQ
+  $fix_kernel_issue = array(
+    "name" => "Fix kernel issue with tsan",
+    "shell" => "echo 2 >/proc/sys/kernel/randomize_va_space",
+    "user" => "root"
+  );
+
+  $steps[] = $fix_git_ignore;
+  $steps[] = $fix_kernel_issue;
+
+  // This will be the command used to execute particular type of tests.
+  $cmd = "";
+
+  if ($applyDiff) {
+    // Patch the code (keep your fingures crossed).
+    $patch = array(
+      "name" => "Patch " . $diffID,
+      "shell" => "arc --arcrc-file ~/.arcrc "
+                  . "patch --nocommit --diff " . escapeshellarg($diffID),
+      "user" => "root"
+    );
+
+    $steps[] = $patch;
+
+    updateTestStatus($diffID, $test);
+    $cmd = buildUpdateTestStatusCmd($diffID, $test, "running") . "; ";
+  }
+
+  // Run the actual command.
+  $cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " .
+           escapeshellarg($test) . "; exit_code=$?; ";
+
+  if ($applyDiff) {
+    $cmd = $cmd . "([[ \$exit_code -eq 0 ]] &&"
+                . buildUpdateTestStatusCmd($diffID, $test, "pass") . ")"
+                . "||" . buildUpdateTestStatusCmd($diffID, $test, "fail")
+                . "; ";
+  }
+
+  // shell command to sort the tests based on exit code and print
+  // the output of the log files.
+  $cat_sorted_logs = "
+    while read code log_file;
+      do echo \"################ cat \$log_file [exit_code : \$code] ################\";
+      cat \$log_file;
+    done < <(tail -n +2 LOG | sort -k7,7n -k4,4gr | awk '{print \$7,\$NF}')";
+
+  // Shell command to cat all log files
+  $cat_all_logs = "for f in `ls t/!(run-*)`; do echo \$f;cat \$f; done";
+
+  // If LOG file exist use it to cat log files sorted by exit code, otherwise
+  // cat everything
+  $logs_cmd = "if [ -f LOG ]; then {$cat_sorted_logs}; else {$cat_all_logs}; fi";
+
+  $cmd = $cmd . " cat /tmp/precommit-check.log"
+              . "; shopt -s extglob; {$logs_cmd}"
+              . "; shopt -u extglob; [[ \$exit_code -eq 0 ]]";
+  assert(strlen($cmd) > 0);
+
+  $run_test = array(
+    "name" => "Run " . $test,
+    "shell" => $cmd,
+    "user" => "root",
+    "parser" => "python build_tools/error_filter.py " . escapeshellarg($test),
+  );
+
+  $steps[] = $run_test;
+
+  if ($applyDiff) {
+    // Clean up the user arc config we are using.
+    $cleanup = array(
+      "name" => "Arc cleanup",
+      "shell" => "rm -f ~/.arcrc",
+      "user" => "root"
+    );
+
+    $steps[] = $cleanup;
+  }
+
+  assert(count($steps) > 0);
+  return $steps;
+}
+
+function getSandcastleConfig() {
+  $sandcastle_config = array();
+
+  $cwd = getcwd();
+  $cwd_token_file = "{$cwd}/.sandcastle";
+  // This is a case when we're executed from a continuous run. Fetch the values
+  // from the environment.
+  if (getenv(ENV_POST_RECEIVE_HOOK)) {
+    $sandcastle_config[0] = getenv(ENV_HTTPS_APP_VALUE);
+    $sandcastle_config[1] = getenv(ENV_HTTPS_TOKEN_VALUE);
+  } else {
+    // This is a typical `[p]arc diff` case. Fetch the values from the specific
+    // configuration files.
+    for ($i = 0; $i < 50; $i++) {
+      if (file_exists(PRIMARY_TOKEN_FILE) ||
+          file_exists($cwd_token_file)) {
+        break;
+      }
+      // If we failed to fetch the tokens, sleep for 0.2 second and try again
+      usleep(200000);
+    }
+    assert(file_exists(PRIMARY_TOKEN_FILE) ||
+           file_exists($cwd_token_file));
+
+    // Try the primary location first, followed by a secondary.
+    if (file_exists(PRIMARY_TOKEN_FILE)) {
+      $cmd = 'cat ' . PRIMARY_TOKEN_FILE;
+    } else {
+      $cmd = 'cat ' . escapeshellarg($cwd_token_file);
+    }
+
+    assert(strlen($cmd) > 0);
+    $sandcastle_config = explode(':', rtrim(shell_exec($cmd)));
+  }
+
+  // In this case be very explicit about the implications.
+  if (count($sandcastle_config) != 2) {
+    echo "Sandcastle configuration files don't contain valid information " .
+         "or the necessary environment variables aren't defined. Unable " .
+         "to validate the code changes.";
+    exit(1);
+  }
+
+  assert(strlen($sandcastle_config[0]) > 0);
+  assert(strlen($sandcastle_config[1]) > 0);
+  assert(count($sandcastle_config) > 0);
+
+  return $sandcastle_config;
+}
+
+// This function can be called either from `[p]arc diff` command or during
+// the Git post-receive hook.
+ function startTestsInSandcastle($applyDiff, $workflow, $diffID) {
+  // Default options don't terminate on failure, but that's what we want. In
+  // the current case we use assertions intentionally as "terminate on failure
+  // invariants".
+  assert_options(ASSERT_BAIL, true);
+
+  // In case of a diff we'll send notificatios to the author. Else it'll go to
+  // the entire team because failures indicate that build quality has regressed.
+  $username = $applyDiff ? exec("whoami") : CONT_RUN_ALIAS;
+  assert(strlen($username) > 0);
+
+  if ($applyDiff) {
+    assert($workflow);
+    assert(strlen($diffID) > 0);
+    assert(is_numeric($diffID));
+  }
+
+  // List of tests we want to run in Sandcastle.
+  $tests = array("unit", "unit_non_shm", "unit_481", "clang_unit", "tsan",
+                 "asan", "lite_test", "valgrind", "release", "release_481",
+                 "clang_release", "clang_analyze", "code_cov",
+                 "java_build", "no_compression", "unity", "ubsan");
+
+  $send_email_template = array(
+    'type' => 'email',
+    'triggers' => array('fail'),
+    'emails' => array($username . '@fb.com'),
+  );
+
+  // Construct a job definition for each test and add it to the master plan.
+  foreach ($tests as $test) {
+    $stepName = "RocksDB diff " . $diffID . " test " . $test;
+
+    if (!$applyDiff) {
+      $stepName = "RocksDB continuous integration test " . $test;
+    }
+
+    $arg[] = array(
+      "name" => $stepName,
+      "report" => array($send_email_template),
+      "steps" => getSteps($applyDiff, $diffID, $username, $test)
+    );
+  }
+
+  // We cannot submit the parallel execution master plan to Sandcastle and
+  // need supply the job plan as a determinator. So we construct a small job
+  // that will spit out the master job plan which Sandcastle will parse and
+  // execute. Why compress the job definitions? Otherwise we run over the max
+  // string size.
+  $cmd = "echo " . base64_encode(json_encode($arg))
+         . (PHP_OS == "Darwin" ?
+             " | gzip -f | base64" :
+                 " | gzip -f | base64 -w0");
+  assert(strlen($cmd) > 0);
+
+  $arg_encoded = shell_exec($cmd);
+  assert(strlen($arg_encoded) > 0);
+
+  $runName = "Run diff " . $diffID . "for user " . $username;
+
+  if (!$applyDiff) {
+    $runName = "RocksDB continuous integration build and test run";
+  }
+
+  $command = array(
+    "name" => $runName,
+    "steps" => array()
+  );
+
+  $command["steps"][] = array(
+    "name" => "Generate determinator",
+    "shell" => "echo " . $arg_encoded . " | base64 --decode | gzip -d"
+               . " | base64 --decode",
+    "determinator" => true,
+    "user" => "root"
+  );
+
+  // Submit to Sandcastle.
+  $url = 'https://interngraph.intern.facebook.com/sandcastle/create';
+
+  $job = array(
+    'command' => 'SandcastleUniversalCommand',
+    'args' => $command,
+    'capabilities' => array(
+      'vcs' => 'rocksdb-int-git',
+      'type' => 'lego',
+    ),
+    'hash' => 'origin/master',
+    'user' => $username,
+    'alias' => 'rocksdb-precommit',
+    'tags' => array('rocksdb'),
+    'description' => 'Rocksdb precommit job',
+  );
+
+  // Fetch the configuration necessary to submit a successful HTTPS request.
+  $sandcastle_config = getSandcastleConfig();
+
+  $app = $sandcastle_config[0];
+  $token = $sandcastle_config[1];
+
+  $cmd = 'curl -s -k '
+          . ' -F app=' . escapeshellarg($app)
+          . ' -F token=' . escapeshellarg($token)
+          . ' -F job=' . escapeshellarg(json_encode($job))
+          .' ' . escapeshellarg($url);
+
+  $output = shell_exec($cmd);
+  assert(strlen($output) > 0);
+
+  // Extract Sandcastle URL from the response.
+  preg_match('/url": "(.+)"/', $output, $sandcastle_url);
+
+  assert(count($sandcastle_url) > 0, "Unable to submit Sandcastle request.");
+  assert(strlen($sandcastle_url[1]) > 0, "Unable to extract Sandcastle URL.");
+
+  if ($applyDiff) {
+    echo "\nSandcastle URL: " . $sandcastle_url[1] . "\n";
+    // Ask Phabricator to display it on the diff UI.
+    postURL($diffID, $sandcastle_url[1]);
+  } else {
+    echo "Continuous integration started Sandcastle tests. You can look at ";
+    echo "the progress at:\n" . $sandcastle_url[1] . "\n";
+  }
+}
+
+// Continuous run cript will set the environment variable and based on that
+// we'll trigger the execution of tests in Sandcastle. In that case we don't
+// need to apply any diffs and there's no associated workflow either.
+if (getenv(ENV_POST_RECEIVE_HOOK)) {
+  startTestsInSandcastle(
+    false /* $applyDiff */,
+    NULL /* $workflow */,
+    NULL /* $diffID */);
+}

build_tools/amalgamate.py

@@ -1,5 +1,4 @@
 #!/usr/bin/python
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 # amalgamate.py creates an amalgamation from a unity build.
 # It can be run with either Python 2 or 3.

build_tools/build_detect_platform

@@ -9,7 +9,6 @@
 #   PLATFORM_LDFLAGS            Linker flags
 #   JAVA_LDFLAGS                Linker flags for RocksDBJava
 #   JAVA_STATIC_LDFLAGS         Linker flags for RocksDBJava static build
-#   JAVAC_ARGS                  Arguments for javac
 #   PLATFORM_SHARED_EXT         Extension for shared libraries
 #   PLATFORM_SHARED_LDFLAGS     Flags for building shared library
 #   PLATFORM_SHARED_CFLAGS      Flags for compiling objects for shared library
@@ -57,10 +56,10 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
     if [ -n "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
       # we need this to build with MySQL. Don't use for other purposes.
       source "$PWD/build_tools/fbcode_config4.8.1.sh"
-    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_5xx" ]; then
-      source "$PWD/build_tools/fbcode_config.sh"
-    else
+    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007" ]; then
       source "$PWD/build_tools/fbcode_config_platform007.sh"
+    else
+      source "$PWD/build_tools/fbcode_config.sh"
     fi
 fi
 
@@ -151,24 +150,6 @@ case "$TARGET_OS" in
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
         fi
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
-        if test $ROCKSDB_USE_IO_URING; then
-            # check for liburing
-            $CXX $CFLAGS -x c++ - -luring -o /dev/null 2>/dev/null  <<EOF
-              #include <liburing.h>
-              int main() {
-                struct io_uring ring;
-                io_uring_queue_init(1, &ring, 0);
-                return 0;
-              }
-EOF
-            if [ "$?" = 0 ]; then
-                PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
-                COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
-            fi
-        fi
-        if test -z "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-          USE_FOLLY_DISTRIBUTED_MUTEX=1
-        fi
         # PORT_FILES=port/linux/linux_specific.cc
         ;;
     SunOS)
@@ -240,7 +221,6 @@ esac
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS ${CXXFLAGS}"
 JAVA_LDFLAGS="$PLATFORM_LDFLAGS"
 JAVA_STATIC_LDFLAGS="$PLATFORM_LDFLAGS"
-JAVAC_ARGS="-source 7"
 
 if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
     # Cross-compiling; do not try any compilation tests.
@@ -254,7 +234,7 @@ else
           #include <linux/falloc.h>
           int main() {
       int fd = open("/dev/null", 0);
-      fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, 1024);
+      fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
           }
 EOF
         if [ "$?" = 0 ]; then
@@ -417,7 +397,6 @@ EOF
           #include <malloc.h>
           int main() {
             size_t res = malloc_usable_size(0);
-            (void)res;
             return 0;
           }
 EOF
@@ -432,7 +411,6 @@ EOF
           #include <pthread.h>
           int main() {
             int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-            (void)x;
             return 0;
           }
 EOF
@@ -444,7 +422,7 @@ EOF
     if ! test $ROCKSDB_DISABLE_BACKTRACE; then
         # Test whether backtrace is available
         $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <execinfo.h>
+          #include <execinfo.h>>
           int main() {
             void* frames[1];
             backtrace_symbols(frames, backtrace(frames, 1));
@@ -502,7 +480,6 @@ EOF
           #include <sched.h>
           int main() {
             int cpuid = sched_getcpu();
-            (void)cpuid;
           }
 EOF
         if [ "$?" = 0 ]; then
@@ -510,20 +487,6 @@ EOF
         fi
     fi
 
-    if ! test $ROCKSDB_DISABLE_AUXV_GETAUXVAL; then
-        # Test whether getauxval is supported
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <sys/auxv.h>
-          int main() {
-            uint64_t auxv = getauxval(AT_HWCAP);
-            (void)auxv;
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_AUXV_GETAUXVAL_PRESENT"
-        fi
-    fi
-
     if ! test $ROCKSDB_DISABLE_ALIGNED_NEW; then
         # Test whether c++17 aligned-new is supported
         $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
@@ -552,11 +515,11 @@ fi
 
 if test "$USE_HDFS"; then
   if test -z "$JAVA_HOME"; then
-    echo "JAVA_HOME has to be set for HDFS usage." >&2
+    echo "JAVA_HOME has to be set for HDFS usage."
     exit 1
   fi
-  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS -I$HADOOP_HOME/include"
-  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64 -L$HADOOP_HOME/lib/native"
+  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64"
   HDFS_LDFLAGS="$HDFS_LDFLAGS -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib"
   HDFS_LDFLAGS="$HDFS_LDFLAGS -ldl -lverify -ljava -ljvm"
   COMMON_FLAGS="$COMMON_FLAGS $HDFS_CCFLAGS"
@@ -564,64 +527,42 @@ if test "$USE_HDFS"; then
   JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi
 
-if test "0$PORTABLE" -eq 0; then
+if test -z "$PORTABLE"; then
   if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
     # Tune for this POWER processor, treating '+' models as base models
     POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
     COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
   elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
     COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep -e^arm -e^aarch64`"; then
+  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^arm`"; then
     # TODO: Handle this with approprite options.
     COMMON_FLAGS="$COMMON_FLAGS"
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^aarch64`"; then
-    COMMON_FLAGS="$COMMON_FLAGS"
   elif [ "$TARGET_OS" == "IOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS"
-  elif [ "$TARGET_OS" == "AIX" ] || [ "$TARGET_OS" == "SunOS" ]; then
-    # TODO: Not sure why we don't use -march=native on these OSes
-    if test "$USE_SSE"; then
-      TRY_SSE_ETC="1"
-    fi
-  else
+  elif [ "$TARGET_OS" != "AIX" ] && [ "$TARGET_OS" != "SunOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS -march=native "
+  elif test "$USE_SSE"; then
+    COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
   fi
-else
-  # PORTABLE=1
-  if test "$USE_SSE"; then
-    TRY_SSE_ETC="1"
-  fi
+elif test "$USE_SSE"; then
+  COMMON_FLAGS="$COMMON_FLAGS -msse4.2 -mpclmul"
 fi
 
-if test "$TRY_SSE_ETC"; then
-  # The USE_SSE flag now means "attempt to compile with widely-available
-  # Intel architecture extensions utilized by specific optimizations in the
-  # source code." It's a qualifier on PORTABLE=1 that means "mostly portable."
-  # It doesn't even really check that your current CPU is compatible.
-  #
-  # SSE4.2 available since nehalem, ca. 2008-2010
-  TRY_SSE42="-msse4.2"
-  # PCLMUL available since westmere, ca. 2010-2011
-  TRY_PCLMUL="-mpclmul"
-  # AVX2 available since haswell, ca. 2013-2015
-  TRY_AVX2="-mavx2"
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o /dev/null 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
   #include <cstdint>
   #include <nmmintrin.h>
   int main() {
     volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
   }
 EOF
 if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_SSE42 -DHAVE_SSE42"
+  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_SSE42"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
+  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling"
+  exit 1
 fi
 
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
   #include <cstdint>
   #include <wmmintrin.h>
   int main() {
@@ -629,41 +570,13 @@ $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/n
     const auto b = _mm_set_epi64x(0, 0);
     const auto c = _mm_clmulepi64_si128(a, b, 0x00);
     auto d = _mm_cvtsi128_si64(c);
-    (void)d;
   }
 EOF
 if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_PCLMUL -DHAVE_PCLMUL"
+  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_PCLMUL"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main() {
-    const auto a = _mm256_setr_epi32(0, 1, 2, 3, 4, 7, 6, 5);
-    const auto b = _mm256_permutevar8x32_epi32(a, a);
-    (void)b;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_AVX2 -DHAVE_AVX2"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use AVX2 intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  int main() {
-    uint64_t a = 0xffffFFFFffffFFFF;
-    __uint128_t b = __uint128_t(a) * a;
-    a = static_cast<uint64_t>(b >> 64);
-    (void)a;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_UINT128_EXTENSION"
+  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling"
+  exit 1
 fi
 
 # iOS doesn't support thread-local storage, but this check would erroneously
@@ -676,7 +589,6 @@ if [ "$PLATFORM" != IOS ]; then
   #endif
   int main() {
     static __thread int tls;
-    (void)tls;
   }
 EOF
   if [ "$?" = 0 ]; then
@@ -684,19 +596,6 @@ EOF
   fi
 fi
 
-if [ "$FBCODE_BUILD" != "true" -a "$PLATFORM" = OS_LINUX ]; then
-  $CXX $COMMON_FLAGS $PLATFORM_SHARED_CFLAGS -x c++ -c - -o test_dl.o 2>/dev/null <<EOF
-  void dummy_func() {}
-EOF
-  if [ "$?" = 0 ]; then
-    $CXX $COMMON_FLAGS $PLATFORM_SHARED_LDFLAGS test_dl.o -o /dev/null 2>/dev/null
-    if [ "$?" = 0 ]; then
-      EXEC_LDFLAGS+="-ldl"
-      rm -f test_dl.o
-    fi
-  fi
-fi
-
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"
 
@@ -712,7 +611,6 @@ echo "PLATFORM=$PLATFORM" >> "$OUTPUT"
 echo "PLATFORM_LDFLAGS=$PLATFORM_LDFLAGS" >> "$OUTPUT"
 echo "JAVA_LDFLAGS=$JAVA_LDFLAGS" >> "$OUTPUT"
 echo "JAVA_STATIC_LDFLAGS=$JAVA_STATIC_LDFLAGS" >> "$OUTPUT"
-echo "JAVAC_ARGS=$JAVAC_ARGS" >> "$OUTPUT"
 echo "VALGRIND_VER=$VALGRIND_VER" >> "$OUTPUT"
 echo "PLATFORM_CCFLAGS=$PLATFORM_CCFLAGS" >> "$OUTPUT"
 echo "PLATFORM_CXXFLAGS=$PLATFORM_CXXFLAGS" >> "$OUTPUT"
@@ -742,6 +640,3 @@ if test -n "$WITH_JEMALLOC_FLAG"; then
   echo "WITH_JEMALLOC_FLAG=$WITH_JEMALLOC_FLAG" >> "$OUTPUT"
 fi
 echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
-if test -n "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
-  echo "USE_FOLLY_DISTRIBUTED_MUTEX=$USE_FOLLY_DISTRIBUTED_MUTEX" >> "$OUTPUT"
-fi

build_tools/cont_integration.sh

@@ -0,0 +1,137 @@
+#!/usr/bin/env bash
+#
+# Copyright (c) 2016, Facebook. All rights reserved.
+#
+# Overall wrapper script for RocksDB continuous builds. The implementation is a
+# trivial pulling scheme. We loop infinitely, check if any new changes have been
+# committed, if yes then trigger a Sandcastle run, and finally go to sleep again
+# for a certain interval.
+#
+
+SRC_GIT_REPO=/data/git/rocksdb-public
+error=0
+
+function log {
+  DATE=`date +%Y-%m-%d:%H:%M:%S`
+  # shellcheck disable=SC2068
+  echo $DATE $@
+}
+
+function log_err {
+  # shellcheck disable=SC2145
+  log "ERROR: $@ Error code: $error."
+}
+
+function update_repo_status {
+  # Update the parent first.
+  pushd $SRC_GIT_REPO
+
+  # This is a fatal error. Something in the environment isn't right and we will
+  # terminate the execution.
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "Where is $SRC_GIT_REPO?"
+    exit $error
+  fi
+
+  HTTPS_PROXY=fwdproxy:8080 git fetch -f
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git fetch -f failed."
+    popd
+    return $error
+  fi
+
+  git update-ref refs/heads/master refs/remotes/origin/master
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git update-ref failed."
+    popd
+    return $error
+  fi
+
+  popd
+
+  # We're back in an instance-specific directory. Get the latest changes.
+  git pull --rebase
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git pull --rebase failed."
+    return $error
+  fi
+}
+
+#
+# Execution starts here.
+#
+
+# Path to the determinator from the root of the RocksDB repo.
+CONTRUN_DETERMINATOR=./build_tools/RocksDBCommonHelper.php
+
+# Value of the previous commit.
+PREV_COMMIT=
+
+log "Starting to monitor for new RocksDB changes ..."
+log "Running under `pwd` as `whoami`."
+
+# Paranoia. Make sure that we're using the right branch.
+git checkout master
+
+error=$?
+if [ ! $error -eq 0 ]; then
+  log_err "This is not good. Can't checkout master. Bye-bye!"
+  exit 1
+fi
+
+# We'll run forever and let the execution environment terminate us if we'll
+# exceed whatever timeout is set for the job.
+while true;
+do
+  # Get the latest changes committed.
+  update_repo_status
+
+  error=$?
+  if [  $error -eq 0 ]; then
+    LAST_COMMIT=`git log -1 | head -1 | grep commit | awk '{ print $2; }'`
+
+    log "Last commit is '$LAST_COMMIT', previous commit is '$PREV_COMMIT'."
+
+    if [ "$PREV_COMMIT" == "$LAST_COMMIT" ]; then
+      log "There were no changes since the last time I checked. Going to sleep."
+    else
+      if [ ! -z "$LAST_COMMIT" ]; then
+        log "New code has been committed or previous commit not known. " \
+            "Will trigger the tests."
+
+        PREV_COMMIT=$LAST_COMMIT
+        log "Updated previous commit to '$PREV_COMMIT'."
+
+        #
+        # This is where we'll trigger the Sandcastle run. The values for
+        # HTTPS_APP_VALUE and HTTPS_APP_VALUE will be set in the container we're
+        # running in.
+        #
+        POST_RECEIVE_HOOK=1 php $CONTRUN_DETERMINATOR
+
+        error=$?
+        if [ $error -eq 0 ]; then
+          log "Sandcastle run successfully triggered."
+        else
+          log_err "Failed to trigger Sandcastle run."
+        fi
+      else
+        log_err "Previous commit not updated. Don't know what the last one is."
+      fi
+    fi
+  else
+    log_err "Getting latest changes failed. Will skip running tests for now."
+  fi
+
+  # Always sleep, even if errors happens while trying to determine the latest
+  # commit. This will prevent us terminating in case of transient errors.
+  log "Will go to sleep for 5 minutes."
+  sleep 5m
+done

build_tools/dependencies.sh

@@ -1,19 +1,18 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/5.x/centos7-native/c447969
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1bd23f9917738974ad0ff305aa23eb5f93f18305/9.0.0/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/5.x/gcc-5-glibc-2.23/339d858
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.23/gcc-5-glibc-2.23/ca1d1c0
+GCC_BASE=/mnt/gvfs/third-party2/gcc/112ec378fec7002ad3e09afde022e656049f7191/5.x/centos7-native/c447969
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/04999bdb3ce81a11073535dcb00b5e13dc1cbaf5/stable/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/92b0c8e5c8eecc71eb042594ce1ab3413799b385/5.x/gcc-5-glibc-2.23/339d858
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/3d8698d5973ba94f41620a80a67e4457fdf01e90/2.23/gcc-5-glibc-2.23/ca1d1c0
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/gcc-5-glibc-2.23/9bc6787
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/gcc-5-glibc-2.23/9bc6787
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/gcc-5-glibc-2.23/9bc6787
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/gcc-5-glibc-2.23/9bc6787
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/gcc-5-glibc-2.23/9bc6787
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/gcc-5-glibc-2.23/03859b5
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/gcc-5-glibc-2.23/9bc6787
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/af6628a46758f1a15484a1760cd7294164bc5ba1/1.3.5/gcc-5-glibc-2.23/03859b5
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/gcc-5-glibc-2.23/9bc6787
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/gcc-5-glibc-2.23/0c8f76d
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/gcc-5-glibc-2.23/9bc6787
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/gcc-5-glibc-2.23/b443de1
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/gcc-5-glibc-2.23/9bc6787
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/2e3cb7d119b3cea5f1e738cc13a1ac69f49eb875/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/gcc-5-glibc-2.23/9bc6787
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b1a0e56c1e3e6929813a4331ade3a58ff083afbb/master/gcc-5-glibc-2.23/aa64d6b
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/gcc-5-glibc-2.23/9bc6787
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/gcc-5-glibc-2.23/b443de1
+TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/gcc-5-glibc-2.23/9bc6787
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/55031de95a2b46c82948743419a603b3d6aefe28/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/gcc-5-glibc-2.23/9bc6787
 LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.2.3/gcc-5-glibc-2.23/65372bd

build_tools/dependencies_4.8.1.sh

@@ -1,5 +1,4 @@
 # shellcheck disable=SC2148
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 GCC_BASE=/mnt/gvfs/third-party2/gcc/cf7d14c625ce30bae1a4661c2319c5a283e4dd22/4.8.1/centos6-native/cc6c9dc
 CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/8598c375b0e94e1448182eb3df034704144a838d/stable/centos6-native/3f16ddd
 LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d6e0a7da6faba45f5e5b1638f9edd7afc2f34e7d/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc

build_tools/dependencies_platform007.sh

@@ -1,20 +1,18 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/963d9aeda70cc4779885b1277484fe7544a04e3e/9.0.0/platform007/9e92d53/
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+GCC_BASE=/mnt/gvfs/third-party2/gcc/6e8e715624fd15256a7970073387793dfcf79b46/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/ef37e1faa1c29782abfac1ae65a291b9b7966f6d/stable/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/c67031f0f739ac61575a061518d6ef5038f99f90/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/60d6f124a78798b73944f5ba87c2306ae3460153/2.26/platform007/f259413
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/platform007/ca4da3d
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/3ee276cbacfad3074e3f07bf826ac47f06970f4e/1.3.5/platform007/15a3614
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
-LIBURING_BASE=/mnt/gvfs/third-party2/liburing/79427253fd0d42677255aacfe6d13bfe63f752eb/20190828/platform007/ca4da3d
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/ab9f09bba370e7066cafd4eb59752db93f2e8312/2.29.1/platform007/15a3614
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/9c910d36d6235cc40e8ff559358f1833452300ca/master/platform007/5b0f53e
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/92ff90349e2f43ea0a8246d8b1cf17b6869013e3/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/platform007/ca4da3d
 LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832

build_tools/dockerbuild.sh

@@ -1,3 +1,2 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 docker run -v $PWD:/rocks -w /rocks buildpack-deps make

build_tools/error_filter.py

@@ -132,17 +132,11 @@ _TEST_NAME_TO_PARSERS = {
     'lite': [CompilerErrorParser],
     'lite_test': [CompilerErrorParser, GTestErrorParser],
     'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_atomic_flush': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_txn': [CompilerErrorParser, DbCrashErrorParser],
     'write_stress': [CompilerErrorParser, WriteStressErrorParser],
     'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
     'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_atomic_flush': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_txn': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
     'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
     'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_atomic_flush': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_txn': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
     'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
     'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
     'format_compatible': [CompilerErrorParser, CompatErrorParser],

build_tools/fb_compile_mongo.sh

@@ -1,5 +1,5 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+
 # fail early
 set -e
 

build_tools/fbcode_config.sh

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ and clang compilers and also
@@ -86,10 +85,9 @@ else
 fi
 CFLAGS+=" -DTBB"
 
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
@@ -160,6 +158,4 @@ else
   LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
 fi
 
-USE_FOLLY_DISTRIBUTED_MUTEX=1
-
 export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB

build_tools/fbcode_config4.8.1.sh

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ compiler and also
@@ -53,10 +52,9 @@ LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
 TBB_INCLUDE=" -isystem $TBB_BASE/include/"
 TBB_LIBS="$TBB_BASE/lib/libtbb.a"
 
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"

build_tools/fbcode_config_platform007.sh

@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Set environment variables so that we can compile rocksdb using
 # fbcode settings.  It uses the latest g++ and clang compilers and also
@@ -86,24 +85,14 @@ else
 fi
 CFLAGS+=" -DTBB"
 
-# location of LIBURING
-LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
-if test -z $PIC_BUILD; then
-  LIBURING_LIBS="$LIBURING_BASE/lib/liburing.a"
-else
-  LIBURING_LIBS="$LIBURING_BASE/lib/liburing_pic.a"
-fi
-CFLAGS+=" -DLIBURING"
-
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
+# use Intel SSE support for checksum calculations
+export USE_SSE=1
+export PORTABLE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
 
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE"
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"
 
 STDLIBS="-L $GCC_BASE/lib64"
 
@@ -144,10 +133,10 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
 CXXFLAGS+=" $CFLAGS"
 
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS"
+EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
 EXEC_LDFLAGS+=" -B$BINUTILS/gold"
 EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
@@ -157,7 +146,7 @@ EXEC_LDFLAGS+=" -ldl"
 
 PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
 
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS $LIBURING_LIBS"
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS"
 
 VALGRIND_VER="$VALGRIND_BASE/bin/"
 
@@ -165,6 +154,4 @@ VALGRIND_VER="$VALGRIND_BASE/bin/"
 LUA_PATH=
 LUA_LIB=
 
-USE_FOLLY_DISTRIBUTED_MUTEX=1
-
 export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB

build_tools/format-diff.sh

@@ -1,5 +1,4 @@
 #!/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 [ -z $CLANG_FORMAT_DIFF ]
@@ -13,14 +12,9 @@ then
   echo "You didn't have clang-format-diff.py and/or clang-format available in your computer!"
   echo "You can download clang-format-diff.py by running: "
   echo "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
-  echo "You can download clang-format by running:"
+  echo "You can download clang-format by running: "
   echo "    brew install clang-format"
-  echo "  Or"
-  echo "    apt install clang-format"
-  echo "  This might work too:"
-  echo "    yum install git-clang-format"
   echo "Then, move both files (i.e. ${CLANG_FORMAT_DIFF} and clang-format) to some directory within PATH=${PATH}"
-  echo "and make sure ${CLANG_FORMAT_DIFF} is executable."
   exit 128
 fi
 
@@ -59,25 +53,15 @@ fi
 set -e
 
 uncommitted_code=`git diff HEAD`
+LAST_MASTER=`git merge-base master HEAD`
 
 # If there's no uncommitted changes, we assume user are doing post-commit
-# format check, in which case we'll try to check the modified lines vs. the
-# facebook/rocksdb.git master branch. Otherwise, we'll check format of the
-# uncommitted code only.
+# format check, in which case we'll check the modified lines since last commit
+# from master. Otherwise, we'll check format of the uncommitted code only.
 if [ -z "$uncommitted_code" ]
 then
-  # Attempt to get name of facebook/rocksdb.git remote.
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE="$(git remote -v | grep 'facebook/rocksdb.git' | head -n 1 | cut -f 1)"
-  # Fall back on 'origin' if that fails
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE=origin
-  # Use master branch from that remote
-  [ "$FORMAT_UPSTREAM" ] || FORMAT_UPSTREAM="$FORMAT_REMOTE/master"
-  # Get the common ancestor with that remote branch. Everything after that
-  # common ancestor would be considered the contents of a pull request, so
-  # 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" | $CLANG_FORMAT_DIFF -p 1)
+  # Check the format of last commit
+  diffs=$(git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -p 1)
 else
   # Check the format of uncommitted lines,
   diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
@@ -91,12 +75,12 @@ fi
 
 # Highlight the insertion/deletion from the clang-format-diff.py's output
 COLOR_END="\033[0m"
-COLOR_RED="\033[0;31m"
-COLOR_GREEN="\033[0;32m"
+COLOR_RED="\033[0;31m" 
+COLOR_GREEN="\033[0;32m" 
 
 echo -e "Detect lines that doesn't follow the format rules:\r"
 # Add the color to the diff. lines added will be green; lines removed will be red.
-echo "$diffs" |
+echo "$diffs" | 
   sed -e "s/\(^-.*$\)/`echo -e \"$COLOR_RED\1$COLOR_END\"`/" |
   sed -e "s/\(^+.*$\)/`echo -e \"$COLOR_GREEN\1$COLOR_END\"`/"
 
@@ -119,7 +103,7 @@ fi
 # Do in-place format adjustment.
 if [ -z "$uncommitted_code" ]
 then
-  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -i -p 1
 else
   git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -i -p 1
 fi

build_tools/gnu_parallel

@@ -5801,7 +5801,7 @@ sub workdir {
 		    . "-" . $self->seq();
 	    } else {
 		$workdir = $opt::workdir;
-		# Rsync treats /./ special. We don't want that
+		# Rsync treats /./ special. We dont want that
 		$workdir =~ s:/\./:/:g; # Remove /./
 		$workdir =~ s:/+$::; # Remove ending / if any
 		$workdir =~ s:^\./::g; # Remove starting ./ if any

build_tools/make_package.sh

@@ -1,6 +1,5 @@
 # shellcheck disable=SC1113
 #/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 set -e
 

build_tools/precommit_checker.py

@@ -1,5 +1,4 @@
-#!/usr/bin/env python2.7
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#!/usr/local/fbcode/gcc-4.9-glibc-2.20-fb/bin/python2.7
 
 from __future__ import absolute_import
 from __future__ import division

build_tools/regression_build_test.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 set -e
 
@@ -378,7 +377,7 @@ function send_to_ods {
     echo >&2 "ERROR: Key $key doesn't have a value."
     return
   fi
-  curl --silent "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build$git_br&key=$key&value=$value" \
+  curl -s "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build$git_br&key=$key&value=$value" \
     --connect-timeout 60
 }
 

build_tools/rocksdb-lego-determinator

@@ -63,21 +63,6 @@ CLEANUP_ENV="
     'user':'root'
 }"
 
-UPLOAD_DB_DIR="
-{
-    'name':'Upload database directory',
-    'shell':'tar -cvzf rocksdb_db.tar.gz /dev/shm/rocksdb/',
-    'user':'root',
-    'cleanup':true,
-    'provide_artifacts': [
-    {
-      'name':'rocksdb_db_dir',
-      'paths': ['rocksdb_db.tar.gz'],
-      'bundle': false,
-    },
-    ],
-}"
-
 # We will eventually set the RATIO to 1, but we want do this
 # in steps. RATIO=$(nproc) will make it work as J=1
 if [ -z $RATIO ]; then
@@ -124,6 +109,13 @@ else
   TASK_CREATION_TOOL="false"
 fi
 
+ARTIFACTS=" 'artifacts': [
+    {
+        'name':'database',
+        'paths':[ '/dev/shm/rocksdb' ],
+    }
+]"
+
 #
 # A mechanism to disable tests temporarily
 #
@@ -148,7 +140,6 @@ UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -169,7 +160,6 @@ UNIT_TEST_NON_SHM_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -192,7 +182,6 @@ RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -213,7 +202,6 @@ UNIT_TEST_COMMANDS_481="[
     {
         'name':'Rocksdb Unit Test on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -234,7 +222,6 @@ RELEASE_BUILD_COMMANDS_481="[
     {
         'name':'Rocksdb Release on GCC 4.8.1',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -255,7 +242,6 @@ CLANG_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -276,7 +262,6 @@ CLANG_RELEASE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb CLANG Release Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -297,7 +282,6 @@ CLANG_ANALYZE_COMMANDS="[
     {
         'name':'Rocksdb analyze',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -318,7 +302,6 @@ CODE_COV_COMMANDS="[
     {
         'name':'Rocksdb Unit Test Code Coverage',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -339,7 +322,6 @@ UNITY_COMMANDS="[
     {
         'name':'Rocksdb Unity',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -360,7 +342,6 @@ LITE_BUILD_COMMANDS="[
     {
         'name':'Rocksdb Lite build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -380,7 +361,6 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
     {
         'name':'Rocksdb Lite Binary Size',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -396,9 +376,8 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
 #
 STRESS_CRASH_TEST_COMMANDS="[
     {
-        'name':'Rocksdb Stress and Crash Test',
+        'name':'Rocksdb Stress/Crash Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -414,69 +393,9 @@ STRESS_CRASH_TEST_COMMANDS="[
                 'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test with atomic flush
-#
-STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with atomic flush',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests with atomic flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_atomic_flush || $CONTRUN_NAME=crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test with txn
-#
-STRESS_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with txn',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests with txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_txn || $CONTRUN_NAME=crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
+            }
         ],
+        $ARTIFACTS,
         $REPORT
     }
 ]"
@@ -488,7 +407,6 @@ WRITE_STRESS_COMMANDS="[
     {
         'name':'Rocksdb Write Stress Test',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -511,7 +429,6 @@ ASAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under ASAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -532,7 +449,6 @@ ASAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under ASAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -543,55 +459,6 @@ ASAN_CRASH_TEST_COMMANDS="[
                 'user':'root',
                 $PARSER
             },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with atomic flush under address sanitizer
-#
-ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with atomic flush under ASAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test_with_atomic_flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_atomic_flush || $CONTRUN_NAME=asan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with txn under address sanitizer
-#
-ASAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with txn under ASAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test_with_txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_txn || $CONTRUN_NAME=asan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
         ],
         $REPORT
     }
@@ -604,12 +471,11 @@ UBSAN_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under UBSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Test RocksDB debug under UBSAN',
-                'shell':'set -o pipefail && $SHM $UBSAN $CLANG $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $UBSAN $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             }
@@ -625,66 +491,16 @@ UBSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb crash test under UBSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Build and run RocksDB debug ubsan_crash_test',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with atomic flush under undefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with atomic flush under UBSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test_with_atomic_flush',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with txn under undefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with txn under UBSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test_with_txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_txn || $CONTRUN_NAME=ubsan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
         ],
         $REPORT
     }
@@ -697,7 +513,6 @@ VALGRIND_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under valgrind',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -720,7 +535,6 @@ TSAN_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under TSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -743,7 +557,6 @@ TSAN_CRASH_TEST_COMMANDS="[
     {
         'name':'Rocksdb Crash Test under TSAN',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
@@ -754,55 +567,6 @@ TSAN_CRASH_TEST_COMMANDS="[
                 'user':'root',
                 $PARSER
             },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash test with atomic flush under TSAN
-#
-TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test with atomic flush under TSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_atomic_flush || $CONTRUN_NAME=tsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash test with txn under TSAN
-#
-TSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test with txn under TSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_txn || $CONTRUN_NAME=tsan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
         ],
         $REPORT
     }
@@ -825,7 +589,6 @@ FORMAT_COMPATIBLE_COMMANDS="[
     {
         'name':'Rocksdb Format Compatible tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -848,7 +611,7 @@ run_no_compression()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
   make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzstd | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
+  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
   mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
   cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
   mv .tmp.Makefile Makefile
@@ -859,7 +622,6 @@ NO_COMPRESSION_COMMANDS="[
     {
         'name':'Rocksdb No Compression tests',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -884,7 +646,7 @@ run_regression()
 
   # parameters: $1 -- key, $2 -- value
   function send_size_to_ods {
-    curl --silent "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=rocksdb.build_size.$1&value=$2" \
+    curl -s "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=rocksdb.build_size.$1&value=$2" \
       --connect-timeout 60
   }
 
@@ -937,7 +699,6 @@ JAVA_BUILD_TEST_COMMANDS="[
     {
         'name':'Rocksdb Java Build',
         'oncall':'$ONCALL',
-        'executeLocal': 'true',
         'steps': [
             $CLEANUP_ENV,
             {
@@ -992,12 +753,6 @@ case $1 in
   stress_crash)
     echo $STRESS_CRASH_TEST_COMMANDS
     ;;
-  stress_crash_with_atomic_flush)
-    echo $STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  stress_crash_with_txn)
-    echo $STRESS_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   write_stress)
     echo $WRITE_STRESS_COMMANDS
     ;;
@@ -1007,24 +762,12 @@ case $1 in
   asan_crash)
     echo $ASAN_CRASH_TEST_COMMANDS
     ;;
-  asan_crash_with_atomic_flush)
-    echo $ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  asan_crash_with_txn)
-    echo $ASAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   ubsan)
     echo $UBSAN_TEST_COMMANDS
     ;;
   ubsan_crash)
     echo $UBSAN_CRASH_TEST_COMMANDS
     ;;
-  ubsan_crash_with_atomic_flush)
-    echo $UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  ubsan_crash_with_txn)
-    echo $UBSAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   valgrind)
     echo $VALGRIND_TEST_COMMANDS
     ;;
@@ -1034,12 +777,6 @@ case $1 in
   tsan_crash)
     echo $TSAN_CRASH_TEST_COMMANDS
     ;;
-  tsan_crash_with_atomic_flush)
-    echo $TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
-  tsan_crash_with_txn)
-    echo $TSAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   format_compatible)
     echo $FORMAT_COMPATIBLE_COMMANDS
     ;;
@@ -1063,6 +800,5 @@ case $1 in
     ;;
   *)
     echo "Invalid determinator command"
-    exit 1
     ;;
 esac

build_tools/run_ci_db_test.ps1

@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # This script enables you running RocksDB tests by running
 # All the tests concurrently and utilizing all the cores
 Param(

build_tools/setup_centos7.sh

@@ -1,5 +1,4 @@
 #!/bin/bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 set -e
 
 ROCKSDB_VERSION="5.10.3"

build_tools/update_dependencies.sh

@@ -1,17 +1,10 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Update dependencies.sh file with the latest avaliable versions
 
 BASEDIR=$(dirname $0)
 OUTPUT=""
 
-function log_header()
-{
-  echo "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved." >> "$OUTPUT"
-}
-
-
 function log_variable()
 {
   echo "$1=${!1}" >> "$OUTPUT"
@@ -75,7 +68,6 @@ echo "Writing dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/7.x/centos7-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
@@ -92,7 +84,6 @@ get_lib_base jemalloc   LATEST  platform007
 get_lib_base numa       LATEST  platform007
 get_lib_base libunwind  LATEST  platform007
 get_lib_base tbb        LATEST  platform007
-get_lib_base liburing   LATEST  platform007
 
 get_lib_base kernel-headers fb platform007
 get_lib_base binutils   LATEST centos7-native
@@ -116,7 +107,6 @@ echo "Writing dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos7-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
@@ -156,7 +146,6 @@ echo "Writing 4.8.1 dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 

build_tools/version.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 if [ "$#" = "0" ]; then
   echo "Usage: $0 major|minor|patch|full"
   exit 1

cache/cache_bench.cc

@@ -3,6 +3,9 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
 #ifndef GFLAGS
 #include <cstdio>
 int main() {
@@ -11,9 +14,9 @@ int main() {
 }
 #else
 
-#include <stdio.h>
+#include <inttypes.h>
 #include <sys/types.h>
-#include <cinttypes>
+#include <stdio.h>
 
 #include "port/port.h"
 #include "rocksdb/cache.h"
@@ -45,7 +48,7 @@ DEFINE_int32(erase_percent, 10,
 
 DEFINE_bool(use_clock_cache, false, "");
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CacheBench;
 namespace {
@@ -154,7 +157,7 @@ class CacheBench {
   }
 
   bool Run() {
-    ROCKSDB_NAMESPACE::Env* env = ROCKSDB_NAMESPACE::Env::Default();
+    rocksdb::Env* env = rocksdb::Env::Default();
 
     PrintEnv();
     SharedState shared(this);
@@ -257,7 +260,7 @@ class CacheBench {
     printf("----------------------------\n");
   }
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ParseCommandLineFlags(&argc, &argv, true);
@@ -267,7 +270,7 @@ int main(int argc, char** argv) {
     exit(1);
   }
 
-  ROCKSDB_NAMESPACE::CacheBench bench;
+  rocksdb::CacheBench bench;
   if (FLAGS_populate_cache) {
     bench.PopulateCache();
   }

cache/cache_test.cc

@@ -16,11 +16,11 @@
 #include <vector>
 #include "cache/clock_cache.h"
 #include "cache/lru_cache.h"
-#include "test_util/testharness.h"
 #include "util/coding.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // Conversions between numeric keys/values and the types expected by Cache.
 static std::string EncodeKey(int k) {
@@ -73,7 +73,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
     current_ = this;
   }
 
-  ~CacheTest() override {}
+  ~CacheTest() {
+  }
 
   std::shared_ptr<Cache> NewCache(size_t capacity) {
     auto type = GetParam();
@@ -86,27 +87,19 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return nullptr;
   }
 
-  std::shared_ptr<Cache> NewCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      CacheMetadataChargePolicy charge_policy = kDontChargeCacheMetadata) {
+  std::shared_ptr<Cache> NewCache(size_t capacity, int num_shard_bits,
+                                  bool strict_capacity_limit) {
     auto type = GetParam();
     if (type == kLRU) {
-      LRUCacheOptions co;
-      co.capacity = capacity;
-      co.num_shard_bits = num_shard_bits;
-      co.strict_capacity_limit = strict_capacity_limit;
-      co.high_pri_pool_ratio = 0;
-      co.metadata_charge_policy = charge_policy;
-      return NewLRUCache(co);
+      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit);
     }
     if (type == kClock) {
-      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit,
-                           charge_policy);
+      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit);
     }
     return nullptr;
   }
 
-  int Lookup(std::shared_ptr<Cache> cache, int key) {
+  int Lookup(shared_ptr<Cache> cache, int key) {
     Cache::Handle* handle = cache->Lookup(EncodeKey(key));
     const int r = (handle == nullptr) ? -1 : DecodeValue(cache->Value(handle));
     if (handle != nullptr) {
@@ -115,16 +108,16 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return r;
   }
 
-  void Insert(std::shared_ptr<Cache> cache, int key, int value,
-              int charge = 1) {
+  void Insert(shared_ptr<Cache> cache, int key, int value, int charge = 1) {
     cache->Insert(EncodeKey(key), EncodeValue(value), charge,
                   &CacheTest::Deleter);
   }
 
-  void Erase(std::shared_ptr<Cache> cache, int key) {
+  void Erase(shared_ptr<Cache> cache, int key) {
     cache->Erase(EncodeKey(key));
   }
 
+
   int Lookup(int key) {
     return Lookup(cache_, key);
   }
@@ -151,15 +144,10 @@ class CacheTest : public testing::TestWithParam<std::string> {
 };
 CacheTest* CacheTest::current_;
 
-class LRUCacheTest : public CacheTest {};
-
 TEST_P(CacheTest, UsageTest) {
   // cache is std::shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 0, false, kFullChargeCacheMetadata);
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
+  auto cache = NewCache(kCapacity, 8, false);
 
   size_t usage = 0;
   char value[10] = "abcdef";
@@ -168,45 +156,31 @@ TEST_P(CacheTest, UsageTest) {
     std::string key(i, 'a');
     auto kv_size = key.size() + 5;
     cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter);
     usage += kv_size;
     ASSERT_EQ(usage, cache->GetUsage());
-    ASSERT_LT(usage, precise_cache->GetUsage());
   }
 
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
-
   // make sure the cache will be overloaded
   for (uint64_t i = 1; i < kCapacity; ++i) {
     auto key = ToString(i);
     cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                   dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
   }
 
   // the usage should be close to the capacity
   ASSERT_GT(kCapacity, cache->GetUsage());
-  ASSERT_GT(kCapacity, precise_cache->GetUsage());
   ASSERT_LT(kCapacity * 0.95, cache->GetUsage());
-  ASSERT_LT(kCapacity * 0.95, precise_cache->GetUsage());
 }
 
 TEST_P(CacheTest, PinnedUsageTest) {
   // cache is std::shared_ptr and will be automatically cleaned up.
-  const uint64_t kCapacity = 200000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 8, false, kFullChargeCacheMetadata);
+  const uint64_t kCapacity = 100000;
+  auto cache = NewCache(kCapacity, 8, false);
 
   size_t pinned_usage = 0;
   char value[10] = "abcdef";
 
   std::forward_list<Cache::Handle*> unreleased_handles;
-  std::forward_list<Cache::Handle*> unreleased_handles_in_precise_cache;
 
