Extend existing unit tests to run with WriteUnPrepared as well

2026-07-07 22:55:23 +08:00 · 2018-06-01 10:48:18 -07:00
1031 changed files with 47353 additions and 112329 deletions
@@ -32,7 +32,6 @@ ldb
 manifest_dump
 sst_dump
 blob_dump
-block_cache_trace_analyzer
 column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
@@ -46,9 +45,6 @@ etags
 rocksdb_dump
 rocksdb_undump
 db_test2
-trace_analyzer
-trace_analyzer_test
-.DS_Store

 java/out
 java/target
@@ -1,4 +0,0 @@
-extraction:
-  cpp:
-    index:
-      build_command: make static_lib
@@ -1,4 +1,5 @@
-dist: xenial
+sudo: false
+dist: trusty
 language: cpp
 os:
  - linux
@@ -8,23 +9,14 @@ compiler:
  - gcc
 osx_image: xcode8.3
 jdk:
-  - openjdk7
+  - oraclejdk7
 cache:
  - ccache
  - apt

 addons:
-  apt:
-    sources:
-      - ubuntu-toolchain-r-test
-    packages:
-      - curl
-      - g++-8
-      - libbz2-dev
-      - libgflags-dev
-      - libsnappy-dev
-      - mingw-w64
-      - zlib1g-dev
+   apt:
+      packages: ['zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev', 'mingw-w64']
 env:
  - TEST_GROUP=platform_dependent # 16-18 minutes
  - TEST_GROUP=1 # 33-35 minutes
@@ -38,7 +30,6 @@ env:
  # Build examples
  - JOB_NAME=examples # 5-7 minutes
  - JOB_NAME=cmake # 3-5 minutes
-  - JOB_NAME=cmake-gcc8 # 3-5 minutes
  - JOB_NAME=cmake-mingw # 3 minutes

 matrix:
@@ -51,8 +42,6 @@ matrix:
    env: TEST_GROUP=3
  - os: osx
    env: TEST_GROUP=4
-  - os: osx
-    env: JOB_NAME=cmake-gcc8
  - os : osx
    env: JOB_NAME=cmake-mingw
  - os : linux
@@ -63,17 +52,11 @@ matrix:
 # https://docs.travis-ci.com/user/caching/#ccache-cache
 install:
  - if [ "${TRAVIS_OS_NAME}" == osx ]; then
-      brew install ccache zstd lz4 snappy xz;
+      brew install ccache;
      PATH=$PATH:/usr/local/opt/ccache/libexec;
    fi
-  - if [ "${JOB_NAME}" == cmake-gcc8 ]; then
-      CC=gcc-8 && CXX=g++-8;
-    fi
  - if [[ "${JOB_NAME}" == cmake* ]] && [ "${TRAVIS_OS_NAME}" == linux ]; then
-      mkdir cmake-dist && curl -sfSL https://github.com/Kitware/CMake/releases/download/v3.14.5/cmake-3.14.5-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
-    fi
-  - if [[ "${JOB_NAME}" == java_test ]]; then
-      java -version && echo "JAVA_HOME=${JAVA_HOME}";
+      mkdir cmake-dist && curl -sfSL https://cmake.org/files/v3.8/cmake-3.8.1-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$PWD/cmake-dist/bin:$PATH;
    fi

 before_script:
@@ -84,41 +67,16 @@ before_script:
 script:
  - ${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=full_filter_block_test make -j4 check_some
-      ;;
-    2)
-      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=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
-      ;;
-    esac
-  - case $JOB_NAME in
-    java_test)
-      OPT=-DTRAVIS V=1 make rocksdbjava jtest
-      ;;
-    lite_build)
-      OPT='-DTRAVIS -DROCKSDB_LITE' V=1 make -j4 static_lib tools
-      ;;
-    examples)
-      OPT=-DTRAVIS V=1 make -j4 static_lib && cd examples && make -j4
-      ;;
-    cmake-mingw)
-      sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
-      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
-      ;;
-    cmake*)
-      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release && make -j4 rocksdb rocksdbjni
-      ;;
-    esac
+  - if [ "${TEST_GROUP}" == 'platform_dependent' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=db_block_cache_test make -j4 all_but_some_tests check_some; fi
+  - if [ "${TEST_GROUP}" == '1' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=full_filter_block_test make -j4 check_some; fi
+  - if [ "${TEST_GROUP}" == '2' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=full_filter_block_test ROCKSDBTESTS_END=write_batch_with_index_test make -j4 check_some; fi
+  - if [ "${TEST_GROUP}" == '3' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_batch_with_index_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some; fi
+  - if [ "${TEST_GROUP}" == '4' ]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_prepared_transaction_test make -j4 check_some; fi
+  - if [ "${JOB_NAME}" == 'java_test' ]; then OPT=-DTRAVIS V=1 make clean jclean && make rocksdbjava jtest; fi
+  - if [ "${JOB_NAME}" == 'lite_build' ]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib tools; fi
+  - if [ "${JOB_NAME}" == 'examples' ]; then OPT=-DTRAVIS V=1 make -j4 static_lib; cd examples; make -j4; fi
+  - if [ "${JOB_NAME}" == 'cmake' ]; then mkdir build && cd build && cmake -DJNI=1 .. && make -j4 rocksdb rocksdbjni; fi
+  - if [ "${JOB_NAME}" == 'cmake-mingw' ]; then 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; fi
 notifications:
    email:
      - leveldb@fb.com
@@ -44,21 +44,10 @@ endif()

 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")

-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)
-
 option(WITH_JEMALLOC "build with JeMalloc" OFF)
 option(WITH_SNAPPY "build with SNAPPY" OFF)
 option(WITH_LZ4 "build with lz4" OFF)
 option(WITH_ZLIB "build with zlib" OFF)
-option(WITH_ZSTD "build with zstd" OFF)
-option(WITH_WINDOWS_UTF8_FILENAMES "use UTF8 as characterset for opening files, regardles of the system code page" OFF)
-if (WITH_WINDOWS_UTF8_FILENAMES)
-  add_definitions(-DROCKSDB_WINDOWS_UTF8_FILENAMES)
-endif()
 if(MSVC)
  # Defaults currently different for GFLAGS.
  #  We will address find_package work a little later
@@ -98,15 +87,9 @@ else()
  endif()

  if(WITH_ZLIB)
-    find_package(ZLIB REQUIRED)
+    find_package(zlib REQUIRED)
    add_definitions(-DZLIB)
-    if(ZLIB_INCLUDE_DIRS)
-      # CMake 3
-      include_directories(${ZLIB_INCLUDE_DIRS})
-    else()
-      # CMake 2
-      include_directories(${ZLIB_INCLUDE_DIR})
-    endif()
+    include_directories(${ZLIB_INCLUDE_DIR})
    list(APPEND THIRDPARTY_LIBS ${ZLIB_LIBRARIES})
  endif()

@@ -125,6 +108,7 @@ else()
    list(APPEND THIRDPARTY_LIBS ${LZ4_LIBRARIES})
  endif()

+  option(WITH_ZSTD "build with zstd" OFF)
  if(WITH_ZSTD)
    find_package(zstd REQUIRED)
    add_definitions(-DZSTD)
@@ -183,11 +167,10 @@ else()
  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")
-    add_definitions(-D_POSIX_C_SOURCE=1)
  endif()
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
  if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-omit-frame-pointer")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O2 -fno-omit-frame-pointer")
    include(CheckCXXCompilerFlag)
    CHECK_CXX_COMPILER_FLAG("-momit-leaf-frame-pointer" HAVE_OMIT_LEAF_FRAME_POINTER)
    if(HAVE_OMIT_LEAF_FRAME_POINTER)
@@ -208,15 +191,6 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
  endif(HAS_ALTIVEC)
 endif(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")