   // Add entries. Unpin some of them after insertion. Then, pin some of them
   // again. Check GetPinnedUsage().
@@ -214,72 +188,40 @@ TEST_P(CacheTest, PinnedUsageTest) {
     std::string key(i, 'a');
     auto kv_size = key.size() + 5;
     Cache::Handle* handle;
-    Cache::Handle* handle_in_precise_cache;
     cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter,
                   &handle);
-    assert(handle);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter, &handle_in_precise_cache);
-    assert(handle_in_precise_cache);
     pinned_usage += kv_size;
     ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-    ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     if (i % 2 == 0) {
       cache->Release(handle);
-      precise_cache->Release(handle_in_precise_cache);
       pinned_usage -= kv_size;
       ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     } else {
       unreleased_handles.push_front(handle);
-      unreleased_handles_in_precise_cache.push_front(handle_in_precise_cache);
     }
     if (i % 3 == 0) {
       unreleased_handles.push_front(cache->Lookup(key));
-      auto x = precise_cache->Lookup(key);
-      assert(x);
-      unreleased_handles_in_precise_cache.push_front(x);
       // If i % 2 == 0, then the entry was unpinned before Lookup, so pinned
       // usage increased
       if (i % 2 == 0) {
         pinned_usage += kv_size;
       }
       ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     }
   }
-  auto precise_cache_pinned_usage = precise_cache->GetPinnedUsage();
-  ASSERT_LT(pinned_usage, precise_cache_pinned_usage);
 
   // check that overloading the cache does not change the pinned usage
   for (uint64_t i = 1; i < 2 * kCapacity; ++i) {
     auto key = ToString(i);
     cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                   dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
   }
   ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
-
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
 
   // release handles for pinned entries to prevent memory leaks
   for (auto handle : unreleased_handles) {
     cache->Release(handle);
   }
-  for (auto handle : unreleased_handles_in_precise_cache) {
-    precise_cache->Release(handle);
-  }
-  ASSERT_EQ(0, cache->GetPinnedUsage());
-  ASSERT_EQ(0, precise_cache->GetPinnedUsage());
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
 }
 
 TEST_P(CacheTest, HitAndMiss) {
@@ -365,7 +307,7 @@ TEST_P(CacheTest, EvictionPolicy) {
   Insert(200, 201);
 
   // Frequently used entry must be kept around
-  for (int i = 0; i < kCacheSize * 2; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
     Insert(1000+i, 2000+i);
     ASSERT_EQ(101, Lookup(100));
   }
@@ -418,7 +360,7 @@ TEST_P(CacheTest, EvictionPolicyRef) {
   Insert(303, 104);
 
   // Insert entries much more than Cache capacity
-  for (int i = 0; i < kCacheSize * 2; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
     Insert(1000 + i, 2000 + i);
   }
 
@@ -609,10 +551,10 @@ TEST_P(CacheTest, SetCapacity) {
   }
 }
 
-TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
+TEST_P(CacheTest, SetStrictCapacityLimit) {
   // test1: set the flag to false. Insert more keys than capacity. See if they
   // all go through.
-  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
+  std::shared_ptr<Cache> cache = NewLRUCache(5, 0, false);
   std::vector<Cache::Handle*> handles(10);
   Status s;
   for (size_t i = 0; i < 10; i++) {
@@ -621,7 +563,6 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
     ASSERT_OK(s);
     ASSERT_NE(nullptr, handles[i]);
   }
-  ASSERT_EQ(10, cache->GetUsage());
 
   // test2: set the flag to true. Insert and check if it fails.
   std::string extra_key = "extra";
@@ -631,14 +572,13 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
   s = cache->Insert(extra_key, extra_value, 1, &deleter, &handle);
   ASSERT_TRUE(s.IsIncomplete());
   ASSERT_EQ(nullptr, handle);
-  ASSERT_EQ(10, cache->GetUsage());
 
   for (size_t i = 0; i < 10; i++) {
     cache->Release(handles[i]);
   }
 
   // test3: init with flag being true.
-  std::shared_ptr<Cache> cache2 = NewCache(5, 0, true);
+  std::shared_ptr<Cache> cache2 = NewLRUCache(5, 0, true);
   for (size_t i = 0; i < 5; i++) {
     std::string key = ToString(i + 1);
     s = cache2->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
@@ -652,7 +592,7 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
   s = cache2->Insert(extra_key, extra_value, 1, &deleter);
   // AS if the key have been inserted into cache but get evicted immediately.
   ASSERT_OK(s);
-  ASSERT_EQ(5, cache2->GetUsage());
+  ASSERT_EQ(5, cache->GetUsage());
   ASSERT_EQ(nullptr, cache2->Lookup(extra_key));
 
   for (size_t i = 0; i < 5; i++) {
@@ -747,25 +687,15 @@ TEST_P(CacheTest, DefaultShardBits) {
   ASSERT_EQ(6, sc->GetNumShardBits());
 }
 
-TEST_P(CacheTest, GetCharge) {
-  Insert(1, 2);
-  Cache::Handle* h1 = cache_->Lookup(EncodeKey(1));
-  ASSERT_EQ(2, DecodeValue(cache_->Value(h1)));
-  ASSERT_EQ(1, cache_->GetCharge(h1));
-  cache_->Release(h1);
-}
-
 #ifdef SUPPORT_CLOCK_CACHE
-std::shared_ptr<Cache> (*new_clock_cache_func)(
-    size_t, int, bool, CacheMetadataChargePolicy) = NewClockCache;
+shared_ptr<Cache> (*new_clock_cache_func)(size_t, int, bool) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                         testing::Values(kLRU, kClock));
 #else
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest, testing::Values(kLRU));
 #endif  // SUPPORT_CLOCK_CACHE
-INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest, testing::Values(kLRU));
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

cache/clock_cache.cc

@@ -11,16 +11,15 @@
 
 #ifndef SUPPORT_CLOCK_CACHE
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
-std::shared_ptr<Cache> NewClockCache(
-    size_t /*capacity*/, int /*num_shard_bits*/, bool /*strict_capacity_limit*/,
-    CacheMetadataChargePolicy /*metadata_charge_policy*/) {
+std::shared_ptr<Cache> NewClockCache(size_t /*capacity*/, int /*num_shard_bits*/,
+                                     bool /*strict_capacity_limit*/) {
   // Clock cache not supported.
   return nullptr;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #else
 
@@ -36,12 +35,11 @@ std::shared_ptr<Cache> NewClockCache(
 #include "tbb/concurrent_hash_map.h"
 
 #include "cache/sharded_cache.h"
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 namespace {
 
@@ -204,27 +202,6 @@ struct CacheHandle {
     deleter = a.deleter;
     return *this;
   }
-
-  inline static size_t CalcTotalCharge(
-      Slice key, size_t charge,
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-      meta_charge += sizeof(CacheHandle);
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge +=
-          malloc_usable_size(static_cast<void*>(const_cast<char*>(key.data())));
-#else
-      meta_charge += key.size();
-#endif
-    }
-    return charge + meta_charge;
-  }
-
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    return CalcTotalCharge(key, charge, metadata_charge_policy);
-  }
 };
 
 // Key of hash map. We store hash value with the key for convenience.
@@ -257,35 +234,38 @@ struct CleanupContext {
 };
 
 // A cache shard which maintains its own CLOCK cache.
-class ClockCacheShard final : public CacheShard {
+class ClockCacheShard : public CacheShard {
  public:
   // Hash map type.
   typedef tbb::concurrent_hash_map<CacheKey, CacheHandle*, CacheKey> HashTable;
 
   ClockCacheShard();
-  ~ClockCacheShard() override;
+  ~ClockCacheShard();
 
   // Interfaces
-  void SetCapacity(size_t capacity) override;
-  void SetStrictCapacityLimit(bool strict_capacity_limit) override;
-  Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value),
-                Cache::Handle** handle, Cache::Priority priority) override;
-  Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
+  virtual void SetCapacity(size_t capacity) override;
+  virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override;
+  virtual Status Insert(const Slice& key, uint32_t hash, void* value,
+                        size_t charge,
+                        void (*deleter)(const Slice& key, void* value),
+                        Cache::Handle** handle,
+                        Cache::Priority priority) override;
+  virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
   // If the entry in in cache, increase reference count and return true.
   // Return false otherwise.
   //
   // Not necessary to hold mutex_ before being called.
-  bool Ref(Cache::Handle* handle) override;
-  bool Release(Cache::Handle* handle, bool force_erase = false) override;
-  void Erase(const Slice& key, uint32_t hash) override;
+  virtual bool Ref(Cache::Handle* handle) override;
+  virtual bool Release(Cache::Handle* handle,
+                       bool force_erase = false) override;
+  virtual void Erase(const Slice& key, uint32_t hash) override;
   bool EraseAndConfirm(const Slice& key, uint32_t hash,
                        CleanupContext* context);
-  size_t GetUsage() const override;
-  size_t GetPinnedUsage() const override;
-  void EraseUnRefEntries() override;
-  void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
-                              bool thread_safe) override;
+  virtual size_t GetUsage() const override;
+  virtual size_t GetPinnedUsage() const override;
+  virtual void EraseUnRefEntries() override;
+  virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
+                                      bool thread_safe) override;
 
  private:
   static const uint32_t kInCacheBit = 1;
@@ -427,12 +407,11 @@ void ClockCacheShard::RecycleHandle(CacheHandle* handle,
   assert(!InCache(handle->flags) && CountRefs(handle->flags) == 0);
   context->to_delete_key.push_back(handle->key.data());
   context->to_delete_value.emplace_back(*handle);
-  size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
   handle->key.clear();
   handle->value = nullptr;
   handle->deleter = nullptr;
   recycle_.push_back(handle);
-  usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+  usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
 }
 
 void ClockCacheShard::Cleanup(const CleanupContext& context) {
@@ -458,8 +437,7 @@ bool ClockCacheShard::Ref(Cache::Handle* h) {
                                             std::memory_order_relaxed)) {
       if (CountRefs(flags) == 0) {
         // No reference count before the operation.
-        size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-        pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+        pinned_usage_.fetch_add(handle->charge, std::memory_order_relaxed);
       }
       return true;
     }
@@ -479,8 +457,7 @@ bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
   assert(CountRefs(flags) > 0);
   if (CountRefs(flags) == 1) {
     // this is the last reference.
-    size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-    pinned_usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
     // Cleanup if it is the last reference.
     if (!InCache(flags)) {
       MutexLock l(&mutex_);
@@ -565,10 +542,8 @@ CacheHandle* ClockCacheShard::Insert(
     const Slice& key, uint32_t hash, void* value, size_t charge,
     void (*deleter)(const Slice& key, void* value), bool hold_reference,
     CleanupContext* context) {
-  size_t total_charge =
-      CacheHandle::CalcTotalCharge(key, charge, metadata_charge_policy_);
   MutexLock l(&mutex_);
-  bool success = EvictFromCache(total_charge, context);
+  bool success = EvictFromCache(charge, context);
   bool strict = strict_capacity_limit_.load(std::memory_order_relaxed);
   if (!success && (strict || !hold_reference)) {
     context->to_delete_key.push_back(key.data());
@@ -603,9 +578,9 @@ CacheHandle* ClockCacheShard::Insert(
   }
   table_.insert(HashTable::value_type(CacheKey(key, hash), handle));
   if (hold_reference) {
-    pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_add(charge, std::memory_order_relaxed);
   }
-  usage_.fetch_add(total_charge, std::memory_order_relaxed);
+  usage_.fetch_add(charge, std::memory_order_relaxed);
   return handle;
 }
 
@@ -700,45 +675,41 @@ void ClockCacheShard::EraseUnRefEntries() {
   Cleanup(context);
 }
 
-class ClockCache final : public ShardedCache {
+class ClockCache : public ShardedCache {
  public:
-  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-             CacheMetadataChargePolicy metadata_charge_policy)
+  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit)
       : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
     int num_shards = 1 << num_shard_bits;
     shards_ = new ClockCacheShard[num_shards];
-    for (int i = 0; i < num_shards; i++) {
-      shards_[i].set_metadata_charge_policy(metadata_charge_policy);
-    }
     SetCapacity(capacity);
     SetStrictCapacityLimit(strict_capacity_limit);
   }
 
-  ~ClockCache() override { delete[] shards_; }
+  virtual ~ClockCache() { delete[] shards_; }
 
-  const char* Name() const override { return "ClockCache"; }
+  virtual const char* Name() const override { return "ClockCache"; }
 
-  CacheShard* GetShard(int shard) override {
+  virtual CacheShard* GetShard(int shard) override {
     return reinterpret_cast<CacheShard*>(&shards_[shard]);
   }
 
-  const CacheShard* GetShard(int shard) const override {
+  virtual const CacheShard* GetShard(int shard) const override {
     return reinterpret_cast<CacheShard*>(&shards_[shard]);
   }
 
-  void* Value(Handle* handle) override {
+  virtual void* Value(Handle* handle) override {
     return reinterpret_cast<const CacheHandle*>(handle)->value;
   }
 
-  size_t GetCharge(Handle* handle) const override {
+  virtual size_t GetCharge(Handle* handle) const override {
     return reinterpret_cast<const CacheHandle*>(handle)->charge;
   }
 
-  uint32_t GetHash(Handle* handle) const override {
+  virtual uint32_t GetHash(Handle* handle) const override {
     return reinterpret_cast<const CacheHandle*>(handle)->hash;
   }
 
-  void DisownData() override { shards_ = nullptr; }
+  virtual void DisownData() override { shards_ = nullptr; }
 
  private:
   ClockCacheShard* shards_;
@@ -746,16 +717,15 @@ class ClockCache final : public ShardedCache {
 
 }  // end anonymous namespace
 
-std::shared_ptr<Cache> NewClockCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
+                                     bool strict_capacity_limit) {
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  return std::make_shared<ClockCache>(
-      capacity, num_shard_bits, strict_capacity_limit, metadata_charge_policy);
+  return std::make_shared<ClockCache>(capacity, num_shard_bits,
+                                      strict_capacity_limit);
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #endif  // SUPPORT_CLOCK_CACHE

cache/lru_cache.cc

@@ -7,6 +7,10 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/lru_cache.h"
 
 #include <assert.h>
@@ -16,7 +20,7 @@
 
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {
   Resize();
@@ -24,7 +28,7 @@ LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {
 
 LRUHandleTable::~LRUHandleTable() {
   ApplyToAllCacheEntries([](LRUHandle* h) {
-    if (!h->HasRefs()) {
+    if (h->refs == 1) {
       h->Free();
     }
   });
@@ -96,18 +100,14 @@ void LRUHandleTable::Resize() {
 }
 
 LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                             double high_pri_pool_ratio,
-                             bool use_adaptive_mutex,
-                             CacheMetadataChargePolicy metadata_charge_policy)
+                             double high_pri_pool_ratio)
     : capacity_(0),
       high_pri_pool_usage_(0),
       strict_capacity_limit_(strict_capacity_limit),
       high_pri_pool_ratio_(high_pri_pool_ratio),
       high_pri_pool_capacity_(0),
       usage_(0),
-      lru_usage_(0),
-      mutex_(use_adaptive_mutex) {
-  set_metadata_charge_policy(metadata_charge_policy);
+      lru_usage_(0) {
   // Make empty circular linked list
   lru_.next = &lru_;
   lru_.prev = &lru_;
@@ -115,20 +115,30 @@ LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
   SetCapacity(capacity);
 }
 
+LRUCacheShard::~LRUCacheShard() {}
+
+bool LRUCacheShard::Unref(LRUHandle* e) {
+  assert(e->refs > 0);
+  e->refs--;
+  return e->refs == 0;
+}
+
+// Call deleter and free
+
 void LRUCacheShard::EraseUnRefEntries() {
   autovector<LRUHandle*> last_reference_list;
   {
     MutexLock l(&mutex_);
     while (lru_.next != &lru_) {
       LRUHandle* old = lru_.next;
-      // LRU list contains only elements which can be evicted
-      assert(old->InCache() && !old->HasRefs());
+      assert(old->InCache());
+      assert(old->refs ==
+             1);  // LRU list contains elements which may be evicted
       LRU_Remove(old);
       table_.Remove(old->key(), old->hash);
       old->SetInCache(false);
-      size_t total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
+      Unref(old);
+      usage_ -= old->charge;
       last_reference_list.push_back(old);
     }
   }
@@ -140,27 +150,22 @@ void LRUCacheShard::EraseUnRefEntries() {
 
 void LRUCacheShard::ApplyToAllCacheEntries(void (*callback)(void*, size_t),
                                            bool thread_safe) {
-  const auto applyCallback = [&]() {
-    table_.ApplyToAllCacheEntries(
-        [callback](LRUHandle* h) { callback(h->value, h->charge); });
-  };
-
   if (thread_safe) {
-    MutexLock l(&mutex_);
-    applyCallback();
-  } else {
-    applyCallback();
+    mutex_.Lock();
+  }
+  table_.ApplyToAllCacheEntries(
+      [callback](LRUHandle* h) { callback(h->value, h->charge); });
+  if (thread_safe) {
+    mutex_.Unlock();
   }
 }
 
 void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
-  MutexLock l(&mutex_);
   *lru = &lru_;
   *lru_low_pri = lru_low_pri_;
 }
 
 size_t LRUCacheShard::TEST_GetLRUSize() {
-  MutexLock l(&mutex_);
   LRUHandle* lru_handle = lru_.next;
   size_t lru_size = 0;
   while (lru_handle != &lru_) {
@@ -184,19 +189,16 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   e->next->prev = e->prev;
   e->prev->next = e->next;
   e->prev = e->next = nullptr;
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-  assert(lru_usage_ >= total_charge);
-  lru_usage_ -= total_charge;
+  lru_usage_ -= e->charge;
   if (e->InHighPriPool()) {
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    assert(high_pri_pool_usage_ >= e->charge);
+    high_pri_pool_usage_ -= e->charge;
   }
 }
 
 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
   assert(e->next == nullptr);
   assert(e->prev == nullptr);
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
   if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
     // Inset "e" to head of LRU list.
     e->next = &lru_;
@@ -204,7 +206,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->prev->next = e;
     e->next->prev = e;
     e->SetInHighPriPool(true);
-    high_pri_pool_usage_ += total_charge;
+    high_pri_pool_usage_ += e->charge;
     MaintainPoolSize();
   } else {
     // Insert "e" to the head of low-pri pool. Note that when
@@ -216,7 +218,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->SetInHighPriPool(false);
     lru_low_pri_ = e;
   }
-  lru_usage_ += total_charge;
+  lru_usage_ += e->charge;
 }
 
 void LRUCacheShard::MaintainPoolSize() {
@@ -225,25 +227,21 @@ void LRUCacheShard::MaintainPoolSize() {
     lru_low_pri_ = lru_low_pri_->next;
     assert(lru_low_pri_ != &lru_);
     lru_low_pri_->SetInHighPriPool(false);
-    size_t total_charge =
-        lru_low_pri_->CalcTotalCharge(metadata_charge_policy_);
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    high_pri_pool_usage_ -= lru_low_pri_->charge;
   }
 }
 
 void LRUCacheShard::EvictFromLRU(size_t charge,
                                  autovector<LRUHandle*>* deleted) {
-  while ((usage_ + charge) > capacity_ && lru_.next != &lru_) {
+  while (usage_ + charge > capacity_ && lru_.next != &lru_) {
     LRUHandle* old = lru_.next;
-    // LRU list contains only elements which can be evicted
-    assert(old->InCache() && !old->HasRefs());
+    assert(old->InCache());
+    assert(old->refs == 1);  // LRU list contains elements which may be evicted
     LRU_Remove(old);
     table_.Remove(old->key(), old->hash);
     old->SetInCache(false);
-    size_t old_total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-    assert(usage_ >= old_total_charge);
-    usage_ -= old_total_charge;
+    Unref(old);
+    usage_ -= old->charge;
     deleted->push_back(old);
   }
 }
@@ -256,8 +254,8 @@ void LRUCacheShard::SetCapacity(size_t capacity) {
     high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
     EvictFromLRU(0, &last_reference_list);
   }
-
-  // Free the entries outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
   for (auto entry : last_reference_list) {
     entry->Free();
   }
@@ -273,22 +271,22 @@ Cache::Handle* LRUCacheShard::Lookup(const Slice& key, uint32_t hash) {
   LRUHandle* e = table_.Lookup(key, hash);
   if (e != nullptr) {
     assert(e->InCache());
-    if (!e->HasRefs()) {
-      // The entry is in LRU since it's in hash and has no external references
+    if (e->refs == 1) {
       LRU_Remove(e);
     }
-    e->Ref();
+    e->refs++;
     e->SetHit();
   }
   return reinterpret_cast<Cache::Handle*>(e);
 }
 
 bool LRUCacheShard::Ref(Cache::Handle* h) {
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(h);
+  LRUHandle* handle = reinterpret_cast<LRUHandle*>(h);
   MutexLock l(&mutex_);
-  // To create another reference - entry must be already externally referenced
-  assert(e->HasRefs());
-  e->Ref();
+  if (handle->InCache() && handle->refs == 1) {
+    LRU_Remove(handle);
+  }
+  handle->refs++;
   return true;
 }
 
@@ -307,29 +305,30 @@ bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
   bool last_reference = false;
   {
     MutexLock l(&mutex_);
-    last_reference = e->Unref();
-    if (last_reference && e->InCache()) {
+    last_reference = Unref(e);
+    if (last_reference) {
+      usage_ -= e->charge;
+    }
+    if (e->refs == 1 && e->InCache()) {
       // The item is still in cache, and nobody else holds a reference to it
       if (usage_ > capacity_ || force_erase) {
+        // the cache is full
         // The LRU list must be empty since the cache is full
-        assert(lru_.next == &lru_ || force_erase);
-        // Take this opportunity and remove the item
+        assert(!(usage_ > capacity_) || lru_.next == &lru_);
+        // take this opportunity and remove the item
         table_.Remove(e->key(), e->hash);
         e->SetInCache(false);
+        Unref(e);
+        usage_ -= e->charge;
+        last_reference = true;
       } else {
-        // Put the item back on the LRU list, and don't free it
+        // put the item on the list to be potentially freed
         LRU_Insert(e);
-        last_reference = false;
       }
     }
-    if (last_reference) {
-      size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
-    }
   }
 
-  // Free the entry here outside of mutex for performance reasons
+  // free outside of mutex
   if (last_reference) {
     e->Free();
   }
@@ -345,7 +344,7 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   // It shouldn't happen very often though.
   LRUHandle* e = reinterpret_cast<LRUHandle*>(
       new char[sizeof(LRUHandle) - 1 + key.size()]);
-  Status s = Status::OK();
+  Status s;
   autovector<LRUHandle*> last_reference_list;
 
   e->value = value;
@@ -354,26 +353,26 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   e->key_length = key.size();
   e->flags = 0;
   e->hash = hash;
-  e->refs = 0;
+  e->refs = (handle == nullptr
+                 ? 1
+                 : 2);  // One from LRUCache, one for the returned handle
   e->next = e->prev = nullptr;
   e->SetInCache(true);
   e->SetPriority(priority);
   memcpy(e->key_data, key.data(), key.size());
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
 
   {
     MutexLock l(&mutex_);
 
     // Free the space following strict LRU policy until enough space
     // is freed or the lru list is empty
-    EvictFromLRU(total_charge, &last_reference_list);
+    EvictFromLRU(charge, &last_reference_list);
 
-    if ((usage_ + total_charge) > capacity_ &&
+    if (usage_ - lru_usage_ + charge > capacity_ &&
         (strict_capacity_limit_ || handle == nullptr)) {
       if (handle == nullptr) {
         // Don't insert the entry but still return ok, as if the entry inserted
         // into cache and get evicted immediately.
-        e->SetInCache(false);
         last_reference_list.push_back(e);
       } else {
         delete[] reinterpret_cast<char*>(e);
@@ -381,33 +380,32 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
         s = Status::Incomplete("Insert failed due to LRU cache being full.");
       }
     } else {
-      // Insert into the cache. Note that the cache might get larger than its
-      // capacity if not enough space was freed up.
+      // insert into the cache
+      // note that the cache might get larger than its capacity if not enough
+      // space was freed
       LRUHandle* old = table_.Insert(e);
-      usage_ += total_charge;
+      usage_ += e->charge;
       if (old != nullptr) {
-        assert(old->InCache());
         old->SetInCache(false);
-        if (!old->HasRefs()) {
-          // old is on LRU because it's in cache and its reference count is 0
+        if (Unref(old)) {
+          usage_ -= old->charge;
+          // old is on LRU because it's in cache and its reference count
+          // was just 1 (Unref returned 0)
           LRU_Remove(old);
-          size_t old_total_charge =
-              old->CalcTotalCharge(metadata_charge_policy_);
-          assert(usage_ >= old_total_charge);
-          usage_ -= old_total_charge;
           last_reference_list.push_back(old);
         }
       }
       if (handle == nullptr) {
         LRU_Insert(e);
       } else {
-        e->Ref();
         *handle = reinterpret_cast<Cache::Handle*>(e);
       }
+      s = Status::OK();
     }
   }
 
-  // Free the entries here outside of mutex for performance reasons
+  // we free the entries here outside of mutex for
+  // performance reasons
   for (auto entry : last_reference_list) {
     entry->Free();
   }
@@ -422,20 +420,18 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
     MutexLock l(&mutex_);
     e = table_.Remove(key, hash);
     if (e != nullptr) {
-      assert(e->InCache());
-      e->SetInCache(false);
-      if (!e->HasRefs()) {
-        // The entry is in LRU since it's in hash and has no external references
-        LRU_Remove(e);
-        size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-        assert(usage_ >= total_charge);
-        usage_ -= total_charge;
-        last_reference = true;
+      last_reference = Unref(e);
+      if (last_reference) {
+        usage_ -= e->charge;
       }
+      if (last_reference && e->InCache()) {
+        LRU_Remove(e);
+      }
+      e->SetInCache(false);
     }
   }
 
-  // Free the entry here outside of mutex for performance reasons
+  // mutex not held here
   // last_reference will only be true if e != nullptr
   if (last_reference) {
     e->Free();
@@ -466,9 +462,7 @@ std::string LRUCacheShard::GetPrintableOptions() const {
 
 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
                    bool strict_capacity_limit, double high_pri_pool_ratio,
-                   std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex,
-                   CacheMetadataChargePolicy metadata_charge_policy)
+                   std::shared_ptr<MemoryAllocator> allocator)
     : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
                    std::move(allocator)) {
   num_shards_ = 1 << num_shard_bits;
@@ -477,8 +471,7 @@ LRUCache::LRUCache(size_t capacity, int num_shard_bits,
   size_t per_shard = (capacity + (num_shards_ - 1)) / num_shards_;
   for (int i = 0; i < num_shards_; i++) {
     new (&shards_[i])
-        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio,
-                      use_adaptive_mutex, metadata_charge_policy);
+        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio);
   }
 }
 
@@ -547,15 +540,13 @@ std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
   return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
                      cache_opts.strict_capacity_limit,
                      cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-                     cache_opts.metadata_charge_policy);
+                     cache_opts.memory_allocator);
 }
 
 std::shared_ptr<Cache> NewLRUCache(
     size_t capacity, int num_shard_bits, bool strict_capacity_limit,
     double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+    std::shared_ptr<MemoryAllocator> memory_allocator) {
   if (num_shard_bits >= 20) {
     return nullptr;  // the cache cannot be sharded into too many fine pieces
   }
@@ -566,9 +557,9 @@ std::shared_ptr<Cache> NewLRUCache(
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  return std::make_shared<LRUCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      std::move(memory_allocator), use_adaptive_mutex, metadata_charge_policy);
+  return std::make_shared<LRUCache>(capacity, num_shard_bits,
+                                    strict_capacity_limit, high_pri_pool_ratio,
+                                    std::move(memory_allocator));
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cache/lru_cache.h

@@ -12,40 +12,36 @@
 
 #include "cache/sharded_cache.h"
 
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
-// LRU cache implementation. This class is not thread-safe.
+// LRU cache implementation
 
 // An entry is a variable length heap-allocated structure.
 // Entries are referenced by cache and/or by any external entity.
-// The cache keeps all its entries in a hash table. Some elements
+// The cache keeps all its entries in table. Some elements
 // are also stored on LRU list.
 //
 // LRUHandle can be in these states:
 // 1. Referenced externally AND in hash table.
-//    In that case the entry is *not* in the LRU list
-//    (refs >= 1 && in_cache == true)
-// 2. Not referenced externally AND in hash table.
-//    In that case the entry is in the LRU list and can be freed.
-//    (refs == 0 && in_cache == true)
-// 3. Referenced externally AND not in hash table.
-//    In that case the entry is not in the LRU list and not in hash table.
-//    The entry can be freed when refs becomes 0.
-//    (refs >= 1 && in_cache == false)
+//  In that case the entry is *not* in the LRU. (refs > 1 && in_cache == true)
+// 2. Not referenced externally and in hash table. In that case the entry is
+// in the LRU and can be freed. (refs == 1 && in_cache == true)
+// 3. Referenced externally and not in hash table. In that case the entry is
+// in not on LRU and not in table. (refs >= 1 && in_cache == false)
 //
 // All newly created LRUHandles are in state 1. If you call
-// LRUCacheShard::Release on entry in state 1, it will go into state 2.
-// To move from state 1 to state 3, either call LRUCacheShard::Erase or
-// LRUCacheShard::Insert with the same key (but possibly different value).
+// LRUCacheShard::Release
+// on entry in state 1, it will go into state 2. To move from state 1 to
+// state 3, either call LRUCacheShard::Erase or LRUCacheShard::Insert with the
+// same key.
 // To move from state 2 to state 1, use LRUCacheShard::Lookup.
 // Before destruction, make sure that no handles are in state 1. This means
 // that any successful LRUCacheShard::Lookup/LRUCacheShard::Insert have a
-// matching LRUCache::Release (to move into state 2) or LRUCacheShard::Erase
-// (to move into state 3).
+// matching
+// RUCache::Release (to move into state 2) or LRUCacheShard::Erase (for state 3)
 
 struct LRUHandle {
   void* value;
@@ -55,95 +51,67 @@ struct LRUHandle {
   LRUHandle* prev;
   size_t charge;  // TODO(opt): Only allow uint32_t?
   size_t key_length;
-  // The hash of key(). Used for fast sharding and comparisons.
-  uint32_t hash;
-  // The number of external refs to this entry. The cache itself is not counted.
-  uint32_t refs;
+  uint32_t refs;     // a number of refs to this entry
+                     // cache itself is counted as 1
 
-  enum Flags : uint8_t {
-    // Whether this entry is referenced by the hash table.
-    IN_CACHE = (1 << 0),
-    // Whether this entry is high priority entry.
-    IS_HIGH_PRI = (1 << 1),
-    // Whether this entry is in high-pri pool.
-    IN_HIGH_PRI_POOL = (1 << 2),
-    // Wwhether this entry has had any lookups (hits).
-    HAS_HIT = (1 << 3),
-  };
+  // Include the following flags:
+  //   in_cache:    whether this entry is referenced by the hash table.
+  //   is_high_pri: whether this entry is high priority entry.
+  //   in_high_pri_pool: whether this entry is in high-pri pool.
+  char flags;
 
-  uint8_t flags;
+  uint32_t hash;     // Hash of key(); used for fast sharding and comparisons
 
-  // Beginning of the key (MUST BE THE LAST FIELD IN THIS STRUCT!)
-  char key_data[1];
+  char key_data[1];  // Beginning of key
 
-  Slice key() const { return Slice(key_data, key_length); }
-
-  // Increase the reference count by 1.
-  void Ref() { refs++; }
-
-  // Just reduce the reference count by 1. Return true if it was last reference.
-  bool Unref() {
-    assert(refs > 0);
-    refs--;
-    return refs == 0;
+  Slice key() const {
+    // For cheaper lookups, we allow a temporary Handle object
+    // to store a pointer to a key in "value".
+    if (next == this) {
+      return *(reinterpret_cast<Slice*>(value));
+    } else {
+      return Slice(key_data, key_length);
+    }
   }
 
-  // Return true if there are external refs, false otherwise.
-  bool HasRefs() const { return refs > 0; }
-
-  bool InCache() const { return flags & IN_CACHE; }
-  bool IsHighPri() const { return flags & IS_HIGH_PRI; }
-  bool InHighPriPool() const { return flags & IN_HIGH_PRI_POOL; }
-  bool HasHit() const { return flags & HAS_HIT; }
+  bool InCache() { return flags & 1; }
+  bool IsHighPri() { return flags & 2; }
+  bool InHighPriPool() { return flags & 4; }
+  bool HasHit() { return flags & 8; }
 
   void SetInCache(bool in_cache) {
     if (in_cache) {
-      flags |= IN_CACHE;
+      flags |= 1;
     } else {
-      flags &= ~IN_CACHE;
+      flags &= ~1;
     }
   }
 
   void SetPriority(Cache::Priority priority) {
     if (priority == Cache::Priority::HIGH) {
-      flags |= IS_HIGH_PRI;
+      flags |= 2;
     } else {
-      flags &= ~IS_HIGH_PRI;
+      flags &= ~2;
     }
   }
 
   void SetInHighPriPool(bool in_high_pri_pool) {
     if (in_high_pri_pool) {
-      flags |= IN_HIGH_PRI_POOL;
+      flags |= 4;
     } else {
-      flags &= ~IN_HIGH_PRI_POOL;
+      flags &= ~4;
     }
   }
 
-  void SetHit() { flags |= HAS_HIT; }
+  void SetHit() { flags |= 8; }
 
   void Free() {
-    assert(refs == 0);
+    assert((refs == 1 && InCache()) || (refs == 0 && !InCache()));
     if (deleter) {
       (*deleter)(key(), value);
     }
     delete[] reinterpret_cast<char*>(this);
   }
-
-  // Caclculate the memory usage by metadata
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge += malloc_usable_size(static_cast<void*>(this));
-#else
-      // This is the size that is used when a new handle is created
-      meta_charge += sizeof(LRUHandle) - 1 + key_length;
-#endif
-    }
-    return charge + meta_charge;
-  }
 };
 
 // We provide our own simple hash table since it removes a whole bunch
@@ -189,12 +157,11 @@ class LRUHandleTable {
 };
 
 // A single shard of sharded cache.
-class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
+class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
  public:
   LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                double high_pri_pool_ratio, bool use_adaptive_mutex,
-                CacheMetadataChargePolicy metadata_charge_policy);
-  virtual ~LRUCacheShard() override = default;
+                double high_pri_pool_ratio);
+  virtual ~LRUCacheShard();
 
   // Separate from constructor so caller can easily make an array of LRUCache
   // if current usage is more than new capacity, the function will attempt to
@@ -250,6 +217,10 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   // high-pri pool is no larger than the size specify by high_pri_pool_pct.
   void MaintainPoolSize();
 
+  // Just reduce the reference count by 1.
+  // Return true if last reference
+  bool Unref(LRUHandle* e);
+
   // Free some space following strict LRU policy until enough space
   // to hold (usage_ + charge) is freed or the lru list is empty
   // This function is not thread safe - it needs to be executed while
@@ -305,18 +276,11 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
   mutable port::Mutex mutex_;
 };
 
-class LRUCache
-#ifdef NDEBUG
-    final
-#endif
-    : public ShardedCache {
+class LRUCache : public ShardedCache {
  public:
   LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
            double high_pri_pool_ratio,
-           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
+           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
   virtual ~LRUCache();
   virtual const char* Name() const override { return "LRUCache"; }
   virtual CacheShard* GetShard(int shard) override;
@@ -336,4 +300,4 @@ class LRUCache
   int num_shards_ = 0;
 };
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cache/lru_cache_test.cc

@@ -8,14 +8,14 @@
 #include <string>
 #include <vector>
 #include "port/port.h"
-#include "test_util/testharness.h"
+#include "util/testharness.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class LRUCacheTest : public testing::Test {
  public:
   LRUCacheTest() {}
-  ~LRUCacheTest() override { DeleteCache(); }
+  ~LRUCacheTest() { DeleteCache(); }
 
   void DeleteCache() {
     if (cache_ != nullptr) {
@@ -25,14 +25,12 @@ class LRUCacheTest : public testing::Test {
     }
   }
 
-  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0,
-                bool use_adaptive_mutex = kDefaultToAdaptiveMutex) {
+  void NewCache(size_t capacity, double high_pri_pool_ratio = 0.0) {
     DeleteCache();
     cache_ = reinterpret_cast<LRUCacheShard*>(
         port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
     new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
-                               high_pri_pool_ratio, use_adaptive_mutex,
-                               kDontChargeCacheMetadata);
+                               high_pri_pool_ratio);
   }
 
   void Insert(const std::string& key,
@@ -190,7 +188,7 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   ValidateLRUList({"e", "f", "g", "Z", "d"}, 2);
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

cache/sharded_cache.cc

@@ -7,13 +7,17 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
 #include "cache/sharded_cache.h"
 
 #include <string>
 
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 ShardedCache::ShardedCache(size_t capacity, int num_shard_bits,
                            bool strict_capacity_limit,
@@ -159,4 +163,4 @@ int GetDefaultCacheShardBits(size_t capacity) {
   return num_shard_bits;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cache/sharded_cache.h

@@ -16,7 +16,7 @@
 #include "rocksdb/cache.h"
 #include "util/hash.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // Single cache shard interface.
 class CacheShard {
@@ -40,13 +40,6 @@ class CacheShard {
                                       bool thread_safe) = 0;
   virtual void EraseUnRefEntries() = 0;
   virtual std::string GetPrintableOptions() const { return ""; }
-  void set_metadata_charge_policy(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    metadata_charge_policy_ = metadata_charge_policy;
-  }
-
- protected:
-  CacheMetadataChargePolicy metadata_charge_policy_ = kDontChargeCacheMetadata;
 };
 
 // Generic cache interface which shards cache by hash of keys. 2^num_shard_bits
@@ -61,8 +54,7 @@ class ShardedCache : public Cache {
   virtual CacheShard* GetShard(int shard) = 0;
   virtual const CacheShard* GetShard(int shard) const = 0;
   virtual void* Value(Handle* handle) override = 0;
-  virtual size_t GetCharge(Handle* handle) const override = 0;
-
+  virtual size_t GetCharge(Handle* handle) const = 0;
   virtual uint32_t GetHash(Handle* handle) const = 0;
   virtual void DisownData() override = 0;
 
@@ -91,7 +83,7 @@ class ShardedCache : public Cache {
 
  private:
   static inline uint32_t HashSlice(const Slice& s) {
-    return static_cast<uint32_t>(GetSliceNPHash64(s));
+    return Hash(s.data(), s.size(), 0);
   }
 
   uint32_t Shard(uint32_t hash) {
@@ -108,4 +100,4 @@ class ShardedCache : public Cache {
 
 extern int GetDefaultCacheShardBits(size_t capacity);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cmake/modules/FindJeMalloc.cmake

@@ -1,29 +1,21 @@
 # - Find JeMalloc library
 # Find the native JeMalloc includes and library
 #
-# JeMalloc_INCLUDE_DIRS - where to find jemalloc.h, etc.
-# JeMalloc_LIBRARIES - List of libraries when using jemalloc.
-# JeMalloc_FOUND - True if jemalloc found.
+# JEMALLOC_INCLUDE_DIR - where to find jemalloc.h, etc.
+# JEMALLOC_LIBRARIES - List of libraries when using jemalloc.
+# JEMALLOC_FOUND - True if jemalloc found.
 
-find_path(JeMalloc_INCLUDE_DIRS
+find_path(JEMALLOC_INCLUDE_DIR
   NAMES jemalloc/jemalloc.h
   HINTS ${JEMALLOC_ROOT_DIR}/include)
 
-find_library(JeMalloc_LIBRARIES
+find_library(JEMALLOC_LIBRARIES
   NAMES jemalloc
   HINTS ${JEMALLOC_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(JeMalloc DEFAULT_MSG JeMalloc_LIBRARIES JeMalloc_INCLUDE_DIRS)
+find_package_handle_standard_args(jemalloc DEFAULT_MSG JEMALLOC_LIBRARIES JEMALLOC_INCLUDE_DIR)
 
 mark_as_advanced(
-  JeMalloc_LIBRARIES
-  JeMalloc_INCLUDE_DIRS)
-
-if(JeMalloc_FOUND AND NOT (TARGET JeMalloc::JeMalloc))
-  add_library (JeMalloc::JeMalloc UNKNOWN IMPORTED)
-  set_target_properties(JeMalloc::JeMalloc
-    PROPERTIES
-      IMPORTED_LOCATION ${JeMalloc_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${JeMalloc_INCLUDE_DIRS})
-endif()
+  JEMALLOC_LIBRARIES
+  JEMALLOC_INCLUDE_DIR)

cmake/modules/FindNUMA.cmake

@@ -1,11 +1,11 @@
 # - Find NUMA
 # Find the NUMA library and includes
 #
-# NUMA_INCLUDE_DIRS - where to find numa.h, etc.
+# NUMA_INCLUDE_DIR - where to find numa.h, etc.
 # NUMA_LIBRARIES - List of libraries when using NUMA.
 # NUMA_FOUND - True if NUMA found.
 
-find_path(NUMA_INCLUDE_DIRS
+find_path(NUMA_INCLUDE_DIR
   NAMES numa.h numaif.h
   HINTS ${NUMA_ROOT_DIR}/include)
 
@@ -14,16 +14,8 @@ find_library(NUMA_LIBRARIES
   HINTS ${NUMA_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIRS)
+find_package_handle_standard_args(NUMA DEFAULT_MSG NUMA_LIBRARIES NUMA_INCLUDE_DIR)
 
 mark_as_advanced(
   NUMA_LIBRARIES
-  NUMA_INCLUDE_DIRS)
-
-if(NUMA_FOUND AND NOT (TARGET NUMA::NUMA))
-  add_library (NUMA::NUMA UNKNOWN IMPORTED)
-  set_target_properties(NUMA::NUMA
-    PROPERTIES
-      IMPORTED_LOCATION ${NUMA_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${NUMA_INCLUDE_DIRS})
-endif()
+  NUMA_INCLUDE_DIR)

cmake/modules/FindTBB.cmake

@@ -1,7 +1,7 @@
 # - Find TBB
 # Find the Thread Building Blocks library and includes
 #
-# TBB_INCLUDE_DIRS - where to find tbb.h, etc.
+# TBB_INCLUDE_DIR - where to find tbb.h, etc.
 # TBB_LIBRARIES - List of libraries when using TBB.
 # TBB_FOUND - True if TBB found.
 
@@ -9,25 +9,17 @@ if(NOT DEFINED TBB_ROOT_DIR)
   set(TBB_ROOT_DIR "$ENV{TBBROOT}")
 endif()
 
-find_path(TBB_INCLUDE_DIRS
-  NAMES tbb/tbb.h
-  HINTS ${TBB_ROOT_DIR}/include)
+find_path(TBB_INCLUDE_DIR
+NAMES tbb/tbb.h
+HINTS ${TBB_ROOT_DIR}/include)
 
 find_library(TBB_LIBRARIES
-  NAMES tbb
-  HINTS ${TBB_ROOT_DIR}/lib ENV LIBRARY_PATH)
+NAMES tbb
+HINTS ${TBB_ROOT_DIR}/lib ENV LIBRARY_PATH)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIRS)
+find_package_handle_standard_args(TBB DEFAULT_MSG TBB_LIBRARIES TBB_INCLUDE_DIR)
 
 mark_as_advanced(
-  TBB_LIBRARIES
-  TBB_INCLUDE_DIRS)
-
-if(TBB_FOUND AND NOT (TARGET TBB::TBB))
-  add_library (TBB::TBB UNKNOWN IMPORTED)
-  set_target_properties(TBB::TBB
-    PROPERTIES
-      IMPORTED_LOCATION ${TBB_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${TBB_INCLUDE_DIRS})
-endif()
+TBB_LIBRARIES
+TBB_INCLUDE_DIR)

cmake/modules/Findbzip2.cmake

@@ -0,0 +1,21 @@
+# - Find Bzip2
+# Find the bzip2 compression library and includes
+#
+# BZIP2_INCLUDE_DIR - where to find bzlib.h, etc.
+# BZIP2_LIBRARIES - List of libraries when using bzip2.
+# BZIP2_FOUND - True if bzip2 found.
+
+find_path(BZIP2_INCLUDE_DIR
+  NAMES bzlib.h
+  HINTS ${BZIP2_ROOT_DIR}/include)
+
+find_library(BZIP2_LIBRARIES
+  NAMES bz2
+  HINTS ${BZIP2_ROOT_DIR}/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(bzip2 DEFAULT_MSG BZIP2_LIBRARIES BZIP2_INCLUDE_DIR)
+
+mark_as_advanced(
+  BZIP2_LIBRARIES
+  BZIP2_INCLUDE_DIR)

cmake/modules/Findgflags.cmake

@@ -1,29 +0,0 @@
-# - Find gflags library
-# Find the gflags includes and library
-#
-# gflags_INCLUDE_DIR - where to find gflags.h.
-# gflags_LIBRARIES - List of libraries when using gflags.
-# gflags_FOUND - True if gflags found.
-
-find_path(GFLAGS_INCLUDE_DIR
-  NAMES gflags/gflags.h)
-
-find_library(GFLAGS_LIBRARIES
-  NAMES gflags)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(gflags
-  DEFAULT_MSG GFLAGS_LIBRARIES GFLAGS_INCLUDE_DIR)
-
-mark_as_advanced(
-  GFLAGS_LIBRARIES
-  GFLAGS_INCLUDE_DIR)
-
-if(gflags_FOUND AND NOT (TARGET gflags::gflags))
-  add_library(gflags::gflags UNKNOWN IMPORTED)
-  set_target_properties(gflags::gflags
-    PROPERTIES
-      IMPORTED_LOCATION ${GFLAGS_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${GFLAGS_INCLUDE_DIR}
-      IMPORTED_LINK_INTERFACE_LANGUAGES "CXX")
-endif()

cmake/modules/Findlz4.cmake

@@ -1,29 +1,21 @@
 # - Find Lz4
 # Find the lz4 compression library and includes
 #
-# lz4_INCLUDE_DIRS - where to find lz4.h, etc.
-# lz4_LIBRARIES - List of libraries when using lz4.
-# lz4_FOUND - True if lz4 found.
+# LZ4_INCLUDE_DIR - where to find lz4.h, etc.
+# LZ4_LIBRARIES - List of libraries when using lz4.
+# LZ4_FOUND - True if lz4 found.
 
-find_path(lz4_INCLUDE_DIRS
+find_path(LZ4_INCLUDE_DIR
   NAMES lz4.h
-  HINTS ${lz4_ROOT_DIR}/include)
+  HINTS ${LZ4_ROOT_DIR}/include)
 
-find_library(lz4_LIBRARIES
+find_library(LZ4_LIBRARIES
   NAMES lz4
-  HINTS ${lz4_ROOT_DIR}/lib)
+  HINTS ${LZ4_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(lz4 DEFAULT_MSG lz4_LIBRARIES lz4_INCLUDE_DIRS)
+find_package_handle_standard_args(lz4 DEFAULT_MSG LZ4_LIBRARIES LZ4_INCLUDE_DIR)
 
 mark_as_advanced(
-  lz4_LIBRARIES
-  lz4_INCLUDE_DIRS)
-
-if(lz4_FOUND AND NOT (TARGET lz4::lz4))
-  add_library(lz4::lz4 UNKNOWN IMPORTED)
-  set_target_properties(lz4::lz4
-    PROPERTIES
-      IMPORTED_LOCATION ${lz4_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${lz4_INCLUDE_DIRS})
-endif()
+  LZ4_LIBRARIES
+  LZ4_INCLUDE_DIR)

cmake/modules/Findsnappy.cmake

@@ -1,29 +1,21 @@
 # - Find Snappy
 # Find the snappy compression library and includes
 #
-# snappy_INCLUDE_DIRS - where to find snappy.h, etc.
-# snappy_LIBRARIES - List of libraries when using snappy.
-# snappy_FOUND - True if snappy found.
+# SNAPPY_INCLUDE_DIR - where to find snappy.h, etc.
+# SNAPPY_LIBRARIES - List of libraries when using snappy.
+# SNAPPY_FOUND - True if snappy found.
 