-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
-        CHECK_C_COMPILER_FLAG("-march=armv8-a+crc" HAS_ARMV8_CRC)
-  if(HAS_ARMV8_CRC)
-    message(STATUS " HAS_ARMV8_CRC yes")
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc -Wno-unused-function")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc -Wno-unused-function")
-  endif(HAS_ARMV8_CRC)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
-
 option(PORTABLE "build a portable binary" OFF)
 option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
 if(PORTABLE)
@@ -229,7 +203,7 @@ else()
  if(MSVC)
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
  else()
-    if(NOT HAVE_POWER8 AND NOT HAS_ARMV8_CRC)
+    if(NOT HAVE_POWER8)
      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
    endif()
  endif()
@@ -333,9 +307,13 @@ 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)
+# Used to run CI build and tests so we can run faster
+set(OPTIMIZE_DEBUG_DEFAULT 0)        # Debug build is unoptimized by default use -DOPTDBG=1 to optimize
+
+if(DEFINED OPTDBG)
+   set(OPTIMIZE_DEBUG ${OPTDBG})
+else()
+   set(OPTIMIZE_DEBUG ${OPTIMIZE_DEBUG_DEFAULT})
 endif()

 if(DEFINED USE_RTTI)
@@ -344,40 +322,22 @@ if(DEFINED USE_RTTI)
    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -DROCKSDB_USE_RTTI")
  else()
-    if(MSVC)
-      message(STATUS "Disabling RTTI in Release builds. Always on in Debug.")
-      set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
-      set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
-    else()
-      message(STATUS "Disabling RTTI in Release builds")
-      set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-rtti")
-      set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
-    endif()
+    message(STATUS "Disabling RTTI")
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-rtti")
+    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
  endif()
 else()
  message(STATUS "Enabling RTTI in Debug builds only (default)")
  set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
-  if(MSVC)
-     set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
-  else()
-    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
-  endif()
+  set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
 endif()

-# Used to run CI build and tests so we can run faster
-option(OPTDBG "Build optimized debug build with MSVC" OFF)
-option(WITH_RUNTIME_DEBUG "build with debug version of runtime library" ON)
 if(MSVC)
-  if(OPTDBG)
+  if((${OPTIMIZE_DEBUG} EQUAL 1))
    message(STATUS "Debug optimization is enabled")
-    set(CMAKE_CXX_FLAGS_DEBUG "/Oxt")
+    set(CMAKE_CXX_FLAGS_DEBUG "/Oxt /${RUNTIME_LIBRARY}d")
  else()
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm")
-  endif()
-  if(WITH_RUNTIME_DEBUG)
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}d")
-  else()
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}")
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm /${RUNTIME_LIBRARY}d")
  endif()
  set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /Oxt /Zp8 /Gm- /Gy /${RUNTIME_LIBRARY}")

@@ -392,7 +352,7 @@ endif()
 option(ROCKSDB_LITE "Build RocksDBLite version" OFF)
 if(ROCKSDB_LITE)
  add_definitions(-DROCKSDB_LITE)
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions -Os")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions")
 endif()

 if(CMAKE_SYSTEM_NAME MATCHES "Cygwin")
@@ -436,7 +396,7 @@ 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)
@@ -481,6 +441,8 @@ include_directories(${PROJECT_SOURCE_DIR}/include)
 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
@@ -491,28 +453,24 @@ set(SOURCES
        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_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
-        db/error_handler.cc
        db/event_helpers.cc
        db/experimental.cc
        db/external_sst_file_ingestion_job.cc
@@ -520,18 +478,17 @@ 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
        db/log_writer.cc
        db/malloc_stats.cc
+        db/managed_iterator.cc
        db/memtable.cc
        db/memtable_list.cc
        db/merge_helper.cc
        db/merge_operator.cc
        db/range_del_aggregator.cc
-        db/range_tombstone_fragmenter.cc
        db/repair.cc
        db/snapshot_impl.cc
        db/table_cache.cc
@@ -550,17 +507,8 @@ set(SOURCES
        env/env_encryption.cc
        env/env_hdfs.cc
        env/mock_env.cc
-        file/delete_scheduler.cc
-        file/file_util.cc
-        file/filename.cc
-        file/sst_file_manager_impl.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
@@ -568,12 +516,10 @@ 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
@@ -586,93 +532,102 @@ set(SOURCES
        options/options_parser.cc
        options/options_sanity_check.cc
        port/stack_trace.cc
-        table/adaptive/adaptive_table_factory.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_reader.cc
-        table/block_based/block_builder.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/flush_block_policy.cc
-        table/block_based/full_filter_block.cc
-        table/block_based/index_builder.cc
-        table/block_based/partitioned_filter_block.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/block_prefix_index.cc
        table/bloom_block.cc
-        table/cuckoo/cuckoo_table_builder.cc
-        table/cuckoo/cuckoo_table_factory.cc
-        table/cuckoo/cuckoo_table_reader.cc
+        table/cuckoo_table_builder.cc
+        table/cuckoo_table_factory.cc
+        table/cuckoo_table_reader.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_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/sst_file_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_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_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_task_limiter_impl.cc
+        util/concurrent_arena.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/log_buffer.cc
        util/murmurhash.cc
        util/random.cc
        util/rate_limiter.cc
        util/slice.cc
+        util/sst_file_manager_impl.cc
        util/status.cc
+        util/status_message.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/transaction_test_util.cc
        util/xxhash.cc
        utilities/backupable/backupable_db.cc
        utilities/blob_db/blob_compaction_filter.cc
        utilities/blob_db/blob_db.cc
        utilities/blob_db/blob_db_impl.cc
-        utilities/blob_db/blob_db_impl_filesnapshot.cc
        utilities/blob_db/blob_dump_tool.cc
        utilities/blob_db/blob_file.cc
        utilities/blob_db/blob_log_reader.cc
        utilities/blob_db/blob_log_writer.cc
        utilities/blob_db/blob_log_format.cc
+        utilities/blob_db/ttl_extractor.cc
        utilities/cassandra/cassandra_compaction_filter.cc
        utilities/cassandra/format.cc
        utilities/cassandra/merge_operator.cc
        utilities/checkpoint/checkpoint_impl.cc
+        utilities/col_buf_decoder.cc
+        utilities/col_buf_encoder.cc
+        utilities/column_aware_encoding_util.cc
        utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
+        utilities/date_tiered/date_tiered_db_impl.cc
        utilities/debug.cc
+        utilities/document/document_db.cc
+        utilities/document/json_document.cc
+        utilities/document/json_document_builder.cc
        utilities/env_mirror.cc
        utilities/env_timed.cc
+        utilities/geodb/geodb_impl.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
@@ -687,10 +642,10 @@ 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/redis/redis_lists.cc
        utilities/simulator_cache/sim_cache.cc
+        utilities/spatialdb/spatial_db.cc
        utilities/table_properties_collectors/compact_on_deletion_collector.cc
-        utilities/trace/file_trace_reader_writer.cc
        utilities/transactions/optimistic_transaction_db_impl.cc
        utilities/transactions/optimistic_transaction.cc
        utilities/transactions/pessimistic_transaction.cc
@@ -709,10 +664,12 @@ set(SOURCES
        utilities/write_batch_with_index/write_batch_with_index_internal.cc
        $<TARGET_OBJECTS:build_version>)

-if(HAVE_SSE42 AND NOT MSVC)
-  set_source_files_properties(
-    util/crc32c.cc
-    PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
+if(HAVE_SSE42 AND NOT FORCE_SSE42)
+  if(NOT MSVC)
+set_source_files_properties(
+  util/crc32c.cc
+      PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
+  endif()
 endif()

 if(HAVE_POWER8)
@@ -721,11 +678,6 @@ if(HAVE_POWER8)
    util/crc32c_ppc_asm.S)
 endif(HAVE_POWER8)

-if(HAS_ARMV8_CRC)
-  list(APPEND SOURCES
-    util/crc32c_arm64.cc)
-endif(HAS_ARMV8_CRC)
-
 if(WIN32)
  list(APPEND SOURCES
    port/win/io_win.cc
@@ -849,7 +801,6 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
    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}"
@@ -873,16 +824,15 @@ endif()