-find_path(snappy_INCLUDE_DIRS
+find_path(SNAPPY_INCLUDE_DIR
   NAMES snappy.h
-  HINTS ${snappy_ROOT_DIR}/include)
+  HINTS ${SNAPPY_ROOT_DIR}/include)
 
-find_library(snappy_LIBRARIES
+find_library(SNAPPY_LIBRARIES
   NAMES snappy
-  HINTS ${snappy_ROOT_DIR}/lib)
+  HINTS ${SNAPPY_ROOT_DIR}/lib)
 
 include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(snappy DEFAULT_MSG snappy_LIBRARIES snappy_INCLUDE_DIRS)
+find_package_handle_standard_args(snappy DEFAULT_MSG SNAPPY_LIBRARIES SNAPPY_INCLUDE_DIR)
 
 mark_as_advanced(
-  snappy_LIBRARIES
-  snappy_INCLUDE_DIRS)
-
-if(snappy_FOUND AND NOT (TARGET snappy::snappy))
-  add_library (snappy::snappy UNKNOWN IMPORTED)
-  set_target_properties(snappy::snappy
-    PROPERTIES
-      IMPORTED_LOCATION ${snappy_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${snappy_INCLUDE_DIRS})
-endif()
+  SNAPPY_LIBRARIES
+  SNAPPY_INCLUDE_DIR)

cmake/modules/Findzstd.cmake

@@ -1,29 +1,21 @@
 # - 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_DIR - 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_DIR
   NAMES zstd.h
-  HINTS ${zstd_ROOT_DIR}/include)
+  HINTS ${ZSTD_ROOT_DIR}/include)
 
-find_library(zstd_LIBRARIES
+find_library(ZSTD_LIBRARIES
   NAMES zstd
-  HINTS ${zstd_ROOT_DIR}/lib)
+  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_DIR)
 
 mark_as_advanced(
-  zstd_LIBRARIES
-  zstd_INCLUDE_DIRS)
-
-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})
-endif()
+  ZSTD_LIBRARIES
+  ZSTD_INCLUDE_DIR)

cmake/modules/ReadVersion.cmake

@@ -1,10 +0,0 @@
-# Read rocksdb version from version.h header file.
-
-function(get_rocksdb_version version_var)
-  file(READ "${CMAKE_CURRENT_SOURCE_DIR}/include/rocksdb/version.h" version_header_file)
-  foreach(component MAJOR MINOR PATCH)
-    string(REGEX MATCH "#define ROCKSDB_${component} ([0-9]+)" _ ${version_header_file})
-    set(ROCKSDB_VERSION_${component} ${CMAKE_MATCH_1})
-  endforeach()
-  set(${version_var} "${ROCKSDB_VERSION_MAJOR}.${ROCKSDB_VERSION_MINOR}.${ROCKSDB_VERSION_PATCH}" PARENT_SCOPE)
-endfunction()

coverage/coverage_test.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 # Exit on error.
 set -e

coverage/parse_gcov_output.py

@@ -1,5 +1,3 @@
-#!/usr/bin/env python2
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 import re
 import sys
 

db/arena_wrapped_db_iter.cc

@@ -1,106 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/arena_wrapped_db_iter.h"
-#include "memory/arena.h"
-#include "rocksdb/env.h"
-#include "rocksdb/iterator.h"
-#include "rocksdb/options.h"
-#include "table/internal_iterator.h"
-#include "table/iterator_wrapper.h"
-#include "util/user_comparator_wrapper.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
-                                       std::string* prop) {
-  if (prop_name == "rocksdb.iterator.super-version-number") {
-    // First try to pass the value returned from inner iterator.
-    if (!db_iter_->GetProperty(prop_name, prop).ok()) {
-      *prop = ToString(sv_number_);
-    }
-    return Status::OK();
-  }
-  return db_iter_->GetProperty(prop_name, prop);
-}
-
-void ArenaWrappedDBIter::Init(Env* env, const ReadOptions& read_options,
-                              const ImmutableCFOptions& cf_options,
-                              const MutableCFOptions& mutable_cf_options,
-                              const SequenceNumber& sequence,
-                              uint64_t max_sequential_skip_in_iteration,
-                              uint64_t version_number,
-                              ReadCallback* read_callback, DBImpl* db_impl,
-                              ColumnFamilyData* cfd, bool allow_blob,
-                              bool allow_refresh) {
-  auto mem = arena_.AllocateAligned(sizeof(DBIter));
-  db_iter_ = new (mem) DBIter(env, read_options, cf_options, mutable_cf_options,
-                              cf_options.user_comparator, nullptr, sequence,
-                              true, max_sequential_skip_in_iteration,
-                              read_callback, db_impl, cfd, allow_blob);
-  sv_number_ = version_number;
-  allow_refresh_ = allow_refresh;
-}
-
-Status ArenaWrappedDBIter::Refresh() {
-  if (cfd_ == nullptr || db_impl_ == nullptr || !allow_refresh_) {
-    return Status::NotSupported("Creating renew iterator is not allowed.");
-  }
-  assert(db_iter_ != nullptr);
-  // 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.
-  SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
-  uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
-  if (sv_number_ != cur_sv_number) {
-    Env* env = db_iter_->env();
-    db_iter_->~DBIter();
-    arena_.~Arena();
-    new (&arena_) Arena();
-
-    SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
-    if (read_callback_) {
-      read_callback_->Refresh(latest_seq);
-    }
-    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
-         latest_seq, sv->mutable_cf_options.max_sequential_skip_in_iterations,
-         cur_sv_number, read_callback_, db_impl_, cfd_, allow_blob_,
-         allow_refresh_);
-
-    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
-        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
-        latest_seq);
-    SetIterUnderDBIter(internal_iter);
-  } else {
-    db_iter_->set_sequence(latest_seq);
-    db_iter_->set_valid(false);
-  }
-  return Status::OK();
-}
-
-ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-    bool allow_blob, bool allow_refresh) {
-  ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
-  iter->Init(env, read_options, cf_options, mutable_cf_options, sequence,
-             max_sequential_skip_in_iterations, version_number, read_callback,
-             db_impl, cfd, allow_blob, allow_refresh);
-  if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
-    iter->StoreRefreshInfo(read_options, db_impl, cfd, read_callback,
-                           allow_blob);
-  }
-
-  return iter;
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/arena_wrapped_db_iter.h

@@ -1,115 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-#include <stdint.h>
-#include <string>
-#include "db/db_impl/db_impl.h"
-#include "db/db_iter.h"
-#include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
-#include "memory/arena.h"
-#include "options/cf_options.h"
-#include "rocksdb/db.h"
-#include "rocksdb/iterator.h"
-#include "util/autovector.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class Arena;
-
-// A wrapper iterator which wraps DB Iterator and the arena, with which the DB
-// iterator is supposed to be allocated. This class is used as an entry point of
-// a iterator hierarchy whose memory can be allocated inline. In that way,
-// accessing the iterator tree can be more cache friendly. It is also faster
-// to allocate.
-// When using the class's Iterator interface, the behavior is exactly
-// the same as the inner DBIter.
-class ArenaWrappedDBIter : public Iterator {
- public:
-  virtual ~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
-
-  // Get the arena to be used to allocate memory for DBIter to be wrapped,
-  // as well as child iterators in it.
-  virtual Arena* GetArena() { return &arena_; }
-  virtual ReadRangeDelAggregator* GetRangeDelAggregator() {
-    return db_iter_->GetRangeDelAggregator();
-  }
-
-  // Set the internal iterator wrapped inside the DB Iterator. Usually it is
-  // a merging iterator.
-  virtual void SetIterUnderDBIter(InternalIterator* iter) {
-    db_iter_->SetIter(iter);
-  }
-
-  bool Valid() const override { return db_iter_->Valid(); }
-  void SeekToFirst() override { db_iter_->SeekToFirst(); }
-  void SeekToLast() override { db_iter_->SeekToLast(); }
-  // 'target' does not contain timestamp, even if user timestamp feature is
-  // enabled.
-  void Seek(const Slice& target) override { db_iter_->Seek(target); }
-  void SeekForPrev(const Slice& target) override {
-    db_iter_->SeekForPrev(target);
-  }
-  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(); }
-  Status status() const override { return db_iter_->status(); }
-  Slice timestamp() const override { return db_iter_->timestamp(); }
-  bool IsBlob() const { return db_iter_->IsBlob(); }
-
-  Status GetProperty(std::string prop_name, std::string* prop) override;
-
-  Status Refresh() override;
-
-  void Init(Env* env, const ReadOptions& read_options,
-            const ImmutableCFOptions& cf_options,
-            const MutableCFOptions& mutable_cf_options,
-            const SequenceNumber& sequence,
-            uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-            ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-            bool allow_blob, bool allow_refresh);
-
-  // Store some parameters so we can refresh the iterator at a later point
-  // with these same params
-  void StoreRefreshInfo(const ReadOptions& read_options, DBImpl* db_impl,
-                        ColumnFamilyData* cfd, ReadCallback* read_callback,
-                        bool allow_blob) {
-    read_options_ = read_options;
-    db_impl_ = db_impl;
-    cfd_ = cfd;
-    read_callback_ = read_callback;
-    allow_blob_ = allow_blob;
-  }
-
- private:
-  DBIter* db_iter_;
-  Arena arena_;
-  uint64_t sv_number_;
-  ColumnFamilyData* cfd_ = nullptr;
-  DBImpl* db_impl_ = nullptr;
-  ReadOptions read_options_;
-  ReadCallback* read_callback_;
-  bool allow_blob_ = false;
-  bool allow_refresh_ = true;
-};
-
-// Generate the arena wrapped iterator class.
-// `db_impl` and `cfd` are used for reneweal. If left null, renewal will not
-// be supported.
-extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl = nullptr,
-    ColumnFamilyData* cfd = nullptr, bool allow_blob = false,
-    bool allow_refresh = true);
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_constants.h

@@ -1,16 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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 <cstdint>
-
-#include "rocksdb/rocksdb_namespace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-constexpr uint64_t kInvalidBlobFileNumber = 0;
-
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_addition.cc

@@ -1,154 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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/blob/blob_file_addition.h"
-
-#include <ostream>
-#include <sstream>
-
-#include "logging/event_logger.h"
-#include "rocksdb/slice.h"
-#include "rocksdb/status.h"
-#include "test_util/sync_point.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-// Tags for custom fields. Note that these get persisted in the manifest,
-// so existing tags should not be modified.
-enum BlobFileAddition::CustomFieldTags : uint32_t {
-  kEndMarker,
-
-  // Add forward compatible fields here
-
-  /////////////////////////////////////////////////////////////////////
-
-  kForwardIncompatibleMask = 1 << 6,
-
-  // Add forward incompatible fields here
-};
-
-void BlobFileAddition::EncodeTo(std::string* output) const {
-  PutVarint64(output, blob_file_number_);
-  PutVarint64(output, total_blob_count_);
-  PutVarint64(output, total_blob_bytes_);
-  PutLengthPrefixedSlice(output, checksum_method_);
-  PutLengthPrefixedSlice(output, checksum_value_);
-
-  // Encode any custom fields here. The format to use is a Varint32 tag (see
-  // CustomFieldTags above) followed by a length prefixed slice. Unknown custom
-  // fields will be ignored during decoding unless they're in the forward
-  // incompatible range.
-
-  TEST_SYNC_POINT_CALLBACK("BlobFileAddition::EncodeTo::CustomFields", output);
-
-  PutVarint32(output, kEndMarker);
-}
-
-Status BlobFileAddition::DecodeFrom(Slice* input) {
-  constexpr char class_name[] = "BlobFileAddition";
-
-  if (!GetVarint64(input, &blob_file_number_)) {
-    return Status::Corruption(class_name, "Error decoding blob file number");
-  }
-
-  if (!GetVarint64(input, &total_blob_count_)) {
-    return Status::Corruption(class_name, "Error decoding total blob count");
-  }
-
-  if (!GetVarint64(input, &total_blob_bytes_)) {
-    return Status::Corruption(class_name, "Error decoding total blob bytes");
-  }
-
-  Slice checksum_method;
-  if (!GetLengthPrefixedSlice(input, &checksum_method)) {
-    return Status::Corruption(class_name, "Error decoding checksum method");
-  }
-  checksum_method_ = checksum_method.ToString();
-
-  Slice checksum_value;
-  if (!GetLengthPrefixedSlice(input, &checksum_value)) {
-    return Status::Corruption(class_name, "Error decoding checksum value");
-  }
-  checksum_value_ = checksum_value.ToString();
-
-  while (true) {
-    uint32_t custom_field_tag = 0;
-    if (!GetVarint32(input, &custom_field_tag)) {
-      return Status::Corruption(class_name, "Error decoding custom field tag");
-    }
-
-    if (custom_field_tag == kEndMarker) {
-      break;
-    }
-
-    if (custom_field_tag & kForwardIncompatibleMask) {
-      return Status::Corruption(
-          class_name, "Forward incompatible custom field encountered");
-    }
-
-    Slice custom_field_value;
-    if (!GetLengthPrefixedSlice(input, &custom_field_value)) {
-      return Status::Corruption(class_name,
-                                "Error decoding custom field value");
-    }
-  }
-
-  return Status::OK();
-}
-
-std::string BlobFileAddition::DebugString() const {
-  std::ostringstream oss;
-
-  oss << *this;
-
-  return oss.str();
-}
-
-std::string BlobFileAddition::DebugJSON() const {
-  JSONWriter jw;
-
-  jw << *this;
-
-  jw.EndObject();
-
-  return jw.Get();
-}
-
-bool operator==(const BlobFileAddition& lhs, const BlobFileAddition& rhs) {
-  return lhs.GetBlobFileNumber() == rhs.GetBlobFileNumber() &&
-         lhs.GetTotalBlobCount() == rhs.GetTotalBlobCount() &&
-         lhs.GetTotalBlobBytes() == rhs.GetTotalBlobBytes() &&
-         lhs.GetChecksumMethod() == rhs.GetChecksumMethod() &&
-         lhs.GetChecksumValue() == rhs.GetChecksumValue();
-}
-
-bool operator!=(const BlobFileAddition& lhs, const BlobFileAddition& rhs) {
-  return !(lhs == rhs);
-}
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileAddition& blob_file_addition) {
-  os << "blob_file_number: " << blob_file_addition.GetBlobFileNumber()
-     << " total_blob_count: " << blob_file_addition.GetTotalBlobCount()
-     << " total_blob_bytes: " << blob_file_addition.GetTotalBlobBytes()
-     << " checksum_method: " << blob_file_addition.GetChecksumMethod()
-     << " checksum_value: " << blob_file_addition.GetChecksumValue();
-
-  return os;
-}
-
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileAddition& blob_file_addition) {
-  jw << "BlobFileNumber" << blob_file_addition.GetBlobFileNumber()
-     << "TotalBlobCount" << blob_file_addition.GetTotalBlobCount()
-     << "TotalBlobBytes" << blob_file_addition.GetTotalBlobBytes()
-     << "ChecksumMethod" << blob_file_addition.GetChecksumMethod()
-     << "ChecksumValue" << blob_file_addition.GetChecksumValue();
-
-  return jw;
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_addition.h

@@ -1,67 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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 <cassert>
-#include <cstdint>
-#include <iosfwd>
-#include <string>
-
-#include "db/blob/blob_constants.h"
-#include "rocksdb/rocksdb_namespace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class JSONWriter;
-class Slice;
-class Status;
-
-class BlobFileAddition {
- public:
-  BlobFileAddition() = default;
-
-  BlobFileAddition(uint64_t blob_file_number, uint64_t total_blob_count,
-                   uint64_t total_blob_bytes, std::string checksum_method,
-                   std::string checksum_value)
-      : blob_file_number_(blob_file_number),
-        total_blob_count_(total_blob_count),
-        total_blob_bytes_(total_blob_bytes),
-        checksum_method_(std::move(checksum_method)),
-        checksum_value_(std::move(checksum_value)) {
-    assert(checksum_method_.empty() == checksum_value_.empty());
-  }
-
-  uint64_t GetBlobFileNumber() const { return blob_file_number_; }
-  uint64_t GetTotalBlobCount() const { return total_blob_count_; }
-  uint64_t GetTotalBlobBytes() const { return total_blob_bytes_; }
-  const std::string& GetChecksumMethod() const { return checksum_method_; }
-  const std::string& GetChecksumValue() const { return checksum_value_; }
-
-  void EncodeTo(std::string* output) const;
-  Status DecodeFrom(Slice* input);
-
-  std::string DebugString() const;
-  std::string DebugJSON() const;
-
- private:
-  enum CustomFieldTags : uint32_t;
-
-  uint64_t blob_file_number_ = kInvalidBlobFileNumber;
-  uint64_t total_blob_count_ = 0;
-  uint64_t total_blob_bytes_ = 0;
-  std::string checksum_method_;
-  std::string checksum_value_;
-};
-
-bool operator==(const BlobFileAddition& lhs, const BlobFileAddition& rhs);
-bool operator!=(const BlobFileAddition& lhs, const BlobFileAddition& rhs);
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileAddition& blob_file_addition);
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileAddition& blob_file_addition);
-
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_addition_test.cc

@@ -1,206 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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/blob/blob_file_addition.h"
-
-#include <cstdint>
-#include <cstring>
-#include <string>
-
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class BlobFileAdditionTest : public testing::Test {
- public:
-  static void TestEncodeDecode(const BlobFileAddition& blob_file_addition) {
-    std::string encoded;
-    blob_file_addition.EncodeTo(&encoded);
-
-    BlobFileAddition decoded;
-    Slice input(encoded);
-    ASSERT_OK(decoded.DecodeFrom(&input));
-
-    ASSERT_EQ(blob_file_addition, decoded);
-  }
-};
-
-TEST_F(BlobFileAdditionTest, Empty) {
-  BlobFileAddition blob_file_addition;
-
-  ASSERT_EQ(blob_file_addition.GetBlobFileNumber(), kInvalidBlobFileNumber);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobCount(), 0);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobBytes(), 0);
-  ASSERT_TRUE(blob_file_addition.GetChecksumMethod().empty());
-  ASSERT_TRUE(blob_file_addition.GetChecksumValue().empty());
-
-  TestEncodeDecode(blob_file_addition);
-}
-
-TEST_F(BlobFileAdditionTest, NonEmpty) {
-  constexpr uint64_t blob_file_number = 123;
-  constexpr uint64_t total_blob_count = 2;
-  constexpr uint64_t total_blob_bytes = 123456;
-  const std::string checksum_method("SHA1");
-  const std::string checksum_value("bdb7f34a59dfa1592ce7f52e99f98c570c525cbd");
-
-  BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
-                                      total_blob_bytes, checksum_method,
-                                      checksum_value);
-
-  ASSERT_EQ(blob_file_addition.GetBlobFileNumber(), blob_file_number);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobCount(), total_blob_count);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobBytes(), total_blob_bytes);
-  ASSERT_EQ(blob_file_addition.GetChecksumMethod(), checksum_method);
-  ASSERT_EQ(blob_file_addition.GetChecksumValue(), checksum_value);
-
-  TestEncodeDecode(blob_file_addition);
-}
-
-TEST_F(BlobFileAdditionTest, DecodeErrors) {
-  std::string str;
-  Slice slice(str);
-
-  BlobFileAddition blob_file_addition;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "blob file number"));
-  }
-
-  constexpr uint64_t blob_file_number = 123;
-  PutVarint64(&str, blob_file_number);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "total blob count"));
-  }
-
-  constexpr uint64_t total_blob_count = 4567;
-  PutVarint64(&str, total_blob_count);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "total blob bytes"));
-  }
-
-  constexpr uint64_t total_blob_bytes = 12345678;
-  PutVarint64(&str, total_blob_bytes);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "checksum method"));
-  }
-
-  constexpr char checksum_method[] = "SHA1";
-  PutLengthPrefixedSlice(&str, checksum_method);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "checksum value"));
-  }
-
-  constexpr char checksum_value[] = "bdb7f34a59dfa1592ce7f52e99f98c570c525cbd";
-  PutLengthPrefixedSlice(&str, checksum_value);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field tag"));
-  }
-
-  constexpr uint32_t custom_tag = 2;
-  PutVarint32(&str, custom_tag);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field value"));
-  }
-}
-
-TEST_F(BlobFileAdditionTest, ForwardCompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileAddition::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_compatible_tag = 2;
-        PutVarint32(output, forward_compatible_tag);
-
-        PutLengthPrefixedSlice(output, "deadbeef");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 678;
-  constexpr uint64_t total_blob_count = 9999;
-  constexpr uint64_t total_blob_bytes = 100000000;
-  const std::string checksum_method("CRC32");
-  const std::string checksum_value("3d87ff57");
-
-  BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
-                                      total_blob_bytes, checksum_method,
-                                      checksum_value);
-
-  TestEncodeDecode(blob_file_addition);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_F(BlobFileAdditionTest, ForwardIncompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileAddition::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_incompatible_tag = (1 << 6) + 1;
-        PutVarint32(output, forward_incompatible_tag);
-
-        PutLengthPrefixedSlice(output, "foobar");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 456;
-  constexpr uint64_t total_blob_count = 100;
-  constexpr uint64_t total_blob_bytes = 2000000;
-  const std::string checksum_method("CRC32B");
-  const std::string checksum_value("6dbdf23a");
-
-  BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
-                                      total_blob_bytes, checksum_method,
-                                      checksum_value);
-
-  std::string encoded;
-  blob_file_addition.EncodeTo(&encoded);
-
-  BlobFileAddition decoded_blob_file_addition;
-  Slice input(encoded);
-  const Status s = decoded_blob_file_addition.DecodeFrom(&input);
-
-  ASSERT_TRUE(s.IsCorruption());
-  ASSERT_TRUE(std::strstr(s.getState(), "Forward incompatible"));
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/blob/blob_file_garbage.cc

@@ -1,134 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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/blob/blob_file_garbage.h"
-
-#include <ostream>
-#include <sstream>
-
-#include "logging/event_logger.h"
-#include "rocksdb/slice.h"
-#include "rocksdb/status.h"
-#include "test_util/sync_point.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-// Tags for custom fields. Note that these get persisted in the manifest,
-// so existing tags should not be modified.
-enum BlobFileGarbage::CustomFieldTags : uint32_t {
-  kEndMarker,
-
-  // Add forward compatible fields here
-
-  /////////////////////////////////////////////////////////////////////
-
-  kForwardIncompatibleMask = 1 << 6,
-
-  // Add forward incompatible fields here
-};
-
-void BlobFileGarbage::EncodeTo(std::string* output) const {
-  PutVarint64(output, blob_file_number_);
-  PutVarint64(output, garbage_blob_count_);
-  PutVarint64(output, garbage_blob_bytes_);
-
-  // Encode any custom fields here. The format to use is a Varint32 tag (see
-  // CustomFieldTags above) followed by a length prefixed slice. Unknown custom
-  // fields will be ignored during decoding unless they're in the forward
-  // incompatible range.
-
-  TEST_SYNC_POINT_CALLBACK("BlobFileGarbage::EncodeTo::CustomFields", output);
-
-  PutVarint32(output, kEndMarker);
-}
-
-Status BlobFileGarbage::DecodeFrom(Slice* input) {
-  constexpr char class_name[] = "BlobFileGarbage";
-
-  if (!GetVarint64(input, &blob_file_number_)) {
-    return Status::Corruption(class_name, "Error decoding blob file number");
-  }
-
-  if (!GetVarint64(input, &garbage_blob_count_)) {
-    return Status::Corruption(class_name, "Error decoding garbage blob count");
-  }
-
-  if (!GetVarint64(input, &garbage_blob_bytes_)) {
-    return Status::Corruption(class_name, "Error decoding garbage blob bytes");
-  }
-
-  while (true) {
-    uint32_t custom_field_tag = 0;
-    if (!GetVarint32(input, &custom_field_tag)) {
-      return Status::Corruption(class_name, "Error decoding custom field tag");
-    }
-
-    if (custom_field_tag == kEndMarker) {
-      break;
-    }
-
-    if (custom_field_tag & kForwardIncompatibleMask) {
-      return Status::Corruption(
-          class_name, "Forward incompatible custom field encountered");
-    }
-
-    Slice custom_field_value;
-    if (!GetLengthPrefixedSlice(input, &custom_field_value)) {
-      return Status::Corruption(class_name,
-                                "Error decoding custom field value");
-    }
-  }
-
-  return Status::OK();
-}
-
-std::string BlobFileGarbage::DebugString() const {
-  std::ostringstream oss;
-
-  oss << *this;
-
-  return oss.str();
-}
-
-std::string BlobFileGarbage::DebugJSON() const {
-  JSONWriter jw;
-
-  jw << *this;
-
-  jw.EndObject();
-
-  return jw.Get();
-}
-
-bool operator==(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs) {
-  return lhs.GetBlobFileNumber() == rhs.GetBlobFileNumber() &&
-         lhs.GetGarbageBlobCount() == rhs.GetGarbageBlobCount() &&
-         lhs.GetGarbageBlobBytes() == rhs.GetGarbageBlobBytes();
-}
-
-bool operator!=(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs) {
-  return !(lhs == rhs);
-}
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileGarbage& blob_file_garbage) {
-  os << "blob_file_number: " << blob_file_garbage.GetBlobFileNumber()
-     << " garbage_blob_count: " << blob_file_garbage.GetGarbageBlobCount()
-     << " garbage_blob_bytes: " << blob_file_garbage.GetGarbageBlobBytes();
-
-  return os;
-}
-
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileGarbage& blob_file_garbage) {
-  jw << "BlobFileNumber" << blob_file_garbage.GetBlobFileNumber()
-     << "GarbageBlobCount" << blob_file_garbage.GetGarbageBlobCount()
-     << "GarbageBlobBytes" << blob_file_garbage.GetGarbageBlobBytes();
-
-  return jw;
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_garbage.h

@@ -1,57 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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 <cstdint>
-#include <iosfwd>
-#include <string>
-
-#include "db/blob/blob_constants.h"
-#include "rocksdb/rocksdb_namespace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class JSONWriter;
-class Slice;
-class Status;
-
-class BlobFileGarbage {
- public:
-  BlobFileGarbage() = default;
-
-  BlobFileGarbage(uint64_t blob_file_number, uint64_t garbage_blob_count,
-                  uint64_t garbage_blob_bytes)
-      : blob_file_number_(blob_file_number),
-        garbage_blob_count_(garbage_blob_count),
-        garbage_blob_bytes_(garbage_blob_bytes) {}
-
-  uint64_t GetBlobFileNumber() const { return blob_file_number_; }
-  uint64_t GetGarbageBlobCount() const { return garbage_blob_count_; }
-  uint64_t GetGarbageBlobBytes() const { return garbage_blob_bytes_; }
-
-  void EncodeTo(std::string* output) const;
-  Status DecodeFrom(Slice* input);
-
-  std::string DebugString() const;
-  std::string DebugJSON() const;
-
- private:
-  enum CustomFieldTags : uint32_t;
-
-  uint64_t blob_file_number_ = kInvalidBlobFileNumber;
-  uint64_t garbage_blob_count_ = 0;
-  uint64_t garbage_blob_bytes_ = 0;
-};
-
-bool operator==(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs);
-bool operator!=(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs);
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileGarbage& blob_file_garbage);
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileGarbage& blob_file_garbage);
-
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_garbage_test.cc

@@ -1,173 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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/blob/blob_file_garbage.h"
-
-#include <cstdint>
-#include <cstring>
-#include <string>
-
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class BlobFileGarbageTest : public testing::Test {
- public:
-  static void TestEncodeDecode(const BlobFileGarbage& blob_file_garbage) {
-    std::string encoded;
-    blob_file_garbage.EncodeTo(&encoded);
-
-    BlobFileGarbage decoded;
-    Slice input(encoded);
-    ASSERT_OK(decoded.DecodeFrom(&input));
-
-    ASSERT_EQ(blob_file_garbage, decoded);
-  }
-};
-
-TEST_F(BlobFileGarbageTest, Empty) {
-  BlobFileGarbage blob_file_garbage;
-
-  ASSERT_EQ(blob_file_garbage.GetBlobFileNumber(), kInvalidBlobFileNumber);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobCount(), 0);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobBytes(), 0);
-
-  TestEncodeDecode(blob_file_garbage);
-}
-
-TEST_F(BlobFileGarbageTest, NonEmpty) {
-  constexpr uint64_t blob_file_number = 123;
-  constexpr uint64_t garbage_blob_count = 1;
-  constexpr uint64_t garbage_blob_bytes = 9876;
-
-  BlobFileGarbage blob_file_garbage(blob_file_number, garbage_blob_count,
-                                    garbage_blob_bytes);
-
-  ASSERT_EQ(blob_file_garbage.GetBlobFileNumber(), blob_file_number);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobCount(), garbage_blob_count);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobBytes(), garbage_blob_bytes);
-
-  TestEncodeDecode(blob_file_garbage);
-}
-
-TEST_F(BlobFileGarbageTest, DecodeErrors) {
-  std::string str;
-  Slice slice(str);
-
-  BlobFileGarbage blob_file_garbage;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "blob file number"));
-  }
-
-  constexpr uint64_t blob_file_number = 123;
-  PutVarint64(&str, blob_file_number);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "garbage blob count"));
-  }
-
-  constexpr uint64_t garbage_blob_count = 4567;
-  PutVarint64(&str, garbage_blob_count);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "garbage blob bytes"));
-  }
-
-  constexpr uint64_t garbage_blob_bytes = 12345678;
-  PutVarint64(&str, garbage_blob_bytes);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field tag"));
-  }
-
-  constexpr uint32_t custom_tag = 2;
-  PutVarint32(&str, custom_tag);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field value"));
-  }
-}
-
-TEST_F(BlobFileGarbageTest, ForwardCompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileGarbage::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_compatible_tag = 2;
-        PutVarint32(output, forward_compatible_tag);
-
-        PutLengthPrefixedSlice(output, "deadbeef");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 678;
-  constexpr uint64_t garbage_blob_count = 9999;
-  constexpr uint64_t garbage_blob_bytes = 100000000;
-
-  BlobFileGarbage blob_file_garbage(blob_file_number, garbage_blob_count,
-                                    garbage_blob_bytes);
-
-  TestEncodeDecode(blob_file_garbage);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_F(BlobFileGarbageTest, ForwardIncompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileGarbage::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_incompatible_tag = (1 << 6) + 1;
-        PutVarint32(output, forward_incompatible_tag);
-
-        PutLengthPrefixedSlice(output, "foobar");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 456;
-  constexpr uint64_t garbage_blob_count = 100;
-  constexpr uint64_t garbage_blob_bytes = 2000000;
-
-  BlobFileGarbage blob_file_garbage(blob_file_number, garbage_blob_count,
-                                    garbage_blob_bytes);
-
-  std::string encoded;
-  blob_file_garbage.EncodeTo(&encoded);
-
-  BlobFileGarbage decoded_blob_file_addition;
-  Slice input(encoded);
-  const Status s = decoded_blob_file_addition.DecodeFrom(&input);
-
-  ASSERT_TRUE(s.IsCorruption());
-  ASSERT_TRUE(std::strstr(s.getState(), "Forward incompatible"));
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/builder.cc

@@ -13,7 +13,7 @@
 #include <deque>
 #include <vector>
 
-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
@@ -21,9 +21,6 @@
 #include "db/range_del_aggregator.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
-#include "file/filename.h"
-#include "file/read_write_util.h"
-#include "file/writable_file_writer.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -31,13 +28,15 @@
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block_based_table_builder.h"
+#include "table/block_based_table_builder.h"
 #include "table/format.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
+#include "util/file_reader_writer.h"
+#include "util/filename.h"
 #include "util/stop_watch.h"
+#include "util/sync_point.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class TableFactory;
 
@@ -48,27 +47,24 @@ TableBuilder* NewTableBuilder(
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
     WritableFileWriter* file, const CompressionType compression_type,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    int level, const bool skip_filters, const uint64_t creation_time,
-    const uint64_t oldest_key_time, const uint64_t target_file_size,
-    const uint64_t file_creation_time) {
+    const CompressionOptions& compression_opts, int level,
+    const std::string* compression_dict, const bool skip_filters,
+    const uint64_t creation_time, const uint64_t oldest_key_time) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
   return ioptions.table_factory->NewTableBuilder(
       TableBuilderOptions(ioptions, moptions, internal_comparator,
                           int_tbl_prop_collector_factories, compression_type,
-                          sample_for_compression, compression_opts,
-                          skip_filters, column_family_name, level,
-                          creation_time, oldest_key_time, target_file_size,
-                          file_creation_time),
+                          compression_opts, compression_dict, skip_filters,
+                          column_family_name, level, creation_time,
+                          oldest_key_time),
       column_family_id, file);
 }
 
 Status BuildTable(
-    const std::string& dbname, Env* env, FileSystem* fs,
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, const FileOptions& file_options,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
+    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
@@ -79,12 +75,11 @@ Status BuildTable(
     std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     SnapshotChecker* snapshot_checker, const CompressionType compression,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    bool paranoid_file_checks, InternalStats* internal_stats,
-    TableFileCreationReason reason, EventLogger* event_logger, int job_id,
-    const Env::IOPriority io_priority, TableProperties* table_properties,
-    int level, const uint64_t creation_time, const uint64_t oldest_key_time,
-    Env::WriteLifeTimeHint write_hint, const uint64_t file_creation_time) {
+    const CompressionOptions& compression_opts, bool paranoid_file_checks,
+    InternalStats* internal_stats, TableFileCreationReason reason,
+    EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
+    TableProperties* table_properties, int level, const uint64_t creation_time,
+    const uint64_t oldest_key_time, Env::WriteLifeTimeHint write_hint) {
   assert((column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          column_family_name.empty());
@@ -110,38 +105,31 @@ Status BuildTable(
   if (iter->Valid() || !range_del_agg->IsEmpty()) {
     TableBuilder* builder;
     std::unique_ptr<WritableFileWriter> file_writer;
-    // Currently we only enable dictionary compression during compaction to the
-    // bottommost level.
-    CompressionOptions compression_opts_for_flush(compression_opts);
-    compression_opts_for_flush.max_dict_bytes = 0;
-    compression_opts_for_flush.zstd_max_train_bytes = 0;
     {
-      std::unique_ptr<FSWritableFile> file;
+      std::unique_ptr<WritableFile> file;
 #ifndef NDEBUG
-      bool use_direct_writes = file_options.use_direct_writes;
+      bool use_direct_writes = env_options.use_direct_writes;
       TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
 #endif  // !NDEBUG
-      s = NewWritableFile(fs, fname, &file, file_options);
+      s = NewWritableFile(env, fname, &file, env_options);
       if (!s.ok()) {
         EventHelpers::LogAndNotifyTableFileCreationFinished(
             event_logger, ioptions.listeners, dbname, column_family_name, fname,
-            job_id, meta->fd, kInvalidBlobFileNumber, tp, reason, s);
+            job_id, meta->fd, tp, reason, s);
         return s;
       }
       file->SetIOPriority(io_priority);
       file->SetWriteLifeTimeHint(write_hint);
 
-      file_writer.reset(new WritableFileWriter(
-          std::move(file), fname, file_options, env, ioptions.statistics,
-          ioptions.listeners, ioptions.sst_file_checksum_func));
-
+      file_writer.reset(
+          new WritableFileWriter(std::move(file), fname, env_options, env,
+                                 ioptions.statistics, ioptions.listeners));
       builder = NewTableBuilder(
           ioptions, mutable_cf_options, internal_comparator,
           int_tbl_prop_collector_factories, column_family_id,
-          column_family_name, file_writer.get(), compression,
-          sample_for_compression, compression_opts_for_flush, level,
-          false /* skip_filters */, creation_time, oldest_key_time,
-          0 /*target_file_size*/, file_creation_time);
+          column_family_name, file_writer.get(), compression, compression_opts,
+          level, nullptr /* compression_dict */, false /* skip_filters */,
+          creation_time, oldest_key_time);
     }
 
     MergeHelper merge(env, internal_comparator.user_comparator(),
@@ -159,9 +147,8 @@ Status BuildTable(
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
-      const ParsedInternalKey& ikey = c_iter.ikey();
       builder->Add(key, value);
-      meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
+      meta->UpdateBoundaries(key, c_iter.ikey().sequence);
 
       // TODO(noetzli): Update stats after flush, too.
       if (io_priority == Env::IO_HIGH &&
@@ -200,9 +187,6 @@ Status BuildTable(
       if (table_properties) {
         *table_properties = tp;
       }
-      // Add the checksum information to file metadata.
-      meta->file_checksum = builder->GetFileChecksum();
-      meta->file_checksum_func_name = builder->GetFileChecksumFuncName();
     }
     delete builder;
 
@@ -223,14 +207,13 @@ Status BuildTable(
       // we will regrad this verification as user reads since the goal is
       // to cache it here for further user reads
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          ReadOptions(), file_options, internal_comparator, *meta,
+          ReadOptions(), env_options, internal_comparator, *meta,
           nullptr /* range_del_agg */,
           mutable_cf_options.prefix_extractor.get(), nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : internal_stats->GetFileReadHist(0),
-          TableReaderCaller::kFlush, /*arena=*/nullptr,
-          /*skip_filter=*/false, level, /*smallest_compaction_key=*/nullptr,
-          /*largest_compaction_key*/ nullptr));
+          false /* for_compaction */, nullptr /* arena */,
+          false /* skip_filter */, level));
       s = it->status();
       if (s.ok() && paranoid_file_checks) {
         for (it->SeekToFirst(); it->Valid(); it->Next()) {
@@ -246,18 +229,15 @@ Status BuildTable(
   }
 
   if (!s.ok() || meta->fd.GetFileSize() == 0) {
-    fs->DeleteFile(fname, IOOptions(), nullptr);
+    env->DeleteFile(fname);
   }
 
-  if (meta->fd.GetFileSize() == 0) {
-    fname = "(nil)";
-  }
   // Output to event logger and fire events.
   EventHelpers::LogAndNotifyTableFileCreationFinished(
       event_logger, ioptions.listeners, dbname, column_family_name, fname,
-      job_id, meta->fd, meta->oldest_blob_file_number, tp, reason, s);
+      job_id, meta->fd, tp, reason, s);
 
   return s;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/builder.h

@@ -11,7 +11,6 @@
 #include <vector>
 #include "db/range_tombstone_fragmenter.h"
 #include "db/table_properties_collector.h"
-#include "logging/event_logger.h"
 #include "options/cf_options.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/env.h"
@@ -21,8 +20,9 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/event_logger.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 struct Options;
 struct FileMetaData;
@@ -40,6 +40,8 @@ class InternalStats;
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown. It must outlive the
 //    TableBuilder returned by this function.
+// @param compression_dict Data for presetting the compression library's
+//    dictionary, or nullptr.
 TableBuilder* NewTableBuilder(
     const ImmutableCFOptions& options, const MutableCFOptions& moptions,
     const InternalKeyComparator& internal_comparator,
@@ -47,11 +49,10 @@ TableBuilder* NewTableBuilder(
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
     WritableFileWriter* file, const CompressionType compression_type,
-    const uint64_t sample_for_compression,
     const CompressionOptions& compression_opts, int level,
+    const std::string* compression_dict = nullptr,
     const bool skip_filters = false, const uint64_t creation_time = 0,
-    const uint64_t oldest_key_time = 0, const uint64_t target_file_size = 0,
-    const uint64_t file_creation_time = 0);
+    const uint64_t oldest_key_time = 0);
 
 // Build a Table file from the contents of *iter.  The generated file
 // will be named according to number specified in meta. On success, the rest of
@@ -62,9 +63,8 @@ TableBuilder* NewTableBuilder(
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown.
 extern Status BuildTable(
-    const std::string& dbname, Env* env, FileSystem* fs,
-    const ImmutableCFOptions& options,
-    const MutableCFOptions& mutable_cf_options, const FileOptions& file_options,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& options,
+    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
@@ -75,14 +75,12 @@ extern Status BuildTable(
     std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     SnapshotChecker* snapshot_checker, const CompressionType compression,
-    const uint64_t sample_for_compression,
     const CompressionOptions& compression_opts, bool paranoid_file_checks,
     InternalStats* internal_stats, TableFileCreationReason reason,
     EventLogger* event_logger = nullptr, int job_id = 0,
     const Env::IOPriority io_priority = Env::IO_HIGH,
     TableProperties* table_properties = nullptr, int level = -1,
     const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
-    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
-    const uint64_t file_creation_time = 0);
+    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/c.cc

@@ -46,74 +46,74 @@
 #include <unordered_set>
 #include <map>
 
-using ROCKSDB_NAMESPACE::BackupableDBOptions;
-using ROCKSDB_NAMESPACE::BackupEngine;
-using ROCKSDB_NAMESPACE::BackupID;
-using ROCKSDB_NAMESPACE::BackupInfo;
-using ROCKSDB_NAMESPACE::BatchResult;
-using ROCKSDB_NAMESPACE::BlockBasedTableOptions;
-using ROCKSDB_NAMESPACE::BottommostLevelCompaction;
-using ROCKSDB_NAMESPACE::BytewiseComparator;
-using ROCKSDB_NAMESPACE::Cache;
-using ROCKSDB_NAMESPACE::Checkpoint;
-using ROCKSDB_NAMESPACE::ColumnFamilyDescriptor;
-using ROCKSDB_NAMESPACE::ColumnFamilyHandle;
-using ROCKSDB_NAMESPACE::ColumnFamilyOptions;
-using ROCKSDB_NAMESPACE::CompactionFilter;
-using ROCKSDB_NAMESPACE::CompactionFilterContext;
-using ROCKSDB_NAMESPACE::CompactionFilterFactory;
-using ROCKSDB_NAMESPACE::CompactionOptionsFIFO;
-using ROCKSDB_NAMESPACE::CompactRangeOptions;
-using ROCKSDB_NAMESPACE::Comparator;
-using ROCKSDB_NAMESPACE::CompressionType;
-using ROCKSDB_NAMESPACE::CuckooTableOptions;
-using ROCKSDB_NAMESPACE::DB;
-using ROCKSDB_NAMESPACE::DBOptions;
-using ROCKSDB_NAMESPACE::DbPath;
-using ROCKSDB_NAMESPACE::Env;
-using ROCKSDB_NAMESPACE::EnvOptions;
-using ROCKSDB_NAMESPACE::FileLock;
-using ROCKSDB_NAMESPACE::FilterPolicy;
-using ROCKSDB_NAMESPACE::FlushOptions;
-using ROCKSDB_NAMESPACE::InfoLogLevel;
-using ROCKSDB_NAMESPACE::IngestExternalFileOptions;
-using ROCKSDB_NAMESPACE::Iterator;
-using ROCKSDB_NAMESPACE::LiveFileMetaData;
-using ROCKSDB_NAMESPACE::Logger;
-using ROCKSDB_NAMESPACE::MemoryUtil;
-using ROCKSDB_NAMESPACE::MergeOperator;
-using ROCKSDB_NAMESPACE::MergeOperators;
-using ROCKSDB_NAMESPACE::NewBloomFilterPolicy;
-using ROCKSDB_NAMESPACE::NewGenericRateLimiter;
-using ROCKSDB_NAMESPACE::NewLRUCache;
-using ROCKSDB_NAMESPACE::OptimisticTransactionDB;
-using ROCKSDB_NAMESPACE::OptimisticTransactionOptions;
-using ROCKSDB_NAMESPACE::Options;
-using ROCKSDB_NAMESPACE::PerfContext;
-using ROCKSDB_NAMESPACE::PerfLevel;
-using ROCKSDB_NAMESPACE::PinnableSlice;
-using ROCKSDB_NAMESPACE::RandomAccessFile;
-using ROCKSDB_NAMESPACE::Range;
-using ROCKSDB_NAMESPACE::RateLimiter;
-using ROCKSDB_NAMESPACE::ReadOptions;
-using ROCKSDB_NAMESPACE::RestoreOptions;
-using ROCKSDB_NAMESPACE::SequentialFile;
-using ROCKSDB_NAMESPACE::Slice;
-using ROCKSDB_NAMESPACE::SliceParts;
-using ROCKSDB_NAMESPACE::SliceTransform;
-using ROCKSDB_NAMESPACE::Snapshot;
-using ROCKSDB_NAMESPACE::SstFileWriter;
-using ROCKSDB_NAMESPACE::Status;
-using ROCKSDB_NAMESPACE::Transaction;
-using ROCKSDB_NAMESPACE::TransactionDB;
-using ROCKSDB_NAMESPACE::TransactionDBOptions;
-using ROCKSDB_NAMESPACE::TransactionLogIterator;
-using ROCKSDB_NAMESPACE::TransactionOptions;
-using ROCKSDB_NAMESPACE::WALRecoveryMode;
-using ROCKSDB_NAMESPACE::WritableFile;
-using ROCKSDB_NAMESPACE::WriteBatch;
-using ROCKSDB_NAMESPACE::WriteBatchWithIndex;
-using ROCKSDB_NAMESPACE::WriteOptions;
+using rocksdb::BytewiseComparator;
+using rocksdb::Cache;
+using rocksdb::ColumnFamilyDescriptor;
+using rocksdb::ColumnFamilyHandle;
+using rocksdb::ColumnFamilyOptions;
+using rocksdb::CompactionFilter;
+using rocksdb::CompactionFilterFactory;
+using rocksdb::CompactionFilterContext;
+using rocksdb::CompactionOptionsFIFO;
+using rocksdb::Comparator;
+using rocksdb::CompressionType;
+using rocksdb::WALRecoveryMode;
+using rocksdb::DB;
+using rocksdb::DBOptions;
+using rocksdb::DbPath;
+using rocksdb::Env;
+using rocksdb::EnvOptions;
+using rocksdb::InfoLogLevel;
+using rocksdb::FileLock;
+using rocksdb::FilterPolicy;
+using rocksdb::FlushOptions;
+using rocksdb::IngestExternalFileOptions;
+using rocksdb::Iterator;
+using rocksdb::Logger;
+using rocksdb::MergeOperator;
+using rocksdb::MergeOperators;
+using rocksdb::NewBloomFilterPolicy;
+using rocksdb::NewLRUCache;
+using rocksdb::Options;
+using rocksdb::BlockBasedTableOptions;
+using rocksdb::CuckooTableOptions;
+using rocksdb::RandomAccessFile;
+using rocksdb::Range;
+using rocksdb::ReadOptions;
+using rocksdb::SequentialFile;
+using rocksdb::Slice;
+using rocksdb::SliceParts;
+using rocksdb::SliceTransform;
+using rocksdb::Snapshot;
+using rocksdb::SstFileWriter;
+using rocksdb::Status;
+using rocksdb::WritableFile;
+using rocksdb::WriteBatch;
+using rocksdb::WriteBatchWithIndex;
+using rocksdb::WriteOptions;
+using rocksdb::LiveFileMetaData;
+using rocksdb::BackupEngine;
+using rocksdb::BackupableDBOptions;
+using rocksdb::BackupInfo;
+using rocksdb::BackupID;
+using rocksdb::RestoreOptions;
+using rocksdb::CompactRangeOptions;
+using rocksdb::BottommostLevelCompaction;
+using rocksdb::RateLimiter;
+using rocksdb::NewGenericRateLimiter;
+using rocksdb::PinnableSlice;
+using rocksdb::TransactionDBOptions;
+using rocksdb::TransactionDB;
+using rocksdb::TransactionOptions;
+using rocksdb::OptimisticTransactionDB;
+using rocksdb::OptimisticTransactionOptions;
+using rocksdb::Transaction;
+using rocksdb::Checkpoint;
+using rocksdb::TransactionLogIterator;
+using rocksdb::BatchResult;
+using rocksdb::PerfLevel;
+using rocksdb::PerfContext;
+using rocksdb::MemoryUtil;
 
 using std::shared_ptr;
 using std::vector;
@@ -208,10 +208,13 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
   const char* (*name_)(void*);
   unsigned char ignore_snapshots_;
 
-  ~rocksdb_compactionfilter_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_compactionfilter_t() {
+    (*destructor_)(state_);
+  }
 
-  bool Filter(int level, const Slice& key, const Slice& existing_value,
-              std::string* new_value, bool* value_changed) const override {
+  virtual bool Filter(int level, const Slice& key, const Slice& existing_value,
+                      std::string* new_value,
+                      bool* value_changed) const override {
     char* c_new_value = nullptr;
     size_t new_value_length = 0;
     unsigned char c_value_changed = 0;
@@ -228,9 +231,9 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
     return result;
   }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  bool IgnoreSnapshots() const override { return ignore_snapshots_; }
+  virtual bool IgnoreSnapshots() const override { return ignore_snapshots_; }
 };
 
 struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
@@ -240,9 +243,9 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
       void*, rocksdb_compactionfiltercontext_t* context);
   const char* (*name_)(void*);
 
-  ~rocksdb_compactionfilterfactory_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_compactionfilterfactory_t() { (*destructor_)(state_); }
 
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
       const CompactionFilter::Context& context) override {
     rocksdb_compactionfiltercontext_t ccontext;
     ccontext.rep = context;
@@ -250,7 +253,7 @@ struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
     return std::unique_ptr<CompactionFilter>(cf);
   }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 };
 
 struct rocksdb_comparator_t : public Comparator {
@@ -262,17 +265,20 @@ struct rocksdb_comparator_t : public Comparator {
       const char* b, size_t blen);
   const char* (*name_)(void*);
 
-  ~rocksdb_comparator_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_comparator_t() {
+    (*destructor_)(state_);
+  }
 
-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
     return (*compare_)(state_, a.data(), a.size(), b.data(), b.size());
   }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
   // No-ops since the C binding does not support key shortening methods.
-  void FindShortestSeparator(std::string*, const Slice&) const override {}
-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortestSeparator(std::string*,
+                                     const Slice&) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 
 struct rocksdb_filterpolicy_t : public FilterPolicy {
@@ -292,11 +298,14 @@ struct rocksdb_filterpolicy_t : public FilterPolicy {
       void*,
       const char* filter, size_t filter_length);
 
-  ~rocksdb_filterpolicy_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_filterpolicy_t() {
+    (*destructor_)(state_);
+  }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  void CreateFilter(const Slice* keys, int n, std::string* dst) const override {
+  virtual void CreateFilter(const Slice* keys, int n,
+                            std::string* dst) const override {
     std::vector<const char*> key_pointers(n);
     std::vector<size_t> key_sizes(n);
     for (int i = 0; i < n; i++) {
@@ -314,7 +323,8 @@ struct rocksdb_filterpolicy_t : public FilterPolicy {
     }
   }
 
-  bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
+  virtual bool KeyMayMatch(const Slice& key,
+                           const Slice& filter) const override {
     return (*key_match_)(state_, key.data(), key.size(),
                          filter.data(), filter.size());
   }
@@ -339,12 +349,14 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
       void*,
       const char* value, size_t value_length);
 
-  ~rocksdb_mergeoperator_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_mergeoperator_t() {
+    (*destructor_)(state_);
+  }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  bool FullMergeV2(const MergeOperationInput& merge_in,
-                   MergeOperationOutput* merge_out) const override {
+  virtual bool FullMergeV2(const MergeOperationInput& merge_in,
+                           MergeOperationOutput* merge_out) const override {
     size_t n = merge_in.operand_list.size();
     std::vector<const char*> operand_pointers(n);
     std::vector<size_t> operand_sizes(n);
@@ -378,10 +390,10 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
     return success;
   }
 
-  bool PartialMergeMulti(const Slice& key,
-                         const std::deque<Slice>& operand_list,
-                         std::string* new_value,
-                         Logger* /*logger*/) const override {
+  virtual bool PartialMergeMulti(const Slice& key,
+                                 const std::deque<Slice>& operand_list,
+                                 std::string* new_value,
+                                 Logger* /*logger*/) const override {
     size_t operand_count = operand_list.size();
     std::vector<const char*> operand_pointers(operand_count);
     std::vector<size_t> operand_sizes(operand_count);
@@ -432,27 +444,29 @@ struct rocksdb_slicetransform_t : public SliceTransform {
       void*,
       const char* key, size_t length);
 
-  ~rocksdb_slicetransform_t() override { (*destructor_)(state_); }
+  virtual ~rocksdb_slicetransform_t() {
+    (*destructor_)(state_);
+  }
 
-  const char* Name() const override { return (*name_)(state_); }
+  virtual const char* Name() const override { return (*name_)(state_); }
 
-  Slice Transform(const Slice& src) const override {
+  virtual Slice Transform(const Slice& src) const override {
     size_t len;
     char* dst = (*transform_)(state_, src.data(), src.size(), &len);
     return Slice(dst, len);
   }
 
-  bool InDomain(const Slice& src) const override {
+  virtual bool InDomain(const Slice& src) const override {
     return (*in_domain_)(state_, src.data(), src.size());
   }
 
-  bool InRange(const Slice& src) const override {
+  virtual bool InRange(const Slice& src) const override {
     return (*in_range_)(state_, src.data(), src.size());
   }
 };
 
 struct rocksdb_universal_compaction_options_t {
-  ROCKSDB_NAMESPACE::CompactionOptionsUniversal* rep;
+  rocksdb::CompactionOptionsUniversal *rep;
 };
 
 static bool SaveError(char** errptr, const Status& s) {
@@ -494,9 +508,8 @@ rocksdb_t* rocksdb_open_with_ttl(
     const char* name,
     int ttl,
     char** errptr) {
-  ROCKSDB_NAMESPACE::DBWithTTL* db;
-  if (SaveError(errptr, ROCKSDB_NAMESPACE::DBWithTTL::Open(
-                            options->rep, std::string(name), &db, ttl))) {
+  rocksdb::DBWithTTL* db;
+  if (SaveError(errptr, rocksdb::DBWithTTL::Open(options->rep, std::string(name), &db, ttl))) {
     return nullptr;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -518,21 +531,6 @@ rocksdb_t* rocksdb_open_for_read_only(
   return result;
 }
 
-rocksdb_t* rocksdb_open_as_secondary(const rocksdb_options_t* options,
-                                     const char* name,
-                                     const char* secondary_path,
-                                     char** errptr) {
-  DB* db;
-  if (SaveError(errptr,
-                DB::OpenAsSecondary(options->rep, std::string(name),
-                                    std::string(secondary_path), &db))) {
-    return nullptr;
-  }
-  rocksdb_t* result = new rocksdb_t;
-  result->rep = db;
-  return result;
-}
-
 rocksdb_backup_engine_t* rocksdb_backup_engine_open(
     const rocksdb_options_t* options, const char* path, char** errptr) {
   BackupEngine* be;
@@ -665,15 +663,17 @@ void rocksdb_close(rocksdb_t* db) {
 }
 
 void rocksdb_options_set_uint64add_merge_operator(rocksdb_options_t* opt) {
-  opt->rep.merge_operator =
-      ROCKSDB_NAMESPACE::MergeOperators::CreateUInt64AddOperator();
+  opt->rep.merge_operator = rocksdb::MergeOperators::CreateUInt64AddOperator();
 }
 
 rocksdb_t* rocksdb_open_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
-    rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
+    const rocksdb_options_t* db_options,
+    const char* name,
+    int num_column_families,
+    const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
+    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.push_back(ColumnFamilyDescriptor(
@@ -699,11 +699,14 @@ rocksdb_t* rocksdb_open_column_families(
 }
 
 rocksdb_t* rocksdb_open_for_read_only_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
+    const rocksdb_options_t* db_options,
+    const char* name,
+    int num_column_families,
+    const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
     rocksdb_column_family_handle_t** column_family_handles,
-    unsigned char error_if_log_file_exist, char** errptr) {
+    unsigned char error_if_log_file_exist,
+    char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
     column_families.push_back(ColumnFamilyDescriptor(
@@ -728,37 +731,6 @@ rocksdb_t* rocksdb_open_for_read_only_column_families(
   return result;
 }
 
-rocksdb_t* rocksdb_open_as_secondary_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    const char* secondary_path, int num_column_families,
-    const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
-    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(
-        std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep));
-  }
-  DB* db;
-  std::vector<ColumnFamilyHandle*> handles;
-  if (SaveError(errptr, DB::OpenAsSecondary(DBOptions(db_options->rep),
-                                            std::string(name),
-                                            std::string(secondary_path),
-                                            column_families, &handles, &db))) {
-    return nullptr;
-  }
-  for (size_t i = 0; i != handles.size(); ++i) {
-    rocksdb_column_family_handle_t* c_handle =
-        new rocksdb_column_family_handle_t;
-    c_handle->rep = handles[i];
-    column_family_handles[i] = c_handle;
-  }
-  rocksdb_t* result = new rocksdb_t;
-  result->rep = db;
-  return result;
-}
-
 char** rocksdb_list_column_families(
     const rocksdb_options_t* options,
     const char* name,
@@ -848,17 +820,6 @@ void rocksdb_delete_cf(
         Slice(key, keylen)));
 }
 
-void rocksdb_delete_range_cf(rocksdb_t* db,
-                             const rocksdb_writeoptions_t* options,
-                             rocksdb_column_family_handle_t* column_family,
-                             const char* start_key, size_t start_key_len,
-                             const char* end_key, size_t end_key_len,
-                             char** errptr) {
-  SaveError(errptr, db->rep->DeleteRange(options->rep, column_family->rep,
-                                         Slice(start_key, start_key_len),
-                                         Slice(end_key, end_key_len)));
-}
-
 void rocksdb_merge(
     rocksdb_t* db,
     const rocksdb_writeoptions_t* options,
@@ -1041,7 +1002,7 @@ void rocksdb_wal_iter_destroy (const rocksdb_wal_iterator_t* iter) {
 rocksdb_writebatch_t* rocksdb_wal_iter_get_batch (const rocksdb_wal_iterator_t* iter, uint64_t* seq) {
   rocksdb_writebatch_t* result = rocksdb_writebatch_create();
   BatchResult wal_batch = iter->rep->GetBatch();
-  result->rep = std::move(*wal_batch.writeBatchPtr);
+  result->rep = * wal_batch.writeBatchPtr.release();
   if (seq != nullptr) {
     *seq = wal_batch.sequence;
   }
@@ -1123,18 +1084,6 @@ int rocksdb_property_int(
   }
 }
 
-int rocksdb_property_int_cf(
-    rocksdb_t* db,
-    rocksdb_column_family_handle_t* column_family,
-    const char* propname,
-    uint64_t *out_val) {
-  if (db->rep->GetIntProperty(column_family->rep, Slice(propname), out_val)) {
-    return 0;
-  } else {
-    return -1;
-  }
-}
-
 char* rocksdb_property_value_cf(
     rocksdb_t* db,
     rocksdb_column_family_handle_t* column_family,
@@ -1248,14 +1197,6 @@ void rocksdb_flush(
   SaveError(errptr, db->rep->Flush(options->rep));
 }
 
-void rocksdb_flush_cf(
-    rocksdb_t* db,
-    const rocksdb_flushoptions_t* options,
-    rocksdb_column_family_handle_t* column_family,
-    char** errptr) {
-  SaveError(errptr, db->rep->Flush(options->rep, column_family->rep));
-}
-
 void rocksdb_disable_file_deletions(
     rocksdb_t* db,
     char** errptr) {
@@ -1554,10 +1495,10 @@ class H : public WriteBatch::Handler {
   void* state_;
   void (*put_)(void*, const char* k, size_t klen, const char* v, size_t vlen);
   void (*deleted_)(void*, const char* k, size_t klen);
-  void Put(const Slice& key, const Slice& value) override {
+  virtual void Put(const Slice& key, const Slice& value) override {
     (*put_)(state_, key.data(), key.size(), value.data(), value.size());
   }
-  void Delete(const Slice& key) override {
+  virtual void Delete(const Slice& key) override {
     (*deleted_)(state_, key.data(), key.size());
   }
 };
@@ -2039,17 +1980,6 @@ void rocksdb_block_based_options_set_index_type(
   options->rep.index_type = static_cast<BlockBasedTableOptions::IndexType>(v);
 }
 
-void rocksdb_block_based_options_set_data_block_index_type(
-    rocksdb_block_based_table_options_t* options, int v) {
-  options->rep.data_block_index_type =
-          static_cast<BlockBasedTableOptions::DataBlockIndexType>(v);
-}
-
-void rocksdb_block_based_options_set_data_block_hash_ratio(
-    rocksdb_block_based_table_options_t* options, double v) {
-  options->rep.data_block_hash_table_util_ratio = v;
-}
-
 void rocksdb_block_based_options_set_hash_index_allow_collision(
     rocksdb_block_based_table_options_t* options, unsigned char v) {
   options->rep.hash_index_allow_collision = v;
@@ -2080,7 +2010,7 @@ void rocksdb_options_set_block_based_table_factory(
     rocksdb_block_based_table_options_t* table_options) {
   if (table_options) {
     opt->rep.table_factory.reset(
-        ROCKSDB_NAMESPACE::NewBlockBasedTableFactory(table_options->rep));
+        rocksdb::NewBlockBasedTableFactory(table_options->rep));
   }
 }
 
@@ -2124,7 +2054,7 @@ void rocksdb_options_set_cuckoo_table_factory(
     rocksdb_cuckoo_table_options_t* table_options) {
   if (table_options) {
     opt->rep.table_factory.reset(
-        ROCKSDB_NAMESPACE::NewCuckooTableFactory(table_options->rep));
+        rocksdb::NewCuckooTableFactory(table_options->rep));
   }
 }
 
@@ -2314,7 +2244,7 @@ void rocksdb_options_set_max_bytes_for_level_multiplier_additional(
 }
 
 void rocksdb_options_enable_statistics(rocksdb_options_t* opt) {
-  opt->rep.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  opt->rep.statistics = rocksdb::CreateDBStatistics();
 }
 
 void rocksdb_options_set_skip_stats_update_on_db_open(rocksdb_options_t* opt,
@@ -2322,11 +2252,6 @@ void rocksdb_options_set_skip_stats_update_on_db_open(rocksdb_options_t* opt,
   opt->rep.skip_stats_update_on_db_open = val;
 }
 
-void rocksdb_options_set_skip_checking_sst_file_sizes_on_db_open(
-    rocksdb_options_t* opt, unsigned char val) {
-  opt->rep.skip_checking_sst_file_sizes_on_db_open = val;
-}
-
 void rocksdb_options_set_num_levels(rocksdb_options_t* opt, int n) {
   opt->rep.num_levels = n;
 }
@@ -2470,20 +2395,16 @@ 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;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::NONE;
       break;
     case 1:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::NORMAL;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::NORMAL;
       break;
     case 2:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::SEQUENTIAL;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::SEQUENTIAL;
       break;
     case 3:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::WILLNEED;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::WILLNEED;
       break;
   }
 }
@@ -2536,21 +2457,11 @@ void rocksdb_options_set_max_write_buffer_number_to_maintain(
   opt->rep.max_write_buffer_number_to_maintain = n;
 }
 
-void rocksdb_options_set_max_write_buffer_size_to_maintain(
-    rocksdb_options_t* opt, int64_t n) {
-  opt->rep.max_write_buffer_size_to_maintain = n;
-}
-
 void rocksdb_options_set_enable_pipelined_write(rocksdb_options_t* opt,
                                                 unsigned char v) {
   opt->rep.enable_pipelined_write = v;
 }
 
-void rocksdb_options_set_unordered_write(rocksdb_options_t* opt,
-                                         unsigned char v) {
-  opt->rep.unordered_write = v;
-}
-
 void rocksdb_options_set_max_subcompactions(rocksdb_options_t* opt,
                                             uint32_t n) {
   opt->rep.max_subcompactions = n;
@@ -2649,7 +2560,7 @@ void rocksdb_options_prepare_for_bulk_load(rocksdb_options_t* opt) {
 }
 
 void rocksdb_options_set_memtable_vector_rep(rocksdb_options_t *opt) {
-  opt->rep.memtable_factory.reset(new ROCKSDB_NAMESPACE::VectorRepFactory);
+  opt->rep.memtable_factory.reset(new rocksdb::VectorRepFactory);
 }
 
 void rocksdb_options_set_memtable_prefix_bloom_size_ratio(
@@ -2665,29 +2576,26 @@ void rocksdb_options_set_memtable_huge_page_size(rocksdb_options_t* opt,
 void rocksdb_options_set_hash_skip_list_rep(
     rocksdb_options_t *opt, size_t bucket_count,
     int32_t skiplist_height, int32_t skiplist_branching_factor) {
-  ROCKSDB_NAMESPACE::MemTableRepFactory* factory =
-      ROCKSDB_NAMESPACE::NewHashSkipListRepFactory(
-          bucket_count, skiplist_height, skiplist_branching_factor);
+  rocksdb::MemTableRepFactory* factory = rocksdb::NewHashSkipListRepFactory(
+      bucket_count, skiplist_height, skiplist_branching_factor);
   opt->rep.memtable_factory.reset(factory);
 }
 
 void rocksdb_options_set_hash_link_list_rep(
     rocksdb_options_t *opt, size_t bucket_count) {
-  opt->rep.memtable_factory.reset(
-      ROCKSDB_NAMESPACE::NewHashLinkListRepFactory(bucket_count));
+  opt->rep.memtable_factory.reset(rocksdb::NewHashLinkListRepFactory(bucket_count));
 }
 
 void rocksdb_options_set_plain_table_factory(
     rocksdb_options_t *opt, uint32_t user_key_len, int bloom_bits_per_key,
     double hash_table_ratio, size_t index_sparseness) {
-  ROCKSDB_NAMESPACE::PlainTableOptions options;
+  rocksdb::PlainTableOptions options;
   options.user_key_len = user_key_len;
   options.bloom_bits_per_key = bloom_bits_per_key;
   options.hash_table_ratio = hash_table_ratio;
   options.index_sparseness = index_sparseness;
 
-  ROCKSDB_NAMESPACE::TableFactory* factory =
-      ROCKSDB_NAMESPACE::NewPlainTableFactory(options);
+  rocksdb::TableFactory* factory = rocksdb::NewPlainTableFactory(options);
   opt->rep.table_factory.reset(factory);
 }
 
@@ -2717,8 +2625,7 @@ void rocksdb_options_set_report_bg_io_stats(
 }
 
 void rocksdb_options_set_compaction_style(rocksdb_options_t *opt, int style) {
-  opt->rep.compaction_style =
-      static_cast<ROCKSDB_NAMESPACE::CompactionStyle>(style);
+  opt->rep.compaction_style = static_cast<rocksdb::CompactionStyle>(style);
 }
 
 void rocksdb_options_set_universal_compaction_options(rocksdb_options_t *opt, rocksdb_universal_compaction_options_t *uco) {
@@ -2732,7 +2639,7 @@ void rocksdb_options_set_fifo_compaction_options(
 }
 
 char *rocksdb_options_statistics_get_string(rocksdb_options_t *opt) {
-  ROCKSDB_NAMESPACE::Statistics* statistics = opt->rep.statistics.get();
+  rocksdb::Statistics *statistics = opt->rep.statistics.get();
   if (statistics) {
     return strdup(statistics->ToString().c_str());
   }
@@ -2745,11 +2652,6 @@ void rocksdb_options_set_ratelimiter(rocksdb_options_t *opt, rocksdb_ratelimiter
   }
 }
 
-void rocksdb_options_set_atomic_flush(rocksdb_options_t* opt,
-                                      unsigned char atomic_flush) {
-  opt->rep.atomic_flush = atomic_flush;
-}
-
 rocksdb_ratelimiter_t* rocksdb_ratelimiter_create(
     int64_t rate_bytes_per_sec,
     int64_t refill_period_us,
@@ -2765,12 +2667,6 @@ void rocksdb_ratelimiter_destroy(rocksdb_ratelimiter_t *limiter) {
   delete limiter;
 }
 
-void rocksdb_options_set_row_cache(rocksdb_options_t* opt, rocksdb_cache_t* cache) {
-  if(cache) {
-    opt->rep.row_cache = cache->rep;
-  }
-}
-
 void rocksdb_set_perf_level(int v) {
   PerfLevel level = static_cast<PerfLevel>(v);
   SetPerfLevel(level);
@@ -2778,7 +2674,7 @@ void rocksdb_set_perf_level(int v) {
 
 rocksdb_perfcontext_t* rocksdb_perfcontext_create() {
   rocksdb_perfcontext_t* context = new rocksdb_perfcontext_t;
-  context->rep = ROCKSDB_NAMESPACE::get_perf_context();
+  context->rep = rocksdb::get_perf_context();
   return context;
 }
 
@@ -2970,7 +2866,7 @@ rocksdb_compactionfilter_t* rocksdb_compactionfilter_create(
   result->state_ = state;
   result->destructor_ = destructor;
   result->filter_ = filter;
-  result->ignore_snapshots_ = true;
+  result->ignore_snapshots_ = false;
   result->name_ = name;
   return result;
 }
@@ -3070,7 +2966,7 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
   // supplied C functions.
   struct Wrapper : public rocksdb_filterpolicy_t {
     const FilterPolicy* rep_;
-    ~Wrapper() override { delete rep_; }
+    ~Wrapper() { delete rep_; }
     const char* Name() const override { return rep_->Name(); }
     void CreateFilter(const Slice* keys, int n,
                       std::string* dst) const override {
@@ -3079,17 +2975,7 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
     bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
       return rep_->KeyMayMatch(key, filter);
     }
-    // No need to override GetFilterBitsBuilder if this one is overridden
-    ROCKSDB_NAMESPACE::FilterBitsBuilder* GetBuilderWithContext(
-        const ROCKSDB_NAMESPACE::FilterBuildingContext& context)
-        const override {
-      return rep_->GetBuilderWithContext(context);
-    }
-    ROCKSDB_NAMESPACE::FilterBitsReader* GetFilterBitsReader(
-        const Slice& contents) const override {
-      return rep_->GetFilterBitsReader(contents);
-    }
-    static void DoNothing(void*) {}
+    static void DoNothing(void*) { }
   };
   Wrapper* wrapper = new Wrapper;
   wrapper->rep_ = NewBloomFilterPolicy(bits_per_key, original_format);
@@ -3187,7 +3073,7 @@ void rocksdb_readoptions_set_iterate_lower_bound(
 
 void rocksdb_readoptions_set_read_tier(
     rocksdb_readoptions_t* opt, int v) {
-  opt->rep.read_tier = static_cast<ROCKSDB_NAMESPACE::ReadTier>(v);
+  opt->rep.read_tier = static_cast<rocksdb::ReadTier>(v);
 }
 
 void rocksdb_readoptions_set_tailing(
@@ -3271,11 +3157,6 @@ void rocksdb_writeoptions_set_low_pri(
   opt->rep.low_pri = v;
 }
 
-void rocksdb_writeoptions_set_memtable_insert_hint_per_batch(
-    rocksdb_writeoptions_t* opt, unsigned char v) {
-  opt->rep.memtable_insert_hint_per_batch = v;
-}
-
 rocksdb_compactoptions_t* rocksdb_compactoptions_create() {
   return new rocksdb_compactoptions_t;
 }
@@ -3359,7 +3240,7 @@ rocksdb_env_t* rocksdb_create_default_env() {
 
 rocksdb_env_t* rocksdb_create_mem_env() {
   rocksdb_env_t* result = new rocksdb_env_t;
-  result->rep = ROCKSDB_NAMESPACE::NewMemEnv(Env::Default());
+  result->rep = rocksdb::NewMemEnv(Env::Default());
   result->is_default = false;
   return result;
 }
@@ -3376,22 +3257,6 @@ void rocksdb_env_join_all_threads(rocksdb_env_t* env) {
   env->rep->WaitForJoin();
 }
 
-void rocksdb_env_lower_thread_pool_io_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolIOPriority();
-}
-
-void rocksdb_env_lower_high_priority_thread_pool_io_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolIOPriority(Env::HIGH);
-}
-
-void rocksdb_env_lower_thread_pool_cpu_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolCPUPriority();
-}
-
-void rocksdb_env_lower_high_priority_thread_pool_cpu_priority(rocksdb_env_t* env) {
-  env->rep->LowerThreadPoolCPUPriority(Env::HIGH);
-}
-
 void rocksdb_env_destroy(rocksdb_env_t* env) {
   if (!env->is_default) delete env->rep;
   delete env;
@@ -3526,10 +3391,6 @@ void rocksdb_ingest_external_file_cf(
   SaveError(errptr, db->rep->IngestExternalFile(handle->rep, files, opt->rep));
 }
 
-void rocksdb_try_catch_up_with_primary(rocksdb_t* db, char** errptr) {
-  SaveError(errptr, db->rep->TryCatchUpWithPrimary());
-}
-
 rocksdb_slicetransform_t* rocksdb_slicetransform_create(
     void* state,
     void (*destructor)(void*),
@@ -3560,7 +3421,7 @@ void rocksdb_slicetransform_destroy(rocksdb_slicetransform_t* st) {
 
 struct Wrapper : public rocksdb_slicetransform_t {
   const SliceTransform* rep_;
-  ~Wrapper() override { delete rep_; }
+  ~Wrapper() { delete rep_; }
   const char* Name() const override { return rep_->Name(); }
   Slice Transform(const Slice& src) const override {
     return rep_->Transform(src);
@@ -3574,7 +3435,7 @@ struct Wrapper : public rocksdb_slicetransform_t {
 
 rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t prefixLen) {
   Wrapper* wrapper = new Wrapper;
-  wrapper->rep_ = ROCKSDB_NAMESPACE::NewFixedPrefixTransform(prefixLen);
+  wrapper->rep_ = rocksdb::NewFixedPrefixTransform(prefixLen);
   wrapper->state_ = nullptr;
   wrapper->destructor_ = &Wrapper::DoNothing;
   return wrapper;
@@ -3582,7 +3443,7 @@ rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t pref
 
 rocksdb_slicetransform_t* rocksdb_slicetransform_create_noop() {
   Wrapper* wrapper = new Wrapper;
-  wrapper->rep_ = ROCKSDB_NAMESPACE::NewNoopTransform();
+  wrapper->rep_ = rocksdb::NewNoopTransform();
   wrapper->state_ = nullptr;
   wrapper->destructor_ = &Wrapper::DoNothing;
   return wrapper;
@@ -3590,7 +3451,7 @@ rocksdb_slicetransform_t* rocksdb_slicetransform_create_noop() {
 
 rocksdb_universal_compaction_options_t* rocksdb_universal_compaction_options_create() {
   rocksdb_universal_compaction_options_t* result = new rocksdb_universal_compaction_options_t;
-  result->rep = new ROCKSDB_NAMESPACE::CompactionOptionsUniversal;
+  result->rep = new rocksdb::CompactionOptionsUniversal;
   return result;
 }
 
@@ -3621,8 +3482,7 @@ void rocksdb_universal_compaction_options_set_compression_size_percent(
 
 void rocksdb_universal_compaction_options_set_stop_style(
   rocksdb_universal_compaction_options_t* uco, int style) {
-  uco->rep->stop_style =
-      static_cast<ROCKSDB_NAMESPACE::CompactionStopStyle>(style);
+  uco->rep->stop_style = static_cast<rocksdb::CompactionStopStyle>(style);
 }
 
 void rocksdb_universal_compaction_options_destroy(
@@ -3652,7 +3512,7 @@ void rocksdb_options_set_min_level_to_compress(rocksdb_options_t* opt, int level
     assert(level <= opt->rep.num_levels);
     opt->rep.compression_per_level.resize(opt->rep.num_levels);
     for (int i = 0; i < level; i++) {
-      opt->rep.compression_per_level[i] = ROCKSDB_NAMESPACE::kNoCompression;
+      opt->rep.compression_per_level[i] = rocksdb::kNoCompression;
     }
     for (int i = level; i < opt->rep.num_levels; i++) {
       opt->rep.compression_per_level[i] = opt->rep.compression;
@@ -3856,38 +3716,6 @@ rocksdb_transactiondb_t* rocksdb_transactiondb_open(
   return result;
 }
 
-rocksdb_transactiondb_t* rocksdb_transactiondb_open_column_families(
-    const rocksdb_options_t* options,
-    const rocksdb_transactiondb_options_t* txn_db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
-    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.push_back(ColumnFamilyDescriptor(
-        std::string(column_family_names[i]),
-        ColumnFamilyOptions(column_family_options[i]->rep)));
-  }
-
-  TransactionDB* txn_db;
-  std::vector<ColumnFamilyHandle*> handles;
-  if (SaveError(errptr, TransactionDB::Open(options->rep, txn_db_options->rep,
-                                            std::string(name), column_families,
-                                            &handles, &txn_db))) {
-    return nullptr;
-  }
-
-  for (size_t i = 0; i < handles.size(); i++) {
-    rocksdb_column_family_handle_t* c_handle =
-        new rocksdb_column_family_handle_t;
-    c_handle->rep = handles[i];
-    column_family_handles[i] = c_handle;
-  }
-  rocksdb_transactiondb_t* result = new rocksdb_transactiondb_t;
-  result->rep = txn_db;
-  return result;
-}
-
 const rocksdb_snapshot_t* rocksdb_transactiondb_create_snapshot(
     rocksdb_transactiondb_t* txn_db) {
   rocksdb_snapshot_t* result = new rocksdb_snapshot_t;
@@ -4008,26 +3836,6 @@ char* rocksdb_transaction_get_for_update(rocksdb_transaction_t* txn,
   return result;
 }
 
-char* rocksdb_transaction_get_for_update_cf(
-    rocksdb_transaction_t* txn, const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key, size_t klen,
-    size_t* vlen, unsigned char exclusive, char** errptr) {
-  char* result = nullptr;
-  std::string tmp;
-  Status s = txn->rep->GetForUpdate(options->rep, column_family->rep,
-                                    Slice(key, klen), &tmp, exclusive);
-  if (s.ok()) {
-    *vlen = tmp.size();
-    result = CopyString(tmp);
-  } else {
-    *vlen = 0;
-    if (!s.IsNotFound()) {
-      SaveError(errptr, s);
-    }
-  }
-  return result;
-}
-
 // Read a key outside a transaction
 char* rocksdb_transactiondb_get(
     rocksdb_transactiondb_t* txn_db,
@@ -4120,14 +3928,6 @@ void rocksdb_transaction_merge(rocksdb_transaction_t* txn, const char* key,
   SaveError(errptr, txn->rep->Merge(Slice(key, klen), Slice(val, vlen)));
 }
 
-void rocksdb_transaction_merge_cf(rocksdb_transaction_t* txn,
-                                  rocksdb_column_family_handle_t* column_family,
-                                  const char* key, size_t klen, const char* val,
-                                  size_t vlen, char** errptr) {
-  SaveError(errptr, txn->rep->Merge(column_family->rep, Slice(key, klen),
-                                    Slice(val, vlen)));
-}
-
 // Merge a key outside a transaction
 void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
                                  const rocksdb_writeoptions_t* options,
@@ -4137,14 +3937,6 @@ void rocksdb_transactiondb_merge(rocksdb_transactiondb_t* txn_db,
                                        Slice(val, vlen)));
 }
 
-void rocksdb_transactiondb_merge_cf(
-    rocksdb_transactiondb_t* txn_db, const rocksdb_writeoptions_t* options,
-    rocksdb_column_family_handle_t* column_family, const char* key, size_t klen,
-    const char* val, size_t vlen, char** errptr) {
-  SaveError(errptr, txn_db->rep->Merge(options->rep, column_family->rep,
-                                       Slice(key, klen), Slice(val, vlen)));
-}
-
 // Delete a key inside a transaction
 void rocksdb_transaction_delete(rocksdb_transaction_t* txn, const char* key,
                                 size_t klen, char** errptr) {
@@ -4197,14 +3989,6 @@ rocksdb_iterator_t* rocksdb_transactiondb_create_iterator(
   return result;
 }
 
-rocksdb_iterator_t* rocksdb_transactiondb_create_iterator_cf(
-    rocksdb_transactiondb_t* txn_db, const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* column_family) {
-  rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep = txn_db->rep->NewIterator(options->rep, column_family->rep);
-  return result;
-}
-
 void rocksdb_transactiondb_close(rocksdb_transactiondb_t* txn_db) {
   delete txn_db->rep;
   delete txn_db;
@@ -4237,8 +4021,8 @@ rocksdb_optimistictransactiondb_t* rocksdb_optimistictransactiondb_open(
 rocksdb_optimistictransactiondb_t*
 rocksdb_optimistictransactiondb_open_column_families(
     const rocksdb_options_t* db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
+    int num_column_families, const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
@@ -4354,8 +4138,7 @@ const char* rocksdb_pinnableslice_value(const rocksdb_pinnableslice_t* v,
   return v->rep.data();
 }
 
-// container to keep databases and caches in order to use
-// ROCKSDB_NAMESPACE::MemoryUtil
+// container to keep databases and caches in order to use rocksdb::MemoryUtil
 struct rocksdb_memory_consumers_t {
   std::vector<rocksdb_t*> dbs;
   std::unordered_set<rocksdb_cache_t*> caches;
@@ -4383,7 +4166,7 @@ void rocksdb_memory_consumers_destroy(rocksdb_memory_consumers_t* consumers) {
   delete consumers;
 }
 
-// contains memory usage statistics provided by ROCKSDB_NAMESPACE::MemoryUtil
+// contains memory usage statistics provided by rocksdb::MemoryUtil
 struct rocksdb_memory_usage_t {
   uint64_t mem_table_total;
   uint64_t mem_table_unflushed;
@@ -4405,7 +4188,7 @@ rocksdb_memory_usage_t* rocksdb_approximate_memory_usage_create(
     cache_set.insert(const_cast<const Cache*>(cache->rep.get()));
   }
 
-  std::map<ROCKSDB_NAMESPACE::MemoryUtil::UsageType, uint64_t> usage_by_type;
+  std::map<rocksdb::MemoryUtil::UsageType, uint64_t> usage_by_type;
 
   auto status = MemoryUtil::GetApproximateMemoryUsageByType(dbs, cache_set,
                                                             &usage_by_type);

db/c_test.c

@@ -1,7 +1,6 @@
 /* Copyright (c) 2011 The LevelDB Authors. All rights reserved.
    Use of this source code is governed by a BSD-style license that can be
    found in the LICENSE file. See the AUTHORS file for names of contributors. */
-// Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 #include <stdio.h>
 
@@ -45,7 +44,6 @@ static char sstfilename[200];
 static char dbbackupname[200];
 static char dbcheckpointname[200];
 static char dbpathname[200];
-static char secondary_path[200];
 
 static void StartPhase(const char* name) {
   fprintf(stderr, "=== Test %s\n", name);
@@ -487,11 +485,8 @@ int main(int argc, char** argv) {
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
   rocksdb_options_set_base_background_compactions(options, 1);
-
   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_options_set_block_based_table_factory(options, table_options);
 
   rocksdb_options_set_compression(options, rocksdb_no_compression);
@@ -835,6 +830,23 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_wi_iterate(wbi, &pos, CheckPut, CheckDel);
     CheckCondition(pos == 3);
     rocksdb_writebatch_wi_clear(wbi);
+    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
+    rocksdb_writebatch_wi_put(wbi, "bay", 3, "d", 1);
+    rocksdb_writebatch_wi_delete_range(wbi, "bar", 3, "bay", 3);
+    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "bar", NULL);
+    CheckGet(db, roptions, "bay", "d");
+    rocksdb_writebatch_wi_clear(wbi);
+    const char* start_list[1] = {"bay"};
+    const size_t start_sizes[1] = {3};
+    const char* end_list[1] = {"baz"};
+    const size_t end_sizes[1] = {3};
+    rocksdb_writebatch_wi_delete_rangev(wbi, 1, start_list, start_sizes, end_list,
+                                     end_sizes);
+    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "bay", NULL);
     rocksdb_writebatch_wi_destroy(wbi);
   }
 
@@ -1034,20 +1046,17 @@ int main(int argc, char** argv) {
   }
 
   StartPhase("filter");
-  for (run = 0; run <= 2; run++) {
-    // First run uses custom filter
-    // Second run uses old block-based bloom filter
-    // Third run uses full bloom filter
+  for (run = 0; run < 2; run++) {
+    // First run uses custom filter, second run uses bloom filter
     CheckNoError(err);
     rocksdb_filterpolicy_t* policy;
     if (run == 0) {
-      policy = rocksdb_filterpolicy_create(NULL, FilterDestroy, FilterCreate,
-                                           FilterKeyMatch, NULL, FilterName);
-    } else if (run == 1) {
-      policy = rocksdb_filterpolicy_create_bloom(8);
+      policy = rocksdb_filterpolicy_create(
+          NULL, FilterDestroy, FilterCreate, FilterKeyMatch, NULL, FilterName);
     } else {
-      policy = rocksdb_filterpolicy_create_bloom_full(8);
+      policy = rocksdb_filterpolicy_create_bloom(10);
     }
+
     rocksdb_block_based_options_set_filter_policy(table_options, policy);
 
     // Create new database
@@ -1060,24 +1069,12 @@ int main(int argc, char** argv) {
     CheckNoError(err);
     rocksdb_put(db, woptions, "bar", 3, "barvalue", 8, &err);
     CheckNoError(err);
-
-    {
-      // Add enough keys to get just one reasonably populated Bloom filter
-      const int keys_to_add = 1500;
-      int i;
-      char keybuf[100];
-      for (i = 0; i < keys_to_add; i++) {
-        snprintf(keybuf, sizeof(keybuf), "yes%020d", i);
-        rocksdb_put(db, woptions, keybuf, strlen(keybuf), "val", 3, &err);
-        CheckNoError(err);
-      }
-    }
     rocksdb_compact_range(db, NULL, 0, NULL, 0);
 
     fake_filter_result = 1;
     CheckGet(db, roptions, "foo", "foovalue");
     CheckGet(db, roptions, "bar", "barvalue");
-    if (run == 0) {
+    if (phase == 0) {
       // Must not find value when custom filter returns false
       fake_filter_result = 0;
       CheckGet(db, roptions, "foo", NULL);
@@ -1087,43 +1084,6 @@ int main(int argc, char** argv) {
       CheckGet(db, roptions, "foo", "foovalue");
       CheckGet(db, roptions, "bar", "barvalue");
     }
-
-    {
-      // Query some keys not added to identify Bloom filter implementation
-      // from false positive queries, using perfcontext to detect Bloom
-      // filter behavior
-      rocksdb_perfcontext_t* perf = rocksdb_perfcontext_create();
-      rocksdb_perfcontext_reset(perf);
-
-      const int keys_to_query = 10000;
-      int i;
-      char keybuf[100];
-      for (i = 0; i < keys_to_query; i++) {
-        fake_filter_result = i % 2;
-        snprintf(keybuf, sizeof(keybuf), "no%020d", i);
-        CheckGet(db, roptions, keybuf, NULL);
-      }
-
-      const int hits =
-          (int)rocksdb_perfcontext_metric(perf, rocksdb_bloom_sst_hit_count);
-      if (run == 0) {
-        // Due to half true, half false with fake filter result
-        CheckCondition(hits == keys_to_query / 2);
-      } else if (run == 1) {
-        // Essentially a fingerprint of the block-based Bloom schema
-        CheckCondition(hits == 241);
-      } else {
-        // Essentially a fingerprint of the full Bloom schema(s),
-        // format_version < 5, which vary for three different CACHE_LINE_SIZEs
-        CheckCondition(hits == 224 || hits == 180 || hits == 125);
-      }
-      CheckCondition(
-          (keys_to_query - hits) ==
-          (int)rocksdb_perfcontext_metric(perf, rocksdb_bloom_sst_miss_count));
-
-      rocksdb_perfcontext_destroy(perf);
-    }
-
     // Reset the policy
     rocksdb_block_based_options_set_filter_policy(table_options, NULL);
     rocksdb_options_set_block_based_table_factory(options, table_options);
@@ -1227,31 +1187,12 @@ int main(int argc, char** argv) {
     rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &err);
     CheckNoError(err);
 
-    rocksdb_put_cf(db, woptions, handles[1], "foobar1", 7, "hello1", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar2", 7, "hello2", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar3", 7, "hello3", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar4", 7, "hello4", 6, &err);
-    CheckNoError(err);
-
-    rocksdb_flushoptions_t *flush_options = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_options, 1);
-    rocksdb_flush_cf(db, flush_options, handles[1], &err);
-    CheckNoError(err)
-    rocksdb_flushoptions_destroy(flush_options);
-
     CheckGetCF(db, roptions, handles[1], "foo", "hello");
     CheckPinGetCF(db, roptions, handles[1], "foo", "hello");
 
     rocksdb_delete_cf(db, woptions, handles[1], "foo", 3, &err);
     CheckNoError(err);
 
-    rocksdb_delete_range_cf(db, woptions, handles[1], "foobar2", 7, "foobar4",
-                            7, &err);
-    CheckNoError(err);
-
     CheckGetCF(db, roptions, handles[1], "foo", NULL);
     CheckPinGetCF(db, roptions, handles[1], "foo", NULL);
 
@@ -1304,7 +1245,7 @@ int main(int argc, char** argv) {
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
-    CheckCondition(i == 3);
+    CheckCondition(i == 1);
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -1328,7 +1269,7 @@ int main(int argc, char** argv) {
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
-    CheckCondition(i == 3);
+    CheckCondition(i == 1);
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -1518,7 +1459,6 @@ int main(int argc, char** argv) {
        CheckCondition(!rocksdb_iter_valid(iter));
 
        rocksdb_iter_destroy(iter);
-       rocksdb_readoptions_set_iterate_upper_bound(roptions, NULL, 0);
     }
   }
 
@@ -1775,59 +1715,6 @@ int main(int argc, char** argv) {
     CheckNoError(err);
   }
 
-  // Check that secondary instance works.
-  StartPhase("open_as_secondary");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-
-    rocksdb_options_t* db_options = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(db_options, 1);
-    db = rocksdb_open(db_options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_t* db1;
-    rocksdb_options_t* opts = rocksdb_options_create();
-    rocksdb_options_set_max_open_files(opts, -1);
-    rocksdb_options_set_create_if_missing(opts, 1);
-    snprintf(secondary_path, sizeof(secondary_path),
-             "%s/rocksdb_c_test_secondary-%d", GetTempDir(), ((int)geteuid()));
-    db1 = rocksdb_open_as_secondary(opts, dbname, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_writeoptions_set_sync(woptions, 0);
-    rocksdb_writeoptions_disable_WAL(woptions, 1);
-    rocksdb_put(db, woptions, "key0", 4, "value0", 6, &err);
-    CheckNoError(err);
-    rocksdb_flushoptions_t* flush_opts = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_opts, 1);
-    rocksdb_flush(db, flush_opts, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    rocksdb_readoptions_t* ropts = rocksdb_readoptions_create();
-    rocksdb_readoptions_set_verify_checksums(ropts, 1);
-    rocksdb_readoptions_set_snapshot(ropts, NULL);
-    CheckGet(db, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key0", "value0");
-
-    rocksdb_writeoptions_disable_WAL(woptions, 0);
-    rocksdb_put(db, woptions, "key1", 4, "value1", 6, &err);
-    CheckNoError(err);
-    rocksdb_try_catch_up_with_primary(db1, &err);
-    CheckNoError(err);
-    CheckGet(db1, ropts, "key0", "value0");
-    CheckGet(db1, ropts, "key1", "value1");
-
-    rocksdb_close(db1);
-    rocksdb_destroy_db(opts, secondary_path, &err);
-    CheckNoError(err);
-
-    rocksdb_options_destroy(db_options);
-    rocksdb_options_destroy(opts);
-    rocksdb_readoptions_destroy(ropts);
-    rocksdb_flushoptions_destroy(flush_opts);
-  }
-
   // Simple sanity check that options setting db_paths work.
   StartPhase("open_db_paths");
   {

db/column_family.cc

@@ -9,34 +9,36 @@
 
 #include "db/column_family.h"
 
-#include <algorithm>
-#include <cinttypes>
-#include <limits>
-#include <string>
-#include <vector>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
 
-#include "db/compaction/compaction_picker.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
-#include "db/db_impl/db_impl.h"
+#include <inttypes.h>
+#include <vector>
+#include <string>
+#include <algorithm>
+#include <limits>
+
+#include "db/compaction_picker.h"
+#include "db/compaction_picker_fifo.h"
+#include "db/compaction_picker_universal.h"
+#include "db/db_impl.h"
 #include "db/internal_stats.h"
 #include "db/job_context.h"
 #include "db/range_del_aggregator.h"
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
-#include "file/sst_file_manager_impl.h"
 #include "memtable/hash_skiplist_rep.h"
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
-#include "port/port.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "util/autovector.h"
 #include "util/compression.h"
+#include "util/sst_file_manager_impl.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 ColumnFamilyHandleImpl::ColumnFamilyHandleImpl(
     ColumnFamilyData* column_family_data, DBImpl* db, InstrumentedMutex* mutex)
@@ -60,22 +62,13 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
     ColumnFamilyOptions initial_cf_options_copy = cfd_->initial_cf_options();
     JobContext job_context(0);
     mutex_->Lock();
-    bool dropped = cfd_->IsDropped();
-    if (cfd_->UnrefAndTryDelete()) {
-      if (dropped) {
-        db_->FindObsoleteFiles(&job_context, false, true);
-      }
+    if (cfd_->Unref()) {
+      delete cfd_;
     }
+    db_->FindObsoleteFiles(&job_context, false, true);
     mutex_->Unlock();
     if (job_context.HaveSomethingToDelete()) {
-      bool defer_purge =
-          db_->immutable_db_options().avoid_unnecessary_blocking_io;
-      db_->PurgeObsoleteFiles(job_context, defer_purge);
-      if (defer_purge) {
-        mutex_->Lock();
-        db_->SchedulePurge();
-        mutex_->Unlock();
-      }
+      db_->PurgeObsoleteFiles(job_context);
     }
     job_context.Clean();
   }
@@ -185,11 +178,6 @@ Status CheckCFPathsSupported(const DBOptions& db_options,
   return Status::OK();
 }
 
-namespace {
-const uint64_t kDefaultTtl = 0xfffffffffffffffe;
-const uint64_t kDefaultPeriodicCompSecs = 0xfffffffffffffffe;
-};  // namespace
-
 ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                     const ColumnFamilyOptions& src) {
   ColumnFamilyOptions result = src;
@@ -230,14 +218,7 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
   if (result.max_write_buffer_number < 2) {
     result.max_write_buffer_number = 2;
   }
-  // fall back max_write_buffer_number_to_maintain if
-  // max_write_buffer_size_to_maintain is not set
-  if (result.max_write_buffer_size_to_maintain < 0) {
-    result.max_write_buffer_size_to_maintain =
-        result.max_write_buffer_number *
-        static_cast<int64_t>(result.write_buffer_size);
-  } else if (result.max_write_buffer_size_to_maintain == 0 &&
-             result.max_write_buffer_number_to_maintain < 0) {
+  if (result.max_write_buffer_number_to_maintain < 0) {
     result.max_write_buffer_number_to_maintain = result.max_write_buffer_number;
   }
   // bloom filter size shouldn't exceed 1/4 of memtable size.
@@ -345,61 +326,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     result.max_compaction_bytes = result.target_file_size_base * 25;
   }
 
-  bool is_block_based_table =
-      (result.table_factory->Name() == BlockBasedTableFactory().Name());
-
-  const uint64_t kAdjustedTtl = 30 * 24 * 60 * 60;
-  if (result.ttl == kDefaultTtl) {
-    if (is_block_based_table &&
-        result.compaction_style != kCompactionStyleFIFO) {
-      result.ttl = kAdjustedTtl;
-    } else {
-      result.ttl = 0;
-    }
-  }
-
-  const uint64_t kAdjustedPeriodicCompSecs = 30 * 24 * 60 * 60;
-
-  // Turn on periodic compactions and set them to occur once every 30 days if
-  // compaction filters are used and periodic_compaction_seconds is set to the
-  // default value.
-  if (result.compaction_style != kCompactionStyleFIFO) {
-    if ((result.compaction_filter != nullptr ||
-         result.compaction_filter_factory != nullptr) &&
-        result.periodic_compaction_seconds == kDefaultPeriodicCompSecs &&
-        is_block_based_table) {
-      result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-    }
-  } else {
-    // result.compaction_style == kCompactionStyleFIFO
-    if (result.ttl == 0) {
-      if (is_block_based_table) {
-        if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-          result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-        }
-        result.ttl = result.periodic_compaction_seconds;
-      }
-    } else if (result.periodic_compaction_seconds != 0) {
-      result.ttl = std::min(result.ttl, result.periodic_compaction_seconds);
-    }
-  }
-
-  // TTL compactions would work similar to Periodic Compactions in Universal in
-  // most of the cases. So, if ttl is set, execute the periodic compaction
-  // codepath.
-  if (result.compaction_style == kCompactionStyleUniversal && result.ttl != 0) {
-    if (result.periodic_compaction_seconds != 0) {
-      result.periodic_compaction_seconds =
-          std::min(result.ttl, result.periodic_compaction_seconds);
-    } else {
-      result.periodic_compaction_seconds = result.ttl;
-    }
-  }
-
-  if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-    result.periodic_compaction_seconds = 0;
-  }
-
   return result;
 }
 
@@ -436,18 +362,13 @@ void SuperVersion::Cleanup() {
     to_delete.push_back(m);
   }
   current->Unref();
-  if (cfd->Unref()) {
-    delete cfd;
-  }
 }
 
-void SuperVersion::Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
-                        MemTableListVersion* new_imm, Version* new_current) {
-  cfd = new_cfd;
+void SuperVersion::Init(MemTable* new_mem, MemTableListVersion* new_imm,
+                        Version* new_current) {
   mem = new_mem;
   imm = new_imm;
   current = new_current;
-  cfd->Ref();
   mem->Ref();
   imm->Ref();
   current->Ref();
@@ -471,23 +392,11 @@ void SuperVersionUnrefHandle(void* ptr) {
 }
 }  // anonymous namespace
 
-std::vector<std::string> ColumnFamilyData::GetDbPaths() const {
-  std::vector<std::string> paths;
-  paths.reserve(ioptions_.cf_paths.size());
-  for (const DbPath& db_path : ioptions_.cf_paths) {
-    paths.emplace_back(db_path.path);
-  }
-  return paths;
-}
-
-const uint32_t ColumnFamilyData::kDummyColumnFamilyDataId = port::kMaxUint32;
-
 ColumnFamilyData::ColumnFamilyData(
     uint32_t id, const std::string& name, Version* _dummy_versions,
     Cache* _table_cache, WriteBufferManager* write_buffer_manager,
     const ColumnFamilyOptions& cf_options, const ImmutableDBOptions& db_options,
-    const FileOptions& file_options, ColumnFamilySet* column_family_set,
-    BlockCacheTracer* const block_cache_tracer)
+    const EnvOptions& env_options, ColumnFamilySet* column_family_set)
     : id_(id),
       name_(name),
       dummy_versions_(_dummy_versions),
@@ -504,8 +413,7 @@ ColumnFamilyData::ColumnFamilyData(
       write_buffer_manager_(write_buffer_manager),
       mem_(nullptr),
       imm_(ioptions_.min_write_buffer_number_to_merge,
-           ioptions_.max_write_buffer_number_to_maintain,
-           ioptions_.max_write_buffer_size_to_maintain),
+           ioptions_.max_write_buffer_number_to_maintain),
       super_version_(nullptr),
       super_version_number_(0),
       local_sv_(new ThreadLocalPtr(&SuperVersionUnrefHandle)),
@@ -518,23 +426,7 @@ ColumnFamilyData::ColumnFamilyData(
       queued_for_compaction_(false),
       prev_compaction_needed_bytes_(0),
       allow_2pc_(db_options.allow_2pc),
-      last_memtable_id_(0),
-      db_paths_registered_(false) {
-  if (id_ != kDummyColumnFamilyDataId) {
-    // TODO(cc): RegisterDbPaths can be expensive, considering moving it
-    // outside of this constructor which might be called with db mutex held.
-    // TODO(cc): considering using ioptions_.fs, currently some tests rely on
-    // EnvWrapper, that's the main reason why we use env here.
-    Status s = ioptions_.env->RegisterDbPaths(GetDbPaths());
-    if (s.ok()) {
-      db_paths_registered_ = true;
-    } else {
-      ROCKS_LOG_ERROR(
-          ioptions_.info_log,
-          "Failed to register data paths of column family (id: %d, name: %s)",
-          id_, name_.c_str());
-    }
-  }
+      last_memtable_id_(0) {
   Ref();
 