 option(WITH_TESTS "build with tests" ON)
 if(WITH_TESTS)
-  add_subdirectory(third-party/gtest-1.7.0/fused-src/gtest)
  set(TESTS
        cache/cache_test.cc
        cache/lru_cache_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
@@ -905,7 +855,6 @@ if(WITH_TESTS)
        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
@@ -917,7 +866,6 @@ if(WITH_TESTS)
        db/db_write_test.cc
        db/dbformat_test.cc
        db/deletefile_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
@@ -935,8 +883,6 @@ if(WITH_TESTS)
        db/perf_context_test.cc
        db/plain_table_db_test.cc
        db/prefix_test.cc
-        db/range_del_aggregator_test.cc
-        db/range_tombstone_fragmenter_test.cc
        db/repair_test.cc
        db/table_properties_collector_test.cc
        db/version_builder_test.cc
@@ -949,47 +895,39 @@ if(WITH_TESTS)
        env/env_basic_test.cc
        env/env_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/full_filter_block_test.cc
        table/merger_test.cc
-        table/sst_file_reader_test.cc
        table/table_test.cc
-        tools/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/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/rate_limiter_test.cc
-        util/repeatable_thread_test.cc
        util/slice_transform_test.cc
        util/timer_queue_test.cc
        util/thread_list_test.cc
@@ -1001,6 +939,12 @@ if(WITH_TESTS)
        utilities/cassandra/cassandra_row_merge_test.cc
        utilities/cassandra/cassandra_serialize_test.cc
        utilities/checkpoint/checkpoint_test.cc
+        utilities/column_aware_encoding_test.cc
+        utilities/date_tiered/date_tiered_test.cc
+        utilities/document/document_db_test.cc
+        utilities/document/json_document_test.cc
+        utilities/geodb/geodb_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
@@ -1008,13 +952,13 @@ 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/redis/redis_lists_test.cc
+        utilities/spatialdb/spatial_db_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
        utilities/transactions/transaction_test.cc
        utilities/transactions/write_prepared_transaction_test.cc
-        utilities/transactions/write_unprepared_transaction_test.cc
        utilities/ttl/ttl_test.cc
        utilities/write_batch_with_index/write_batch_with_index_test.cc
  )
@@ -1025,11 +969,11 @@ if(WITH_TESTS)
  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/column_aware_encoding_exp.cc
    utilities/persistent_cache/hash_table_bench.cc)
-  add_library(testharness OBJECT test_util/testharness.cc)
+  add_library(testharness OBJECT util/testharness.cc)
  foreach(sourcefile ${BENCHMARKS})
    get_filename_component(exename ${sourcefile} NAME_WE)
    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
@@ -1043,7 +987,7 @@ if(WITH_TESTS)
      db/db_test_util.cc
      monitoring/thread_status_updater_debug.cc
      table/mock_table.cc
-      test_util/fault_injection_test_env.cc
+      util/fault_injection_test_env.cc
      utilities/cassandra/test_utils.cc
  )
  # test utilities are only build in debug
@@ -1,239 +1,14 @@
 # Rocksdb Change Log
 ## Unreleased
-### 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 explictly 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
-* Now DB::Close() will return Aborted() error when there is unreleased snapshot. Users can retry after all snapshots are released.
-* Index and filter blocks are now handled similarly to data blocks with regards to the block cache: instead of storing reader objects in the cache, only the blocks themselves are cached. In addition, index and filter blocks (as well as filter partitions) no longer get evicted from the cache when a table is closed. Moreover, index blocks can now use the compressed block cache (if any).
-* Partitions of partitioned indexes no longer affect the read amplification statistics.
-* Due to the above refactoring, block cache eviction statistics for indexes and filters 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.
-* The semantics of the per-block-type block read counts in the performance context now match those of the generic block_read_count.
-* Add C bindings for secondary instance, i.e. DBImplSecondary.
-* db_bench adds a "benchmark" stats_history, which prints out the whole stats history.
-* 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
-* 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
-
-### New Features
-* Add an option `snap_refresh_nanos` (default to 0.1s) 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 argument `--secondary_path` to ldb to open the database as the secondary instance. This would keep the original DB intact.
-
-### 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
-* Reduce iterator key comparision for upper/lower bound check.
-* 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 ingested file and directory not being fsync.
-* Return TryAgain status in place of Corruption when new tail is not visible to TransactionLogIterator.
-* 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 destorying 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.
-* RocksDB may choose to preopen some files even if options.max_open_files != -1. This may make DB open slightly longer.
-* 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.
-* Remove geodb, spatial_db, document_db, json_document, date_tiered_db, and redis_lists.
-* 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.
-
-### Bug Fixes
-* Fix a deadlock caused by compaction and file ingestion waiting for each other in the event of write stalls.
-* Fix a memory leak when files with range tombstones are read in mmap mode and block cache is enabled
-* Fix handling of corrupt range tombstone blocks such that corruptions cannot cause deleted keys to reappear
-* Lock free MultiGet
-* Fix incorrect `NotFound` point lookup result when querying the endpoint of a file that has been extended by a range tombstone.
-* Fix with pipelined write, write leaders's callback failure lead to the whole write group fail.
-
-### Change Default Options
-* Change options.compaction_pri's default to kMinOverlappingRatio
-
-## 5.18.0 (11/30/2018)
-### New Features
-* Introduced `JemallocNodumpAllocator` memory allocator. When being use, block cache will be excluded from core dump.
-* Introduced `PerfContextByLevel` as part of `PerfContext` which allows storing perf context at each level. Also replaced `__thread` with `thread_local` keyword for perf_context. Added per-level perf context for bloom filter and `Get` query.
-* With level_compaction_dynamic_level_bytes = true, level multiplier may be adjusted automatically when Level 0 to 1 compaction is lagged behind.
-* Introduced DB option `atomic_flush`. If true, RocksDB supports flushing multiple column families and atomically committing the result to MANIFEST. Useful when WAL is disabled.
-* Added `num_deletions` and `num_merge_operands` members to `TableProperties`.
-* Added "rocksdb.min-obsolete-sst-number-to-keep" DB property that reports the lower bound on SST file numbers that are being kept from deletion, even if the SSTs are obsolete.
-* Add xxhash64 checksum support
-* Introduced `MemoryAllocator`, which lets the user specify custom memory allocator for block based table.
-* Improved `DeleteRange` to prevent read performance degradation. The feature is no longer marked as experimental.
-
-### Public API Change
-* `DBOptions::use_direct_reads` now affects reads issued by `BackupEngine` on the database's SSTs.
-* `NO_ITERATORS` is divided into two counters `NO_ITERATOR_CREATED` and `NO_ITERATOR_DELETE`. Both of them are only increasing now, just as other counters.
-
-### Bug Fixes
-* Fix corner case where a write group leader blocked due to write stall blocks other writers in queue with WriteOptions::no_slowdown set.
-* Fix in-memory range tombstone truncation to avoid erroneously covering newer keys at a lower level, and include range tombstones in compacted files whose largest key is the range tombstone's start key.
-* Properly set the stop key for a truncated manual CompactRange
-* Fix slow flush/compaction when DB contains many snapshots. The problem became noticeable to us in DBs with 100,000+ snapshots, though it will affect others at different thresholds.
-* Fix the bug that WriteBatchWithIndex's SeekForPrev() doesn't see the entries with the same key.
-* Fix the bug where user comparator was sometimes fed with InternalKey instead of the user key. The bug manifests when during GenerateBottommostFiles.
-* Fix a bug in WritePrepared txns where if the number of old snapshots goes beyond the snapshot cache size (128 default) the rest will not be checked when evicting a commit entry from the commit cache.
-* Fixed Get correctness bug in the presence of range tombstones where merge operands covered by a range tombstone always result in NotFound.
-* Start populating `NO_FILE_CLOSES` ticker statistic, which was always zero previously.
-* The default value of NewBloomFilterPolicy()'s argument use_block_based_builder is changed to false. Note that this new default may cause large temp memory usage when building very large SST files.
-
-## 5.17.0 (10/05/2018)
-### Public API Change
-* `OnTableFileCreated` will now be called for empty files generated during compaction. In that case, `TableFileCreationInfo::file_path` will be "(nil)" and `TableFileCreationInfo::file_size` will be zero.
-* Add `FlushOptions::allow_write_stall`, which controls whether Flush calls start working immediately, even if it causes user writes to stall, or will wait until flush can be performed without causing write stall (similar to `CompactRangeOptions::allow_write_stall`). Note that the default value is false, meaning we add delay to Flush calls until stalling can be avoided when possible. This is behavior change compared to previous RocksDB versions, where Flush calls didn't check if they might cause stall or not.
-* Application using PessimisticTransactionDB is expected to rollback/commit recovered transactions before starting new ones. This assumption is used to skip concurrency control during recovery.
-* Expose column family id to `OnCompactionCompleted`.
-
-### New Features
-* TransactionOptions::skip_concurrency_control allows pessimistic transactions to skip the overhead of concurrency control. Could be used for optimizing certain transactions or during recovery.
-
-### Bug Fixes
-* Avoid creating empty SSTs and subsequently deleting them in certain cases during compaction.
-* Sync CURRENT file contents during checkpoint.
-
-## 5.16.3 (10/1/2018)
-### Bug Fixes
-* Fix crash caused when `CompactFiles` run with `CompactionOptions::compression == CompressionType::kDisableCompressionOption`. Now that setting causes the compression type to be chosen according to the column family-wide compression options.
-
-## 5.16.2 (9/21/2018)
-### Bug Fixes
-* Fix bug in partition filters with format_version=4.
-
-## 5.16.1 (9/17/2018)
-### Bug Fixes
-* Remove trace_analyzer_tool from rocksdb_lib target in TARGETS file.
-* Fix RocksDB Java build and tests.
-* Remove sync point in Block destructor.
-
-## 5.16.0 (8/21/2018)
-### Public API Change
-* The merge operands are passed to `MergeOperator::ShouldMerge` in the reversed order relative to how they were merged (passed to FullMerge or FullMergeV2) for performance reasons
-* GetAllKeyVersions() to take an extra argument of `max_num_ikeys`.
-* Using ZSTD dictionary trainer (i.e., setting `CompressionOptions::zstd_max_train_bytes` to a nonzero value) now requires ZSTD version 1.1.3 or later.
-
-### New Features
-* Changes the format of index blocks by delta encoding the index values, which are the block handles. This saves the encoding of BlockHandle::offset of the non-head index entries in each restart interval. The feature is backward compatible but not forward compatible. It is disabled by default unless format_version 4 or above is used.
-* Add a new tool: trace_analyzer. Trace_analyzer analyzes the trace file generated by using trace_replay API. It can convert the binary format trace file to a human readable txt file, output the statistics of the analyzed query types such as access statistics and size statistics, combining the dumped whole key space file to analyze, support query correlation analyzing, and etc. Current supported query types are: Get, Put, Delete, SingleDelete, DeleteRange, Merge, Iterator (Seek, SeekForPrev only).
-* Add hash index support to data blocks, which helps reducing the cpu utilization of point-lookup operations. This feature is backward compatible with the data block created without the hash index. It is disabled by default unless BlockBasedTableOptions::data_block_index_type is set to data_block_index_type = kDataBlockBinaryAndHash.
-
-### Bug Fixes
-* Fix a bug in misreporting the estimated partition index size in properties block.
-
-## 5.15.0 (7/17/2018)
-### Public API Change
-* Remove managed iterator. ReadOptions.managed is not effective anymore.
-* For bottommost_compression, a compatible CompressionOptions is added via `bottommost_compression_opts`. To keep backward compatible, a new boolean `enabled` is added to CompressionOptions. For compression_opts, it will be always used no matter what value of `enabled` is. For bottommost_compression_opts, it will only be used when user set `enabled=true`, otherwise, compression_opts will be used for bottommost_compression as default.
-* With LRUCache, when high_pri_pool_ratio > 0, midpoint insertion strategy will be enabled to put low-pri items to the tail of low-pri list (the midpoint) when they first inserted into the cache. This is to make cache entries never get hit age out faster, improving cache efficiency when large background scan presents.
 * For users of `Statistics` objects created via `CreateDBStatistics()`, the format of the string returned by its `ToString()` method has changed.
-* The "rocksdb.num.entries" table property no longer counts range deletion tombstones as entries.
+* With LRUCache, when high_pri_pool_ratio > 0, midpoint insertion strategy will be enabled to put low-pri items to the tail of low-pri list (the midpoint) when they first inserted into the cache. This is to make cache entries never get hit age out faster, improving cache efficiency when large background scan presents.

 ### New Features
-* Changes the format of index blocks by storing the key in their raw form rather than converting them to InternalKey. This saves 8 bytes per index key. The feature is backward compatible but not forward compatible. It is disabled by default unless format_version 3 or above is used.
-* Avoid memcpy when reading mmap files with OpenReadOnly and max_open_files==-1.
-* Support dynamically changing `ColumnFamilyOptions::ttl` via `SetOptions()`.
-* Add a new table property, "rocksdb.num.range-deletions", which counts the number of range deletion tombstones in the table.
-* Improve the performance of iterators doing long range scans by using readahead, when using direct IO.
-* pin_top_level_index_and_filter (default true) in BlockBasedTableOptions can be used in combination with cache_index_and_filter_blocks to prefetch and pin the top-level index of partitioned index and filter blocks in cache. It has no impact when cache_index_and_filter_blocks is false.
-* Write properties meta-block at the end of block-based table to save read-ahead IO.
+* Changes the format of index blocks by storing the key in their raw form rather than converting them to InternalKey. This saves 8 bytes per index key. The feature is backward compatbile but not forward compatible. It is disabled by default unless format_version 3 or above is used.

 ### Bug Fixes
-* Fix deadlock with enable_pipelined_write=true and max_successive_merges > 0
-* Check conflict at output level in CompactFiles.
-* Fix corruption in non-iterator reads when mmap is used for file reads
-* Fix bug with prefix search in partition filters where a shared prefix would be ignored from the later partitions. The bug could report an eixstent key as missing. The bug could be triggered if prefix_extractor is set and partition filters is enabled.
-* Change default value of `bytes_max_delete_chunk` to 0 in NewSstFileManager() as it doesn't work well with checkpoints.
-* Fix a bug caused by not copying the block trailer with compressed SST file, direct IO, prefetcher and no compressed block cache.
-* Fix write can stuck indefinitely if enable_pipelined_write=true. The issue exists since pipelined write was introduced in 5.5.0.
+* fix deadlock with enable_pipelined_write=true and max_successive_merges > 0

 ## 5.14.0 (5/16/2018)
 ### Public API Change
@@ -343,8 +118,7 @@
 * `BackupableDBOptions::max_valid_backups_to_open == 0` now means no backups will be opened during BackupEngine initialization. Previously this condition disabled limiting backups opened.
 * `DBOptions::preserve_deletes` is a new option that allows one to specify that DB should not drop tombstones for regular deletes if they have sequence number larger than what was set by the new API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)`. Disabled by default.
 * API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)` was added, users who wish to preserve deletes are expected to periodically call this function to advance the cutoff seqnum (all deletes made before this seqnum can be dropped by DB). It's user responsibility to figure out how to advance the seqnum in the way so the tombstones are kept for the desired period of time, yet are eventually processed in time and don't eat up too much space.
-* `ReadOptions::iter_start_seqnum` was added;
-if set to something > 0 user will see 2 changes in iterators behavior 1) only keys written with sequence larger than this parameter would be returned and 2) the `Slice` returned by iter->key() now points to the memory that keep User-oriented representation of the internal key, rather than user key. New struct `FullKey` was added to represent internal keys, along with a new helper function `ParseFullKey(const Slice& internal_key, FullKey* result);`.
+* `ReadOptions::iter_start_seqnum` was added; if set to something > 0 user will see 2 changes in iterators behavior 1) only keys written with sequence larger than this parameter would be returned and 2) the `Slice` returned by iter->key() now points to the memory that keep User-oriented representation of the internal key, rather than user key. New struct `FullKey` was added to represent internal keys, along with a new helper function `ParseFullKey(const Slice& internal_key, FullKey* result);`.
 * Deprecate trash_dir param in NewSstFileManager, right now we will rename deleted files to <name>.trash instead of moving them to trash directory
 * Allow setting a custom trash/DB size ratio limit in the SstFileManager, after which files that are to be scheduled for deletion are deleted immediately, regardless of any delete ratelimit.
 * Return an error on write if write_options.sync = true and write_options.disableWAL = true to warn user of inconsistent options. Previously we will not write to WAL and not respecting the sync options in this case.
@@ -43,8 +43,6 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
      command line flags processing. You can compile rocksdb library even
      if you don't have gflags installed.

-* If you wish to build the RocksJava static target, then cmake is required for building Snappy.
-
 ## Supported platforms