   // Convert user defined table properties collector factories to internal ones.
@@ -544,8 +436,7 @@ ColumnFamilyData::ColumnFamilyData(
   if (_dummy_versions != nullptr) {
     internal_stats_.reset(
         new InternalStats(ioptions_.num_levels, db_options.env, this));
-    table_cache_.reset(new TableCache(ioptions_, file_options, _table_cache,
-                                      block_cache_tracer));
+    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache));
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
           new LevelCompactionPicker(ioptions_, &internal_comparator_));
@@ -610,7 +501,21 @@ ColumnFamilyData::~ColumnFamilyData() {
   // compaction_queue_ and we destroyed it
   assert(!queued_for_flush_);
   assert(!queued_for_compaction_);
-  assert(super_version_ == nullptr);
+
+  if (super_version_ != nullptr) {
+    // Release SuperVersion reference kept in ThreadLocalPtr.
+    // This must be done outside of mutex_ since unref handler can lock mutex.
+    super_version_->db_mutex->Unlock();
+    local_sv_.reset();
+    super_version_->db_mutex->Lock();
+
+    bool is_last_reference __attribute__((__unused__));
+    is_last_reference = super_version_->Unref();
+    assert(is_last_reference);
+    super_version_->Cleanup();
+    delete super_version_;
+    super_version_ = nullptr;
+  }
 
   if (dummy_versions_ != nullptr) {
     // List must be empty
@@ -628,48 +533,6 @@ ColumnFamilyData::~ColumnFamilyData() {
   for (MemTable* m : to_delete) {
     delete m;
   }
-
-  if (db_paths_registered_) {
-    // TODO(cc): considering using ioptions_.fs, currently some tests rely on
-    // EnvWrapper, that's the main reason why we use env here.
-    Status s = ioptions_.env->UnregisterDbPaths(GetDbPaths());
-    if (!s.ok()) {
-      ROCKS_LOG_ERROR(
-          ioptions_.info_log,
-          "Failed to unregister data paths of column family (id: %d, name: %s)",
-          id_, name_.c_str());
-    }
-  }
-}
-
-bool ColumnFamilyData::UnrefAndTryDelete() {
-  int old_refs = refs_.fetch_sub(1);
-  assert(old_refs > 0);
-
-  if (old_refs == 1) {
-    assert(super_version_ == nullptr);
-    delete this;
-    return true;
-  }
-
-  if (old_refs == 2 && super_version_ != nullptr) {
-    // Only the super_version_ holds me
-    SuperVersion* sv = super_version_;
-    super_version_ = nullptr;
-    // Release SuperVersion reference kept in ThreadLocalPtr.
-    // This must be done outside of mutex_ since unref handler can lock mutex.
-    sv->db_mutex->Unlock();
-    local_sv_.reset();
-    sv->db_mutex->Lock();
-
-    if (sv->Unref()) {
-      // May delete this ColumnFamilyData after calling Cleanup()
-      sv->Cleanup();
-      delete sv;
-      return true;
-    }
-  }
-  return false;
 }
 
 void ColumnFamilyData::SetDropped() {
@@ -1006,8 +869,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
   return write_stall_condition;
 }
 
-const FileOptions* ColumnFamilyData::soptions() const {
-  return &(column_family_set_->file_options_);
+const EnvOptions* ColumnFamilyData::soptions() const {
+  return &(column_family_set_->env_options_);
 }
 
 void ColumnFamilyData::SetCurrent(Version* current_version) {
@@ -1047,12 +910,8 @@ bool ColumnFamilyData::NeedsCompaction() const {
 
 Compaction* ColumnFamilyData::PickCompaction(
     const MutableCFOptions& mutable_options, LogBuffer* log_buffer) {
-  SequenceNumber earliest_mem_seqno =
-      std::min(mem_->GetEarliestSequenceNumber(),
-               imm_.current()->GetEarliestSequenceNumber(false));
   auto* result = compaction_picker_->PickCompaction(
-      GetName(), mutable_options, current_->storage_info(), log_buffer,
-      earliest_mem_seqno);
+      GetName(), mutable_options, current_->storage_info(), log_buffer);
   if (result != nullptr) {
     result->SetInputVersion(current_);
   }
@@ -1123,22 +982,22 @@ const int ColumnFamilyData::kCompactToBaseLevel = -2;
 
 Compaction* ColumnFamilyData::CompactRange(
     const MutableCFOptions& mutable_cf_options, int input_level,
-    int output_level, const CompactRangeOptions& compact_range_options,
+    int output_level, uint32_t output_path_id, uint32_t max_subcompactions,
     const InternalKey* begin, const InternalKey* end,
-    InternalKey** compaction_end, bool* conflict,
-    uint64_t max_file_num_to_ignore) {
+    InternalKey** compaction_end, bool* conflict) {
   auto* result = compaction_picker_->CompactRange(
       GetName(), mutable_cf_options, current_->storage_info(), input_level,
-      output_level, compact_range_options, begin, end, compaction_end, conflict,
-      max_file_num_to_ignore);
+      output_level, output_path_id, max_subcompactions, begin, end,
+      compaction_end, conflict);
   if (result != nullptr) {
     result->SetInputVersion(current_);
   }
   return result;
 }
 
-SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(DBImpl* db) {
-  SuperVersion* sv = GetThreadLocalSuperVersion(db);
+SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
+    InstrumentedMutex* db_mutex) {
+  SuperVersion* sv = GetThreadLocalSuperVersion(db_mutex);
   sv->Ref();
   if (!ReturnThreadLocalSuperVersion(sv)) {
     // This Unref() corresponds to the Ref() in GetThreadLocalSuperVersion()
@@ -1150,7 +1009,8 @@ SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(DBImpl* db) {
   return sv;
 }
 
-SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
+SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
+    InstrumentedMutex* db_mutex) {
   // The SuperVersion is cached in thread local storage to avoid acquiring
   // mutex when SuperVersion does not change since the last use. When a new
   // SuperVersion is installed, the compaction or flush thread cleans up
@@ -1177,21 +1037,16 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
 
     if (sv && sv->Unref()) {
       RecordTick(ioptions_.statistics, NUMBER_SUPERVERSION_CLEANUPS);
-      db->mutex()->Lock();
+      db_mutex->Lock();
       // NOTE: underlying resources held by superversion (sst files) might
       // not be released until the next background job.
       sv->Cleanup();
-      if (db->immutable_db_options().avoid_unnecessary_blocking_io) {
-        db->AddSuperVersionsToFreeQueue(sv);
-        db->SchedulePurge();
-      } else {
-        sv_to_delete = sv;
-      }
+      sv_to_delete = sv;
     } else {
-      db->mutex()->Lock();
+      db_mutex->Lock();
     }
     sv = super_version_->Ref();
-    db->mutex()->Unlock();
+    db_mutex->Unlock();
 
     delete sv_to_delete;
   }
@@ -1229,7 +1084,7 @@ void ColumnFamilyData::InstallSuperVersion(
   SuperVersion* new_superversion = sv_context->new_superversion.release();
   new_superversion->db_mutex = db_mutex;
   new_superversion->mutable_cf_options = mutable_cf_options;
-  new_superversion->Init(this, mem_, imm_.current(), current_);
+  new_superversion->Init(mem_, imm_.current(), current_);
   SuperVersion* old_superversion = super_version_;
   super_version_ = new_superversion;
   ++super_version_number_;
@@ -1279,56 +1134,13 @@ void ColumnFamilyData::ResetThreadLocalSuperVersions() {
   }
 }
 
-Status ColumnFamilyData::ValidateOptions(
-    const DBOptions& db_options, const ColumnFamilyOptions& cf_options) {
-  Status s;
-  s = CheckCompressionSupported(cf_options);
-  if (s.ok() && db_options.allow_concurrent_memtable_write) {
-    s = CheckConcurrentWritesSupported(cf_options);
-  }
-  if (s.ok() && db_options.unordered_write &&
-      cf_options.max_successive_merges != 0) {
-    s = Status::InvalidArgument(
-        "max_successive_merges > 0 is incompatible with unordered_write");
-  }
-  if (s.ok()) {
-    s = CheckCFPathsSupported(db_options, cf_options);
-  }
-  if (!s.ok()) {
-    return s;
-  }
-
-  if (cf_options.ttl > 0 && cf_options.ttl != kDefaultTtl) {
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "TTL is only supported in Block-Based Table format. ");
-    }
-  }
-
-  if (cf_options.periodic_compaction_seconds > 0 &&
-      cf_options.periodic_compaction_seconds != kDefaultPeriodicCompSecs) {
-    if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported in "
-          "Block-Based Table format. ");
-    }
-  }
-  return s;
-}
-
 #ifndef ROCKSDB_LITE
 Status ColumnFamilyData::SetOptions(
-    const DBOptions& db_options,
-    const std::unordered_map<std::string, std::string>& options_map) {
+      const std::unordered_map<std::string, std::string>& options_map) {
   MutableCFOptions new_mutable_cf_options;
   Status s =
       GetMutableOptionsFromStrings(mutable_cf_options_, options_map,
                                    ioptions_.info_log, &new_mutable_cf_options);
-  if (s.ok()) {
-    ColumnFamilyOptions cf_options =
-        BuildColumnFamilyOptions(initial_cf_options_, new_mutable_cf_options);
-    s = ValidateOptions(db_options, cf_options);
-  }
   if (s.ok()) {
     mutable_cf_options_ = new_mutable_cf_options;
     mutable_cf_options_.RefreshDerivedOptions(ioptions_);
@@ -1350,41 +1162,28 @@ Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int 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 ColumnFamilyData::AddDirectories() {
   Status s;
-  assert(created_dirs != nullptr);
   assert(data_dirs_.empty());
   for (auto& p : ioptions_.cf_paths) {
-    auto existing_dir = created_dirs->find(p.path);
-
-    if (existing_dir == created_dirs->end()) {
-      std::unique_ptr<FSDirectory> path_directory;
-      s = DBImpl::CreateAndNewDirectory(ioptions_.fs, p.path, &path_directory);
-      if (!s.ok()) {
-        return s;
-      }
-      assert(path_directory != nullptr);
-      data_dirs_.emplace_back(path_directory.release());
-      (*created_dirs)[p.path] = data_dirs_.back();
-    } else {
-      data_dirs_.emplace_back(existing_dir->second);
+    std::unique_ptr<Directory> path_directory;
+    s = DBImpl::CreateAndNewDirectory(ioptions_.env, p.path, &path_directory);
+    if (!s.ok()) {
+      return s;
     }
+    assert(path_directory != nullptr);
+    data_dirs_.emplace_back(path_directory.release());
   }
   assert(data_dirs_.size() == ioptions_.cf_paths.size());
   return s;
 }
 
-FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
+Directory* ColumnFamilyData::GetDataDir(size_t path_id) const {
   if (data_dirs_.empty()) {
     return nullptr;
   }
@@ -1395,24 +1194,21 @@ FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
 
 ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                  const ImmutableDBOptions* db_options,
-                                 const FileOptions& file_options,
+                                 const EnvOptions& env_options,
                                  Cache* table_cache,
                                  WriteBufferManager* write_buffer_manager,
-                                 WriteController* write_controller,
-                                 BlockCacheTracer* const block_cache_tracer)
+                                 WriteController* write_controller)
     : max_column_family_(0),
-      dummy_cfd_(new ColumnFamilyData(
-          ColumnFamilyData::kDummyColumnFamilyDataId, "", nullptr, nullptr,
-          nullptr, ColumnFamilyOptions(), *db_options, file_options, nullptr,
-          block_cache_tracer)),
+      dummy_cfd_(new ColumnFamilyData(0, "", nullptr, nullptr, nullptr,
+                                      ColumnFamilyOptions(), *db_options,
+                                      env_options, nullptr)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
-      file_options_(file_options),
+      env_options_(env_options),
       table_cache_(table_cache),
       write_buffer_manager_(write_buffer_manager),
-      write_controller_(write_controller),
-      block_cache_tracer_(block_cache_tracer) {
+      write_controller_(write_controller) {
   // initialize linked list
   dummy_cfd_->prev_ = dummy_cfd_;
   dummy_cfd_->next_ = dummy_cfd_;
@@ -1423,12 +1219,14 @@ ColumnFamilySet::~ColumnFamilySet() {
     // cfd destructor will delete itself from column_family_data_
     auto cfd = column_family_data_.begin()->second;
     bool last_ref __attribute__((__unused__));
-    last_ref = cfd->UnrefAndTryDelete();
+    last_ref = cfd->Unref();
     assert(last_ref);
+    delete cfd;
   }
   bool dummy_last_ref __attribute__((__unused__));
-  dummy_last_ref = dummy_cfd_->UnrefAndTryDelete();
+  dummy_last_ref = dummy_cfd_->Unref();
   assert(dummy_last_ref);
+  delete dummy_cfd_;
 }
 
 ColumnFamilyData* ColumnFamilySet::GetDefault() const {
@@ -1478,7 +1276,7 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
   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_);
+      *db_options_, env_options_, this);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   max_column_family_ = std::max(max_column_family_, id);
@@ -1560,4 +1358,4 @@ const Comparator* GetColumnFamilyUserComparator(
   return nullptr;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/column_family.h

@@ -24,10 +24,9 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
-#include "trace_replay/block_cache_tracer.h"
 #include "util/thread_local.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class Version;
 class VersionSet;
@@ -46,112 +45,6 @@ class InstrumentedMutexLock;
 struct SuperVersionContext;
 
 extern const double kIncSlowdownRatio;
-// This file contains a list of data structures for managing column family
-// level metadata.
-//
-// The basic relationships among classes declared here are illustrated as
-// following:
-//
-//       +----------------------+    +----------------------+   +--------+
-//   +---+ ColumnFamilyHandle 1 | +--+ ColumnFamilyHandle 2 |   | DBImpl |
-//   |   +----------------------+ |  +----------------------+   +----+---+
-//   | +--------------------------+                                  |
-//   | |                               +-----------------------------+
-//   | |                               |
-//   | | +-----------------------------v-------------------------------+
-//   | | |                                                             |
-//   | | |                      ColumnFamilySet                        |
-//   | | |                                                             |
-//   | | +-------------+--------------------------+----------------+---+
-//   | |               |                          |                |
-//   | +-------------------------------------+    |                |
-//   |                 |                     |    |                v
-//   |   +-------------v-------------+ +-----v----v---------+
-//   |   |                           | |                    |
-//   |   |     ColumnFamilyData 1    | | ColumnFamilyData 2 |    ......
-//   |   |                           | |                    |
-//   +--->                           | |                    |
-//       |                 +---------+ |                    |
-//       |                 | MemTable| |                    |
-//       |                 |  List   | |                    |
-//       +--------+---+--+-+----+----+ +--------------------++
-//                |   |  |      |
-//                |   |  |      |
-//                |   |  |      +-----------------------+
-//                |   |  +-----------+                  |
-//                v   +--------+     |                  |
-//       +--------+--------+   |     |                  |
-//       |                 |   |     |       +----------v----------+
-// +---> |SuperVersion 1.a +----------------->                     |
-//       |                 +------+  |       | MemTableListVersion |
-//       +---+-------------+   |  |  |       |                     |
-//           |                 |  |  |       +----+------------+---+
-//           |      current    |  |  |            |            |
-//           |   +-------------+  |  |mem         |            |
-//           |   |                |  |            |            |
-//         +-v---v-------+    +---v--v---+  +-----v----+  +----v-----+
-//         |             |    |          |  |          |  |          |
-//         | Version 1.a |    | memtable |  | memtable |  | memtable |
-//         |             |    |   1.a    |  |   1.b    |  |   1.c    |
-//         +-------------+    |          |  |          |  |          |
-//                            +----------+  +----------+  +----------+
-//
-// DBImpl keeps a ColumnFamilySet, which references to all column families by
-// pointing to respective ColumnFamilyData object of each column family.
-// This is how DBImpl can list and operate on all the column families.
-// ColumnFamilyHandle also points to ColumnFamilyData directly, so that
-// when a user executes a query, it can directly find memtables and Version
-// as well as SuperVersion to the column family, without going through
-// ColumnFamilySet.
-//
-// ColumnFamilySet points to the latest view of the LSM-tree (list of memtables
-// and SST files) indirectly, while ongoing operations may hold references
-// to a current or an out-of-date SuperVersion, which in turn points to a
-// point-in-time view of the LSM-tree. This guarantees the memtables and SST
-// files being operated on will not go away, until the SuperVersion is
-// unreferenced to 0 and destoryed.
-//
-// The following graph illustrates a possible referencing relationships:
-//
-// Column       +--------------+      current       +-----------+
-// Family +---->+              +------------------->+           |
-//  Data        | SuperVersion +----------+         | Version A |
-//              |      3       |   imm    |         |           |
-// Iter2 +----->+              |  +-------v------+  +-----------+
-//              +-----+--------+  | MemtableList +----------------> Empty
-//                    |           |   Version r  |  +-----------+
-//                    |           +--------------+  |           |
-//                    +------------------+   current| Version B |
-//              +--------------+         |   +----->+           |
-//              |              |         |   |      +-----+-----+
-// Compaction +>+ SuperVersion +-------------+            ^
-//    Job       |      2       +------+  |                |current
-//              |              +----+ |  |     mem        |    +------------+
-//              +--------------+    | |  +--------------------->            |
-//                                  | +------------------------> MemTable a |
-//                                  |          mem        |    |            |
-//              +--------------+    |                     |    +------------+
-//              |              +--------------------------+
-//  Iter1 +-----> SuperVersion |    |                          +------------+
-//              |      1       +------------------------------>+            |
-//              |              +-+  |        mem               | MemTable b |
-//              +--------------+ |  |                          |            |
-//                               |  |    +--------------+      +-----^------+
-//                               |  |imm | MemtableList |            |
-//                               |  +--->+   Version s  +------------+
-//                               |       +--------------+
-//                               |       +--------------+
-//                               |       | MemtableList |
-//                               +------>+   Version t  +-------->  Empty
-//                                 imm   +--------------+
-//
-// In this example, even if the current LSM-tree consists of Version A and
-// memtable a, which is also referenced by SuperVersion, two older SuperVersion
-// SuperVersion2 and Superversion1 still exist, and are referenced by a
-// compaction job and an old iterator Iter1, respectively. SuperVersion2
-// contains Version B, memtable a and memtable b; SuperVersion1 contains
-// Version B and memtable b (mutable). As a result, Version B and memtable b
-// are prevented from being destroyed or deleted.
 
 // ColumnFamilyHandleImpl is the class that clients use to access different
 // column families. It has non-trivial destructor, which gets called when client
@@ -198,7 +91,6 @@ class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
 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;
   MemTable* mem;
   MemTableListVersion* imm;
   Version* current;
@@ -222,8 +114,8 @@ 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);
+  void Init(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
@@ -276,7 +168,7 @@ class ColumnFamilyData {
   // Ref() can only be called from a context where the caller can guarantee
   // that ColumnFamilyData is alive (while holding a non-zero ref already,
   // holding a DB mutex, or as the leader in a write batch group).
-  void Ref() { refs_.fetch_add(1); }
+  void Ref() { refs_.fetch_add(1, std::memory_order_relaxed); }
 
   // Unref decreases the reference count, but does not handle deletion
   // when the count goes to 0.  If this method returns true then the
@@ -284,16 +176,11 @@ class ColumnFamilyData {
   // FreeDeadColumnFamilies().  Unref() can only be called while holding
   // a DB mutex, or during single-threaded recovery.
   bool Unref() {
-    int old_refs = refs_.fetch_sub(1);
+    int old_refs = refs_.fetch_sub(1, std::memory_order_relaxed);
     assert(old_refs > 0);
     return old_refs == 1;
   }
 
-  // UnrefAndTryDelete() decreases the reference count and do free if needed,
-  // return true if this is freed else false, UnrefAndTryDelete() can only
-  // be called while holding a DB mutex, or during single-threaded recovery.
-  bool UnrefAndTryDelete();
-
   // SetDropped() can only be called under following conditions:
   // 1) Holding a DB mutex,
   // 2) from single-threaded write thread, AND
@@ -324,7 +211,7 @@ class ColumnFamilyData {
   }
   FlushReason GetFlushReason() const { return flush_reason_; }
   // thread-safe
-  const FileOptions* soptions() const;
+  const EnvOptions* soptions() const;
   const ImmutableCFOptions* ioptions() const { return &ioptions_; }
   // REQUIRES: DB mutex held
   // This returns the MutableCFOptions used by current SuperVersion
@@ -345,13 +232,9 @@ class ColumnFamilyData {
 
   bool is_delete_range_supported() { return is_delete_range_supported_; }
 
-  // Validate CF options against DB options
-  static Status ValidateOptions(const DBOptions& db_options,
-                                const ColumnFamilyOptions& cf_options);
 #ifndef ROCKSDB_LITE
   // REQUIRES: DB mutex held
   Status SetOptions(
-      const DBOptions& db_options,
       const std::unordered_map<std::string, std::string>& options_map);
 #endif  // ROCKSDB_LITE
 
@@ -413,10 +296,9 @@ class ColumnFamilyData {
   // REQUIRES: DB mutex held
   Compaction* CompactRange(const MutableCFOptions& mutable_cf_options,
                            int input_level, int output_level,
-                           const CompactRangeOptions& compact_range_options,
+                           uint32_t output_path_id, uint32_t max_subcompactions,
                            const InternalKey* begin, const InternalKey* end,
-                           InternalKey** compaction_end, bool* manual_conflict,
-                           uint64_t max_file_num_to_ignore);
+                           InternalKey** compaction_end, bool* manual_conflict);
 
   CompactionPicker* compaction_picker() { return compaction_picker_.get(); }
   // thread-safe
@@ -436,11 +318,11 @@ class ColumnFamilyData {
   SuperVersion* GetSuperVersion() { return super_version_; }
   // thread-safe
   // Return a already referenced SuperVersion to be used safely.
-  SuperVersion* GetReferencedSuperVersion(DBImpl* db);
+  SuperVersion* GetReferencedSuperVersion(InstrumentedMutex* db_mutex);
   // thread-safe
   // Get SuperVersion stored in thread local storage. If it does not exist,
   // get a reference from a current SuperVersion.
-  SuperVersion* GetThreadLocalSuperVersion(DBImpl* db);
+  SuperVersion* GetThreadLocalSuperVersion(InstrumentedMutex* db_mutex);
   // Try to return SuperVersion back to thread local storage. Retrun true on
   // success and false on failure. It fails when the thread local storage
   // contains anything other than SuperVersion::kSVInUse flag.
@@ -497,28 +379,21 @@ class ColumnFamilyData {
 
   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(
-      std::map<std::string, std::shared_ptr<FSDirectory>>* created_dirs);
+  Status AddDirectories();
 
-  FSDirectory* GetDataDir(size_t path_id) const;
+  Directory* GetDataDir(size_t path_id) const;
 
   ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
 
  private:
   friend class ColumnFamilySet;
-  static const uint32_t kDummyColumnFamilyDataId;
   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);
-
-  std::vector<std::string> GetDbPaths() const;
+                   const EnvOptions& env_options,
+                   ColumnFamilySet* column_family_set);
 
   uint32_t id_;
   const std::string name_;
@@ -595,9 +470,7 @@ class ColumnFamilyData {
   std::atomic<uint64_t> last_memtable_id_;
 
   // Directories corresponding to cf_paths.
-  std::vector<std::shared_ptr<FSDirectory>> data_dirs_;
-
-  bool db_paths_registered_;
+  std::vector<std::unique_ptr<Directory>> data_dirs_;
 };
 
 // ColumnFamilySet has interesting thread-safety requirements
@@ -646,10 +519,9 @@ class ColumnFamilySet {
 
   ColumnFamilySet(const std::string& dbname,
                   const ImmutableDBOptions* db_options,
-                  const FileOptions& file_options, Cache* table_cache,
+                  const EnvOptions& env_options, Cache* table_cache,
                   WriteBufferManager* write_buffer_manager,
-                  WriteController* write_controller,
-                  BlockCacheTracer* const block_cache_tracer);
+                  WriteController* write_controller);
   ~ColumnFamilySet();
 
   ColumnFamilyData* GetDefault() const;
@@ -704,11 +576,10 @@ class ColumnFamilySet {
 
   const std::string db_name_;
   const ImmutableDBOptions* const db_options_;
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
   Cache* table_cache_;
   WriteBufferManager* write_buffer_manager_;
   WriteController* write_controller_;
-  BlockCacheTracer* const block_cache_tracer_;
 };
 
 // We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access
@@ -759,4 +630,4 @@ extern uint32_t GetColumnFamilyID(ColumnFamilyHandle* column_family);
 extern const Comparator* GetColumnFamilyUserComparator(
     ColumnFamilyHandle* column_family);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/column_family_test.cc

@@ -12,25 +12,22 @@
 #include <string>
 #include <thread>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/db_test_util.h"
-#include "memtable/hash_skiplist_rep.h"
 #include "options/options_parser.h"
 #include "port/port.h"
-#include "port/stack_trace.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
-#include "rocksdb/utilities/object_registry.h"
-#include "test_util/fault_injection_test_env.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/coding.h"
+#include "util/fault_injection_test_env.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 static const int kValueSize = 1000;
 
@@ -62,20 +59,8 @@ class EnvCounter : public EnvWrapper {
 
 class ColumnFamilyTestBase : public testing::Test {
  public:
-  explicit ColumnFamilyTestBase(uint32_t format) : rnd_(139), format_(format) {
-    Env* base_env = Env::Default();
-#ifndef ROCKSDB_LITE
-    const char* test_env_uri = getenv("TEST_ENV_URI");
-    if (test_env_uri) {
-      Env* test_env = nullptr;
-      Status s = Env::LoadEnv(test_env_uri, &test_env, &env_guard_);
-      base_env = test_env;
-      EXPECT_OK(s);
-      EXPECT_NE(Env::Default(), base_env);
-    }
-#endif  // !ROCKSDB_LITE
-    EXPECT_NE(nullptr, base_env);
-    env_ = new EnvCounter(base_env);
+  ColumnFamilyTestBase(uint32_t format) : rnd_(139), format_(format) {
+    env_ = new EnvCounter(Env::Default());
     dbname_ = test::PerThreadDBPath("column_family_test");
     db_options_.create_if_missing = true;
     db_options_.fail_if_options_file_error = true;
@@ -83,7 +68,7 @@ class ColumnFamilyTestBase : public testing::Test {
     DestroyDB(dbname_, Options(db_options_, column_family_options_));
   }
 
-  ~ColumnFamilyTestBase() override {
+  virtual ~ColumnFamilyTestBase() {
     std::vector<ColumnFamilyDescriptor> column_families;
     for (auto h : handles_) {
       ColumnFamilyDescriptor cfdescriptor;
@@ -91,7 +76,7 @@ class ColumnFamilyTestBase : public testing::Test {
       column_families.push_back(cfdescriptor);
     }
     Close();
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
     Destroy(column_families);
     delete env_;
   }
@@ -546,7 +531,6 @@ class ColumnFamilyTestBase : public testing::Test {
   std::string dbname_;
   DB* db_ = nullptr;
   EnvCounter* env_;
-  std::shared_ptr<Env> env_guard_;
   Random rnd_;
   uint32_t format_;
 };
@@ -595,15 +579,14 @@ TEST_P(ColumnFamilyTest, DontReuseColumnFamilyID) {
 TEST_P(ColumnFamilyTest, CreateCFRaceWithGetAggProperty) {
   Open();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"DBImpl::WriteOptionsFile:1",
         "ColumnFamilyTest.CreateCFRaceWithGetAggProperty:1"},
        {"ColumnFamilyTest.CreateCFRaceWithGetAggProperty:2",
         "DBImpl::WriteOptionsFile:2"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  ROCKSDB_NAMESPACE::port::Thread thread(
-      [&] { CreateColumnFamilies({"one"}); });
+  rocksdb::port::Thread thread([&] { CreateColumnFamilies({"one"}); });
 
   TEST_SYNC_POINT("ColumnFamilyTest.CreateCFRaceWithGetAggProperty:1");
   uint64_t pv;
@@ -612,7 +595,7 @@ TEST_P(ColumnFamilyTest, CreateCFRaceWithGetAggProperty) {
 
   thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -821,7 +804,7 @@ TEST_P(ColumnFamilyTest, BulkAddDrop) {
 }
 
 TEST_P(ColumnFamilyTest, DropTest) {
-  // first iteration - don't reopen DB before dropping
+  // first iteration - dont reopen DB before dropping
   // second iteration - reopen DB before dropping
   for (int iter = 0; iter < 2; ++iter) {
     Open({"default"});
@@ -1133,25 +1116,22 @@ TEST_P(ColumnFamilyTest, DifferentWriteBufferSizes) {
   default_cf.arena_block_size = 4 * 4096;
   default_cf.max_write_buffer_number = 10;
   default_cf.min_write_buffer_number_to_merge = 1;
-  default_cf.max_write_buffer_size_to_maintain = 0;
+  default_cf.max_write_buffer_number_to_maintain = 0;
   one.write_buffer_size = 200000;
   one.arena_block_size = 4 * 4096;
   one.max_write_buffer_number = 10;
   one.min_write_buffer_number_to_merge = 2;
-  one.max_write_buffer_size_to_maintain =
-      static_cast<int>(one.write_buffer_size);
+  one.max_write_buffer_number_to_maintain = 1;
   two.write_buffer_size = 1000000;
   two.arena_block_size = 4 * 4096;
   two.max_write_buffer_number = 10;
   two.min_write_buffer_number_to_merge = 3;
-  two.max_write_buffer_size_to_maintain =
-      static_cast<int>(two.write_buffer_size);
+  two.max_write_buffer_number_to_maintain = 2;
   three.write_buffer_size = 4096 * 22;
   three.arena_block_size = 4096;
   three.max_write_buffer_number = 10;
   three.min_write_buffer_number_to_merge = 4;
-  three.max_write_buffer_size_to_maintain =
-      static_cast<int>(three.write_buffer_size);
+  three.max_write_buffer_number_to_maintain = -1;
 
   Reopen({default_cf, one, two, three});
 
@@ -1226,42 +1206,38 @@ TEST_P(ColumnFamilyTest, DifferentWriteBufferSizes) {
 }
 #endif  // !ROCKSDB_LITE
 
-// The test is commented out because we want to test that snapshot is
-// not created for memtables not supported it, but There isn't a memtable
-// that doesn't support snapshot right now. If we have one later, we can
-// re-enable the test.
-//
-// #ifndef ROCKSDB_LITE  // Cuckoo is not supported in lite
-//   TEST_P(ColumnFamilyTest, MemtableNotSupportSnapshot) {
-//   db_options_.allow_concurrent_memtable_write = false;
-//   Open();
-//   auto* s1 = dbfull()->GetSnapshot();
-//   ASSERT_TRUE(s1 != nullptr);
-//   dbfull()->ReleaseSnapshot(s1);
+#ifndef ROCKSDB_LITE  // Cuckoo is not supported in lite
+TEST_P(ColumnFamilyTest, MemtableNotSupportSnapshot) {
+  db_options_.allow_concurrent_memtable_write = false;
+  Open();
+  auto* s1 = dbfull()->GetSnapshot();
+  ASSERT_TRUE(s1 != nullptr);
+  dbfull()->ReleaseSnapshot(s1);
 
-//   // Add a column family that doesn't support snapshot
-//   ColumnFamilyOptions first;
-//   first.memtable_factory.reset(new DummyMemtableNotSupportingSnapshot());
-//   CreateColumnFamilies({"first"}, {first});
-//   auto* s2 = dbfull()->GetSnapshot();
-//   ASSERT_TRUE(s2 == nullptr);
+  // Add a column family that doesn't support snapshot
+  ColumnFamilyOptions first;
+  first.memtable_factory.reset(NewHashCuckooRepFactory(1024 * 1024));
+  CreateColumnFamilies({"first"}, {first});
+  auto* s2 = dbfull()->GetSnapshot();
+  ASSERT_TRUE(s2 == nullptr);
 
-//   // Add a column family that supports snapshot. Snapshot stays not
-//   supported. ColumnFamilyOptions second; CreateColumnFamilies({"second"},
-//   {second}); auto* s3 = dbfull()->GetSnapshot(); ASSERT_TRUE(s3 == nullptr);
-//   Close();
-// }
-// #endif  // !ROCKSDB_LITE
+  // Add a column family that supports snapshot. Snapshot stays not supported.
+  ColumnFamilyOptions second;
+  CreateColumnFamilies({"second"}, {second});
+  auto* s3 = dbfull()->GetSnapshot();
+  ASSERT_TRUE(s3 == nullptr);
+  Close();
+}
+#endif  // !ROCKSDB_LITE
 
 class TestComparator : public Comparator {
-  int Compare(const ROCKSDB_NAMESPACE::Slice& /*a*/,
-              const ROCKSDB_NAMESPACE::Slice& /*b*/) const override {
+  int Compare(const rocksdb::Slice& /*a*/,
+              const rocksdb::Slice& /*b*/) const override {
     return 0;
   }
   const char* Name() const override { return "Test"; }
-  void FindShortestSeparator(
-      std::string* /*start*/,
-      const ROCKSDB_NAMESPACE::Slice& /*limit*/) const override {}
+  void FindShortestSeparator(std::string* /*start*/,
+                             const rocksdb::Slice& /*limit*/) const override {}
   void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 
@@ -1429,11 +1405,11 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
     AssertFilesPerLevel(ToString(i + 1), 1);
   }
   bool cf_1_1 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::MultiManual:4", "ColumnFamilyTest::MultiManual:1"},
        {"ColumnFamilyTest::MultiManual:2", "ColumnFamilyTest::MultiManual:5"},
        {"ColumnFamilyTest::MultiManual:2", "ColumnFamilyTest::MultiManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::MultiManual:4");
@@ -1442,7 +1418,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   std::vector<port::Thread> threads;
   threads.emplace_back([&] {
     CompactRangeOptions compact_options;
@@ -1485,8 +1461,8 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
   Close();
 }
 
@@ -1525,11 +1501,11 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
       dbfull()->TEST_write_controler().GetCompactionPressureToken();
 
   bool cf_1_1 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:1"},
        {"ColumnFamilyTest::AutoManual:2", "ColumnFamilyTest::AutoManual:5"},
        {"ColumnFamilyTest::AutoManual:2", "ColumnFamilyTest::AutoManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           cf_1_1 = false;
@@ -1537,7 +1513,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
           TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:3");
         }
       });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   // SETUP column family "one" -- universal style
   for (int i = 0; i < one.level0_file_num_compaction_trigger; ++i) {
     PutRandomData(1, 10, 12000, true);
@@ -1555,7 +1531,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
     WaitForFlush(2);
     AssertFilesPerLevel(ToString(i + 1), 2);
   }
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1582,8 +1558,8 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
@@ -1629,11 +1605,11 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:1"},
        {"ColumnFamilyTest::ManualAuto:5", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:2", "ColumnFamilyTest::ManualAuto:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
@@ -1645,8 +1621,8 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1681,8 +1657,8 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
@@ -1723,13 +1699,13 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualManual:4", "ColumnFamilyTest::ManualManual:2"},
        {"ColumnFamilyTest::ManualManual:4", "ColumnFamilyTest::ManualManual:5"},
        {"ColumnFamilyTest::ManualManual:1", "ColumnFamilyTest::ManualManual:2"},
        {"ColumnFamilyTest::ManualManual:1",
         "ColumnFamilyTest::ManualManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualManual:4");
@@ -1741,8 +1717,8 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = true;
     ASSERT_OK(
@@ -1762,7 +1738,7 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
                         1);
   }
 
-  ROCKSDB_NAMESPACE::port::Thread threads1([&] {
+  rocksdb::port::Thread threads1([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1783,8 +1759,8 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
@@ -1825,12 +1801,12 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:5"},
        {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
@@ -1842,8 +1818,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1876,8 +1852,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
@@ -1918,14 +1894,14 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:5"},
        {"ColumnFamilyTest::ManualAuto:3", "ColumnFamilyTest::ManualAuto:2"},
        {"LevelCompactionPicker::PickCompactionBySize:0",
         "ColumnFamilyTest::ManualAuto:3"},
        {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
@@ -1937,8 +1913,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1969,8 +1945,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 // In this test, we generate enough files to trigger automatic compactions.
@@ -2010,12 +1986,12 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
 
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:2"},
        {"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:5"},
        {"CompactionPicker::CompactRange:Conflict",
         "ColumnFamilyTest::AutoManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:4");
@@ -2027,7 +2003,7 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // SETUP column family "one" -- universal style
   for (int i = 0; i < one.level0_file_num_compaction_trigger; ++i) {
@@ -2061,8 +2037,8 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -2367,45 +2343,6 @@ TEST_P(ColumnFamilyTest, ReadDroppedColumnFamily) {
   }
 }
 
-TEST_P(ColumnFamilyTest, LiveIteratorWithDroppedColumnFamily) {
-  db_options_.create_missing_column_families = true;
-  db_options_.max_open_files = 20;
-  // delete obsolete files always
-  db_options_.delete_obsolete_files_period_micros = 0;
-  Open({"default", "one", "two"});
-  ColumnFamilyOptions options;
-  options.level0_file_num_compaction_trigger = 100;
-  options.level0_slowdown_writes_trigger = 200;
-  options.level0_stop_writes_trigger = 200;
-  options.write_buffer_size = 100000;  // small write buffer size
-  Reopen({options, options, options});
-
-  // 1MB should create ~10 files for each CF
-  int kKeysNum = 10000;
-  PutRandomData(1, kKeysNum, 100);
-
-  {
-    std::unique_ptr<Iterator> iterator(
-        db_->NewIterator(ReadOptions(), handles_[1]));
-    iterator->SeekToFirst();
-
-    DropColumnFamilies({1});
-
-    // Make sure iterator created can still be used.
-    int count = 0;
-    for (; iterator->Valid(); iterator->Next()) {
-      ASSERT_OK(iterator->status());
-      ++count;
-    }
-    ASSERT_OK(iterator->status());
-    ASSERT_EQ(count, kKeysNum);
-  }
-
-  Reopen();
-  Close();
-  Destroy();
-}
-
 TEST_P(ColumnFamilyTest, FlushAndDropRaceCondition) {
   db_options_.create_missing_column_families = true;
   Open({"default", "one"});
@@ -2417,7 +2354,7 @@ TEST_P(ColumnFamilyTest, FlushAndDropRaceCondition) {
   options.write_buffer_size = 100000;  // small write buffer size
   Reopen({options, options});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"VersionSet::LogAndApply::ColumnFamilyDrop:0",
         "FlushJob::WriteLevel0Table"},
        {"VersionSet::LogAndApply::ColumnFamilyDrop:1",
@@ -2425,7 +2362,7 @@ TEST_P(ColumnFamilyTest, FlushAndDropRaceCondition) {
        {"FlushJob::InstallResults",
         "VersionSet::LogAndApply::ColumnFamilyDrop:2"}});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   test::SleepingBackgroundTask sleeping_task;
 
   env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask, &sleeping_task,
@@ -2504,21 +2441,21 @@ TEST_P(ColumnFamilyTest, CreateAndDropRace) {
 
   auto main_thread_id = std::this_thread::get_id();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "PersistRocksDBOptions:start", [&](void* /*arg*/) {
-        auto current_thread_id = std::this_thread::get_id();
-        // If it's the main thread hitting this sync-point, then it
-        // will be blocked until some other thread update the test_stage.
-        if (main_thread_id == current_thread_id) {
-          test_stage = kMainThreadStartPersistingOptionsFile;
-          while (test_stage < kChildThreadFinishDroppingColumnFamily &&
-                 !ordered_by_writethread) {
-            Env::Default()->SleepForMicroseconds(100);
-          }
-        }
-      });
+  rocksdb::SyncPoint::GetInstance()->SetCallBack("PersistRocksDBOptions:start",
+                                                 [&](void* /*arg*/) {
+    auto current_thread_id = std::this_thread::get_id();
+    // If it's the main thread hitting this sync-point, then it
+    // will be blocked until some other thread update the test_stage.
+    if (main_thread_id == current_thread_id) {
+      test_stage = kMainThreadStartPersistingOptionsFile;
+      while (test_stage < kChildThreadFinishDroppingColumnFamily &&
+             !ordered_by_writethread) {
+        Env::Default()->SleepForMicroseconds(100);
+      }
+    }
+  });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "WriteThread::EnterUnbatched:Wait", [&](void* /*arg*/) {
         // This means a thread doing DropColumnFamily() is waiting for
         // other thread to finish persisting options.
@@ -2530,12 +2467,12 @@ TEST_P(ColumnFamilyTest, CreateAndDropRace) {
   Open({"default", "one", "two", "three"},
        {cf_opts[0], cf_opts[1], cf_opts[2], cf_opts[3]});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // Start a thread that will drop the first column family
   // and its comparator
-  ROCKSDB_NAMESPACE::port::Thread drop_cf_thread(DropSingleColumnFamily, this,
-                                                 1, &comparators);
+  rocksdb::port::Thread drop_cf_thread(DropSingleColumnFamily, this, 1,
+                                       &comparators);
 
   DropColumnFamilies({2});
 
@@ -2548,8 +2485,8 @@ TEST_P(ColumnFamilyTest, CreateAndDropRace) {
     }
   }
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -2984,10 +2921,10 @@ TEST_P(ColumnFamilyTest, FlushCloseWALFiles) {
   ASSERT_OK(Put(0, "fodor", "mirko"));
   ASSERT_OK(Put(1, "fodor", "mirko"));
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"DBImpl::BGWorkFlush:done", "FlushCloseWALFiles:0"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // Block flush jobs from running
   test::SleepingBackgroundTask sleeping_task;
@@ -3003,7 +2940,7 @@ TEST_P(ColumnFamilyTest, FlushCloseWALFiles) {
   sleeping_task.WakeUp();
   sleeping_task.WaitUntilDone();
   TEST_SYNC_POINT("FlushCloseWALFiles:0");
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   ASSERT_EQ(1, env.num_open_wal_file_.load());
 
   Reopen();
@@ -3081,14 +3018,14 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile2) {
   ASSERT_OK(Put(0, "fodor", "mirko"));
   ASSERT_OK(Put(1, "fodor", "mirko"));
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"ColumnFamilyTest::IteratorCloseWALFile2:0",
        "DBImpl::BGWorkPurge:start"},
       {"ColumnFamilyTest::IteratorCloseWALFile2:2",
        "DBImpl::BackgroundCallFlush:start"},
       {"DBImpl::BGWorkPurge:end", "ColumnFamilyTest::IteratorCloseWALFile2:1"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   WriteOptions wo;
   wo.sync = true;
@@ -3106,7 +3043,7 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile2) {
   TEST_SYNC_POINT("ColumnFamilyTest::IteratorCloseWALFile2:2");
   WaitForFlush(1);
   ASSERT_EQ(1, env.num_open_wal_file_.load());
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   Reopen();
   ASSERT_EQ("mirko", Get(0, "fodor"));
@@ -3150,14 +3087,14 @@ TEST_P(ColumnFamilyTest, ForwardIteratorCloseWALFile) {
   ASSERT_OK(Put(0, "fodor", "mirko"));
   ASSERT_OK(Put(1, "fodor", "mirko"));
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"ColumnFamilyTest::IteratorCloseWALFile2:0",
        "DBImpl::BGWorkPurge:start"},
       {"ColumnFamilyTest::IteratorCloseWALFile2:2",
        "DBImpl::BackgroundCallFlush:start"},
       {"DBImpl::BGWorkPurge:end", "ColumnFamilyTest::IteratorCloseWALFile2:1"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   WriteOptions wo;
   wo.sync = true;
@@ -3181,7 +3118,7 @@ TEST_P(ColumnFamilyTest, ForwardIteratorCloseWALFile) {
   ASSERT_EQ(1, env.delete_count_.load());
 
   delete it;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   Reopen();
   ASSERT_EQ("mirko", Get(0, "fodor"));
@@ -3201,15 +3138,15 @@ TEST_P(ColumnFamilyTest, LogSyncConflictFlush) {
   Put(0, "", "");
   Put(1, "foo", "bar");
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"DBImpl::SyncWAL:BeforeMarkLogsSynced:1",
         "ColumnFamilyTest::LogSyncConflictFlush:1"},
        {"ColumnFamilyTest::LogSyncConflictFlush:2",
         "DBImpl::SyncWAL:BeforeMarkLogsSynced:2"}});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  ROCKSDB_NAMESPACE::port::Thread thread([&] { db_->SyncWAL(); });
+  rocksdb::port::Thread thread([&] { db_->SyncWAL(); });
 
   TEST_SYNC_POINT("ColumnFamilyTest::LogSyncConflictFlush:1");
   Flush(1);
@@ -3220,7 +3157,7 @@ TEST_P(ColumnFamilyTest, LogSyncConflictFlush) {
 
   thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   Close();
 }
 #endif
@@ -3369,19 +3306,9 @@ TEST_P(ColumnFamilyTest, MultipleCFPathsTest) {
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
-
-#ifdef ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
-extern "C" {
-void RegisterCustomObjects(int argc, char** argv);
-}
-#else
-void RegisterCustomObjects(int /*argc*/, char** /*argv*/) {}
-#endif  // !ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
-  RegisterCustomObjects(argc, argv);
   return RUN_ALL_TESTS();
 }

db/compact_files_test.cc

@@ -10,15 +10,15 @@
 #include <thread>
 #include <vector>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CompactFilesTest : public testing::Test {
  public:
@@ -35,9 +35,9 @@ class CompactFilesTest : public testing::Test {
 class FlushedFileCollector : public EventListener {
  public:
   FlushedFileCollector() {}
-  ~FlushedFileCollector() override {}
+  ~FlushedFileCollector() {}
 
-  void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
+  virtual void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
     std::lock_guard<std::mutex> lock(mutex_);
     flushed_files_.push_back(info.file_path);
   }
@@ -81,11 +81,11 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
   assert(s.ok());
   assert(db);
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"CompactFilesImpl:0", "BackgroundCallCompaction:0"},
       {"BackgroundCallCompaction:1", "CompactFilesImpl:1"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // create couple files
   // Background compaction starts and waits in BackgroundCallCompaction:0
@@ -95,7 +95,7 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
     db->Flush(FlushOptions());
   }
 
-  ROCKSDB_NAMESPACE::ColumnFamilyMetaData meta;
+  rocksdb::ColumnFamilyMetaData meta;
   db->GetColumnFamilyMetaData(&meta);
   std::string file1;
   for (auto& file : meta.levels[0].files) {
@@ -108,12 +108,12 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
       // The background compaction then notices that there is an L0 compaction
       // already in progress and doesn't do an L0 compaction
       // Once the background compaction finishes, the compact files finishes
-      ASSERT_OK(db->CompactFiles(ROCKSDB_NAMESPACE::CompactionOptions(),
-                                 {file1, file2}, 0));
+      ASSERT_OK(
+          db->CompactFiles(rocksdb::CompactionOptions(), {file1, file2}, 0));
       break;
     }
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   delete db;
 }
 
@@ -224,14 +224,14 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
   auto l0_files = collector->GetFlushedFiles();
   EXPECT_EQ(5, l0_files.size());
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"CompactFilesImpl:2", "CompactFilesTest.CapturingPendingFiles:0"},
       {"CompactFilesTest.CapturingPendingFiles:1", "CompactFilesImpl:3"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // Start compacting files.
-  ROCKSDB_NAMESPACE::port::Thread compaction_thread(
+  rocksdb::port::Thread compaction_thread(
       [&] { EXPECT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1)); });
 
   // In the meantime flush another file.
@@ -242,7 +242,7 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
 
   compaction_thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   delete db;
 
@@ -256,9 +256,9 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
 TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   class FilterWithGet : public CompactionFilter {
    public:
-    bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-                std::string* /*new_value*/,
-                bool* /*value_changed*/) const override {
+    virtual bool Filter(int /*level*/, const Slice& /*key*/,
+                        const Slice& /*value*/, std::string* /*new_value*/,
+                        bool* /*value_changed*/) const override {
       if (db_ == nullptr) {
         return true;
       }
@@ -271,7 +271,7 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
       db_ = db;
     }
 
-    const char* Name() const override { return "FilterWithGet"; }
+    virtual const char* Name() const override { return "FilterWithGet"; }
 
    private:
     DB* db_;
@@ -296,12 +296,12 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   db->Flush(FlushOptions());
 
   // Compact all L0 files using CompactFiles
-  ROCKSDB_NAMESPACE::ColumnFamilyMetaData meta;
+  rocksdb::ColumnFamilyMetaData meta;
   db->GetColumnFamilyMetaData(&meta);
   for (auto& file : meta.levels[0].files) {
     std::string fname = file.db_path + "/" + file.name;
     ASSERT_OK(
-        db->CompactFiles(ROCKSDB_NAMESPACE::CompactionOptions(), {fname}, 0));
+        db->CompactFiles(rocksdb::CompactionOptions(), {fname}, 0));
   }
 