 * **Linux - Ubuntu**
@@ -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
@@ -12,11 +10,9 @@ This is the list of all known third-party language bindings for RocksDB. If some
 * PHP - https://github.com/Photonios/rocksdb-php
 * C# - https://github.com/warrenfalk/rocksdb-sharp
 * Rust
-    * https://github.com/pingcap/rust-rocksdb (used in production fork of https://github.com/spacejam/rust-rocksdb)
    * https://github.com/spacejam/rust-rocksdb
    * https://github.com/bh1xuw/rust-rocks
 * D programming language - https://github.com/b1naryth1ef/rocksdb
 * Erlang - https://gitlab.com/barrel-db/erlang-rocksdb
 * Elixir - https://github.com/urbint/rox
 * Nim - https://github.com/status-im/nim-rocksdb
-* Swift and Objective-C (iOS/OSX) - https://github.com/iabudiab/ObjectiveRocks 
@@ -82,49 +82,16 @@ ifeq ($(MAKECMDGOALS),rocksdbjavastatic)
 endif

 ifeq ($(MAKECMDGOALS),rocksdbjavastaticrelease)
-	ifneq ($(DEBUG_LEVEL),2)
-		DEBUG_LEVEL=0
-	endif
-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)
-ifneq ($(filter -DROCKSDB_LITE,$(OPT)),)
-  # Be backward compatible and support older format where OPT=-DROCKSDB_LITE is
-  # specified instead of LITE=1 on the command line.
-  LITE=1
-endif
-else ifeq ($(LITE), 1)
-ifeq ($(filter -DROCKSDB_LITE,$(OPT)),)
-	OPT += -DROCKSDB_LITE
-endif
-endif
-
-# Figure out optimize level.
-ifneq ($(DEBUG_LEVEL), 2)
-ifeq ($(LITE), 0)
-	OPT += -O2
-else
-	OPT += -Os
-endif
-endif
-
 # compile with -O2 if debug level is not 2
 ifneq ($(DEBUG_LEVEL), 2)
-OPT += -fno-omit-frame-pointer
+OPT += -O2 -fno-omit-frame-pointer
 # Skip for archs that don't support -momit-leaf-frame-pointer
 ifeq (,$(shell $(CXX) -fsyntax-only -momit-leaf-frame-pointer -xc /dev/null 2>&1))
 OPT += -momit-leaf-frame-pointer
@@ -143,12 +110,6 @@ CFLAGS +=  -DHAVE_POWER8
 HAVE_POWER8=1
 endif

-ifeq (,$(shell $(CXX) -fsyntax-only -march=armv8-a+crc -xc /dev/null 2>&1))
-CXXFLAGS += -march=armv8-a+crc+crypto
-CFLAGS += -march=armv8-a+crc+crypto
-ARMCRC_SOURCE=1
-endif
-
 # if we're compiling for release, compile without debug code (-DNDEBUG)
 ifeq ($(DEBUG_LEVEL),0)
 OPT += -DNDEBUG
@@ -210,7 +171,7 @@ include make_config.mk
 CLEAN_FILES += make_config.mk

 missing_make_config_paths := $(shell				\
-	grep "\./\S*\|/\S*" -o $(CURDIR)/make_config.mk | 	\
+	grep "\/\S*" -o $(CURDIR)/make_config.mk | 		\
 	while read path;					\
 		do [ -e $$path ] || echo $$path; 		\
 	done | sort | uniq)
@@ -353,7 +314,7 @@ endif
 ifeq ("$(wildcard $(LUA_LIB))", "") # LUA_LIB does not exist
 $(error $(LUA_LIB) does not exist.  Try to specify both LUA_PATH and LUA_LIB manually)
 endif
-EXEC_LDFLAGS += $(LUA_LIB)
+LDFLAGS += $(LUA_LIB)

 endif

@@ -404,8 +365,8 @@ LIBOBJECTS += $(TOOL_LIB_SOURCES:.cc=.o)
 MOCKOBJECTS = $(MOCK_LIB_SOURCES:.cc=.o)

 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)

@@ -413,9 +374,7 @@ VALGRIND_OPTS = --error-exitcode=$(VALGRIND_ERROR) --leak-check=full

 BENCHTOOLOBJECTS = $(BENCH_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)

-ANALYZETOOLOBJECTS = $(ANALYZER_LIB_SOURCES:.cc=.o)
-
-EXPOBJECTS = $(LIBOBJECTS) $(TESTUTIL)
+EXPOBJECTS = $(EXP_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)

 TESTS = \
 	db_basic_test \
@@ -432,7 +391,6 @@ TESTS = \
 	inlineskiplist_test \
 	env_basic_test \
 	env_test \
-	env_logger_test \
 	hash_test \
 	thread_local_test \
 	rate_limiter_test \
@@ -456,7 +414,6 @@ TESTS = \
 	db_merge_operator_test \
 	db_options_test \
 	db_range_del_test \
-	db_secondary_test \
 	db_sst_test \
 	db_tailing_iter_test \
 	db_io_failure_test \
@@ -464,7 +421,6 @@ TESTS = \
 	db_table_properties_test \
 	db_statistics_test \
 	db_write_test \
-	error_handler_test \
 	autovector_test \
 	blob_db_test \
 	cleanable_test \
@@ -472,7 +428,6 @@ TESTS = \
 	table_properties_collector_test \
 	arena_test \
 	block_test \
-	data_block_hash_index_test \
 	cache_test \
 	corruption_test \
 	slice_transform_test \
@@ -496,11 +451,11 @@ TESTS = \
 	merger_test \
 	util_merge_operators_test \
 	options_file_test \
+	redis_test \
 	reduce_levels_test \
 	plain_table_db_test \
 	comparator_db_test \
 	external_sst_file_test \
-	import_column_family_test \
 	prefix_test \
 	skiplist_test \
 	write_buffer_manager_test \
@@ -510,9 +465,12 @@ TESTS = \
 	cassandra_row_merge_test \
 	cassandra_serialize_test \
 	ttl_test \
+	date_tiered_test \
 	backupable_db_test \
-	cache_simulator_test \
+	document_db_test \
+	json_document_test \
 	sim_cache_test \
+	spatial_db_test \
 	version_edit_test \
 	version_set_test \
 	compaction_picker_test \
@@ -524,6 +482,7 @@ TESTS = \
 	deletefile_test \
 	obsolete_files_test \
 	table_test \
+	geodb_test \
 	delete_scheduler_test \
 	options_test \
 	options_settable_test \
@@ -540,6 +499,7 @@ TESTS = \
 	compaction_job_test \
 	thread_list_test \
 	sst_dump_test \
+	column_aware_encoding_test \
 	compact_files_test \
 	optimistic_transaction_test \
 	write_callback_test \
@@ -551,22 +511,14 @@ TESTS = \
 	ldb_cmd_test \
 	persistent_cache_test \
 	statistics_test \
-	stats_history_test \
+	lua_test \
+	range_del_aggregator_test \
 	lru_cache_test \
 	object_registry_test \
 	repair_test \
 	env_timed_test \
 	write_prepared_transaction_test \
-	write_unprepared_transaction_test \
 	db_universal_compaction_test \
-	trace_analyzer_test \
-	repeatable_thread_test \
-	range_tombstone_fragmenter_test \
-	range_del_aggregator_test \
-	sst_file_reader_test \
-	db_secondary_test \
-	block_cache_tracer_test \
-	block_cache_trace_analyzer_test \

 PARALLEL_TEST = \
 	backupable_db_test \
@@ -578,7 +530,6 @@ PARALLEL_TEST = \
 	db_universal_compaction_test \
 	db_wal_test \
 	external_sst_file_test \
-	import_column_family_test \
 	fault_injection_test \
 	inlineskiplist_test \
 	manual_compaction_test \
@@ -586,7 +537,6 @@ PARALLEL_TEST = \
 	table_test \
 	transaction_test \
 	write_prepared_transaction_test \
-	write_unprepared_transaction_test \

 # options_settable_test doesn't pass with UBSAN as we use hack in the test
 ifdef COMPILE_WITH_UBSAN
@@ -611,14 +561,12 @@ TOOLS = \
 	rocksdb_dump \
 	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 persistent_cache_bench range_del_aggregator_bench
+BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench column_aware_encoding_exp persistent_cache_bench

 # if user didn't config LIBNAME, set the default
 ifeq ($(LIBNAME),)
@@ -706,10 +654,9 @@ $(SHARED4): $(shared_all_libobjects)
 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 \
+	release tags 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
+	analyze tools tools_lib


 all: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(TESTS)
@@ -839,6 +786,7 @@ J ?= 100%
 # Use this regexp to select the subset of tests whose names match.
 tests-regexp = .

+t_run = $(wildcard t/run-*)
 .PHONY: check_0
 check_0:
 	$(AM_V_GEN)export TEST_TMPDIR=$(TMPD); \
@@ -848,13 +796,13 @@ check_0:
 	test -t 1 && eta=--eta || eta=; \
 	{ \
 		printf './%s\n' $(filter-out $(PARALLEL_TEST),$(TESTS)); \
-		find t -name 'run-*' -print; \
+		printf '%s\n' $(t_run); \
 	} \
 	  | $(prioritize_long_running_tests)				\
 	  | grep -E '$(tests-regexp)'					\
 	  | build_tools/gnu_parallel -j$(J) --plain --joblog=LOG $$eta --gnu '{} >& t/log-{/}'

-valgrind-blacklist-regexp = InlineSkipTest.ConcurrentInsert|TransactionStressTest.DeadlockStress|DBCompactionTest.SuggestCompactRangeNoTwoLevel0Compactions|BackupableDBTest.RateLimiting|DBTest.CloseSpeedup|DBTest.ThreadStatusFlush|DBTest.RateLimitingTest|DBTest.EncodeDecompressedBlockSizeTest|FaultInjectionTest.UninstalledCompaction|HarnessTest.Randomized|ExternalSSTFileTest.CompactDuringAddFileRandom|ExternalSSTFileTest.IngestFileWithGlobalSeqnoRandomized|MySQLStyleTransactionTest.TransactionStressTest
+valgrind-blacklist-regexp = InlineSkipTest.ConcurrentInsert|TransactionTest.DeadlockStress|DBCompactionTest.SuggestCompactRangeNoTwoLevel0Compactions|BackupableDBTest.RateLimiting|DBTest.CloseSpeedup|DBTest.ThreadStatusFlush|DBTest.RateLimitingTest|DBTest.EncodeDecompressedBlockSizeTest|FaultInjectionTest.UninstalledCompaction|HarnessTest.Randomized|ExternalSSTFileTest.CompactDuringAddFileRandom|ExternalSSTFileTest.IngestFileWithGlobalSeqnoRandomized|MySQLStyleTransactionTest.TransactionStressTest

 .PHONY: valgrind_check_0
 valgrind_check_0:
@@ -865,7 +813,7 @@ valgrind_check_0:
 	test -t 1 && eta=--eta || eta=;					\
 	{								\
 	  printf './%s\n' $(filter-out $(PARALLEL_TEST) %skiplist_test options_settable_test, $(TESTS));		\
-	  find t -name 'run-*' -print; \
+	  printf '%s\n' $(t_run);					\
 	}								\
 	  | $(prioritize_long_running_tests)				\
 	  | grep -E '$(tests-regexp)'					\
@@ -917,15 +865,10 @@ 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
-
 blackbox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple 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 --enable_atomic_flush blackbox $(CRASH_TEST_EXT_ARGS)
-
 ifeq ($(CRASH_TEST_KILL_ODD),)
  CRASH_TEST_KILL_ODD=888887
 endif
@@ -936,10 +879,6 @@ whitebox_crash_test: db_stress
 	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 --enable_atomic_flush whitebox  --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
 asan_check:
 	$(MAKE) clean
 	COMPILE_WITH_ASAN=1 $(MAKE) check -j32
@@ -950,11 +889,6 @@ 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
-
 ubsan_check:
 	$(MAKE) clean
 	COMPILE_WITH_UBSAN=1 $(MAKE) check -j32
@@ -965,11 +899,6 @@ 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
-
 valgrind_test:
 	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check

@@ -1057,10 +986,8 @@ unity.a: unity.o
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ unity.o

-
-TOOLLIBOBJECTS = $(TOOL_LIB_SOURCES:.cc=.o)
 # try compiling db_test with unity
-unity_test: db/db_test.o db/db_test_util.o $(TESTHARNESS) $(TOOLLIBOBJECTS) unity.a
+unity_test: db/db_test.o db/db_test_util.o $(TESTHARNESS) unity.a
 	$(AM_LINK)
 	./unity_test

@@ -1080,13 +1007,6 @@ tags:
 	cscope -b `$(FIND) . -name '*.cc'` `$(FIND) . -name '*.h'` `$(FIND) . -name '*.c'`
 	ctags -e -R -o etags *

-tags0:
-	ctags -R .
-	cscope -b `$(FIND) . -name '*.cc' -and ! -name '*_test.cc'` \
-		  `$(FIND) . -name '*.c' -and ! -name '*_test.c'` \
-		  `$(FIND) . -name '*.h' -and ! -name '*_test.h'`
-	ctags -e -R -o etags *
-
 format:
 	build_tools/format-diff.sh

@@ -1100,7 +1020,7 @@ $(LIBRARY): $(LIBOBJECTS)
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $(LIBOBJECTS)

-$(TOOLS_LIBRARY): $(BENCH_LIB_SOURCES:.cc=.o) $(TOOL_LIB_SOURCES:.cc=.o) $(LIB_SOURCES:.cc=.o) $(TESTUTIL) $(ANALYZER_LIB_SOURCES:.cc=.o)
+$(TOOLS_LIBRARY): $(BENCH_LIB_SOURCES:.cc=.o) $(TOOL_LIB_SOURCES:.cc=.o) $(LIB_SOURCES:.cc=.o) $(TESTUTIL)
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^

@@ -1111,12 +1031,6 @@ librocksdb_env_basic_test.a: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 db_bench: tools/db_bench.o $(BENCHTOOLOBJECTS)
 	$(AM_LINK)

-trace_analyzer: tools/trace_analyzer.o $(ANALYZETOOLOBJECTS) $(LIBOBJECTS)
-	$(AM_LINK)
-
-block_cache_trace_analyzer: tools/block_cache_trace_analyzer_tool.o $(ANALYZETOOLOBJECTS) $(LIBOBJECTS)
-	$(AM_LINK)
-
 cache_bench: cache/cache_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)

@@ -1138,7 +1052,7 @@ 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)
@@ -1186,6 +1100,9 @@ cassandra_row_merge_test: utilities/cassandra/cassandra_row_merge_test.o utiliti
 cassandra_serialize_test: utilities/cassandra/cassandra_serialize_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

+redis_test: utilities/redis/redis_lists_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 hash_table_test: utilities/persistent_cache/hash_table_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1267,18 +1184,12 @@ 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_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)
 	$(AM_LINK)

 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)

@@ -1327,12 +1238,18 @@ 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)
+document_db_test: utilities/document/document_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+json_document_test: utilities/document/json_document_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)

+spatial_db_test: utilities/spatialdb/spatial_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 env_mirror_test: utilities/env_mirror_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1350,19 +1267,22 @@ object_registry_test: utilities/object_registry_test.o $(LIBOBJECTS) $(TESTHARNE
 ttl_test: utilities/ttl/ttl_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

+date_tiered_test: utilities/date_tiered/date_tiered_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 write_batch_with_index_test: utilities/write_batch_with_index/write_batch_with_index_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 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)
@@ -1386,7 +1306,7 @@ fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
 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)
@@ -1395,13 +1315,13 @@ 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)
@@ -1413,10 +1333,7 @@ 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)
-	$(AM_LINK)
-
-data_block_hash_index_test: table/block_based/data_block_hash_index_test.o $(LIBOBJECTS) $(TESTHARNESS)
+block_test: table/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 inlineskiplist_test: memtable/inlineskiplist_test.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1434,7 +1351,7 @@ 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)
@@ -1476,16 +1393,19 @@ deletefile_test: db/deletefile_test.o $(LIBOBJECTS) $(TESTHARNESS)
 obsolete_files_test: db/obsolete_files_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

+geodb_test: utilities/geodb/geodb_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
 	$(AM_LINK)

 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)
@@ -1512,10 +1432,7 @@ options_util_test: utilities/options/options_util_test.o $(LIBOBJECTS) $(TESTHAR
 db_bench_tool_test: tools/db_bench_tool_test.o $(BENCHTOOLOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-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)
@@ -1524,6 +1441,9 @@ timer_queue_test: util/timer_queue_test.o $(LIBOBJECTS) $(TESTHARNESS)
 sst_dump_test: tools/sst_dump_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

+column_aware_encoding_test: utilities/column_aware_encoding_test.o $(TESTHARNESS) $(EXPOBJECTS)
+	$(AM_LINK)
+
 optimistic_transaction_test: utilities/transactions/optimistic_transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1536,10 +1456,7 @@ 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)
@@ -1557,15 +1474,15 @@ transaction_test: utilities/transactions/transaction_test.o $(LIBOBJECTS) $(TEST
 write_prepared_transaction_test: utilities/transactions/write_prepared_transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-write_unprepared_transaction_test: utilities/transactions/write_unprepared_transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 sst_dump: tools/sst_dump.o $(LIBOBJECTS)
 	$(AM_LINK)

 blob_dump: tools/blob_dump.o $(LIBOBJECTS)
 	$(AM_LINK)

+column_aware_encoding_exp: utilities/column_aware_encoding_exp.o $(EXPOBJECTS)
+	$(AM_LINK)
+
 repair_test: db/repair_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1584,39 +1501,18 @@ 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)
 	$(AM_LINK)