 
@@ -347,7 +347,7 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
     compaction_opts.compression = CompressionType::kDisableCompressionOption;
     ASSERT_OK(db->CompactFiles(compaction_opts, l0_files, 1));
 
-    ROCKSDB_NAMESPACE::TablePropertiesCollection all_tables_props;
+    rocksdb::TablePropertiesCollection all_tables_props;
     ASSERT_OK(db->GetPropertiesOfAllTables(&all_tables_props));
     for (const auto& name_and_table_props : all_tables_props) {
       ASSERT_EQ(CompressionTypeToString(CompressionType::kZlibCompression),
@@ -387,7 +387,7 @@ TEST_F(CompactFilesTest, GetCompactionJobInfo) {
   auto l0_files_1 = collector->GetFlushedFiles();
   CompactionOptions co;
   co.compression = CompressionType::kLZ4Compression;
-  CompactionJobInfo compaction_job_info{};
+  CompactionJobInfo compaction_job_info;
   ASSERT_OK(
       db->CompactFiles(co, l0_files_1, 0, -1, nullptr, &compaction_job_info));
   ASSERT_EQ(compaction_job_info.base_input_level, 0);
@@ -402,7 +402,7 @@ TEST_F(CompactFilesTest, GetCompactionJobInfo) {
   delete db;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compacted_db_impl.cc

@@ -5,11 +5,11 @@
 
 #ifndef ROCKSDB_LITE
 #include "db/compacted_db_impl.h"
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/version_set.h"
 #include "table/get_context.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 extern void MarkKeyMayExist(void* arg);
 extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
@@ -37,7 +37,7 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                             const Slice& key, PinnableSlice* value) {
   GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                          GetContext::kNotFound, key, value, nullptr, nullptr,
-                         nullptr, true, nullptr, nullptr);
+                         nullptr, nullptr);
   LookupKey lkey(key, kMaxSequenceNumber);
   files_.files[FindFile(key)].fd.table_reader->Get(options, lkey.internal_key(),
                                                    &get_context, nullptr);
@@ -70,7 +70,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
       std::string& value = (*values)[idx];
       GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                              GetContext::kNotFound, keys[idx], &pinnable_val,
-                             nullptr, nullptr, nullptr, true, nullptr, nullptr);
+                             nullptr, nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
       r->Get(options, lkey.internal_key(), &get_context, nullptr);
       value.assign(pinnable_val.data(), pinnable_val.size());
@@ -156,5 +156,5 @@ Status CompactedDBImpl::Open(const Options& options,
   return s;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}   // namespace rocksdb
 #endif  // ROCKSDB_LITE

db/compacted_db_impl.h

@@ -5,19 +5,15 @@
 
 #pragma once
 #ifndef ROCKSDB_LITE
-#include <string>
+#include "db/db_impl.h"
 #include <vector>
-#include "db/db_impl/db_impl.h"
+#include <string>
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CompactedDBImpl : public DBImpl {
  public:
   CompactedDBImpl(const DBOptions& options, const std::string& dbname);
-  // No copying allowed
-  CompactedDBImpl(const CompactedDBImpl&) = delete;
-  void operator=(const CompactedDBImpl&) = delete;
-
   virtual ~CompactedDBImpl();
 
   static Status Open(const Options& options, const std::string& dbname,
@@ -89,15 +85,6 @@ class CompactedDBImpl : public DBImpl {
       const IngestExternalFileOptions& /*ingestion_options*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  using DB::CreateColumnFamilyWithImport;
-  virtual Status CreateColumnFamilyWithImport(
-      const ColumnFamilyOptions& /*options*/,
-      const std::string& /*column_family_name*/,
-      const ImportColumnFamilyOptions& /*import_options*/,
-      const ExportImportFilesMetaData& /*metadata*/,
-      ColumnFamilyHandle** /*handle*/) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
 
  private:
   friend class DB;
@@ -108,6 +95,10 @@ class CompactedDBImpl : public DBImpl {
   Version* version_;
   const Comparator* user_comparator_;
   LevelFilesBrief files_;
+
+  // No copying allowed
+  CompactedDBImpl(const CompactedDBImpl&);
+  void operator=(const CompactedDBImpl&);
 };
-}  // namespace ROCKSDB_NAMESPACE
+}
 #endif  // ROCKSDB_LITE

db/compaction.cc

@@ -7,16 +7,21 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#include <cinttypes>
+#include "db/compaction.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <vector>
 
 #include "db/column_family.h"
-#include "db/compaction/compaction.h"
 #include "rocksdb/compaction_filter.h"
-#include "test_util/sync_point.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 const uint64_t kRangeTombstoneSentinel =
     PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
@@ -245,12 +250,6 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
   if (max_subcompactions_ == 0) {
     max_subcompactions_ = immutable_cf_options_.max_subcompactions;
   }
-  if (!bottommost_level_) {
-    // Currently we only enable dictionary compression during compaction to the
-    // bottommost level.
-    output_compression_opts_.max_dict_bytes = 0;
-    output_compression_opts_.zstd_max_train_bytes = 0;
-  }
 
 #ifndef NDEBUG
   for (size_t i = 1; i < inputs_.size(); ++i) {
@@ -275,7 +274,9 @@ Compaction::~Compaction() {
     input_version_->Unref();
   }
   if (cfd_ != nullptr) {
-    cfd_->UnrefAndTryDelete();
+    if (cfd_->Unref()) {
+      delete cfd_;
+    }
   }
 }
 
@@ -543,22 +544,21 @@ bool Compaction::ShouldFormSubcompactions() const {
   }
 }
 
-uint64_t Compaction::MinInputFileOldestAncesterTime() const {
-  uint64_t min_oldest_ancester_time = port::kMaxUint64;
-  for (const auto& level_files : inputs_) {
-    for (const auto& file : level_files.files) {
-      uint64_t oldest_ancester_time = file->TryGetOldestAncesterTime();
-      if (oldest_ancester_time != 0) {
-        min_oldest_ancester_time =
-            std::min(min_oldest_ancester_time, oldest_ancester_time);
-      }
+uint64_t Compaction::MaxInputFileCreationTime() const {
+  uint64_t max_creation_time = 0;
+  for (const auto& file : inputs_[0].files) {
+    if (file->fd.table_reader != nullptr &&
+        file->fd.table_reader->GetTableProperties() != nullptr) {
+      uint64_t creation_time =
+          file->fd.table_reader->GetTableProperties()->creation_time;
+      max_creation_time = std::max(max_creation_time, creation_time);
     }
   }
-  return min_oldest_ancester_time;
+  return max_creation_time;
 }
 
 int Compaction::GetInputBaseLevel() const {
   return input_vstorage_->base_level();
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction.h

@@ -9,13 +9,11 @@
 
 #pragma once
 #include "db/version_set.h"
-#include "memory/arena.h"
 #include "options/cf_options.h"
+#include "util/arena.h"
 #include "util/autovector.h"
 
-namespace ROCKSDB_NAMESPACE {
-// The file contains class Compaction, as well as some helper functions
-// and data structures used by the class.
+namespace rocksdb {
 
 // Utility for comparing sstable boundary keys. Returns -1 if either a or b is
 // null which provides the property that a==null indicates a key that is less
@@ -65,7 +63,7 @@ class ColumnFamilyData;
 class VersionStorageInfo;
 class CompactionFilter;
 
-// A Compaction encapsulates metadata about a compaction.
+// A Compaction encapsulates information about a compaction.
 class Compaction {
  public:
   Compaction(VersionStorageInfo* input_version,
@@ -291,7 +289,7 @@ class Compaction {
 
   uint32_t max_subcompactions() const { return max_subcompactions_; }
 
-  uint64_t MinInputFileOldestAncesterTime() const;
+  uint64_t MaxInputFileCreationTime() const;
 
  private:
   // mark (or clear) all files that are being compacted
@@ -378,7 +376,7 @@ class Compaction {
   CompactionReason compaction_reason_;
 };
 
-// Return sum of sizes of all files in `files`.
+// Utility function
 extern uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_picker_level.cc

@@ -1,558 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "db/compaction/compaction_picker_level.h"
-#include "logging/log_buffer.h"
-#include "test_util/sync_point.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-bool LevelCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  if (!vstorage->ExpiredTtlFiles().empty()) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForPeriodicCompaction().empty()) {
-    return true;
-  }
-  if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  if (!vstorage->FilesMarkedForCompaction().empty()) {
-    return true;
-  }
-  for (int i = 0; i <= vstorage->MaxInputLevel(); i++) {
-    if (vstorage->CompactionScore(i) >= 1) {
-      return true;
-    }
-  }
-  return false;
-}
-
-namespace {
-// A class to build a leveled compaction step-by-step.
-class LevelCompactionBuilder {
- public:
-  LevelCompactionBuilder(const std::string& cf_name,
-                         VersionStorageInfo* vstorage,
-                         SequenceNumber earliest_mem_seqno,
-                         CompactionPicker* compaction_picker,
-                         LogBuffer* log_buffer,
-                         const MutableCFOptions& mutable_cf_options,
-                         const ImmutableCFOptions& ioptions)
-      : cf_name_(cf_name),
-        vstorage_(vstorage),
-        earliest_mem_seqno_(earliest_mem_seqno),
-        compaction_picker_(compaction_picker),
-        log_buffer_(log_buffer),
-        mutable_cf_options_(mutable_cf_options),
-        ioptions_(ioptions) {}
-
-  // Pick and return a compaction.
-  Compaction* PickCompaction();
-
-  // Pick the initial files to compact to the next level. (or together
-  // in Intra-L0 compactions)
-  void SetupInitialFiles();
-
-  // If the initial files are from L0 level, pick other L0
-  // files if needed.
-  bool SetupOtherL0FilesIfNeeded();
-
-  // Based on initial files, setup other files need to be compacted
-  // in this compaction, accordingly.
-  bool SetupOtherInputsIfNeeded();
-
-  Compaction* GetCompaction();
-
-  // For the specfied level, pick a file that we want to compact.
-  // Returns false if there is no file to compact.
-  // If it returns true, inputs->files.size() will be exactly one.
-  // If level is 0 and there is already a compaction on that level, this
-  // function will return false.
-  bool PickFileToCompact();
-
-  // For L0->L0, picks the longest span of files that aren't currently
-  // undergoing compaction for which work-per-deleted-file decreases. The span
-  // always starts from the newest L0 file.
-  //
-  // Intra-L0 compaction is independent of all other files, so it can be
-  // performed even when L0->base_level compactions are blocked.
-  //
-  // Returns true if `inputs` is populated with a span of files to be compacted;
-  // otherwise, returns false.
-  bool PickIntraL0Compaction();
-
-  void PickExpiredTtlFiles();
-
-  void PickFilesMarkedForPeriodicCompaction();
-
-  const std::string& cf_name_;
-  VersionStorageInfo* vstorage_;
-  SequenceNumber earliest_mem_seqno_;
-  CompactionPicker* compaction_picker_;
-  LogBuffer* log_buffer_;
-  int start_level_ = -1;
-  int output_level_ = -1;
-  int parent_index_ = -1;
-  int base_index_ = -1;
-  double start_level_score_ = 0;
-  bool is_manual_ = false;
-  CompactionInputFiles start_level_inputs_;
-  std::vector<CompactionInputFiles> compaction_inputs_;
-  CompactionInputFiles output_level_inputs_;
-  std::vector<FileMetaData*> grandparents_;
-  CompactionReason compaction_reason_ = CompactionReason::kUnknown;
-
-  const MutableCFOptions& mutable_cf_options_;
-  const ImmutableCFOptions& ioptions_;
-  // Pick a path ID to place a newly generated file, with its level
-  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
-                            const MutableCFOptions& mutable_cf_options,
-                            int level);
-
-  static const int kMinFilesForIntraL0Compaction = 4;
-};
-
-void LevelCompactionBuilder::PickExpiredTtlFiles() {
-  if (vstorage_->ExpiredTtlFiles().empty()) {
-    return;
-  }
-
-  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    start_level_ = level_file.first;
-    output_level_ =
-        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-
-    if ((start_level_ == vstorage_->num_non_empty_levels() - 1) ||
-        (start_level_ == 0 &&
-         !compaction_picker_->level0_compactions_in_progress()->empty())) {
-      return false;
-    }
-
-    start_level_inputs_.files = {level_file.second};
-    start_level_inputs_.level = start_level_;
-    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                      &start_level_inputs_);
-  };
-
-  for (auto& level_file : vstorage_->ExpiredTtlFiles()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-
-  start_level_inputs_.files.clear();
-}
-
-void LevelCompactionBuilder::PickFilesMarkedForPeriodicCompaction() {
-  if (vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
-    return;
-  }
-
-  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
-    // If it's being compacted it has nothing to do here.
-    // If this assert() fails that means that some function marked some
-    // files as being_compacted, but didn't call ComputeCompactionScore()
-    assert(!level_file.second->being_compacted);
-    output_level_ = start_level_ = level_file.first;
-
-    if (start_level_ == 0 &&
-        !compaction_picker_->level0_compactions_in_progress()->empty()) {
-      return false;
-    }
-
-    start_level_inputs_.files = {level_file.second};
-    start_level_inputs_.level = start_level_;
-    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                      &start_level_inputs_);
-  };
-
-  for (auto& level_file : vstorage_->FilesMarkedForPeriodicCompaction()) {
-    if (continuation(level_file)) {
-      // found the compaction!
-      return;
-    }
-  }
-
-  start_level_inputs_.files.clear();
-}
-
-void LevelCompactionBuilder::SetupInitialFiles() {
-  // Find the compactions by size on all levels.
-  bool skipped_l0_to_base = false;
-  for (int i = 0; i < compaction_picker_->NumberLevels() - 1; i++) {
-    start_level_score_ = vstorage_->CompactionScore(i);
-    start_level_ = vstorage_->CompactionScoreLevel(i);
-    assert(i == 0 || start_level_score_ <= vstorage_->CompactionScore(i - 1));
-    if (start_level_score_ >= 1) {
-      if (skipped_l0_to_base && start_level_ == vstorage_->base_level()) {
-        // If L0->base_level compaction is pending, don't schedule further
-        // compaction from base level. Otherwise L0->base_level compaction
-        // may starve.
-        continue;
-      }
-      output_level_ =
-          (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-      if (PickFileToCompact()) {
-        // found the compaction!
-        if (start_level_ == 0) {
-          // L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
-          compaction_reason_ = CompactionReason::kLevelL0FilesNum;
-        } else {
-          // L1+ score = `Level files size` / `MaxBytesForLevel`
-          compaction_reason_ = CompactionReason::kLevelMaxLevelSize;
-        }
-        break;
-      } else {
-        // didn't find the compaction, clear the inputs
-        start_level_inputs_.clear();
-        if (start_level_ == 0) {
-          skipped_l0_to_base = true;
-          // L0->base_level may be blocked due to ongoing L0->base_level
-          // compactions. It may also be blocked by an ongoing compaction from
-          // base_level downwards.
-          //
-          // In these cases, to reduce L0 file count and thus reduce likelihood
-          // of write stalls, we can attempt compacting a span of files within
-          // L0.
-          if (PickIntraL0Compaction()) {
-            output_level_ = 0;
-            compaction_reason_ = CompactionReason::kLevelL0FilesNum;
-            break;
-          }
-        }
-      }
-    }
-  }
-
-  // if we didn't find a compaction, check if there are any files marked for
-  // compaction
-  if (start_level_inputs_.empty()) {
-    parent_index_ = base_index_ = -1;
-
-    compaction_picker_->PickFilesMarkedForCompaction(
-        cf_name_, vstorage_, &start_level_, &output_level_,
-        &start_level_inputs_);
-    if (!start_level_inputs_.empty()) {
-      is_manual_ = true;
-      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
-      return;
-    }
-  }
-
-  // Bottommost Files Compaction on deleting tombstones
-  if (start_level_inputs_.empty()) {
-    size_t i;
-    for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
-         ++i) {
-      auto& level_and_file = vstorage_->BottommostFilesMarkedForCompaction()[i];
-      assert(!level_and_file.second->being_compacted);
-      start_level_inputs_.level = output_level_ = start_level_ =
-          level_and_file.first;
-      start_level_inputs_.files = {level_and_file.second};
-      if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                     &start_level_inputs_)) {
-        break;
-      }
-    }
-    if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
-      start_level_inputs_.clear();
-    } else {
-      assert(!start_level_inputs_.empty());
-      compaction_reason_ = CompactionReason::kBottommostFiles;
-      return;
-    }
-  }
-
-  // TTL Compaction
-  if (start_level_inputs_.empty()) {
-    PickExpiredTtlFiles();
-    if (!start_level_inputs_.empty()) {
-      compaction_reason_ = CompactionReason::kTtl;
-      return;
-    }
-  }
-
-  // Periodic Compaction
-  if (start_level_inputs_.empty()) {
-    PickFilesMarkedForPeriodicCompaction();
-    if (!start_level_inputs_.empty()) {
-      compaction_reason_ = CompactionReason::kPeriodicCompaction;
-      return;
-    }
-  }
-}
-
-bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
-  if (start_level_ == 0 && output_level_ != 0) {
-    return compaction_picker_->GetOverlappingL0Files(
-        vstorage_, &start_level_inputs_, output_level_, &parent_index_);
-  }
-  return true;
-}
-
-bool LevelCompactionBuilder::SetupOtherInputsIfNeeded() {
-  // Setup input files from output level. For output to L0, we only compact
-  // spans of files that do not interact with any pending compactions, so don't
-  // need to consider other levels.
-  if (output_level_ != 0) {
-    output_level_inputs_.level = output_level_;
-    if (!compaction_picker_->SetupOtherInputs(
-            cf_name_, mutable_cf_options_, vstorage_, &start_level_inputs_,
-            &output_level_inputs_, &parent_index_, base_index_)) {
-      return false;
-    }
-
-    compaction_inputs_.push_back(start_level_inputs_);
-    if (!output_level_inputs_.empty()) {
-      compaction_inputs_.push_back(output_level_inputs_);
-    }
-
-    // In some edge cases we could pick a compaction that will be compacting
-    // a key range that overlap with another running compaction, and both
-    // of them have the same output level. This could happen if
-    // (1) we are running a non-exclusive manual compaction
-    // (2) AddFile ingest a new file into the LSM tree
-    // We need to disallow this from happening.
-    if (compaction_picker_->FilesRangeOverlapWithCompaction(compaction_inputs_,
-                                                            output_level_)) {
-      // This compaction output could potentially conflict with the output
-      // of a currently running compaction, we cannot run it.
-      return false;
-    }
-    compaction_picker_->GetGrandparents(vstorage_, start_level_inputs_,
-                                        output_level_inputs_, &grandparents_);
-  } else {
-    compaction_inputs_.push_back(start_level_inputs_);
-  }
-  return true;
-}
-
-Compaction* LevelCompactionBuilder::PickCompaction() {
-  // Pick up the first file to start compaction. It may have been extended
-  // to a clean cut.
-  SetupInitialFiles();
-  if (start_level_inputs_.empty()) {
-    return nullptr;
-  }
-  assert(start_level_ >= 0 && output_level_ >= 0);
-
-  // If it is a L0 -> base level compaction, we need to set up other L0
-  // files if needed.
-  if (!SetupOtherL0FilesIfNeeded()) {
-    return nullptr;
-  }
-
-  // Pick files in the output level and expand more files in the start level
-  // if needed.
-  if (!SetupOtherInputsIfNeeded()) {
-    return nullptr;
-  }
-
-  // Form a compaction object containing the files we picked.
-  Compaction* c = GetCompaction();
-
-  TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
-
-  return c;
-}
-
-Compaction* LevelCompactionBuilder::GetCompaction() {
-  auto c = new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(compaction_inputs_),
-      output_level_,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level_,
-                          ioptions_.compaction_style, vstorage_->base_level(),
-                          ioptions_.level_compaction_dynamic_level_bytes),
-      mutable_cf_options_.max_compaction_bytes,
-      GetPathId(ioptions_, mutable_cf_options_, output_level_),
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
-                         output_level_, vstorage_->base_level()),
-      GetCompressionOptions(ioptions_, vstorage_, output_level_),
-      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
-      start_level_score_, false /* deletion_compaction */, compaction_reason_);
-
-  // If it's level 0 compaction, make sure we don't execute any other level 0
-  // compactions in parallel
-  compaction_picker_->RegisterCompaction(c);
-
-  // Creating a compaction influences the compaction score because the score
-  // takes running compactions into account (by skipping files that are already
-  // being compacted). Since we just changed compaction score, we recalculate it
-  // here
-  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
-  return c;
-}
-
-/*
- * Find the optimal path to place a file
- * Given a level, finds the path where levels up to it will fit in levels
- * up to and including this path
- */
-uint32_t LevelCompactionBuilder::GetPathId(
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, int level) {
-  uint32_t p = 0;
-  assert(!ioptions.cf_paths.empty());
-
-  // size remaining in the most recent path
-  uint64_t current_path_size = ioptions.cf_paths[0].target_size;
-
-  uint64_t level_size;
-  int cur_level = 0;
-
-  // max_bytes_for_level_base denotes L1 size.
-  // We estimate L0 size to be the same as L1.
-  level_size = mutable_cf_options.max_bytes_for_level_base;
-
-  // Last path is the fallback
-  while (p < ioptions.cf_paths.size() - 1) {
-    if (level_size <= current_path_size) {
-      if (cur_level == level) {
-        // Does desired level fit in this path?
-        return p;
-      } else {
-        current_path_size -= level_size;
-        if (cur_level > 0) {
-          if (ioptions.level_compaction_dynamic_level_bytes) {
-            // Currently, level_compaction_dynamic_level_bytes is ignored when
-            // multiple db paths are specified. https://github.com/facebook/
-            // rocksdb/blob/master/db/column_family.cc.
-            // Still, adding this check to avoid accidentally using
-            // max_bytes_for_level_multiplier_additional
-            level_size = static_cast<uint64_t>(
-                level_size * mutable_cf_options.max_bytes_for_level_multiplier);
-          } else {
-            level_size = static_cast<uint64_t>(
-                level_size * mutable_cf_options.max_bytes_for_level_multiplier *
-                mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
-          }
-        }
-        cur_level++;
-        continue;
-      }
-    }
-    p++;
-    current_path_size = ioptions.cf_paths[p].target_size;
-  }
-  return p;
-}
-
-bool LevelCompactionBuilder::PickFileToCompact() {
-  // level 0 files are overlapping. So we cannot pick more
-  // than one concurrent compactions at this level. This
-  // could be made better by looking at key-ranges that are
-  // being compacted at level 0.
-  if (start_level_ == 0 &&
-      !compaction_picker_->level0_compactions_in_progress()->empty()) {
-    TEST_SYNC_POINT("LevelCompactionPicker::PickCompactionBySize:0");
-    return false;
-  }
-
-  start_level_inputs_.clear();
-
-  assert(start_level_ >= 0);
-
-  // Pick the largest file in this level that is not already
-  // being compacted
-  const std::vector<int>& file_size =
-      vstorage_->FilesByCompactionPri(start_level_);
-  const std::vector<FileMetaData*>& level_files =
-      vstorage_->LevelFiles(start_level_);
-
-  unsigned int cmp_idx;
-  for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
-       cmp_idx < file_size.size(); cmp_idx++) {
-    int index = file_size[cmp_idx];
-    auto* f = level_files[index];
-
-    // do not pick a file to compact if it is being compacted
-    // from n-1 level.
-    if (f->being_compacted) {
-      continue;
-    }
-
-    start_level_inputs_.files.push_back(f);
-    start_level_inputs_.level = start_level_;
-    if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                    &start_level_inputs_) ||
-        compaction_picker_->FilesRangeOverlapWithCompaction(
-            {start_level_inputs_}, output_level_)) {
-      // A locked (pending compaction) input-level file was pulled in due to
-      // user-key overlap.
-      start_level_inputs_.clear();
-      continue;
-    }
-
-    // Now that input level is fully expanded, we check whether any output files
-    // are locked due to pending compaction.
-    //
-    // Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
-    // level files are locked, not just the extra ones pulled in for user-key
-    // overlap.
-    InternalKey smallest, largest;
-    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
-    CompactionInputFiles output_level_inputs;
-    output_level_inputs.level = output_level_;
-    vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
-                                    &output_level_inputs.files);
-    if (!output_level_inputs.empty() &&
-        !compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                    &output_level_inputs)) {
-      start_level_inputs_.clear();
-      continue;
-    }
-    base_index_ = index;
-    break;
-  }
-
-  // store where to start the iteration in the next call to PickCompaction
-  vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
-
-  return start_level_inputs_.size() > 0;
-}
-
-bool LevelCompactionBuilder::PickIntraL0Compaction() {
-  start_level_inputs_.clear();
-  const std::vector<FileMetaData*>& level_files =
-      vstorage_->LevelFiles(0 /* level */);
-  if (level_files.size() <
-          static_cast<size_t>(
-              mutable_cf_options_.level0_file_num_compaction_trigger + 2) ||
-      level_files[0]->being_compacted) {
-    // If L0 isn't accumulating much files beyond the regular trigger, don't
-    // resort to L0->L0 compaction yet.
-    return false;
-  }
-  return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
-                               port::kMaxUint64,
-                               mutable_cf_options_.max_compaction_bytes,
-                               &start_level_inputs_, earliest_mem_seqno_);
-}
-}  // namespace
-
-Compaction* LevelCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber earliest_mem_seqno) {
-  LevelCompactionBuilder builder(cf_name, vstorage, earliest_mem_seqno, this,
-                                 log_buffer, mutable_cf_options, ioptions_);
-  return builder.PickCompaction();
-}
-}  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_picker_level.h

@@ -1,32 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-
-#include "db/compaction/compaction_picker.h"
-
-namespace ROCKSDB_NAMESPACE {
-// Picking compactions for leveled compaction. See wiki page
-// https://github.com/facebook/rocksdb/wiki/Leveled-Compaction
-// for description of Leveled compaction.
-class LevelCompactionPicker : public CompactionPicker {
- public:
-  LevelCompactionPicker(const ImmutableCFOptions& ioptions,
-                        const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-
-}  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_picker_universal.h

@@ -1,31 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  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).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-#ifndef ROCKSDB_LITE
-
-#include "db/compaction/compaction_picker.h"
-
-namespace ROCKSDB_NAMESPACE {
-class UniversalCompactionPicker : public CompactionPicker {
- public:
-  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
-                            const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
-  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-}  // namespace ROCKSDB_NAMESPACE
-#endif  // !ROCKSDB_LITE

db/compaction_iteration_stats.h

@@ -5,8 +5,6 @@
 
 #pragma once
 
-#include "rocksdb/rocksdb_namespace.h"
-
 struct CompactionIterationStats {
   // Compaction statistics
 

db/compaction_iterator.cc

@@ -3,14 +3,13 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#include <cinttypes>
+#include "db/compaction_iterator.h"
 
-#include "db/compaction/compaction_iterator.h"
 #include "db/snapshot_checker.h"
 #include "port/likely.h"
 #include "rocksdb/listener.h"
 #include "table/internal_iterator.h"
-#include "test_util/sync_point.h"
+#include "util/sync_point.h"
 
 #define DEFINITELY_IN_SNAPSHOT(seq, snapshot)                       \
   ((seq) <= (snapshot) &&                                           \
@@ -28,7 +27,7 @@
   ((seq) <= earliest_snapshot_ && \
    (snapshot_checker_ == nullptr || LIKELY(IsInEarliestSnapshot(seq))))
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -39,17 +38,14 @@ CompactionIterator::CompactionIterator(
     CompactionRangeDelAggregator* range_del_agg, const Compaction* compaction,
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused,
-    const std::shared_ptr<Logger> info_log)
+    const SequenceNumber preserve_deletes_seqnum)
     : CompactionIterator(
           input, cmp, merge_helper, last_sequence, snapshots,
           earliest_write_conflict_snapshot, snapshot_checker, env,
           report_detailed_time, expect_valid_internal_key, range_del_agg,
           std::unique_ptr<CompactionProxy>(
               compaction ? new CompactionProxy(compaction) : nullptr),
-          compaction_filter, shutting_down, preserve_deletes_seqnum,
-          manual_compaction_paused, info_log) {}
+          compaction_filter, shutting_down, preserve_deletes_seqnum) {}
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -61,9 +57,7 @@ CompactionIterator::CompactionIterator(
     std::unique_ptr<CompactionProxy> compaction,
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused,
-    const std::shared_ptr<Logger> info_log)
+    const SequenceNumber preserve_deletes_seqnum)
     : input_(input),
       cmp_(cmp),
       merge_helper_(merge_helper),
@@ -77,13 +71,12 @@ CompactionIterator::CompactionIterator(
       compaction_(std::move(compaction)),
       compaction_filter_(compaction_filter),
       shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
       preserve_deletes_seqnum_(preserve_deletes_seqnum),
+      ignore_snapshots_(false),
       current_user_key_sequence_(0),
       current_user_key_snapshot_(0),
       merge_out_iter_(merge_helper_),
-      current_key_committed_(false),
-      info_log_(info_log) {
+      current_key_committed_(false) {
   assert(compaction_filter_ == nullptr || compaction_ != nullptr);
   assert(snapshots_ != nullptr);
   bottommost_level_ =
@@ -109,6 +102,13 @@ CompactionIterator::CompactionIterator(
     assert(snapshots_->at(i - 1) < snapshots_->at(i));
   }
 #endif
+  if (compaction_filter_ != nullptr) {
+    if (compaction_filter_->IgnoreSnapshots()) {
+      ignore_snapshots_ = true;
+    }
+  } else {
+    ignore_snapshots_ = false;
+  }
   input_->SetPinnedItersMgr(&pinned_iters_mgr_);
   TEST_SYNC_POINT_CALLBACK("CompactionIterator:AfterInit", compaction_.get());
 }
@@ -147,11 +147,6 @@ void CompactionIterator::Next() {
       // MergeUntil stops when it encounters a corrupt key and does not
       // include them in the result, so we expect the keys here to be valid.
       assert(valid_key);
-      if (!valid_key) {
-        ROCKS_LOG_FATAL(info_log_, "Invalid key (%s) in compaction",
-                        key_.ToString(true).c_str());
-      }
-
       // Keep current_key_ in sync.
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
       key_ = current_key_.GetInternalKey();
@@ -185,7 +180,9 @@ void CompactionIterator::Next() {
 void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
                                               Slice* skip_until) {
   if (compaction_filter_ != nullptr &&
-      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex)) {
+      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex) &&
+      (visible_at_tip_ || ignore_snapshots_ ||
+       DEFINITELY_NOT_IN_SNAPSHOT(ikey_.sequence, latest_snapshot_))) {
     // If the user has specified a compaction filter and the sequence
     // number is greater than any external snapshot, then invoke the
     // filter. If the return value of the compaction filter is true,
@@ -239,8 +236,7 @@ void CompactionIterator::NextFromInput() {
   at_next_ = false;
   valid_ = false;
 
-  while (!valid_ && input_->Valid() && !IsPausingManualCompaction() &&
-         !IsShuttingDown()) {
+  while (!valid_ && input_->Valid() && !IsShuttingDown()) {
     key_ = input_->key();
     value_ = input_->value();
     iter_stats_.num_input_records++;
@@ -348,18 +344,7 @@ void CompactionIterator::NextFromInput() {
       // not compact out.  We will keep this Put, but can drop it's data.
       // (See Optimization 3, below.)
       assert(ikey_.type == kTypeValue);
-      if (ikey_.type != kTypeValue) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "Unexpected key type %d for compaction output",
-                        ikey_.type);
-      }
       assert(current_user_key_snapshot_ == last_snapshot);
-      if (current_user_key_snapshot_ != last_snapshot) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "current_user_key_snapshot_ (%" PRIu64
-                        ") != last_snapshot (%" PRIu64 ")",
-                        current_user_key_snapshot_, last_snapshot);
-      }
 
       value_.clear();
       valid_ = true;
@@ -501,12 +486,17 @@ void CompactionIterator::NextFromInput() {
       // checking since there has already been a record returned for this key
       // in this snapshot.
       assert(last_sequence >= current_user_key_sequence_);
-      if (last_sequence < current_user_key_sequence_) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "last_sequence (%" PRIu64
-                        ") < current_user_key_sequence_ (%" PRIu64 ")",
-                        last_sequence, current_user_key_sequence_);
-      }
+
+      // Note2: if last_snapshot < current_user_key_snapshot, it can only
+      // mean last_snapshot is released between we process last value and
+      // this value, and findEarliestVisibleSnapshot returns the next snapshot
+      // as current_user_key_snapshot. In this case last value and current
+      // value are both in current_user_key_snapshot currently.
+      assert(last_snapshot == current_user_key_snapshot_ ||
+             (snapshot_checker_ != nullptr &&
+              snapshot_checker_->CheckInSnapshot(current_user_key_sequence_,
+                                                 last_snapshot) ==
+                  SnapshotCheckerResult::kSnapshotReleased));
 
       ++iter_stats_.num_record_drop_hidden;  // (A)
       input_->Next();
@@ -590,10 +580,6 @@ void CompactionIterator::NextFromInput() {
         // MergeUntil stops when it encounters a corrupt key and does not
         // include them in the result, so we expect the keys here to valid.
         assert(valid_key);
-        if (!valid_key) {
-          ROCKS_LOG_FATAL(info_log_, "Invalid key (%s) in compaction",
-                          key_.ToString(true).c_str());
-        }
         // Keep current_key_ in sync.
         current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
         key_ = current_key_.GetInternalKey();
@@ -632,65 +618,33 @@ void CompactionIterator::NextFromInput() {
   if (!valid_ && IsShuttingDown()) {
     status_ = Status::ShutdownInProgress();
   }
-
-  if (IsPausingManualCompaction()) {
-    status_ = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
-  }
 }
 
 void CompactionIterator::PrepareOutput() {
-  if (valid_) {
-    if (compaction_filter_ && ikey_.type == kTypeBlobIndex) {
-      const auto blob_decision = compaction_filter_->PrepareBlobOutput(
-          user_key(), value_, &compaction_filter_value_);
-
-      if (blob_decision == CompactionFilter::BlobDecision::kCorruption) {
-        status_ = Status::Corruption(
-            "Corrupted blob reference encountered during GC");
-        valid_ = false;
-      } else if (blob_decision == CompactionFilter::BlobDecision::kIOError) {
-        status_ = Status::IOError("Could not relocate blob during GC");
-        valid_ = false;
-      } else if (blob_decision ==
-                 CompactionFilter::BlobDecision::kChangeValue) {
-        value_ = compaction_filter_value_;
-      }
-    }
-
-    // Zeroing out the sequence number leads to better compression.
-    // If this is the bottommost level (no files in lower levels)
-    // and the earliest snapshot is larger than this seqno
-    // and the userkey differs from the last userkey in compaction
-    // then we can squash the seqno to zero.
-    //
-    // This is safe for TransactionDB write-conflict checking since transactions
-    // only care about sequence number larger than any active snapshots.
-    //
-    // Can we do the same for levels above bottom level as long as
-    // KeyNotExistsBeyondOutputLevel() return true?
-    if (valid_ && compaction_ != nullptr &&
-        !compaction_->allow_ingest_behind() &&
-        ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ &&
-        IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
-      assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
-      if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "Unexpected key type %d for seq-zero optimization",
-                        ikey_.type);
-      }
-      ikey_.sequence = 0;
-      current_key_.UpdateInternalKey(0, ikey_.type);
-    }
+  // Zeroing out the sequence number leads to better compression.
+  // If this is the bottommost level (no files in lower levels)
+  // and the earliest snapshot is larger than this seqno
+  // and the userkey differs from the last userkey in compaction
+  // then we can squash the seqno to zero.
+  //
+  // This is safe for TransactionDB write-conflict checking since transactions
+  // only care about sequence number larger than any active snapshots.
+  //
+  // Can we do the same for levels above bottom level as long as
+  // KeyNotExistsBeyondOutputLevel() return true?
+  if ((compaction_ != nullptr && !compaction_->allow_ingest_behind()) &&
+      ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ && valid_ &&
+      IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge &&
+      !cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
+    assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
+    ikey_.sequence = 0;
+    current_key_.UpdateInternalKey(0, ikey_.type);
   }
 }
 
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  if (snapshots_->size() == 0) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "No snapshot left in findEarliestVisibleSnapshot");
-  }
   auto snapshots_iter = std::lower_bound(
       snapshots_->begin(), snapshots_->end(), in);
   if (snapshots_iter == snapshots_->begin()) {
@@ -698,10 +652,6 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
   } else {
     *prev_snapshot = *std::prev(snapshots_iter);
     assert(*prev_snapshot < in);
-    if (*prev_snapshot >= in) {
-      ROCKS_LOG_FATAL(info_log_,
-                      "*prev_snapshot >= in in findEarliestVisibleSnapshot");
-    }
   }
   if (snapshot_checker_ == nullptr) {
     return snapshots_iter != snapshots_->end()
@@ -711,9 +661,6 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
   for (; snapshots_iter != snapshots_->end(); ++snapshots_iter) {
     auto cur = *snapshots_iter;
     assert(in <= cur);
-    if (in > cur) {
-      ROCKS_LOG_FATAL(info_log_, "in > cur in findEarliestVisibleSnapshot");
-    }
     // Skip if cur is in released_snapshots.
     if (has_released_snapshot && released_snapshots_.count(cur) > 0) {
       continue;
@@ -738,14 +685,9 @@ inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
 
 bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
   assert(snapshot_checker_ != nullptr);
-  bool pre_condition = (earliest_snapshot_ == kMaxSequenceNumber ||
-                        (earliest_snapshot_iter_ != snapshots_->end() &&
-                         *earliest_snapshot_iter_ == earliest_snapshot_));
-  assert(pre_condition);
-  if (!pre_condition) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "Pre-Condition is not hold in IsInEarliestSnapshot");
-  }
+  assert(earliest_snapshot_ == kMaxSequenceNumber ||
+         (earliest_snapshot_iter_ != snapshots_->end() &&
+          *earliest_snapshot_iter_ == earliest_snapshot_));
   auto in_snapshot =
       snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
   while (UNLIKELY(in_snapshot == SnapshotCheckerResult::kSnapshotReleased)) {
@@ -764,11 +706,7 @@ bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
         snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
   }
   assert(in_snapshot != SnapshotCheckerResult::kSnapshotReleased);
-  if (in_snapshot == SnapshotCheckerResult::kSnapshotReleased) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "Unexpected released snapshot in IsInEarliestSnapshot");
-  }
   return in_snapshot == SnapshotCheckerResult::kInSnapshot;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction_iterator.h

@@ -10,8 +10,8 @@
 #include <unordered_set>
 #include <vector>
 
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_iteration_stats.h"
+#include "db/compaction.h"
+#include "db/compaction_iteration_stats.h"
 #include "db/merge_helper.h"
 #include "db/pinned_iterators_manager.h"
 #include "db/range_del_aggregator.h"
@@ -19,7 +19,7 @@
 #include "options/cf_options.h"
 #include "rocksdb/compaction_filter.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CompactionIterator {
  public:
@@ -59,34 +59,30 @@ class CompactionIterator {
     const Compaction* compaction_;
   };
 
-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      const Compaction* compaction = nullptr,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr,
-      const std::shared_ptr<Logger> info_log = nullptr);
+  CompactionIterator(InternalIterator* input, const Comparator* cmp,
+                     MergeHelper* merge_helper, SequenceNumber last_sequence,
+                     std::vector<SequenceNumber>* snapshots,
+                     SequenceNumber earliest_write_conflict_snapshot,
+                     const SnapshotChecker* snapshot_checker, Env* env,
+                     bool report_detailed_time, bool expect_valid_internal_key,
+                     CompactionRangeDelAggregator* range_del_agg,
+                     const Compaction* compaction = nullptr,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0);
 
   // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      std::unique_ptr<CompactionProxy> compaction,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr,
-      const std::shared_ptr<Logger> info_log = nullptr);
+  CompactionIterator(InternalIterator* input, const Comparator* cmp,
+                     MergeHelper* merge_helper, SequenceNumber last_sequence,
+                     std::vector<SequenceNumber>* snapshots,
+                     SequenceNumber earliest_write_conflict_snapshot,
+                     const SnapshotChecker* snapshot_checker, Env* env,
+                     bool report_detailed_time, bool expect_valid_internal_key,
+                     CompactionRangeDelAggregator* range_del_agg,
+                     std::unique_ptr<CompactionProxy> compaction,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0);
 
   ~CompactionIterator();
 
@@ -165,7 +161,6 @@ class CompactionIterator {
   std::unique_ptr<CompactionProxy> compaction_;
   const CompactionFilter* compaction_filter_;
   const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
   const SequenceNumber preserve_deletes_seqnum_;
   bool bottommost_level_;
   bool valid_ = false;
@@ -173,6 +168,8 @@ class CompactionIterator {
   SequenceNumber earliest_snapshot_;
   SequenceNumber latest_snapshot_;
 
+  bool ignore_snapshots_;
+
   // State
   //
   // Points to a copy of the current compaction iterator output (current_key_)
@@ -224,17 +221,10 @@ class CompactionIterator {
   // Used to avoid purging uncommitted values. The application can specify
   // uncommitted values by providing a SnapshotChecker object.
   bool current_key_committed_;
-  std::shared_ptr<Logger> info_log_;
 
   bool IsShuttingDown() {
     // This is a best-effort facility, so memory_order_relaxed is sufficient.
     return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
   }
-
-  bool IsPausingManualCompaction() {
-    // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return manual_compaction_paused_ &&
-           manual_compaction_paused_->load(std::memory_order_relaxed);
-  }
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction_iterator_test.cc

@@ -3,18 +3,18 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#include "db/compaction_iterator.h"
 
 #include <string>
 #include <vector>
 
-#include "db/compaction/compaction_iterator.h"
 #include "port/port.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // Expects no merging attempts.
 class NoMergingMergeOp : public MergeOperator {
@@ -112,39 +112,39 @@ class LoggingForwardVectorIterator : public InternalIterator {
     assert(keys_.size() == values_.size());
   }
 
-  bool Valid() const override { return current_ < keys_.size(); }
+  virtual bool Valid() const override { return current_ < keys_.size(); }
 
-  void SeekToFirst() override {
+  virtual void SeekToFirst() override {
     log.emplace_back(Action::Type::SEEK_TO_FIRST);
     current_ = 0;
   }
-  void SeekToLast() override { assert(false); }
+  virtual void SeekToLast() override { assert(false); }
 
-  void Seek(const Slice& target) override {
+  virtual void Seek(const Slice& target) override {
     log.emplace_back(Action::Type::SEEK, target.ToString());
     current_ = std::lower_bound(keys_.begin(), keys_.end(), target.ToString()) -
                keys_.begin();
   }
 
-  void SeekForPrev(const Slice& /*target*/) override { assert(false); }
+  virtual void SeekForPrev(const Slice& /*target*/) override { assert(false); }
 
-  void Next() override {
+  virtual void Next() override {
     assert(Valid());
     log.emplace_back(Action::Type::NEXT);
     current_++;
   }
-  void Prev() override { assert(false); }
+  virtual void Prev() override { assert(false); }
 
-  Slice key() const override {
+  virtual Slice key() const override {
     assert(Valid());
     return Slice(keys_[current_]);
   }
-  Slice value() const override {
+  virtual Slice value() const override {
     assert(Valid());
     return Slice(values_[current_]);
   }
 
-  Status status() const override { return Status::OK(); }
+  virtual Status status() const override { return Status::OK(); }
 
   std::vector<Action> log;
 
@@ -158,20 +158,22 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
  public:
   FakeCompaction() = default;
 
-  int level(size_t /*compaction_input_level*/) const override { return 0; }
-  bool KeyNotExistsBeyondOutputLevel(
+  virtual int level(size_t /*compaction_input_level*/) const override {
+    return 0;
+  }
+  virtual bool KeyNotExistsBeyondOutputLevel(
       const Slice& /*user_key*/,
       std::vector<size_t>* /*level_ptrs*/) const override {
     return is_bottommost_level || key_not_exists_beyond_output_level;
   }
-  bool bottommost_level() const override { return is_bottommost_level; }
-  int number_levels() const override { return 1; }
-  Slice GetLargestUserKey() const override {
+  virtual bool bottommost_level() const override { return is_bottommost_level; }
+  virtual int number_levels() const override { return 1; }
+  virtual Slice GetLargestUserKey() const override {
     return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
   }
-  bool allow_ingest_behind() const override { return false; }
+  virtual bool allow_ingest_behind() const override { return false; }
 
-  bool preserve_deletes() const override { return false; }
+  virtual bool preserve_deletes() const override { return false; }
 
   bool key_not_exists_beyond_output_level = false;
 
@@ -184,7 +186,7 @@ class TestSnapshotChecker : public SnapshotChecker {
  public:
   explicit TestSnapshotChecker(
       SequenceNumber last_committed_sequence,
-      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {{}})
+      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {})
       : last_committed_sequence_(last_committed_sequence),
         snapshots_(snapshots) {}
 
@@ -375,9 +377,10 @@ TEST_P(CompactionIteratorTest, RangeDeletionWithSnapshots) {
 
 TEST_P(CompactionIteratorTest, CompactionFilterSkipUntil) {
   class Filter : public CompactionFilter {
-    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                      const Slice& existing_value, std::string* /*new_value*/,
-                      std::string* skip_until) const override {
+    virtual Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
+                              const Slice& existing_value,
+                              std::string* /*new_value*/,
+                              std::string* skip_until) const override {
       std::string k = key.ToString();
       std::string v = existing_value.ToString();
       // See InitIterators() call below for the sequence of keys and their
@@ -494,7 +497,7 @@ TEST_P(CompactionIteratorTest, ShuttingDownInFilter) {
   compaction_proxy_->key_not_exists_beyond_output_level = true;
 
   std::atomic<bool> seek_done{false};
-  ROCKSDB_NAMESPACE::port::Thread compaction_thread([&] {
+  rocksdb::port::Thread compaction_thread([&] {
     c_iter_->SeekToFirst();
     EXPECT_FALSE(c_iter_->Valid());
     EXPECT_TRUE(c_iter_->status().IsShutdownInProgress());
@@ -531,7 +534,7 @@ TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
   compaction_proxy_->key_not_exists_beyond_output_level = true;
 
   std::atomic<bool> seek_done{false};
-  ROCKSDB_NAMESPACE::port::Thread compaction_thread([&] {
+  rocksdb::port::Thread compaction_thread([&] {
     c_iter_->SeekToFirst();
     ASSERT_FALSE(c_iter_->Valid());
     ASSERT_TRUE(c_iter_->status().IsShutdownInProgress());
@@ -557,9 +560,10 @@ TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
 
 TEST_P(CompactionIteratorTest, SingleMergeOperand) {
   class Filter : public CompactionFilter {
-    Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
-                      const Slice& existing_value, std::string* /*new_value*/,
-                      std::string* /*skip_until*/) const override {
+    virtual Decision FilterV2(int /*level*/, const Slice& key, ValueType t,
+                              const Slice& existing_value,
+                              std::string* /*new_value*/,
+                              std::string* /*skip_until*/) const override {
       std::string k = key.ToString();
       std::string v = existing_value.ToString();
 
@@ -968,7 +972,7 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_FullMerge) {
       compaction_filter.get());
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compaction_job.cc

@@ -7,8 +7,14 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#include "db/compaction_job.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
-#include <cinttypes>
 #include <functional>
 #include <list>
 #include <memory>
@@ -19,8 +25,7 @@
 #include <vector>
 
 #include "db/builder.h"
-#include "db/compaction/compaction_job.h"
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/db_iter.h"
 #include "db/dbformat.h"
 #include "db/error_handler.h"
@@ -33,12 +38,6 @@
 #include "db/merge_helper.h"
 #include "db/range_del_aggregator.h"
 #include "db/version_set.h"
-#include "file/filename.h"
-#include "file/read_write_util.h"
-#include "file/sst_file_manager_impl.h"
-#include "file/writable_file_writer.h"
-#include "logging/log_buffer.h"
-#include "logging/logging.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/thread_status_util.h"
@@ -48,18 +47,23 @@
 #include "rocksdb/statistics.h"
 #include "rocksdb/status.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block.h"
+#include "table/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "table/table_builder.h"
-#include "test_util/sync_point.h"
 #include "util/coding.h"
+#include "util/file_reader_writer.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
+#include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
+#include "util/sst_file_manager_impl.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 const char* GetCompactionReasonString(CompactionReason compaction_reason) {
   switch (compaction_reason) {
@@ -93,8 +97,6 @@ const char* GetCompactionReasonString(CompactionReason compaction_reason) {
       return "Flush";
     case CompactionReason::kExternalSstIngestion:
       return "ExternalSstIngestion";
-    case CompactionReason::kPeriodicCompaction:
-      return "PeriodicCompaction";
     case CompactionReason::kNumOfReasons:
       // fall through
     default:
@@ -144,6 +146,7 @@ struct CompactionJob::SubcompactionState {
 
   // State during the subcompaction
   uint64_t total_bytes;
+  uint64_t num_input_records;
   uint64_t num_output_records;
   CompactionJobStats compaction_job_stats;
   uint64_t approx_size;
@@ -154,6 +157,7 @@ struct CompactionJob::SubcompactionState {
   uint64_t overlapped_bytes = 0;
   // A flag determine whether the key has been seen in ShouldStopBefore()
   bool seen_key = false;
+  std::string compression_dict;
 
   SubcompactionState(Compaction* c, Slice* _start, Slice* _end,
                      uint64_t size = 0)
@@ -164,11 +168,13 @@ struct CompactionJob::SubcompactionState {
         builder(nullptr),
         current_output_file_size(0),
         total_bytes(0),
+        num_input_records(0),
         num_output_records(0),
         approx_size(size),
         grandparent_index(0),
         overlapped_bytes(0),
-        seen_key(false) {
+        seen_key(false),
+        compression_dict() {
     assert(compaction != nullptr);
   }
 
@@ -184,12 +190,14 @@ struct CompactionJob::SubcompactionState {
     builder = std::move(o.builder);
     current_output_file_size = std::move(o.current_output_file_size);
     total_bytes = std::move(o.total_bytes);
+    num_input_records = std::move(o.num_input_records);
     num_output_records = std::move(o.num_output_records);
     compaction_job_stats = std::move(o.compaction_job_stats);
     approx_size = std::move(o.approx_size);
     grandparent_index = std::move(o.grandparent_index);
     overlapped_bytes = std::move(o.overlapped_bytes);
     seen_key = std::move(o.seen_key);
+    compression_dict = std::move(o.compression_dict);
     return *this;
   }
 
@@ -242,11 +250,13 @@ struct CompactionJob::CompactionState {
   Status status;
 
   uint64_t total_bytes;
+  uint64_t num_input_records;
   uint64_t num_output_records;
 
   explicit CompactionState(Compaction* c)
       : compaction(c),
         total_bytes(0),
+        num_input_records(0),
         num_output_records(0) {}
 
   size_t NumOutputFiles() {
@@ -284,6 +294,7 @@ struct CompactionJob::CompactionState {
 void CompactionJob::AggregateStatistics() {
   for (SubcompactionState& sc : compact_->sub_compact_states) {
     compact_->total_bytes += sc.total_bytes;
+    compact_->num_input_records += sc.num_input_records;
     compact_->num_output_records += sc.num_output_records;
   }
   if (compaction_job_stats_) {
@@ -295,31 +306,28 @@ void CompactionJob::AggregateStatistics() {
 
 CompactionJob::CompactionJob(
     int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
-    const FileOptions& file_options, VersionSet* versions,
+    const EnvOptions env_options, VersionSet* versions,
     const std::atomic<bool>* shutting_down,
     const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
-    FSDirectory* db_directory, FSDirectory* output_directory, Statistics* stats,
+    Directory* db_directory, Directory* output_directory, Statistics* stats,
     InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
     std::vector<SequenceNumber> existing_snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     const SnapshotChecker* snapshot_checker, std::shared_ptr<Cache> table_cache,
     EventLogger* event_logger, bool paranoid_file_checks, bool measure_io_stats,
-    const std::string& dbname, CompactionJobStats* compaction_job_stats,
-    Env::Priority thread_pri, const std::atomic<bool>* manual_compaction_paused)
+    const std::string& dbname, CompactionJobStats* compaction_job_stats)
     : job_id_(job_id),
       compact_(new CompactionState(compaction)),
       compaction_job_stats_(compaction_job_stats),
       compaction_stats_(compaction->compaction_reason(), 1),
       dbname_(dbname),
       db_options_(db_options),
-      file_options_(file_options),
+      env_options_(env_options),
       env_(db_options.env),
-      fs_(db_options.fs.get()),
-      file_options_for_read_(
-          fs_->OptimizeForCompactionTableRead(file_options, db_options_)),
+      env_optiosn_for_read_(
+          env_->OptimizeForCompactionTableRead(env_options, db_options_)),
       versions_(versions),
       shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
       preserve_deletes_seqnum_(preserve_deletes_seqnum),
       log_buffer_(log_buffer),
       db_directory_(db_directory),
@@ -335,8 +343,7 @@ CompactionJob::CompactionJob(
       bottommost_level_(false),
       paranoid_file_checks_(paranoid_file_checks),
       measure_io_stats_(measure_io_stats),
-      write_hint_(Env::WLTH_NOT_SET),
-      thread_pri_(thread_pri) {
+      write_hint_(Env::WLTH_NOT_SET) {
   assert(log_buffer_ != nullptr);
   const auto* cfd = compact_->compaction->column_family_data();
   ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
@@ -406,13 +413,15 @@ void CompactionJob::Prepare() {
 
   write_hint_ =
       c->column_family_data()->CalculateSSTWriteHint(c->output_level());
+  // Is this compaction producing files at the bottommost level?
   bottommost_level_ = c->bottommost_level();
 
   if (c->ShouldFormSubcompactions()) {
-    {
-      StopWatch sw(env_, stats_, SUBCOMPACTION_SETUP_TIME);
-      GenSubcompactionBoundaries();
-    }
+    const uint64_t start_micros = env_->NowMicros();
+    GenSubcompactionBoundaries();
+    MeasureTime(stats_, SUBCOMPACTION_SETUP_TIME,
+                env_->NowMicros() - start_micros);
+
     assert(sizes_.size() == boundaries_.size() + 1);
 
     for (size_t i = 0; i <= boundaries_.size(); i++) {
@@ -420,8 +429,8 @@ void CompactionJob::Prepare() {
       Slice* end = i == boundaries_.size() ? nullptr : &boundaries_[i];
       compact_->sub_compact_states.emplace_back(c, start, end, sizes_[i]);
     }
-    RecordInHistogram(stats_, NUM_SUBCOMPACTIONS_SCHEDULED,
-                      compact_->sub_compact_states.size());
+    MeasureTime(stats_, NUM_SUBCOMPACTIONS_SCHEDULED,
+                compact_->sub_compact_states.size());
   } else {
     compact_->sub_compact_states.emplace_back(c, nullptr, nullptr);
   }
@@ -435,6 +444,11 @@ struct RangeWithSize {
       : range(a, b), size(s) {}
 };
 
+// Generates a histogram representing potential divisions of key ranges from
+// the input. It adds the starting and/or ending keys of certain input files
+// to the working set and then finds the approximate size of data in between
+// each consecutive pair of slices. Then it divides these ranges into
+// consecutive groups such that each group has a similar size.
 void CompactionJob::GenSubcompactionBoundaries() {
   auto* c = compact_->compaction;
   auto* cfd = c->column_family_data();
@@ -504,7 +518,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
   auto* v = compact_->compaction->input_version();
   for (auto it = bounds.begin();;) {
     const Slice a = *it;
-    ++it;
+    it++;
 
     if (it == bounds.end()) {
       break;
@@ -516,9 +530,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
     // to the index block and may incur I/O cost in the process. Unlock db
     // mutex to reduce contention
     db_mutex_->Unlock();
-    uint64_t size = versions_->ApproximateSize(SizeApproximationOptions(), v, a,
-                                               b, start_lvl, out_lvl + 1,
-                                               TableReaderCaller::kCompaction);
+    uint64_t size = versions_->ApproximateSize(v, a, b, start_lvl, out_lvl + 1);
     db_mutex_->Lock();
     ranges.emplace_back(a, b, size);
     sum += size;
@@ -598,9 +610,8 @@ Status CompactionJob::Run() {
         compact_->sub_compact_states[i].compaction_job_stats.cpu_micros;
   }
 
-  RecordTimeToHistogram(stats_, COMPACTION_TIME, compaction_stats_.micros);
-  RecordTimeToHistogram(stats_, COMPACTION_CPU_TIME,
-                        compaction_stats_.cpu_micros);
+  MeasureTime(stats_, COMPACTION_TIME, compaction_stats_.micros);
+  MeasureTime(stats_, COMPACTION_CPU_TIME, compaction_stats_.cpu_micros);
 
   TEST_SYNC_POINT("CompactionJob::Run:BeforeVerify");
 
@@ -614,7 +625,7 @@ Status CompactionJob::Run() {
   }
 
   if (status.ok() && output_directory_) {
-    status = output_directory_->Fsync(IOOptions(), nullptr);
+    status = output_directory_->Fsync();
   }
 
   if (status.ok()) {
@@ -642,15 +653,13 @@ Status CompactionJob::Run() {
         // we will regard this verification as user reads since the goal is
         // to cache it here for further user reads
         InternalIterator* iter = cfd->table_cache()->NewIterator(
-            ReadOptions(), file_options_, cfd->internal_comparator(),
-            *files_meta[file_idx], /*range_del_agg=*/nullptr, prefix_extractor,
-            /*table_reader_ptr=*/nullptr,
+            ReadOptions(), env_options_, cfd->internal_comparator(),
+            *files_meta[file_idx], nullptr /* range_del_agg */,
+            prefix_extractor, nullptr,
             cfd->internal_stats()->GetFileReadHist(
                 compact_->compaction->output_level()),
-            TableReaderCaller::kCompactionRefill, /*arena=*/nullptr,
-            /*skip_filters=*/false, compact_->compaction->output_level(),
-            /*smallest_compaction_key=*/nullptr,
-            /*largest_compaction_key=*/nullptr);
+            false, nullptr /* arena */, false /* skip_filters */,
+            compact_->compaction->output_level());
         auto s = iter->status();
 
         if (s.ok() && paranoid_file_checks_) {
@@ -711,7 +720,7 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
   Status status = compact_->status;
   ColumnFamilyData* cfd = compact_->compaction->column_family_data();
   cfd->internal_stats()->AddCompactionStats(
-      compact_->compaction->output_level(), thread_pri_, compaction_stats_);
+      compact_->compaction->output_level(), compaction_stats_);
 
   if (status.ok()) {
     status = InstallCompactionResults(mutable_cf_options);
@@ -764,12 +773,12 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
   auto stream = event_logger_->LogToBuffer(log_buffer_);
   stream << "job" << job_id_ << "event"
          << "compaction_finished"
-         << "compaction_time_micros" << stats.micros
-         << "compaction_time_cpu_micros" << stats.cpu_micros << "output_level"
-         << compact_->compaction->output_level() << "num_output_files"
-         << compact_->NumOutputFiles() << "total_output_size"
-         << compact_->total_bytes << "num_input_records"
-         << stats.num_input_records << "num_output_records"
+         << "compaction_time_micros" << compaction_stats_.micros
+         << "compaction_time_cpu_micros" << compaction_stats_.cpu_micros
+         << "output_level" << compact_->compaction->output_level()
+         << "num_output_files" << compact_->NumOutputFiles()
+         << "total_output_size" << compact_->total_bytes << "num_input_records"
+         << compact_->num_input_records << "num_output_records"
          << compact_->num_output_records << "num_subcompactions"
          << compact_->sub_compact_states.size() << "output_compression"
          << CompressionTypeToString(compact_->compaction->output_compression());
@@ -807,31 +816,13 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   uint64_t prev_cpu_micros = env_->NowCPUNanos() / 1000;
 
   ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-
-  // Create compaction filter and fail the compaction if
-  // IgnoreSnapshots() = false because it is not supported anymore
-  const CompactionFilter* compaction_filter =
-      cfd->ioptions()->compaction_filter;
-  std::unique_ptr<CompactionFilter> compaction_filter_from_factory = nullptr;
-  if (compaction_filter == nullptr) {
-    compaction_filter_from_factory =
-        sub_compact->compaction->CreateCompactionFilter();
-    compaction_filter = compaction_filter_from_factory.get();
-  }
-  if (compaction_filter != nullptr && !compaction_filter->IgnoreSnapshots()) {
-    sub_compact->status = Status::NotSupported(
-        "CompactionFilter::IgnoreSnapshots() = false is not supported "
-        "anymore.");
-    return;
-  }
-
   CompactionRangeDelAggregator range_del_agg(&cfd->internal_comparator(),
                                              existing_snapshots_);
 
   // Although the v2 aggregator is what the level iterator(s) know about,
   // the AddTombstones calls will be propagated down to the v1 aggregator.
   std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
-      sub_compact->compaction, &range_del_agg, file_options_for_read_));
+      sub_compact->compaction, &range_del_agg, env_optiosn_for_read_));
 
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -856,19 +847,58 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     prev_cpu_read_nanos = IOSTATS(cpu_read_nanos);
   }
 
+  const MutableCFOptions* mutable_cf_options =
+      sub_compact->compaction->mutable_cf_options();
+
+  // To build compression dictionary, we sample the first output file, assuming
+  // it'll reach the maximum length. We optionally pass these samples through
+  // zstd's dictionary trainer, or just use them directly. Then, the dictionary
+  // is used for compressing subsequent output files in the same subcompaction.
+  const bool kUseZstdTrainer =
+      sub_compact->compaction->output_compression_opts().zstd_max_train_bytes >
+      0;
+  const size_t kSampleBytes =
+      kUseZstdTrainer
+          ? sub_compact->compaction->output_compression_opts()
+                .zstd_max_train_bytes
+          : sub_compact->compaction->output_compression_opts().max_dict_bytes;
+  const int kSampleLenShift = 6;  // 2^6 = 64-byte samples
+  std::set<size_t> sample_begin_offsets;
+  if (bottommost_level_ && kSampleBytes > 0) {
+    const size_t kMaxSamples = kSampleBytes >> kSampleLenShift;
+    const size_t kOutFileLen =
+        static_cast<size_t>(MaxFileSizeForLevel(*mutable_cf_options,
+            compact_->compaction->output_level(),
+            cfd->ioptions()->compaction_style,
+            compact_->compaction->GetInputBaseLevel(),
+            cfd->ioptions()->level_compaction_dynamic_level_bytes));
+    if (kOutFileLen != port::kMaxSizet) {
+      const size_t kOutFileNumSamples = kOutFileLen >> kSampleLenShift;
+      Random64 generator{versions_->NewFileNumber()};
+      for (size_t i = 0; i < kMaxSamples; ++i) {
+        sample_begin_offsets.insert(
+            static_cast<size_t>(generator.Uniform(kOutFileNumSamples))
+            << kSampleLenShift);
+      }
+    }
+  }
+
+  auto compaction_filter = cfd->ioptions()->compaction_filter;
+  std::unique_ptr<CompactionFilter> compaction_filter_from_factory = nullptr;
+  if (compaction_filter == nullptr) {
+    compaction_filter_from_factory =
+        sub_compact->compaction->CreateCompactionFilter();
+    compaction_filter = compaction_filter_from_factory.get();
+  }
   MergeHelper merge(
       env_, cfd->user_comparator(), cfd->ioptions()->merge_operator,
       compaction_filter, db_options_.info_log.get(),
       false /* internal key corruption is expected */,
       existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
       snapshot_checker_, compact_->compaction->level(),
-      db_options_.statistics.get());
+      db_options_.statistics.get(), shutting_down_);
 
   TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
-  TEST_SYNC_POINT_CALLBACK(
-      "CompactionJob::Run():PausingManualCompaction:1",
-      reinterpret_cast<void*>(
-          const_cast<std::atomic<bool>*>(manual_compaction_paused_)));
 
   Slice* start = sub_compact->start;
   Slice* end = sub_compact->end;
@@ -886,8 +916,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       &existing_snapshots_, earliest_write_conflict_snapshot_,
       snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_), false,
       &range_del_agg, sub_compact->compaction, compaction_filter,
-      shutting_down_, preserve_deletes_seqnum_, manual_compaction_paused_,
-      db_options_.info_log));
+      shutting_down_, preserve_deletes_seqnum_));
   auto c_iter = sub_compact->c_iter.get();
   c_iter->SeekToFirst();
   if (c_iter->Valid() && sub_compact->compaction->output_level() != 0) {
@@ -898,6 +927,12 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
                                   sub_compact->current_output_file_size);
   }
   const auto& c_iter_stats = c_iter->iter_stats();
+  auto sample_begin_offset_iter = sample_begin_offsets.cbegin();
+  // data_begin_offset and dict_sample_data are only valid while generating
+  // dictionary from the first output file.
+  size_t data_begin_offset = 0;
+  std::string dict_sample_data;
+  dict_sample_data.reserve(kSampleBytes);
 
   while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
     // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
@@ -929,11 +964,59 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     assert(sub_compact->current_output() != nullptr);
     sub_compact->builder->Add(key, value);
     sub_compact->current_output_file_size = sub_compact->builder->FileSize();
-    const ParsedInternalKey& ikey = c_iter->ikey();
     sub_compact->current_output()->meta.UpdateBoundaries(
-        key, value, ikey.sequence, ikey.type);
+        key, c_iter->ikey().sequence);
     sub_compact->num_output_records++;
 
+    if (sub_compact->outputs.size() == 1) {  // first output file
+      // Check if this key/value overlaps any sample intervals; if so, appends
+      // overlapping portions to the dictionary.
+      for (const auto& data_elmt : {key, value}) {
+        size_t data_end_offset = data_begin_offset + data_elmt.size();
+        while (sample_begin_offset_iter != sample_begin_offsets.cend() &&
+               *sample_begin_offset_iter < data_end_offset) {
+          size_t sample_end_offset =
+              *sample_begin_offset_iter + (1 << kSampleLenShift);
+          // Invariant: Because we advance sample iterator while processing the
+          // data_elmt containing the sample's last byte, the current sample
+          // cannot end before the current data_elmt.
+          assert(data_begin_offset < sample_end_offset);
+
+          size_t data_elmt_copy_offset, data_elmt_copy_len;
+          if (*sample_begin_offset_iter <= data_begin_offset) {
+            // The sample starts before data_elmt starts, so take bytes starting
+            // at the beginning of data_elmt.
+            data_elmt_copy_offset = 0;
+          } else {
+            // data_elmt starts before the sample starts, so take bytes starting
+            // at the below offset into data_elmt.
+            data_elmt_copy_offset =
+                *sample_begin_offset_iter - data_begin_offset;
+          }
+          if (sample_end_offset <= data_end_offset) {
+            // The sample ends before data_elmt ends, so take as many bytes as
+            // needed.
+            data_elmt_copy_len =
+                sample_end_offset - (data_begin_offset + data_elmt_copy_offset);
+          } else {
+            // data_elmt ends before the sample ends, so take all remaining
+            // bytes in data_elmt.
+            data_elmt_copy_len =
+                data_end_offset - (data_begin_offset + data_elmt_copy_offset);
+          }
+          dict_sample_data.append(&data_elmt.data()[data_elmt_copy_offset],
+                                  data_elmt_copy_len);
+          if (sample_end_offset > data_end_offset) {
+            // Didn't finish sample. Try to finish it with the next data_elmt.
+            break;
+          }
+          // Next sample may require bytes from same data_elmt.
+          sample_begin_offset_iter++;
+        }
+        data_begin_offset = data_end_offset;
+      }
+    }
+
     // Close output file if it is big enough. Two possibilities determine it's
     // time to close it: (1) the current key should be this file's last key, (2)
     // the next key should not be in this file.
@@ -952,14 +1035,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       input_status = input->status();
       output_file_ended = true;
     }
-    TEST_SYNC_POINT_CALLBACK(
-        "CompactionJob::Run():PausingManualCompaction:2",
-        reinterpret_cast<void*>(
-            const_cast<std::atomic<bool>*>(manual_compaction_paused_)));
     c_iter->Next();
-    if (c_iter->status().IsManualCompactionPaused()) {
-      break;
-    }
     if (!output_file_ended && c_iter->Valid() &&
         sub_compact->compaction->output_level() != 0 &&
         sub_compact->ShouldStopBefore(c_iter->key(),
@@ -982,9 +1058,22 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
                                      &range_del_out_stats, next_key);
       RecordDroppedKeys(range_del_out_stats,
                         &sub_compact->compaction_job_stats);
+      if (sub_compact->outputs.size() == 1) {
+        // Use samples from first output file to create dictionary for
+        // compression of subsequent files.
+        if (kUseZstdTrainer) {
+          sub_compact->compression_dict = ZSTD_TrainDictionary(
+              dict_sample_data, kSampleLenShift,
+              sub_compact->compaction->output_compression_opts()
+                  .max_dict_bytes);
+        } else {
+          sub_compact->compression_dict = std::move(dict_sample_data);
+        }
+      }
     }
   }
 
+  sub_compact->num_input_records = c_iter_stats.num_input_records;
   sub_compact->compaction_job_stats.num_input_deletion_records =
       c_iter_stats.num_input_deletion_records;
   sub_compact->compaction_job_stats.num_corrupt_keys =
@@ -1003,18 +1092,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   RecordDroppedKeys(c_iter_stats, &sub_compact->compaction_job_stats);
   RecordCompactionIOStats();
 
-  if (status.ok() && cfd->IsDropped()) {
-    status =
-        Status::ColumnFamilyDropped("Column family dropped during compaction");
-  }
-  if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      shutting_down_->load(std::memory_order_relaxed)) {
-    status = Status::ShutdownInProgress("Database shutdown");
-  }
-  if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      (manual_compaction_paused_ &&
-       manual_compaction_paused_->load(std::memory_order_relaxed))) {
-    status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
+  if (status.ok() &&
+      (shutting_down_->load(std::memory_order_relaxed) || cfd->IsDropped())) {
+    status = Status::ShutdownInProgress(
+        "Database shutdown or Column family drop during compaction");
   }
   if (status.ok()) {
     status = input->status();
@@ -1147,19 +1228,10 @@ Status CompactionJob::FinishCompactionOutputFile(
       lower_bound = nullptr;
     }
     if (next_table_min_key != nullptr) {
-      // This may be the last file in the subcompaction in some cases, so we
-      // need to compare the end key of subcompaction with the next file start
-      // key. When the end key is chosen by the subcompaction, we know that
-      // it must be the biggest key in output file. Therefore, it is safe to
-      // use the smaller key as the upper bound of the output file, to ensure
-      // that there is no overlapping between different output files.
+      // This isn't the last file in the subcompaction, so extend until the next
+      // file starts.
       upper_bound_guard = ExtractUserKey(*next_table_min_key);
-      if (sub_compact->end != nullptr &&
-          ucmp->Compare(upper_bound_guard, *sub_compact->end) >= 0) {
-        upper_bound = sub_compact->end;
-      } else {
-        upper_bound = &upper_bound_guard;
-      }
+      upper_bound = &upper_bound_guard;
     } else {
       // This is the last file in the subcompaction, so extend until the
       // subcompaction ends.
@@ -1177,13 +1249,6 @@ Status CompactionJob::FinishCompactionOutputFile(
       has_overlapping_endpoints = false;
     }
 
-    // The end key of the subcompaction must be bigger or equal to the upper
-    // bound. If the end of subcompaction is null or the upper bound is null,
-    // it means that this file is the last file in the compaction. So there
-    // will be no overlapping between this file and others.
-    assert(sub_compact->end == nullptr ||
-           upper_bound == nullptr ||
-           ucmp->Compare(*upper_bound , *sub_compact->end) <= 0);
     auto it = range_del_agg->NewIterator(lower_bound, upper_bound,
                                          has_overlapping_endpoints);
     // Position the range tombstone output iterator. There may be tombstone
@@ -1296,11 +1361,6 @@ Status CompactionJob::FinishCompactionOutputFile(
   }
   const uint64_t current_bytes = sub_compact->builder->FileSize();
   if (s.ok()) {
-    // Add the checksum information to file metadata.
-    meta->file_checksum = sub_compact->builder->GetFileChecksum();
-    meta->file_checksum_func_name =
-        sub_compact->builder->GetFileChecksumFuncName();
-
     meta->fd.file_size = current_bytes;
   }
   sub_compact->current_output()->finished = true;
@@ -1350,20 +1410,17 @@ Status CompactionJob::FinishCompactionOutputFile(
   }
   std::string fname;
   FileDescriptor output_fd;
-  uint64_t oldest_blob_file_number = kInvalidBlobFileNumber;
   if (meta != nullptr) {
     fname =
         TableFileName(sub_compact->compaction->immutable_cf_options()->cf_paths,
                       meta->fd.GetNumber(), meta->fd.GetPathId());
     output_fd = meta->fd;
-    oldest_blob_file_number = meta->oldest_blob_file_number;
   } else {
     fname = "(nil)";
   }
   EventHelpers::LogAndNotifyTableFileCreationFinished(
       event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname,
-      job_id_, output_fd, oldest_blob_file_number, tp,
-      TableFileCreationReason::kCompaction, s);
+      job_id_, output_fd, tp, TableFileCreationReason::kCompaction, s);
 
 #ifndef ROCKSDB_LITE
   // Report new file to SstFileManagerImpl
@@ -1456,13 +1513,13 @@ Status CompactionJob::OpenCompactionOutputFile(
       TableFileCreationReason::kCompaction);
 #endif  // !ROCKSDB_LITE
   // Make the output file
-  std::unique_ptr<FSWritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
 #ifndef NDEBUG
-  bool syncpoint_arg = file_options_.use_direct_writes;
+  bool syncpoint_arg = env_options_.use_direct_writes;
   TEST_SYNC_POINT_CALLBACK("CompactionJob::OpenCompactionOutputFile",
                            &syncpoint_arg);
 #endif
-  Status s = NewWritableFile(fs_, fname, &writable_file, file_options_);
+  Status s = NewWritableFile(env_, fname, &writable_file, env_options_);
   if (!s.ok()) {
     ROCKS_LOG_ERROR(
         db_options_.info_log,
@@ -1473,48 +1530,26 @@ Status CompactionJob::OpenCompactionOutputFile(
     LogFlush(db_options_.info_log);
     EventHelpers::LogAndNotifyTableFileCreationFinished(
         event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(),
-        fname, job_id_, FileDescriptor(), kInvalidBlobFileNumber,
-        TableProperties(), TableFileCreationReason::kCompaction, s);
+        fname, job_id_, FileDescriptor(), TableProperties(),
+        TableFileCreationReason::kCompaction, s);
     return s;
   }
 
-  // Try to figure out the output file's oldest ancester time.
-  int64_t temp_current_time = 0;
-  auto get_time_status = env_->GetCurrentTime(&temp_current_time);
-  // Safe to proceed even if GetCurrentTime fails. So, log and proceed.
-  if (!get_time_status.ok()) {
-    ROCKS_LOG_WARN(db_options_.info_log,
-                   "Failed to get current time. Status: %s",
-                   get_time_status.ToString().c_str());
-  }
-  uint64_t current_time = static_cast<uint64_t>(temp_current_time);
-  uint64_t oldest_ancester_time =
-      sub_compact->compaction->MinInputFileOldestAncesterTime();
-  if (oldest_ancester_time == port::kMaxUint64) {
-    oldest_ancester_time = current_time;
-  }
+  SubcompactionState::Output out;
+  out.meta.fd =
+      FileDescriptor(file_number, sub_compact->compaction->output_path_id(), 0);
+  out.finished = false;
 
-  // Initialize a SubcompactionState::Output and add it to sub_compact->outputs
-  {
-    SubcompactionState::Output out;
-    out.meta.fd = FileDescriptor(file_number,
-                                 sub_compact->compaction->output_path_id(), 0);
-    out.meta.oldest_ancester_time = oldest_ancester_time;
-    out.meta.file_creation_time = current_time;
-    out.finished = false;
-    sub_compact->outputs.push_back(out);
-  }
-
-  writable_file->SetIOPriority(Env::IOPriority::IO_LOW);
+  sub_compact->outputs.push_back(out);
+  writable_file->SetIOPriority(Env::IO_LOW);
   writable_file->SetWriteLifeTimeHint(write_hint_);
   writable_file->SetPreallocationBlockSize(static_cast<size_t>(
       sub_compact->compaction->OutputFilePreallocationSize()));
   const auto& listeners =
       sub_compact->compaction->immutable_cf_options()->listeners;
   sub_compact->outfile.reset(
-      new WritableFileWriter(std::move(writable_file), fname, file_options_,
-                             env_, db_options_.statistics.get(), listeners,
-                             db_options_.sst_file_checksum_func.get()));
+      new WritableFileWriter(std::move(writable_file), fname, env_options_,
+                             env_, db_options_.statistics.get(), listeners));
 
   // If the Column family flag is to only optimize filters for hits,
   // we can skip creating filters if this is the bottommost_level where
@@ -1522,16 +1557,30 @@ Status CompactionJob::OpenCompactionOutputFile(
   bool skip_filters =
       cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;
 
+  uint64_t output_file_creation_time =
+      sub_compact->compaction->MaxInputFileCreationTime();
+  if (output_file_creation_time == 0) {
+    int64_t _current_time = 0;
+    auto status = db_options_.env->GetCurrentTime(&_current_time);
+    // Safe to proceed even if GetCurrentTime fails. So, log and proceed.
+    if (!status.ok()) {
+      ROCKS_LOG_WARN(
+          db_options_.info_log,
+          "Failed to get current time to populate creation_time property. "
+          "Status: %s",
+          status.ToString().c_str());
+    }
+    output_file_creation_time = static_cast<uint64_t>(_current_time);
+  }
+
   sub_compact->builder.reset(NewTableBuilder(
       *cfd->ioptions(), *(sub_compact->compaction->mutable_cf_options()),
       cfd->internal_comparator(), cfd->int_tbl_prop_collector_factories(),
       cfd->GetID(), cfd->GetName(), sub_compact->outfile.get(),
       sub_compact->compaction->output_compression(),
-      0 /*sample_for_compression */,
       sub_compact->compaction->output_compression_opts(),
-      sub_compact->compaction->output_level(), skip_filters,
-      oldest_ancester_time, 0 /* oldest_key_time */,
-      sub_compact->compaction->max_output_file_size(), current_time));
+      sub_compact->compaction->output_level(), &sub_compact->compression_dict,
+      skip_filters, output_file_creation_time));
   LogFlush(db_options_.info_log);
   return s;
 }
@@ -1588,8 +1637,6 @@ void CompactionJob::UpdateCompactionStats() {
     }
   }
 
-  uint64_t num_output_records = 0;
-
   for (const auto& sub_compact : compact_->sub_compact_states) {
     size_t num_output_files = sub_compact.outputs.size();
     if (sub_compact.builder != nullptr) {
@@ -1599,16 +1646,13 @@ void CompactionJob::UpdateCompactionStats() {
     }
     compaction_stats_.num_output_files += static_cast<int>(num_output_files);
 
-    num_output_records += sub_compact.num_output_records;
-
     for (const auto& out : sub_compact.outputs) {
       compaction_stats_.bytes_written += out.meta.fd.file_size;
     }
-  }
-
-  if (compaction_stats_.num_input_records > num_output_records) {
-    compaction_stats_.num_dropped_records =
-        compaction_stats_.num_input_records - num_output_records;
+    if (sub_compact.num_input_records > sub_compact.num_output_records) {
+      compaction_stats_.num_dropped_records +=
+          sub_compact.num_input_records - sub_compact.num_output_records;
+    }
   }
 }
 
@@ -1636,7 +1680,7 @@ void CompactionJob::UpdateCompactionJobStats(
     // input information
     compaction_job_stats_->total_input_bytes =
         stats.bytes_read_non_output_levels + stats.bytes_read_output_level;
-    compaction_job_stats_->num_input_records = stats.num_input_records;
+    compaction_job_stats_->num_input_records = compact_->num_input_records;
     compaction_job_stats_->num_input_files =
         stats.num_input_files_in_non_output_levels +
         stats.num_input_files_in_output_level;
@@ -1697,4 +1741,4 @@ void CompactionJob::LogCompaction() {
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction_job.h

@@ -18,7 +18,7 @@
 #include <vector>
 
 #include "db/column_family.h"
-#include "db/compaction/compaction_iterator.h"
+#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
 #include "db/flush_scheduler.h"
 #include "db/internal_stats.h"
@@ -29,7 +29,6 @@
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
-#include "logging/event_logger.h"
 #include "options/cf_options.h"
 #include "options/db_options.h"
 #include "port/port.h"
@@ -41,10 +40,11 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
+#include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class Arena;
 class ErrorHandler;
@@ -55,30 +55,24 @@ class Version;
 class VersionEdit;
 class VersionSet;
 
-// CompactionJob is responsible for executing the compaction. Each (manual or
-// automated) compaction corresponds to a CompactionJob object, and usually
-// goes through the stages of `Prepare()`->`Run()`->`Install()`. CompactionJob
-// will divide the compaction into subcompactions and execute them in parallel
-// if needed.
 class CompactionJob {
  public:
   CompactionJob(int job_id, Compaction* compaction,
                 const ImmutableDBOptions& db_options,
-                const FileOptions& file_options, VersionSet* versions,
+                const EnvOptions env_options, VersionSet* versions,
                 const std::atomic<bool>* shutting_down,
                 const SequenceNumber preserve_deletes_seqnum,
-                LogBuffer* log_buffer, FSDirectory* db_directory,
-                FSDirectory* output_directory, Statistics* stats,
-                InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
+                LogBuffer* log_buffer,
+                Directory* db_directory, Directory* output_directory,
+                Statistics* stats, InstrumentedMutex* db_mutex,
+                ErrorHandler* db_error_handler,
                 std::vector<SequenceNumber> existing_snapshots,
                 SequenceNumber earliest_write_conflict_snapshot,
                 const SnapshotChecker* snapshot_checker,
                 std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
                 bool paranoid_file_checks, bool measure_io_stats,
                 const std::string& dbname,
-                CompactionJobStats* compaction_job_stats,
-                Env::Priority thread_pri,
-                const std::atomic<bool>* manual_compaction_paused = nullptr);
+                CompactionJobStats* compaction_job_stats);
 
   ~CompactionJob();
 
@@ -88,28 +82,17 @@ class CompactionJob {
   CompactionJob& operator=(const CompactionJob& job) = delete;
 
   // REQUIRED: mutex held
-  // Prepare for the compaction by setting up boundaries for each subcompaction
   void Prepare();
   // REQUIRED mutex not held
-  // Launch threads for each subcompaction and wait for them to finish. After
-  // that, verify table is usable and finally do bookkeeping to unify
-  // subcompaction results
   Status Run();
 
   // REQUIRED: mutex held
-  // Add compaction input/output to the current version
   Status Install(const MutableCFOptions& mutable_cf_options);
 
  private:
   struct SubcompactionState;
 
   void AggregateStatistics();
-
-  // Generates a histogram representing potential divisions of key ranges from
-  // the input. It adds the starting and/or ending keys of certain input files
-  // to the working set and then finds the approximate size of data in between
-  // each consecutive pair of slices. Then it divides these ranges into
-  // consecutive groups such that each group has a similar size.
   void GenSubcompactionBoundaries();
 
   // update the thread status for starting a compaction.
@@ -150,19 +133,17 @@ class CompactionJob {
   // DBImpl state
   const std::string& dbname_;
   const ImmutableDBOptions& db_options_;
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
 
   Env* env_;
-  FileSystem* fs_;
   // env_option optimized for compaction table reads
-  FileOptions file_options_for_read_;
+  EnvOptions env_optiosn_for_read_;
   VersionSet* versions_;
   const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
   const SequenceNumber preserve_deletes_seqnum_;
   LogBuffer* log_buffer_;
-  FSDirectory* db_directory_;
-  FSDirectory* output_directory_;
+  Directory* db_directory_;
+  Directory* output_directory_;
   Statistics* stats_;
   InstrumentedMutex* db_mutex_;
   ErrorHandler* db_error_handler_;
@@ -183,7 +164,6 @@ class CompactionJob {
 
   EventLogger* event_logger_;
 
-  // Is this compaction creating a file in the bottom most level?
   bool bottommost_level_;
   bool paranoid_file_checks_;
   bool measure_io_stats_;
@@ -192,7 +172,6 @@ class CompactionJob {
   // Stores the approx size of keys covered in the range of each subcompaction
   std::vector<uint64_t> sizes_;
   Env::WriteLifeTimeHint write_hint_;
-  Env::Priority thread_pri_;
 };
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction_job_stats_test.cc

@@ -7,8 +7,12 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
-#include <cinttypes>
 #include <iostream>
 #include <mutex>
 #include <queue>
@@ -17,14 +21,12 @@
 #include <unordered_set>
 #include <utility>
 
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/dbformat.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
 #include "db/write_batch_internal.h"
 #include "env/mock_env.h"
-#include "file/filename.h"
-#include "logging/logging.h"
 #include "memtable/hash_linklist_rep.h"
 #include "monitoring/statistics.h"
 #include "monitoring/thread_status_util.h"
@@ -45,23 +47,25 @@
 #include "rocksdb/thread_status.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/write_batch_with_index.h"
-#include "table/block_based/block_based_table_factory.h"
+#include "table/block_based_table_factory.h"
 #include "table/mock_table.h"
-#include "table/plain/plain_table_factory.h"
+#include "table/plain_table_factory.h"
 #include "table/scoped_arena_iterator.h"
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/compression.h"
+#include "util/filename.h"
 #include "util/hash.h"
+#include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/rate_limiter.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
 #if !defined(IOS_CROSS_COMPILE)
 #ifndef ROCKSDB_LITE
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 static std::string RandomString(Random* rnd, int len, double ratio) {
   std::string r;
@@ -109,10 +113,10 @@ class CompactionJobStatsTest : public testing::Test,
     Reopen(options);
   }
 
-  ~CompactionJobStatsTest() override {
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({});
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  ~CompactionJobStatsTest() {
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->LoadDependency({});
+    rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
     Close();
     Options options;
     options.db_paths.emplace_back(dbname_, 0);
@@ -422,7 +426,7 @@ class CompactionJobStatsChecker : public EventListener {
   // Once a compaction completed, this function will verify the returned
   // CompactionJobInfo with the oldest CompactionJobInfo added earlier
   // in "expected_stats_" which has not yet being used for verification.
-  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
+  virtual void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) {
     if (verify_next_comp_io_stats_) {
       ASSERT_GT(ci.stats.file_write_nanos, 0);
       ASSERT_GT(ci.stats.file_range_sync_nanos, 0);
@@ -519,7 +523,7 @@ class CompactionJobDeletionStatsChecker : public CompactionJobStatsChecker {
  public:
   // Verifies whether two CompactionJobStats match.
   void Verify(const CompactionJobStats& current_stats,
-              const CompactionJobStats& stats) override {
+              const CompactionJobStats& stats) {
     ASSERT_EQ(
       current_stats.num_input_deletion_records,
       stats.num_input_deletion_records);
@@ -801,7 +805,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
 
     stats_checker->set_verify_next_comp_io_stats(true);
     std::atomic<bool> first_prepare_write(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::Append:BeforePrepareWrite", [&](void* /*arg*/) {
           if (first_prepare_write.load()) {
             options.env->SleepForMicroseconds(3);
@@ -810,7 +814,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
         });
 
     std::atomic<bool> first_flush(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::Flush:BeforeAppend", [&](void* /*arg*/) {
           if (first_flush.load()) {
             options.env->SleepForMicroseconds(3);
@@ -819,7 +823,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
         });
 
     std::atomic<bool> first_sync(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::SyncInternal:0", [&](void* /*arg*/) {
           if (first_sync.load()) {
             options.env->SleepForMicroseconds(3);
@@ -828,14 +832,14 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
         });
 
     std::atomic<bool> first_range_sync(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::RangeSync:0", [&](void* /*arg*/) {
           if (first_range_sync.load()) {
             options.env->SleepForMicroseconds(3);
             first_range_sync.store(false);
           }
         });
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+    rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
     Compact(1, smallest_key, largest_key);
 
@@ -844,7 +848,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
     ASSERT_TRUE(!first_flush.load());
     ASSERT_TRUE(!first_sync.load());
     ASSERT_TRUE(!first_range_sync.load());
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   }
   ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 0U);
 }
@@ -1019,10 +1023,10 @@ TEST_P(CompactionJobStatsTest, UniversalCompactionTest) {
 
 INSTANTIATE_TEST_CASE_P(CompactionJobStatsTest, CompactionJobStatsTest,
                         ::testing::Values(1, 4));
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/compaction_job_test.cc

@@ -6,30 +6,26 @@
 #ifndef ROCKSDB_LITE
 
 #include <algorithm>
-#include <array>
-#include <cinttypes>
 #include <map>
 #include <string>
 #include <tuple>
 
-#include "db/blob/blob_index.h"
 #include "db/column_family.h"
-#include "db/compaction/compaction_job.h"
-#include "db/db_impl/db_impl.h"
+#include "db/compaction_job.h"
 #include "db/error_handler.h"
 #include "db/version_set.h"
-#include "file/writable_file_writer.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/options.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/mock_table.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/file_reader_writer.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 namespace {
 
@@ -72,7 +68,6 @@ class CompactionJobTest : public testing::Test {
  public:
   CompactionJobTest()
       : env_(Env::Default()),
-        fs_(std::make_shared<LegacyFileSystemWrapper>(env_)),
         dbname_(test::PerThreadDBPath("compaction_job_test")),
         db_options_(),
         mutable_cf_options_(cf_options_),
@@ -80,15 +75,12 @@ class CompactionJobTest : public testing::Test {
         write_buffer_manager_(db_options_.db_write_buffer_size),
         versions_(new VersionSet(dbname_, &db_options_, env_options_,
                                  table_cache_.get(), &write_buffer_manager_,
-                                 &write_controller_,
-                                 /*block_cache_tracer=*/nullptr)),
+                                 &write_controller_)),
         shutting_down_(false),
         preserve_deletes_seqnum_(0),
         mock_table_factory_(new mock::MockTableFactory()),
         error_handler_(nullptr, db_options_, &mutex_) {
     EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    db_options_.env = env_;
-    db_options_.fs = fs_;
     db_options_.db_paths.emplace_back(dbname_,
                                       std::numeric_limits<uint64_t>::max());
   }
@@ -101,34 +93,11 @@ class CompactionJobTest : public testing::Test {
     return TableFileName(db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());
   }
 
-  static std::string KeyStr(const std::string& user_key,
-                            const SequenceNumber seq_num, const ValueType t) {
+  std::string KeyStr(const std::string& user_key, const SequenceNumber seq_num,
+      const ValueType t) {
     return InternalKey(user_key, seq_num, t).Encode().ToString();
   }
 
-  static std::string BlobStr(uint64_t blob_file_number, uint64_t offset,
-                             uint64_t size) {
-    std::string blob_index;
-    BlobIndex::EncodeBlob(&blob_index, blob_file_number, offset, size,
-                          kNoCompression);
-    return blob_index;
-  }
-
-  static std::string BlobStrTTL(uint64_t blob_file_number, uint64_t offset,
-                                uint64_t size, uint64_t expiration) {
-    std::string blob_index;
-    BlobIndex::EncodeBlobTTL(&blob_index, expiration, blob_file_number, offset,
-                             size, kNoCompression);
-    return blob_index;
-  }
-
-  static std::string BlobStrInlinedTTL(const Slice& value,
-                                       uint64_t expiration) {
-    std::string blob_index;
-    BlobIndex::EncodeInlinedTTL(&blob_index, expiration, value);
-    return blob_index;
-  }
-
   void AddMockFile(const stl_wrappers::KVMap& contents, int level = 0) {
     assert(contents.size() > 0);
 
@@ -137,13 +106,12 @@ class CompactionJobTest : public testing::Test {
     InternalKey smallest_key, largest_key;
     SequenceNumber smallest_seqno = kMaxSequenceNumber;
     SequenceNumber largest_seqno = 0;
-    uint64_t oldest_blob_file_number = kInvalidBlobFileNumber;
     for (auto kv : contents) {
       ParsedInternalKey key;
       std::string skey;
       std::string value;
       std::tie(skey, value) = kv;
-      bool parsed = ParseInternalKey(skey, &key);
+      ParseInternalKey(skey, &key);
 
       smallest_seqno = std::min(smallest_seqno, key.sequence);
       largest_seqno = std::max(largest_seqno, key.sequence);
@@ -160,24 +128,6 @@ class CompactionJobTest : public testing::Test {
       }
 
       first_key = false;
-
-      if (parsed && key.type == kTypeBlobIndex) {
-        BlobIndex blob_index;
-        const Status s = blob_index.DecodeFrom(value);
-        if (!s.ok()) {
-          continue;
-        }
-
-        if (blob_index.IsInlined() || blob_index.HasTTL() ||
-            blob_index.file_number() == kInvalidBlobFileNumber) {
-          continue;
-        }
-
-        if (oldest_blob_file_number == kInvalidBlobFileNumber ||
-            oldest_blob_file_number > blob_index.file_number()) {
-          oldest_blob_file_number = blob_index.file_number();
-        }
-      }
     }
 
     uint64_t file_number = versions_->NewFileNumber();
@@ -186,9 +136,7 @@ class CompactionJobTest : public testing::Test {
 
     VersionEdit edit;
     edit.AddFile(level, file_number, 0, 10, smallest_key, largest_key,
-                 smallest_seqno, largest_seqno, false, oldest_blob_file_number,
-                 kUnknownOldestAncesterTime, kUnknownFileCreationTime,
-                 kUnknownFileChecksum, kUnknownFileChecksumFuncName);
+        smallest_seqno, largest_seqno, false);
 
     mutex_.Lock();
     versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
@@ -224,7 +172,7 @@ class CompactionJobTest : public testing::Test {
         // This is how the key will look like once it's written in bottommost
         // file
         InternalKey bottommost_internal_key(
-            key, 0, kTypeValue);
+            key, (key == "9999") ? sequence_number : 0, kTypeValue);
 
         if (corrupt_id(k)) {
           test::CorruptKeyType(&internal_key);
@@ -246,22 +194,7 @@ class CompactionJobTest : public testing::Test {
   }
 
   void NewDB() {
-    DestroyDB(dbname_, Options());
-    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    versions_.reset(new VersionSet(dbname_, &db_options_, env_options_,
-                                   table_cache_.get(), &write_buffer_manager_,
-                                   &write_controller_,
-                                   /*block_cache_tracer=*/nullptr));
-    compaction_job_stats_.Reset();
-    SetIdentityFile(env_, dbname_);
-
     VersionEdit new_db;
-    if (db_options_.write_dbid_to_manifest) {
-      DBImpl* impl = new DBImpl(DBOptions(), dbname_);
-      std::string db_id;
-      impl->GetDbIdentityFromIdentityFile(&db_id);
-      new_db.SetDBId(db_id);
-    }
     new_db.SetLogNumber(0);
     new_db.SetNextFile(2);
     new_db.SetLastSequence(0);
@@ -271,8 +204,8 @@ class CompactionJobTest : public testing::Test {
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
-    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-        NewLegacyWritableFileWrapper(std::move(file)), manifest, env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), manifest, env_options_));
     {
       log::Writer log(std::move(file_writer), 0, false);
       std::string record;
@@ -297,9 +230,7 @@ class CompactionJobTest : public testing::Test {
       const std::vector<std::vector<FileMetaData*>>& input_files,
       const stl_wrappers::KVMap& expected_results,
       const std::vector<SequenceNumber>& snapshots = {},
-      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber,
-      int output_level = 1, bool verify = true,
-      uint64_t expected_oldest_blob_file_number = kInvalidBlobFileNumber) {
+      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
     auto cfd = versions_->GetColumnFamilySet()->GetDefault();
 
     size_t num_input_files = 0;
@@ -316,7 +247,7 @@ class CompactionJobTest : public testing::Test {
 
     Compaction compaction(cfd->current()->storage_info(), *cfd->ioptions(),
                           *cfd->GetLatestMutableCFOptions(),
-                          compaction_input_files, output_level, 1024 * 1024,
+                          compaction_input_files, 1, 1024 * 1024,
                           10 * 1024 * 1024, 0, kNoCompression,
                           cfd->ioptions()->compression_opts, 0, {}, true);
     compaction.SetInputVersion(cfd->current());
@@ -331,8 +262,7 @@ class CompactionJobTest : public testing::Test {
         &shutting_down_, preserve_deletes_seqnum_, &log_buffer, nullptr,
         nullptr, nullptr, &mutex_, &error_handler_, snapshots,
         earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_,
-        Env::Priority::USER);
+        &event_logger, false, false, dbname_, &compaction_job_stats_);
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 
     compaction_job.Prepare();
@@ -344,27 +274,19 @@ class CompactionJobTest : public testing::Test {
     ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions()));
     mutex_.Unlock();
 
-    if (verify) {
+    if (expected_results.size() == 0) {
       ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
       ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-
-      if (expected_results.empty()) {
-        ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
-      } else {
-        ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
-        mock_table_factory_->AssertLatestFile(expected_results);
-
-        auto output_files =
-            cfd->current()->storage_info()->LevelFiles(output_level);
-        ASSERT_EQ(output_files.size(), 1);
-        ASSERT_EQ(output_files[0]->oldest_blob_file_number,
-                  expected_oldest_blob_file_number);
-      }
+      ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
+    } else {
+      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
+      ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
+      mock_table_factory_->AssertLatestFile(expected_results);
     }
   }
 
   Env* env_;
-  std::shared_ptr<FileSystem> fs_;
   std::string dbname_;
   EnvOptions env_options_;
   ImmutableDBOptions db_options_;
@@ -457,7 +379,7 @@ TEST_F(CompactionJobTest, SimpleOverwrite) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "val2"},
-                          {KeyStr("b", 0U, kTypeValue), "val3"}});
+                          {KeyStr("b", 4U, kTypeValue), "val3"}});
 
   SetLastSequence(4U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -510,7 +432,7 @@ TEST_F(CompactionJobTest, SimpleMerge) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 0U, kTypeValue), "1,2"}});
+                          {KeyStr("b", 2U, kTypeValue), "1,2"}});
 
   SetLastSequence(5U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -534,7 +456,7 @@ TEST_F(CompactionJobTest, NonAssocMerge) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 0U, kTypeValue), "1,2"}});
+                          {KeyStr("b", 2U, kTypeValue), "1,2"}});
 