-range_del_aggregator_bench: db/range_del_aggregator_bench.o $(LIBOBJECTS) $(TESTUTIL)
-	$(AM_LINK)
-
 blob_db_test: utilities/blob_db/blob_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-repeatable_thread_test: util/repeatable_thread_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-range_tombstone_fragmenter_test: db/range_tombstone_fragmenter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-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_trace_analyzer_test.o tools/block_cache_trace_analyzer.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1662,7 +1558,7 @@ JAVA_INCLUDE = -I$(JAVA_HOME)/include/ -I$(JAVA_HOME)/include/linux
 ifeq ($(PLATFORM), OS_SOLARIS)
 	ARCH := $(shell isainfo -b)
 else ifeq ($(PLATFORM), OS_OPENBSD)
-	ifneq (,$(filter $(MACHINE), amd64 arm64 sparc64 aarch64))
+	ifneq (,$(filter $(MACHINE), amd64 arm64 sparc64))
 		ARCH := 64
 	else
 		ARCH := 32
@@ -1676,9 +1572,6 @@ ifeq (,$(findstring ppc,$(MACHINE)))
 else
        ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE).so
 endif
-ifneq (,$(findstring aarch64,$(MACHINE)))
-        ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE).so
-endif
 ROCKSDB_JAR = rocksdbjni-$(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
@@ -1690,15 +1583,15 @@ ZLIB_SHA256 ?= c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1
 ZLIB_DOWNLOAD_BASE ?= http://zlib.net
 BZIP2_VER ?= 1.0.6
 BZIP2_SHA256 ?= a2848f34fcd5d6cf47def00461fcb528a0484d8edef8208d6d2e2909dc61d9cd
-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 ?= 1.8.3
-LZ4_SHA256 ?= 33af5936ac06536805f9745e0b6d61da606a1f8b4cc5c04dd3cbaca3b9b4fc43
+BZIP2_DOWNLOAD_BASE ?= http://www.bzip.org
+SNAPPY_VER ?= 1.1.4
+SNAPPY_SHA256 ?= 134bfe122fd25599bb807bb8130e7ba6d9bdb851e0b16efcb83ac4f5d0b70057
+SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/releases/download
+LZ4_VER ?= 1.8.0
+LZ4_SHA256 ?= 2ca482ea7a9bb103603108b5a7510b7592b90158c151ff50a28f1ca8389fccf6
 LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
-ZSTD_VER ?= 1.4.0
-ZSTD_SHA256 ?= 63be339137d2b683c6d19a9e34f4fb684790e864fee13c7dd40e197a64c705c1
+ZSTD_VER ?= 1.3.3
+ZSTD_SHA256 ?= a77c47153ee7de02626c5b2a097005786b71688be61e9fb81806a011f90b297b
 ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
 CURL_SSL_OPTS ?= --tlsv1

@@ -1737,9 +1630,7 @@ endif

 libz.a:
 	-rm -rf zlib-$(ZLIB_VER)
-ifeq (,$(wildcard ./zlib-$(ZLIB_VER).tar.gz))
-	curl --output zlib-$(ZLIB_VER).tar.gz -L ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
-endif
+	curl -O -L ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
 	ZLIB_SHA256_ACTUAL=`$(SHA256_CMD) zlib-$(ZLIB_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZLIB_SHA256)" != "$$ZLIB_SHA256_ACTUAL" ]; then \
 		echo zlib-$(ZLIB_VER).tar.gz checksum mismatch, expected=\"$(ZLIB_SHA256)\" actual=\"$$ZLIB_SHA256_ACTUAL\"; \
@@ -1751,9 +1642,7 @@ endif

 libbz2.a:
 	-rm -rf bzip2-$(BZIP2_VER)
-ifeq (,$(wildcard ./bzip2-$(BZIP2_VER).tar.gz))
-	curl --output bzip2-$(BZIP2_VER).tar.gz -L ${BZIP2_DOWNLOAD_BASE}/$(BZIP2_VER)/bzip2-$(BZIP2_VER).tar.gz
-endif
+	curl -O -L ${BZIP2_DOWNLOAD_BASE}/$(BZIP2_VER)/bzip2-$(BZIP2_VER).tar.gz
 	BZIP2_SHA256_ACTUAL=`$(SHA256_CMD) bzip2-$(BZIP2_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(BZIP2_SHA256)" != "$$BZIP2_SHA256_ACTUAL" ]; then \
 		echo bzip2-$(BZIP2_VER).tar.gz checksum mismatch, expected=\"$(BZIP2_SHA256)\" actual=\"$$BZIP2_SHA256_ACTUAL\"; \
@@ -1765,24 +1654,21 @@ endif

 libsnappy.a:
 	-rm -rf snappy-$(SNAPPY_VER)
-ifeq (,$(wildcard ./snappy-$(SNAPPY_VER).tar.gz))
-	curl --output snappy-$(SNAPPY_VER).tar.gz -L ${CURL_SSL_OPTS} ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER).tar.gz
-endif
+	curl -O -L ${CURL_SSL_OPTS} ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER)/snappy-$(SNAPPY_VER).tar.gz
 	SNAPPY_SHA256_ACTUAL=`$(SHA256_CMD) snappy-$(SNAPPY_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(SNAPPY_SHA256)" != "$$SNAPPY_SHA256_ACTUAL" ]; then \
 		echo snappy-$(SNAPPY_VER).tar.gz checksum mismatch, expected=\"$(SNAPPY_SHA256)\" actual=\"$$SNAPPY_SHA256_ACTUAL\"; \
 		exit 1; \
 	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) ${SNAPPY_MAKE_TARGET}
-	cp snappy-$(SNAPPY_VER)/build/libsnappy.a .
+	cd snappy-$(SNAPPY_VER) && CFLAGS='${EXTRA_CFLAGS}' CXXFLAGS='${EXTRA_CXXFLAGS}' LDFLAGS='${EXTRA_LDFLAGS}' ./configure --with-pic --enable-static --disable-shared
+	cd snappy-$(SNAPPY_VER) && $(MAKE) ${SNAPPY_MAKE_TARGET}
+	cp snappy-$(SNAPPY_VER)/.libs/libsnappy.a .

 liblz4.a:
 	-rm -rf lz4-$(LZ4_VER)
-ifeq (,$(wildcard ./lz4-$(LZ4_VER).tar.gz))
-	curl --output lz4-$(LZ4_VER).tar.gz -L ${CURL_SSL_OPTS} ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
-endif
+	curl -O -L ${CURL_SSL_OPTS} ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
+	mv v$(LZ4_VER).tar.gz lz4-$(LZ4_VER).tar.gz
 	LZ4_SHA256_ACTUAL=`$(SHA256_CMD) lz4-$(LZ4_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(LZ4_SHA256)" != "$$LZ4_SHA256_ACTUAL" ]; then \
 		echo lz4-$(LZ4_VER).tar.gz checksum mismatch, expected=\"$(LZ4_SHA256)\" actual=\"$$LZ4_SHA256_ACTUAL\"; \
@@ -1794,9 +1680,8 @@ endif

 libzstd.a:
 	-rm -rf zstd-$(ZSTD_VER)
-ifeq (,$(wildcard ./zstd-$(ZSTD_VER).tar.gz))
-	curl --output zstd-$(ZSTD_VER).tar.gz -L ${CURL_SSL_OPTS} ${ZSTD_DOWNLOAD_BASE}/v$(ZSTD_VER).tar.gz
-endif
+	curl -O -L ${CURL_SSL_OPTS} ${ZSTD_DOWNLOAD_BASE}/v$(ZSTD_VER).tar.gz
+	mv v$(ZSTD_VER).tar.gz zstd-$(ZSTD_VER).tar.gz
 	ZSTD_SHA256_ACTUAL=`$(SHA256_CMD) zstd-$(ZSTD_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZSTD_SHA256)" != "$$ZSTD_SHA256_ACTUAL" ]; then \
 		echo zstd-$(ZSTD_VER).tar.gz checksum mismatch, expected=\"$(ZSTD_SHA256)\" actual=\"$$ZSTD_SHA256_ACTUAL\"; \
@@ -1858,22 +1743,28 @@ rocksdbjavastaticrelease: rocksdbjavastatic
 	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
+rocksdbjavastaticreleasedocker: rocksdbjavastatic
+	DOCKER_LINUX_X64_CONTAINER=`docker ps -aqf name=rocksdb_linux_x64-be`; \
+	if [ -z "$$DOCKER_LINUX_X64_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_x64-be evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_x64-be
+	DOCKER_LINUX_X86_CONTAINER=`docker ps -aqf name=rocksdb_linux_x86-be`; \
+	if [ -z "$$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
 	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 `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerx86_64:
-	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x64-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
 rocksdbjavastaticdockerppc64le:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_ppc64le-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_ppc64le-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