   SetLastSequence(5U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -561,7 +483,7 @@ TEST_F(CompactionJobTest, MergeOperandFilter) {
 
   auto expected_results =
       mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), test::EncodeInt(8U)},
-                          {KeyStr("b", 0U, kTypeValue), test::EncodeInt(2U)}});
+                          {KeyStr("b", 2U, kTypeValue), test::EncodeInt(2U)}});
 
   SetLastSequence(5U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -824,7 +746,7 @@ TEST_F(CompactionJobTest, SingleDeleteZeroSeq) {
   AddMockFile(file2);
 
   auto expected_results = mock::MakeMockFile({
-      {KeyStr("dummy", 0U, kTypeValue), "val2"},
+      {KeyStr("dummy", 5U, kTypeValue), "val2"},
   });
 
   SetLastSequence(22U);
@@ -1008,62 +930,14 @@ TEST_F(CompactionJobTest, CorruptionAfterDeletion) {
       mock::MakeMockFile({{test::KeyStr("A", 0U, kTypeValue), "val3"},
                           {test::KeyStr("a", 0U, kTypeValue, true), "val"},
                           {test::KeyStr("b", 0U, kTypeValue, true), "val"},
-                          {test::KeyStr("c", 0U, kTypeValue), "val2"}});
+                          {test::KeyStr("c", 1U, kTypeValue), "val2"}});
 
   SetLastSequence(6U);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
   RunCompaction({files}, expected_results);
 }
 
-TEST_F(CompactionJobTest, OldestBlobFileNumber) {
-  NewDB();
-
-  // Note: blob1 is inlined TTL, so it will not be considered for the purposes
-  // of identifying the oldest referenced blob file. Similarly, blob6 will be
-  // ignored because it has TTL and hence refers to a TTL blob file.
-  const stl_wrappers::KVMap::value_type blob1(
-      KeyStr("a", 1U, kTypeBlobIndex), BlobStrInlinedTTL("foo", 1234567890ULL));
-  const stl_wrappers::KVMap::value_type blob2(KeyStr("b", 2U, kTypeBlobIndex),
-                                              BlobStr(59, 123456, 999));
-  const stl_wrappers::KVMap::value_type blob3(KeyStr("c", 3U, kTypeBlobIndex),
-                                              BlobStr(138, 1000, 1 << 8));
-  auto file1 = mock::MakeMockFile({blob1, blob2, blob3});
-  AddMockFile(file1);
-
-  const stl_wrappers::KVMap::value_type blob4(KeyStr("d", 4U, kTypeBlobIndex),
-                                              BlobStr(199, 3 << 10, 1 << 20));
-  const stl_wrappers::KVMap::value_type blob5(KeyStr("e", 5U, kTypeBlobIndex),
-                                              BlobStr(19, 6789, 333));
-  const stl_wrappers::KVMap::value_type blob6(
-      KeyStr("f", 6U, kTypeBlobIndex),
-      BlobStrTTL(5, 2048, 1 << 7, 1234567890ULL));
-  auto file2 = mock::MakeMockFile({blob4, blob5, blob6});
-  AddMockFile(file2);
-
-  const stl_wrappers::KVMap::value_type expected_blob1(
-      KeyStr("a", 0U, kTypeBlobIndex), blob1.second);
-  const stl_wrappers::KVMap::value_type expected_blob2(
-      KeyStr("b", 0U, kTypeBlobIndex), blob2.second);
-  const stl_wrappers::KVMap::value_type expected_blob3(
-      KeyStr("c", 0U, kTypeBlobIndex), blob3.second);
-  const stl_wrappers::KVMap::value_type expected_blob4(
-      KeyStr("d", 0U, kTypeBlobIndex), blob4.second);
-  const stl_wrappers::KVMap::value_type expected_blob5(
-      KeyStr("e", 0U, kTypeBlobIndex), blob5.second);
-  const stl_wrappers::KVMap::value_type expected_blob6(
-      KeyStr("f", 0U, kTypeBlobIndex), blob6.second);
-  auto expected_results =
-      mock::MakeMockFile({expected_blob1, expected_blob2, expected_blob3,
-                          expected_blob4, expected_blob5, expected_blob6});
-
-  SetLastSequence(6U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, std::vector<SequenceNumber>(),
-                kMaxSequenceNumber, /* output_level */ 1, /* verify */ true,
-                /* expected_oldest_blob_file_number */ 19);
-}
-
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compaction_picker.cc

@@ -7,23 +7,27 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#include "db/compaction/compaction_picker.h"
+#include "db/compaction_picker.h"
 
-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <limits>
 #include <queue>
 #include <string>
 #include <utility>
 #include <vector>
 #include "db/column_family.h"
-#include "file/filename.h"
-#include "logging/log_buffer.h"
 #include "monitoring/statistics.h"
-#include "test_util/sync_point.h"
+#include "util/filename.h"
+#include "util/log_buffer.h"
 #include "util/random.h"
 #include "util/string_util.h"
+#include "util/sync_point.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 namespace {
 uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
@@ -38,54 +42,29 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
 bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                            size_t min_files_to_compact,
                            uint64_t max_compact_bytes_per_del_file,
-                           uint64_t max_compaction_bytes,
-                           CompactionInputFiles* comp_inputs,
-                           SequenceNumber earliest_mem_seqno) {
-  // Do not pick ingested file when there is at least one memtable not flushed
-  // which of seqno is overlap with the sst.
-  TEST_SYNC_POINT("FindIntraL0Compaction");
-  size_t start = 0;
-  for (; start < level_files.size(); start++) {
-    if (level_files[start]->being_compacted) {
-      return false;
-    }
-    // If there is no data in memtable, the earliest sequence number would the
-    // largest sequence number in last memtable.
-    // Because all files are sorted in descending order by largest_seqno, so we
-    // only need to check the first one.
-    if (level_files[start]->fd.largest_seqno <= earliest_mem_seqno) {
-      break;
-    }
-  }
-  if (start >= level_files.size()) {
-    return false;
-  }
-  size_t compact_bytes = static_cast<size_t>(level_files[start]->fd.file_size);
-  uint64_t compensated_compact_bytes =
-      level_files[start]->compensated_file_size;
+                           CompactionInputFiles* comp_inputs) {
+  size_t compact_bytes = static_cast<size_t>(level_files[0]->fd.file_size);
   size_t compact_bytes_per_del_file = port::kMaxSizet;
-  // Compaction range will be [start, limit).
-  size_t limit;
-  // Pull in files until the amount of compaction work per deleted file begins
-  // increasing or maximum total compaction size is reached.
+  // compaction range will be [0, span_len).
+  size_t span_len;
+  // pull in files until the amount of compaction work per deleted file begins
+  // increasing.
   size_t new_compact_bytes_per_del_file = 0;
-  for (limit = start + 1; limit < level_files.size(); ++limit) {
-    compact_bytes += static_cast<size_t>(level_files[limit]->fd.file_size);
-    compensated_compact_bytes += level_files[limit]->compensated_file_size;
-    new_compact_bytes_per_del_file = compact_bytes / (limit - start);
-    if (level_files[limit]->being_compacted ||
-        new_compact_bytes_per_del_file > compact_bytes_per_del_file ||
-        compensated_compact_bytes > max_compaction_bytes) {
+  for (span_len = 1; span_len < level_files.size(); ++span_len) {
+    compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
+    new_compact_bytes_per_del_file = compact_bytes / span_len;
+    if (level_files[span_len]->being_compacted ||
+        new_compact_bytes_per_del_file > compact_bytes_per_del_file) {
       break;
     }
     compact_bytes_per_del_file = new_compact_bytes_per_del_file;
   }
 
-  if ((limit - start) >= min_files_to_compact &&
+  if (span_len >= min_files_to_compact &&
       compact_bytes_per_del_file < max_compact_bytes_per_del_file) {
     assert(comp_inputs != nullptr);
     comp_inputs->level = 0;
-    for (size_t i = start; i < limit; ++i) {
+    for (size_t i = 0; i < span_len; ++i) {
       comp_inputs->files.push_back(level_files[i]);
     }
     return true;
@@ -564,9 +543,9 @@ void CompactionPicker::GetGrandparents(
 Compaction* CompactionPicker::CompactRange(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     VersionStorageInfo* vstorage, int input_level, int output_level,
-    const CompactRangeOptions& compact_range_options, const InternalKey* begin,
-    const InternalKey* end, InternalKey** compaction_end, bool* manual_conflict,
-    uint64_t max_file_num_to_ignore) {
+    uint32_t output_path_id, uint32_t max_subcompactions,
+    const InternalKey* begin, const InternalKey* end,
+    InternalKey** compaction_end, bool* manual_conflict) {
   // CompactionPickerFIFO has its own implementation of compact range
   assert(ioptions_.compaction_style != kCompactionStyleFIFO);
 
@@ -630,13 +609,11 @@ Compaction* CompactionPicker::CompactRange(
         output_level,
         MaxFileSizeForLevel(mutable_cf_options, output_level,
                             ioptions_.compaction_style),
-        /* max_compaction_bytes */ LLONG_MAX,
-        compact_range_options.target_path_id,
+        /* max_compaction_bytes */ LLONG_MAX, output_path_id,
         GetCompressionType(ioptions_, vstorage, mutable_cf_options,
                            output_level, 1),
         GetCompressionOptions(ioptions_, vstorage, output_level),
-        compact_range_options.max_subcompactions, /* grandparents */ {},
-        /* is manual */ true);
+        max_subcompactions, /* grandparents */ {}, /* is manual */ true);
     RegisterCompaction(c);
     return c;
   }
@@ -681,43 +658,7 @@ Compaction* CompactionPicker::CompactRange(
       }
     }
   }
-  assert(compact_range_options.target_path_id <
-         static_cast<uint32_t>(ioptions_.cf_paths.size()));
-
-  // for BOTTOM LEVEL compaction only, use max_file_num_to_ignore to filter out
-  // files that are created during the current compaction.
-  if (compact_range_options.bottommost_level_compaction ==
-          BottommostLevelCompaction::kForceOptimized &&
-      max_file_num_to_ignore != port::kMaxUint64) {
-    assert(input_level == output_level);
-    // inputs_shrunk holds a continuous subset of input files which were all
-    // created before the current manual compaction
-    std::vector<FileMetaData*> inputs_shrunk;
-    size_t skip_input_index = inputs.size();
-    for (size_t i = 0; i < inputs.size(); ++i) {
-      if (inputs[i]->fd.GetNumber() < max_file_num_to_ignore) {
-        inputs_shrunk.push_back(inputs[i]);
-      } else if (!inputs_shrunk.empty()) {
-        // inputs[i] was created during the current manual compaction and
-        // need to be skipped
-        skip_input_index = i;
-        break;
-      }
-    }
-    if (inputs_shrunk.empty()) {
-      return nullptr;
-    }
-    if (inputs.size() != inputs_shrunk.size()) {
-      inputs.files.swap(inputs_shrunk);
-    }
-    // set covering_the_whole_range to false if there is any file that need to
-    // be compacted in the range of inputs[skip_input_index+1, inputs.size())
-    for (size_t i = skip_input_index + 1; i < inputs.size(); ++i) {
-      if (inputs[i]->fd.GetNumber() < max_file_num_to_ignore) {
-        covering_the_whole_range = false;
-      }
-    }
-  }
+  assert(output_path_id < static_cast<uint32_t>(ioptions_.cf_paths.size()));
 
   InternalKey key_storage;
   InternalKey* next_smallest = &key_storage;
@@ -783,12 +724,11 @@ Compaction* CompactionPicker::CompactRange(
       MaxFileSizeForLevel(mutable_cf_options, output_level,
                           ioptions_.compaction_style, vstorage->base_level(),
                           ioptions_.level_compaction_dynamic_level_bytes),
-      mutable_cf_options.max_compaction_bytes,
-      compact_range_options.target_path_id,
+      mutable_cf_options.max_compaction_bytes, output_path_id,
       GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                          vstorage->base_level()),
       GetCompressionOptions(ioptions_, vstorage, output_level),
-      compact_range_options.max_subcompactions, std::move(grandparents),
+      max_subcompactions, std::move(grandparents),
       /* is manual compaction */ true);
 
   TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);
@@ -1128,4 +1068,484 @@ bool CompactionPicker::GetOverlappingL0Files(
   return true;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+bool LevelCompactionPicker::NeedsCompaction(
+    const VersionStorageInfo* vstorage) const {
+  if (!vstorage->ExpiredTtlFiles().empty()) {
+    return true;
+  }
+  if (!vstorage->BottommostFilesMarkedForCompaction().empty()) {
+    return true;
+  }
+  if (!vstorage->FilesMarkedForCompaction().empty()) {
+    return true;
+  }
+  for (int i = 0; i <= vstorage->MaxInputLevel(); i++) {
+    if (vstorage->CompactionScore(i) >= 1) {
+      return true;
+    }
+  }
+  return false;
+}
+
+namespace {
+// A class to build a leveled compaction step-by-step.
+class LevelCompactionBuilder {
+ public:
+  LevelCompactionBuilder(const std::string& cf_name,
+                         VersionStorageInfo* vstorage,
+                         CompactionPicker* compaction_picker,
+                         LogBuffer* log_buffer,
+                         const MutableCFOptions& mutable_cf_options,
+                         const ImmutableCFOptions& ioptions)
+      : cf_name_(cf_name),
+        vstorage_(vstorage),
+        compaction_picker_(compaction_picker),
+        log_buffer_(log_buffer),
+        mutable_cf_options_(mutable_cf_options),
+        ioptions_(ioptions) {}
+
+  // Pick and return a compaction.
+  Compaction* PickCompaction();
+
+  // Pick the initial files to compact to the next level. (or together
+  // in Intra-L0 compactions)
+  void SetupInitialFiles();
+
+  // If the initial files are from L0 level, pick other L0
+  // files if needed.
+  bool SetupOtherL0FilesIfNeeded();
+
+  // Based on initial files, setup other files need to be compacted
+  // in this compaction, accordingly.
+  bool SetupOtherInputsIfNeeded();
+
+  Compaction* GetCompaction();
+
+  // For the specfied level, pick a file that we want to compact.
+  // Returns false if there is no file to compact.
+  // If it returns true, inputs->files.size() will be exactly one.
+  // If level is 0 and there is already a compaction on that level, this
+  // function will return false.
+  bool PickFileToCompact();
+
+  // For L0->L0, picks the longest span of files that aren't currently
+  // undergoing compaction for which work-per-deleted-file decreases. The span
+  // always starts from the newest L0 file.
+  //
+  // Intra-L0 compaction is independent of all other files, so it can be
+  // performed even when L0->base_level compactions are blocked.
+  //
+  // Returns true if `inputs` is populated with a span of files to be compacted;
+  // otherwise, returns false.
+  bool PickIntraL0Compaction();
+
+  void PickExpiredTtlFiles();
+
+  const std::string& cf_name_;
+  VersionStorageInfo* vstorage_;
+  CompactionPicker* compaction_picker_;
+  LogBuffer* log_buffer_;
+  int start_level_ = -1;
+  int output_level_ = -1;
+  int parent_index_ = -1;
+  int base_index_ = -1;
+  double start_level_score_ = 0;
+  bool is_manual_ = false;
+  CompactionInputFiles start_level_inputs_;
+  std::vector<CompactionInputFiles> compaction_inputs_;
+  CompactionInputFiles output_level_inputs_;
+  std::vector<FileMetaData*> grandparents_;
+  CompactionReason compaction_reason_ = CompactionReason::kUnknown;
+
+  const MutableCFOptions& mutable_cf_options_;
+  const ImmutableCFOptions& ioptions_;
+  // Pick a path ID to place a newly generated file, with its level
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            int level);
+
+  static const int kMinFilesForIntraL0Compaction = 4;
+};
+
+void LevelCompactionBuilder::PickExpiredTtlFiles() {
+  if (vstorage_->ExpiredTtlFiles().empty()) {
+    return;
+  }
+
+  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
+    // If it's being compacted it has nothing to do here.
+    // If this assert() fails that means that some function marked some
+    // files as being_compacted, but didn't call ComputeCompactionScore()
+    assert(!level_file.second->being_compacted);
+    start_level_ = level_file.first;
+    output_level_ =
+        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
+
+    if ((start_level_ == vstorage_->num_non_empty_levels() - 1) ||
+        (start_level_ == 0 &&
+         !compaction_picker_->level0_compactions_in_progress()->empty())) {
+      return false;
+    }
+
+    start_level_inputs_.files = {level_file.second};
+    start_level_inputs_.level = start_level_;
+    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                      &start_level_inputs_);
+  };
+
+  for (auto& level_file : vstorage_->ExpiredTtlFiles()) {
+    if (continuation(level_file)) {
+      // found the compaction!
+      return;
+    }
+  }
+
+  start_level_inputs_.files.clear();
+}
+
+void LevelCompactionBuilder::SetupInitialFiles() {
+  // Find the compactions by size on all levels.
+  bool skipped_l0_to_base = false;
+  for (int i = 0; i < compaction_picker_->NumberLevels() - 1; i++) {
+    start_level_score_ = vstorage_->CompactionScore(i);
+    start_level_ = vstorage_->CompactionScoreLevel(i);
+    assert(i == 0 || start_level_score_ <= vstorage_->CompactionScore(i - 1));
+    if (start_level_score_ >= 1) {
+      if (skipped_l0_to_base && start_level_ == vstorage_->base_level()) {
+        // If L0->base_level compaction is pending, don't schedule further
+        // compaction from base level. Otherwise L0->base_level compaction
+        // may starve.
+        continue;
+      }
+      output_level_ =
+          (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
+      if (PickFileToCompact()) {
+        // found the compaction!
+        if (start_level_ == 0) {
+          // L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
+          compaction_reason_ = CompactionReason::kLevelL0FilesNum;
+        } else {
+          // L1+ score = `Level files size` / `MaxBytesForLevel`
+          compaction_reason_ = CompactionReason::kLevelMaxLevelSize;
+        }
+        break;
+      } else {
+        // didn't find the compaction, clear the inputs
+        start_level_inputs_.clear();
+        if (start_level_ == 0) {
+          skipped_l0_to_base = true;
+          // L0->base_level may be blocked due to ongoing L0->base_level
+          // compactions. It may also be blocked by an ongoing compaction from
+          // base_level downwards.
+          //
+          // In these cases, to reduce L0 file count and thus reduce likelihood
+          // of write stalls, we can attempt compacting a span of files within
+          // L0.
+          if (PickIntraL0Compaction()) {
+            output_level_ = 0;
+            compaction_reason_ = CompactionReason::kLevelL0FilesNum;
+            break;
+          }
+        }
+      }
+    }
+  }
+
+  // if we didn't find a compaction, check if there are any files marked for
+  // compaction
+  if (start_level_inputs_.empty()) {
+    parent_index_ = base_index_ = -1;
+
+    // PickFilesMarkedForCompaction();
+    compaction_picker_->PickFilesMarkedForCompaction(
+        cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_);
+    if (!start_level_inputs_.empty()) {
+      is_manual_ = true;
+      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
+      return;
+    }
+
+    size_t i;
+    for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
+         ++i) {
+      auto& level_and_file = vstorage_->BottommostFilesMarkedForCompaction()[i];
+      assert(!level_and_file.second->being_compacted);
+      start_level_inputs_.level = output_level_ = start_level_ =
+          level_and_file.first;
+      start_level_inputs_.files = {level_and_file.second};
+      if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                     &start_level_inputs_)) {
+        break;
+      }
+    }
+    if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
+      start_level_inputs_.clear();
+    } else {
+      assert(!start_level_inputs_.empty());
+      compaction_reason_ = CompactionReason::kBottommostFiles;
+      return;
+    }
+
+    assert(start_level_inputs_.empty());
+    PickExpiredTtlFiles();
+    if (!start_level_inputs_.empty()) {
+      compaction_reason_ = CompactionReason::kTtl;
+    }
+  }
+}
+
+bool LevelCompactionBuilder::SetupOtherL0FilesIfNeeded() {
+  if (start_level_ == 0 && output_level_ != 0) {
+    return compaction_picker_->GetOverlappingL0Files(
+        vstorage_, &start_level_inputs_, output_level_, &parent_index_);
+  }
+  return true;
+}
+
+bool LevelCompactionBuilder::SetupOtherInputsIfNeeded() {
+  // Setup input files from output level. For output to L0, we only compact
+  // spans of files that do not interact with any pending compactions, so don't
+  // need to consider other levels.
+  if (output_level_ != 0) {
+    output_level_inputs_.level = output_level_;
+    if (!compaction_picker_->SetupOtherInputs(
+            cf_name_, mutable_cf_options_, vstorage_, &start_level_inputs_,
+            &output_level_inputs_, &parent_index_, base_index_)) {
+      return false;
+    }
+
+    compaction_inputs_.push_back(start_level_inputs_);
+    if (!output_level_inputs_.empty()) {
+      compaction_inputs_.push_back(output_level_inputs_);
+    }
+
+    // In some edge cases we could pick a compaction that will be compacting
+    // a key range that overlap with another running compaction, and both
+    // of them have the same output level. This could happen if
+    // (1) we are running a non-exclusive manual compaction
+    // (2) AddFile ingest a new file into the LSM tree
+    // We need to disallow this from happening.
+    if (compaction_picker_->FilesRangeOverlapWithCompaction(compaction_inputs_,
+                                                            output_level_)) {
+      // This compaction output could potentially conflict with the output
+      // of a currently running compaction, we cannot run it.
+      return false;
+    }
+    compaction_picker_->GetGrandparents(vstorage_, start_level_inputs_,
+                                        output_level_inputs_, &grandparents_);
+  } else {
+    compaction_inputs_.push_back(start_level_inputs_);
+  }
+  return true;
+}
+
+Compaction* LevelCompactionBuilder::PickCompaction() {
+  // Pick up the first file to start compaction. It may have been extended
+  // to a clean cut.
+  SetupInitialFiles();
+  if (start_level_inputs_.empty()) {
+    return nullptr;
+  }
+  assert(start_level_ >= 0 && output_level_ >= 0);
+
+  // If it is a L0 -> base level compaction, we need to set up other L0
+  // files if needed.
+  if (!SetupOtherL0FilesIfNeeded()) {
+    return nullptr;
+  }
+
+  // Pick files in the output level and expand more files in the start level
+  // if needed.
+  if (!SetupOtherInputsIfNeeded()) {
+    return nullptr;
+  }
+
+  // Form a compaction object containing the files we picked.
+  Compaction* c = GetCompaction();
+
+  TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
+
+  return c;
+}
+
+Compaction* LevelCompactionBuilder::GetCompaction() {
+  auto c = new Compaction(
+      vstorage_, ioptions_, mutable_cf_options_, std::move(compaction_inputs_),
+      output_level_,
+      MaxFileSizeForLevel(mutable_cf_options_, output_level_,
+                          ioptions_.compaction_style, vstorage_->base_level(),
+                          ioptions_.level_compaction_dynamic_level_bytes),
+      mutable_cf_options_.max_compaction_bytes,
+      GetPathId(ioptions_, mutable_cf_options_, output_level_),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level_, vstorage_->base_level()),
+      GetCompressionOptions(ioptions_, vstorage_, output_level_),
+      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
+      start_level_score_, false /* deletion_compaction */, compaction_reason_);
+
+  // If it's level 0 compaction, make sure we don't execute any other level 0
+  // compactions in parallel
+  compaction_picker_->RegisterCompaction(c);
+
+  // Creating a compaction influences the compaction score because the score
+  // takes running compactions into account (by skipping files that are already
+  // being compacted). Since we just changed compaction score, we recalculate it
+  // here
+  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
+  return c;
+}
+
+/*
+ * Find the optimal path to place a file
+ * Given a level, finds the path where levels up to it will fit in levels
+ * up to and including this path
+ */
+uint32_t LevelCompactionBuilder::GetPathId(
+    const ImmutableCFOptions& ioptions,
+    const MutableCFOptions& mutable_cf_options, int level) {
+  uint32_t p = 0;
+  assert(!ioptions.cf_paths.empty());
+
+  // size remaining in the most recent path
+  uint64_t current_path_size = ioptions.cf_paths[0].target_size;
+
+  uint64_t level_size;
+  int cur_level = 0;
+
+  // max_bytes_for_level_base denotes L1 size.
+  // We estimate L0 size to be the same as L1.
+  level_size = mutable_cf_options.max_bytes_for_level_base;
+
+  // Last path is the fallback
+  while (p < ioptions.cf_paths.size() - 1) {
+    if (level_size <= current_path_size) {
+      if (cur_level == level) {
+        // Does desired level fit in this path?
+        return p;
+      } else {
+        current_path_size -= level_size;
+        if (cur_level > 0) {
+          if (ioptions.level_compaction_dynamic_level_bytes) {
+            // Currently, level_compaction_dynamic_level_bytes is ignored when
+            // multiple db paths are specified. https://github.com/facebook/
+            // rocksdb/blob/master/db/column_family.cc.
+            // Still, adding this check to avoid accidentally using
+            // max_bytes_for_level_multiplier_additional
+            level_size = static_cast<uint64_t>(
+                level_size * mutable_cf_options.max_bytes_for_level_multiplier);
+          } else {
+            level_size = static_cast<uint64_t>(
+                level_size * mutable_cf_options.max_bytes_for_level_multiplier *
+                mutable_cf_options.MaxBytesMultiplerAdditional(cur_level));
+          }
+        }
+        cur_level++;
+        continue;
+      }
+    }
+    p++;
+    current_path_size = ioptions.cf_paths[p].target_size;
+  }
+  return p;
+}
+
+bool LevelCompactionBuilder::PickFileToCompact() {
+  // level 0 files are overlapping. So we cannot pick more
+  // than one concurrent compactions at this level. This
+  // could be made better by looking at key-ranges that are
+  // being compacted at level 0.
+  if (start_level_ == 0 &&
+      !compaction_picker_->level0_compactions_in_progress()->empty()) {
+    TEST_SYNC_POINT("LevelCompactionPicker::PickCompactionBySize:0");
+    return false;
+  }
+
+  start_level_inputs_.clear();
+
+  assert(start_level_ >= 0);
+
+  // Pick the largest file in this level that is not already
+  // being compacted
+  const std::vector<int>& file_size =
+      vstorage_->FilesByCompactionPri(start_level_);
+  const std::vector<FileMetaData*>& level_files =
+      vstorage_->LevelFiles(start_level_);
+
+  unsigned int cmp_idx;
+  for (cmp_idx = vstorage_->NextCompactionIndex(start_level_);
+       cmp_idx < file_size.size(); cmp_idx++) {
+    int index = file_size[cmp_idx];
+    auto* f = level_files[index];
+
+    // do not pick a file to compact if it is being compacted
+    // from n-1 level.
+    if (f->being_compacted) {
+      continue;
+    }
+
+    start_level_inputs_.files.push_back(f);
+    start_level_inputs_.level = start_level_;
+    if (!compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                    &start_level_inputs_) ||
+        compaction_picker_->FilesRangeOverlapWithCompaction(
+            {start_level_inputs_}, output_level_)) {
+      // A locked (pending compaction) input-level file was pulled in due to
+      // user-key overlap.
+      start_level_inputs_.clear();
+      continue;
+    }
+
+    // Now that input level is fully expanded, we check whether any output files
+    // are locked due to pending compaction.
+    //
+    // Note we rely on ExpandInputsToCleanCut() to tell us whether any output-
+    // level files are locked, not just the extra ones pulled in for user-key
+    // overlap.
+    InternalKey smallest, largest;
+    compaction_picker_->GetRange(start_level_inputs_, &smallest, &largest);
+    CompactionInputFiles output_level_inputs;
+    output_level_inputs.level = output_level_;
+    vstorage_->GetOverlappingInputs(output_level_, &smallest, &largest,
+                                    &output_level_inputs.files);
+    if (!output_level_inputs.empty() &&
+        !compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                    &output_level_inputs)) {
+      start_level_inputs_.clear();
+      continue;
+    }
+    base_index_ = index;
+    break;
+  }
+
+  // store where to start the iteration in the next call to PickCompaction
+  vstorage_->SetNextCompactionIndex(start_level_, cmp_idx);
+
+  return start_level_inputs_.size() > 0;
+}
+
+bool LevelCompactionBuilder::PickIntraL0Compaction() {
+  start_level_inputs_.clear();
+  const std::vector<FileMetaData*>& level_files =
+      vstorage_->LevelFiles(0 /* level */);
+  if (level_files.size() <
+          static_cast<size_t>(
+              mutable_cf_options_.level0_file_num_compaction_trigger + 2) ||
+      level_files[0]->being_compacted) {
+    // If L0 isn't accumulating much files beyond the regular trigger, don't
+    // resort to L0->L0 compaction yet.
+    return false;
+  }
+  return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
+                               port::kMaxUint64, &start_level_inputs_);
+}
+}  // namespace
+
+Compaction* LevelCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
+                                 mutable_cf_options, ioptions_);
+  return builder.PickCompaction();
+}
+
+}  // namespace rocksdb

db/compaction_picker.h

@@ -15,35 +15,20 @@
 #include <unordered_set>
 #include <vector>
 
-#include "db/compaction/compaction.h"
+#include "db/compaction.h"
 #include "db/version_set.h"
 #include "options/cf_options.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "rocksdb/status.h"
 
-namespace ROCKSDB_NAMESPACE {
-
-// The file contains an abstract class CompactionPicker, and its two
-// sub-classes LevelCompactionPicker and NullCompactionPicker, as
-// well as some helper functions used by them.
+namespace rocksdb {
 
 class LogBuffer;
 class Compaction;
 class VersionStorageInfo;
 struct CompactionInputFiles;
 
-// An abstract class to pick compactions from an existing LSM-tree.
-//
-// Each compaction style inherits the class and implement the
-// interface to form automatic compactions. If NeedCompaction() is true,
-// then call PickCompaction() to find what files need to be compacted
-// and where to put the output files.
-//
-// Non-virtual functions CompactRange() and CompactFiles() are used to
-// pick files to compact based on users' DB::CompactRange() and
-// DB::CompactFiles() requests, respectively. There is little
-// compaction style specific logic for them.
 class CompactionPicker {
  public:
   CompactionPicker(const ImmutableCFOptions& ioptions,
@@ -54,10 +39,10 @@ class CompactionPicker {
   // Returns nullptr if there is no compaction to be done.
   // Otherwise returns a pointer to a heap-allocated object that
   // describes the compaction.  Caller should delete the result.
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) = 0;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) = 0;
 
   // Return a compaction object for compacting the range [begin,end] in
   // the specified level.  Returns nullptr if there is nothing in that
@@ -73,10 +58,9 @@ class CompactionPicker {
   virtual Compaction* CompactRange(
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
       VersionStorageInfo* vstorage, int input_level, int output_level,
-      const CompactRangeOptions& compact_range_options,
+      uint32_t output_path_id, uint32_t max_subcompactions,
       const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore);
+      InternalKey** compaction_end, bool* manual_conflict);
 
   // The maximum allowed output level.  Default value is NumberLevels() - 1.
   virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
@@ -236,9 +220,21 @@ class CompactionPicker {
   const InternalKeyComparator* const icmp_;
 };
 
+class LevelCompactionPicker : public CompactionPicker {
+ public:
+  LevelCompactionPicker(const ImmutableCFOptions& ioptions,
+                        const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+};
+
 #ifndef ROCKSDB_LITE
-// A dummy compaction that never triggers any automatic
-// compaction.
 class NullCompactionPicker : public CompactionPicker {
  public:
   NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -247,11 +243,10 @@ class NullCompactionPicker : public CompactionPicker {
   virtual ~NullCompactionPicker() {}
 
   // Always return "nullptr"
-  Compaction* PickCompaction(
-      const std::string& /*cf_name*/,
-      const MutableCFOptions& /*mutable_cf_options*/,
-      VersionStorageInfo* /*vstorage*/, LogBuffer* /* log_buffer */,
-      SequenceNumber /* earliest_memtable_seqno */) override {
+  Compaction* PickCompaction(const std::string& /*cf_name*/,
+                             const MutableCFOptions& /*mutable_cf_options*/,
+                             VersionStorageInfo* /*vstorage*/,
+                             LogBuffer* /*log_buffer*/) override {
     return nullptr;
   }
 
@@ -260,12 +255,12 @@ class NullCompactionPicker : public CompactionPicker {
                            const MutableCFOptions& /*mutable_cf_options*/,
                            VersionStorageInfo* /*vstorage*/,
                            int /*input_level*/, int /*output_level*/,
-                           const CompactRangeOptions& /*compact_range_options*/,
+                           uint32_t /*output_path_id*/,
+                           uint32_t /*max_subcompactions*/,
                            const InternalKey* /*begin*/,
                            const InternalKey* /*end*/,
                            InternalKey** /*compaction_end*/,
-                           bool* /*manual_conflict*/,
-                           uint64_t /*max_file_num_to_ignore*/) override {
+                           bool* /*manual_conflict*/) override {
     return nullptr;
   }
 
@@ -277,27 +272,10 @@ class NullCompactionPicker : public CompactionPicker {
 };
 #endif  // !ROCKSDB_LITE
 
-// Attempts to find an intra L0 compaction conforming to the given parameters.
-//
-// @param level_files                     Metadata for L0 files.
-// @param min_files_to_compact            Minimum number of files required to
-//                                        do the compaction.
-// @param max_compact_bytes_per_del_file  Maximum average size in bytes per
-//                                        file that is going to get deleted by
-//                                        the compaction.
-// @param max_compaction_bytes            Maximum total size in bytes (in terms
-//                                        of compensated file size) for files
-//                                        to be compacted.
-// @param [out] comp_inputs               If a compaction was found, will be
-//                                        initialized with corresponding input
-//                                        files. Cannot be nullptr.
-//
-// @return                                true iff compaction was found.
-bool FindIntraL0Compaction(
-    const std::vector<FileMetaData*>& level_files, size_t min_files_to_compact,
-    uint64_t max_compact_bytes_per_del_file, uint64_t max_compaction_bytes,
-    CompactionInputFiles* comp_inputs,
-    SequenceNumber earliest_mem_seqno = kMaxSequenceNumber);
+bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
+                           size_t min_files_to_compact,
+                           uint64_t max_compact_bytes_per_del_file,
+                           CompactionInputFiles* comp_inputs);
 
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
                                    const VersionStorageInfo* vstorage,
@@ -310,4 +288,4 @@ CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
                                          int level,
                                          const bool enable_compression = true);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction_picker_fifo.cc

@@ -7,17 +7,21 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#include "db/compaction/compaction_picker_fifo.h"
+#include "db/compaction_picker_fifo.h"
 #ifndef ROCKSDB_LITE
 
-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <string>
 #include <vector>
 #include "db/column_family.h"
-#include "logging/log_buffer.h"
+#include "util/log_buffer.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 namespace {
 uint64_t GetTotalFilesSize(const std::vector<FileMetaData*>& files) {
   uint64_t total_size = 0;
@@ -37,7 +41,7 @@ bool FIFOCompactionPicker::NeedsCompaction(
 Compaction* FIFOCompactionPicker::PickTTLCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(mutable_cf_options.ttl > 0);
+  assert(mutable_cf_options.compaction_options_fifo.ttl > 0);
 
   const int kLevel0 = 0;
   const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
@@ -54,30 +58,26 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
   }
   const uint64_t current_time = static_cast<uint64_t>(_current_time);
 
-  if (!level0_compactions_in_progress_.empty()) {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: Already executing compaction. No need "
-        "to run parallel compactions since compactions are very fast",
-        cf_name.c_str());
-    return nullptr;
-  }
-
   std::vector<CompactionInputFiles> inputs;
   inputs.emplace_back();
   inputs[0].level = 0;
 
   // avoid underflow
-  if (current_time > mutable_cf_options.ttl) {
+  if (current_time > mutable_cf_options.compaction_options_fifo.ttl) {
     for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-      FileMetaData* f = *ritr;
-      uint64_t creation_time = f->TryGetFileCreationTime();
-      if (creation_time == kUnknownFileCreationTime ||
-          creation_time >= (current_time - mutable_cf_options.ttl)) {
-        break;
+      auto f = *ritr;
+      if (f->fd.table_reader != nullptr &&
+          f->fd.table_reader->GetTableProperties() != nullptr) {
+        auto creation_time =
+            f->fd.table_reader->GetTableProperties()->creation_time;
+        if (creation_time == 0 ||
+            creation_time >= (current_time -
+                              mutable_cf_options.compaction_options_fifo.ttl)) {
+          break;
+        }
+        total_size -= f->compensated_file_size;
+        inputs[0].files.push_back(f);
       }
-      total_size -= f->compensated_file_size;
-      inputs[0].files.push_back(f);
     }
   }
 
@@ -96,7 +96,7 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
                      "[%s] FIFO compaction: picking file %" PRIu64
                      " with creation time %" PRIu64 " for deletion",
                      cf_name.c_str(), f->fd.GetNumber(),
-                     f->TryGetFileCreationTime());
+                     f->fd.table_reader->GetTableProperties()->creation_time);
   }
 
   Compaction* c = new Compaction(
@@ -135,8 +135,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
               mutable_cf_options
                   .level0_file_num_compaction_trigger /* min_files_to_compact */
               ,
-              max_compact_bytes_per_del_file,
-              mutable_cf_options.max_compaction_bytes, &comp_inputs)) {
+              max_compact_bytes_per_del_file, &comp_inputs)) {
         Compaction* c = new Compaction(
             vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
             16 * 1024 * 1024 /* output file size limit */,
@@ -198,12 +197,11 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
 
 Compaction* FIFOCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber /*earliest_memtable_seqno*/) {
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
   assert(vstorage->num_levels() == 1);
 
   Compaction* c = nullptr;
-  if (mutable_cf_options.ttl > 0) {
+  if (mutable_cf_options.compaction_options_fifo.ttl > 0) {
     c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
   }
   if (c == nullptr) {
@@ -216,10 +214,9 @@ Compaction* FIFOCompactionPicker::PickCompaction(
 Compaction* FIFOCompactionPicker::CompactRange(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     VersionStorageInfo* vstorage, int input_level, int output_level,
-    const CompactRangeOptions& /*compact_range_options*/,
+    uint32_t /*output_path_id*/, uint32_t /*max_subcompactions*/,
     const InternalKey* /*begin*/, const InternalKey* /*end*/,
-    InternalKey** compaction_end, bool* /*manual_conflict*/,
-    uint64_t /*max_file_num_to_ignore*/) {
+    InternalKey** compaction_end, bool* /*manual_conflict*/) {
 #ifdef NDEBUG
   (void)input_level;
   (void)output_level;
@@ -234,5 +231,5 @@ Compaction* FIFOCompactionPicker::CompactRange(
   return c;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 #endif  // !ROCKSDB_LITE

db/compaction_picker_fifo.h

@@ -10,27 +10,26 @@
 #pragma once
 #ifndef ROCKSDB_LITE
 
-#include "db/compaction/compaction_picker.h"
+#include "db/compaction_picker.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 class FIFOCompactionPicker : public CompactionPicker {
  public:
   FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
                        const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
 
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* version, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* version,
+                                     LogBuffer* log_buffer) override;
 
   virtual Compaction* CompactRange(
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
       VersionStorageInfo* vstorage, int input_level, int output_level,
-      const CompactRangeOptions& compact_range_options,
+      uint32_t output_path_id, uint32_t max_subcompactions,
       const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore) override;
+      InternalKey** compaction_end, bool* manual_conflict) override;
 
   // The maximum allowed output level.  Always returns 0.
   virtual int MaxOutputLevel() const override { return 0; }
@@ -49,5 +48,5 @@ class FIFOCompactionPicker : public CompactionPicker {
                                  VersionStorageInfo* version,
                                  LogBuffer* log_buffer);
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 #endif  // !ROCKSDB_LITE

db/compaction_picker_test.cc

@@ -3,26 +3,28 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#include "db/compaction_picker.h"
 
 #include <limits>
 #include <string>
 #include <utility>
-#include "db/compaction/compaction.h"
-#include "db/compaction/compaction_picker_fifo.h"
-#include "db/compaction/compaction_picker_level.h"
-#include "db/compaction/compaction_picker_universal.h"
+#include "db/compaction.h"
+#include "db/compaction_picker_fifo.h"
+#include "db/compaction_picker_universal.h"
 
-#include "logging/logging.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/logging.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CountingLogger : public Logger {
  public:
   using Logger::Logv;
-  void Logv(const char* /*format*/, va_list /*ap*/) override { log_count++; }
+  virtual void Logv(const char* /*format*/, va_list /*ap*/) override {
+    log_count++;
+  }
   size_t log_count;
 };
 
@@ -57,8 +59,6 @@ class CompactionPickerTest : public testing::Test {
         log_buffer_(InfoLogLevel::INFO_LEVEL, &logger_),
         file_num_(1),
         vstorage_(nullptr) {
-    mutable_cf_options_.ttl = 0;
-    mutable_cf_options_.periodic_compaction_seconds = 0;
     // ioptions_.compaction_pri = kMinOverlappingRatio has its own set of
     // tests to cover.
     ioptions_.compaction_pri = kByCompensatedSize;
@@ -68,7 +68,8 @@ class CompactionPickerTest : public testing::Test {
                                     std::numeric_limits<uint64_t>::max());
   }
 
-  ~CompactionPickerTest() override {}
+  ~CompactionPickerTest() {
+  }
 
   void NewVersionStorage(int num_levels, CompactionStyle style) {
     DeleteVersionStorage();
@@ -90,15 +91,15 @@ class CompactionPickerTest : public testing::Test {
            SequenceNumber smallest_seq = 100, SequenceNumber largest_seq = 100,
            size_t compensated_file_size = 0) {
     assert(level < vstorage_->num_levels());
-    FileMetaData* f = new FileMetaData(
-        file_number, path_id, file_size,
-        InternalKey(smallest, smallest_seq, kTypeValue),
-        InternalKey(largest, largest_seq, kTypeValue), smallest_seq,
-        largest_seq, /* marked_for_compact */ false, kInvalidBlobFileNumber,
-        kUnknownOldestAncesterTime, kUnknownFileCreationTime,
-        kUnknownFileChecksum, kUnknownFileChecksumFuncName);
+    FileMetaData* f = new FileMetaData;
+    f->fd = FileDescriptor(file_number, path_id, file_size);
+    f->smallest = InternalKey(smallest, smallest_seq, kTypeValue);
+    f->largest = InternalKey(largest, largest_seq, kTypeValue);
+    f->fd.smallest_seqno = smallest_seq;
+    f->fd.largest_seqno = largest_seq;
     f->compensated_file_size =
         (compensated_file_size != 0) ? compensated_file_size : file_size;
+    f->refs = 0;
     vstorage_->AddFile(level, f);
     files_.emplace_back(f);
     file_map_.insert({file_number, {f, level}});
@@ -503,168 +504,6 @@ TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
   ASSERT_TRUE(compaction->is_trivial_move());
 }
 
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction1) {
-  // The case where universal periodic compaction can be picked
-  // with some newer files being compacted.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 2U, "201", "250", kFileSize, 0, 401, 450);
-  Add(0, 4U, "260", "300", kFileSize, 0, 260, 300);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[2].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(4, file_map_[3].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(4, compaction->output_level());
-  ASSERT_EQ(0, compaction->start_level());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction2) {
-  // The case where universal periodic compaction does not
-  // pick up only level to compact if it doesn't cover
-  // any file marked as periodic compaction.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[5].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[1].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_FALSE(compaction);
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction3) {
-  // The case where universal periodic compaction does not
-  // pick up only the last sorted run which is an L0 file if it isn't
-  // marked as periodic compaction.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(0, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[5].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[1].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_FALSE(compaction);
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction4) {
-  // The case where universal periodic compaction couldn't form
-  // a compaction that inlcudes any file marked for periodic compaction.
-  // Right now we form the compaction anyway if it is more than one
-  // sorted run. Just put the case here to validate that it doesn't
-  // crash.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(2, 2U, "010", "080", kFileSize, 0, 200, 251);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[2].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[2].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(!compaction ||
-              compaction->start_level() != compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction5) {
-  // Test single L0 file periodic compaction triggering.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 6U, "150", "200", kFileSize, 0, 500, 550);
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[6].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(0, compaction->start_level());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(6U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(4, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction6) {
-  // Test single sorted run non-L0 periodic compaction
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(4, 5U, "150", "200", kFileSize, 0, 500, 550);
-  Add(4, 6U, "350", "400", kFileSize, 0, 500, 550);
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(4, file_map_[6].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(4, compaction->start_level());
-  ASSERT_EQ(2U, compaction->num_input_files(0));
-  ASSERT_EQ(5U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(6U, compaction->input(0, 1)->fd.GetNumber());
-  ASSERT_EQ(4, compaction->output_level());
-}
-
 TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const int kFileCount =
@@ -1642,98 +1481,7 @@ TEST_F(CompactionPickerTest, CacheNextCompactionIndex) {
   ASSERT_EQ(4, vstorage_->NextCompactionIndex(1 /* level */));
 }
 
-TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesNotHit) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 1000000u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // All 5 L0 files will be picked for intra L0 compaction. The one L1 file
-  // spans entire L0 key range and is marked as being compacted to avoid
-  // L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U, 0, 100, 101);
-  Add(0, 2U, "151", "200", 200000U, 0, 102, 103);
-  Add(0, 3U, "201", "250", 200000U, 0, 104, 105);
-  Add(0, 4U, "251", "300", 200000U, 0, 106, 107);
-  Add(0, 5U, "301", "350", 200000U, 0, 108, 109);
-  Add(1, 6U, "100", "350", 200000U, 0, 110, 111);
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(5U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesHit) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 999999u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // 4 out of 5 L0 files will be picked for intra L0 compaction due to
-  // max_compaction_bytes limit (the minimum number of files for triggering
-  // intra L0 compaction is 4). The one L1 file spans entire L0 key range and
-  // is marked as being compacted to avoid L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U, 0, 100, 101);
-  Add(0, 2U, "151", "200", 200000U, 0, 102, 103);
-  Add(0, 3U, "201", "250", 200000U, 0, 104, 105);
-  Add(0, 4U, "251", "300", 200000U, 0, 106, 107);
-  Add(0, 5U, "301", "350", 200000U, 0, 108, 109);
-  Add(1, 6U, "100", "350", 200000U, 0, 109, 110);
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(4U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, IntraL0ForEarliestSeqno) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 999999u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // 4 out of 6 L0 files will be picked for intra L0 compaction due to
-  // being_compact limit. And the latest one L0 will be skipped due to earliest
-  // seqno. The one L1 file spans entire L0 key range and is marked as being
-  // compacted to avoid L0->L1 compaction.
-  Add(1, 1U, "100", "350", 200000U, 0, 110, 111);
-  Add(0, 2U, "301", "350", 1U, 0, 108, 109);
-  Add(0, 3U, "251", "300", 1U, 0, 106, 107);
-  Add(0, 4U, "201", "250", 1U, 0, 104, 105);
-  Add(0, 5U, "151", "200", 1U, 0, 102, 103);
-  Add(0, 6U, "100", "150", 1U, 0, 100, 101);
-  Add(0, 7U, "100", "100", 1U, 0, 99, 100);
-  vstorage_->LevelFiles(0)[5]->being_compacted = true;
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_, 107));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(4U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compaction_picker_universal.h

@@ -0,0 +1,98 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  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).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+
+#pragma once
+#ifndef ROCKSDB_LITE
+
+#include "db/compaction_picker.h"
+
+namespace rocksdb {
+class UniversalCompactionPicker : public CompactionPicker {
+ public:
+  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
+                            const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
+  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+
+ private:
+  struct SortedRun {
+    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
+              uint64_t _compensated_file_size, bool _being_compacted)
+        : level(_level),
+          file(_file),
+          size(_size),
+          compensated_file_size(_compensated_file_size),
+          being_compacted(_being_compacted) {
+      assert(compensated_file_size > 0);
+      assert(level != 0 || file != nullptr);
+    }
+
+    void Dump(char* out_buf, size_t out_buf_size,
+              bool print_path = false) const;
+
+    // sorted_run_count is added into the string to print
+    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
+                      size_t sorted_run_count) const;
+
+    int level;
+    // `file` Will be null for level > 0. For level = 0, the sorted run is
+    // for this file.
+    FileMetaData* file;
+    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
+    // files in the level. `being_compacted` should be the same for all files
+    // in a non-zero level. Use the value here.
+    uint64_t size;
+    uint64_t compensated_file_size;
+    bool being_compacted;
+  };
+
+  // Pick Universal compaction to limit read amplification
+  Compaction* PickCompactionToReduceSortedRuns(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score, unsigned int ratio,
+      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
+      LogBuffer* log_buffer);
+
+  // Pick Universal compaction to limit space amplification.
+  Compaction* PickCompactionToReduceSizeAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  Compaction* PickDeleteTriggeredCompaction(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  // Used in universal compaction when the enabled_trivial_move
+  // option is set. Checks whether there are any overlapping files
+  // in the input. Returns true if the input files are non
+  // overlapping.
+  bool IsInputFilesNonOverlapping(Compaction* c);
+
+  static std::vector<SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
+      const MutableCFOptions& mutable_cf_options);
+
+  // Pick a path ID to place a newly generated file, with its estimated file
+  // size.
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            uint64_t file_size);
+};
+}  // namespace rocksdb
+#endif  // !ROCKSDB_LITE