@@ -1921,7 +1812,7 @@ $(java_libobjects): jl/%.o: %.cc
 rocksdbjava: $(java_all_libobjects)
 	$(AM_V_GEN)cd java;$(MAKE) javalib;
 	$(AM_V_at)rm -f ./java/target/$(ROCKSDBJNILIB)
-	$(AM_V_at)$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) $(java_all_libobjects) $(JAVA_LDFLAGS) $(COVERAGEFLAGS)
+	$(AM_V_at)$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) $(java_libobjects) $(JAVA_LDFLAGS) $(COVERAGEFLAGS)
 	$(AM_V_at)cd java;jar -cf target/$(ROCKSDB_JAR) HISTORY*.md
 	$(AM_V_at)cd java/target;jar -uf $(ROCKSDB_JAR) $(ROCKSDBJNILIB)
 	$(AM_V_at)cd java/target/classes;jar -uf ../$(ROCKSDB_JAR) org/rocksdb/*.class org/rocksdb/util/*.class
@@ -1953,8 +1844,7 @@ commit_prereq: build_tools/rocksdb-lego-determinator \
 ifeq ($(PLATFORM), IOS)
 # For iOS, create universal object files to be used on both the simulator and
 # a device.
-XCODEROOT=$(shell xcode-select -print-path)
-PLATFORMSROOT=$(XCODEROOT)/Platforms
+PLATFORMSROOT=/Applications/Xcode.app/Contents/Developer/Platforms
 SIMULATORROOT=$(PLATFORMSROOT)/iPhoneSimulator.platform/Developer
 DEVICEROOT=$(PLATFORMSROOT)/iPhoneOS.platform/Developer
 IOSVERSION=$(shell defaults read $(PLATFORMSROOT)/iPhoneOS.platform/version CFBundleShortVersionString)
@@ -1991,7 +1881,7 @@ 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)
+all_sources = $(LIB_SOURCES) $(MAIN_SOURCES) $(MOCK_LIB_SOURCES) $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(TEST_LIB_SOURCES) $(EXP_LIB_SOURCES)
 DEPFILES = $(all_sources:.cc=.cc.d)

 # Add proper dependency support so changing a .h file forces a .cc file to
@@ -4,8 +4,9 @@
 [![Windows Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
 [![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
@@ -1,10 +1,10 @@
-load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
-load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
-load(":defs.bzl", "test_binary")
-
 REPO_PATH = package_name() + "/"

-ROCKSDB_COMPILER_FLAGS = [
+BUCK_BINS = "buck-out/gen/" + REPO_PATH
+
+TEST_RUNNER = REPO_PATH + "buckifier/rocks_test_runner.sh"
+
+rocksdb_compiler_flags = [
    "-fno-builtin-memcmp",
    "-DROCKSDB_PLATFORM_POSIX",
    "-DROCKSDB_LIB_IO_POSIX",
@@ -20,7 +20,6 @@ ROCKSDB_COMPILER_FLAGS = [
    "-DBZIP2",
    "-DLZ4",
    "-DZSTD",
-    "-DZSTD_STATIC_LINKING_ONLY",
    "-DGFLAGS=gflags",
    "-DNUMA",
    "-DTBB",
@@ -29,11 +28,10 @@ ROCKSDB_COMPILER_FLAGS = [
    # Added missing flags from output of build_detect_platform
    "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
    "-DROCKSDB_BACKTRACE",
-    "-Wnarrowing",
-    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
+    "-Wshorten-64-to-32",
 ]

-ROCKSDB_EXTERNAL_DEPS = [
+rocksdb_external_deps = [
    ("bzip2", None, "bz2"),
    ("snappy", None, "snappy"),
    ("zlib", None, "z"),
@@ -45,13 +43,13 @@ ROCKSDB_EXTERNAL_DEPS = [
    ("googletest", None, "gtest"),
 ]

-ROCKSDB_PREPROCESSOR_FLAGS = [
+rocksdb_preprocessor_flags = [
    # Directories with files for #include
    "-I" + REPO_PATH + "include/",
    "-I" + REPO_PATH,
 ]

-ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
+rocksdb_arch_preprocessor_flags = {
    "x86_64": [
        "-DHAVE_SSE42",
        "-DHAVE_PCLMUL",
@@ -64,15 +62,8 @@ is_opt_mode = build_mode.startswith("opt")

 # -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
 # doesn't harm and avoid forgetting to add it.
-ROCKSDB_COMPILER_FLAGS += (["-DNDEBUG"] if is_opt_mode else [])
-
-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_COMPILER_FLAGS += (["-DROCKSDB_JEMALLOC"] if sanitizer == "" else [])
-
-ROCKSDB_EXTERNAL_DEPS += ([("jemalloc", None, "headers")] if sanitizer == "" else [])
+if is_opt_mode:
+    rocksdb_compiler_flags.append("-DNDEBUG")

 cpp_library(
    name = "rocksdb_lib",
@@ -84,28 +75,24 @@ cpp_library(
        "db/c.cc",
        "db/column_family.cc",
        "db/compacted_db_impl.cc",
-        "db/compaction/compaction.cc",
-        "db/compaction/compaction_iterator.cc",
-        "db/compaction/compaction_job.cc",
-        "db/compaction/compaction_picker.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_universal.cc",
        "db/convenience.cc",
        "db/db_filesnapshot.cc",
-        "db/db_impl/db_impl.cc",
-        "db/db_impl/db_impl_compaction_flush.cc",
-        "db/db_impl/db_impl_debug.cc",
-        "db/db_impl/db_impl_experimental.cc",
-        "db/db_impl/db_impl_files.cc",
-        "db/db_impl/db_impl_open.cc",
-        "db/db_impl/db_impl_readonly.cc",
-        "db/db_impl/db_impl_secondary.cc",
-        "db/db_impl/db_impl_write.cc",
+        "db/db_impl.cc",
+        "db/db_impl_compaction_flush.cc",
+        "db/db_impl_debug.cc",
+        "db/db_impl_experimental.cc",
+        "db/db_impl_files.cc",
+        "db/db_impl_open.cc",
+        "db/db_impl_readonly.cc",
+        "db/db_impl_write.cc",
        "db/db_info_dumper.cc",
        "db/db_iter.cc",
        "db/dbformat.cc",
-        "db/error_handler.cc",
        "db/event_helpers.cc",
        "db/experimental.cc",
        "db/external_sst_file_ingestion_job.cc",
@@ -113,18 +100,17 @@ cpp_library(
        "db/flush_job.cc",
        "db/flush_scheduler.cc",
        "db/forward_iterator.cc",
-        "db/import_column_family_job.cc",
        "db/internal_stats.cc",
        "db/log_reader.cc",
        "db/log_writer.cc",
        "db/logs_with_prep_tracker.cc",
        "db/malloc_stats.cc",
+        "db/managed_iterator.cc",
        "db/memtable.cc",
        "db/memtable_list.cc",
        "db/merge_helper.cc",
        "db/merge_operator.cc",
        "db/range_del_aggregator.cc",
-        "db/range_tombstone_fragmenter.cc",
        "db/repair.cc",
        "db/snapshot_impl.cc",
        "db/table_cache.cc",
@@ -145,17 +131,8 @@ cpp_library(
        "env/env_posix.cc",
        "env/io_posix.cc",
        "env/mock_env.cc",
-        "file/delete_scheduler.cc",
-        "file/file_util.cc",
-        "file/filename.cc",
-        "file/sst_file_manager_impl.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",
@@ -163,12 +140,10 @@ cpp_library(
        "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",
@@ -183,91 +158,99 @@ cpp_library(
        "options/options_sanity_check.cc",
        "port/port_posix.cc",
        "port/stack_trace.cc",
-        "table/adaptive/adaptive_table_factory.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_reader.cc",
-        "table/block_based/block_builder.cc",
-        "table/block_based/block_prefix_index.cc",
-        "table/block_based/data_block_footer.cc",
-        "table/block_based/data_block_hash_index.cc",
-        "table/block_based/filter_block_reader_common.cc",
-        "table/block_based/flush_block_policy.cc",
-        "table/block_based/full_filter_block.cc",
-        "table/block_based/index_builder.cc",
-        "table/block_based/partitioned_filter_block.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/block_prefix_index.cc",
        "table/bloom_block.cc",
-        "table/cuckoo/cuckoo_table_builder.cc",
-        "table/cuckoo/cuckoo_table_factory.cc",
-        "table/cuckoo/cuckoo_table_reader.cc",
+        "table/cuckoo_table_builder.cc",
+        "table/cuckoo_table_factory.cc",
+        "table/cuckoo_table_reader.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_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/sst_file_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_writer.cc",
        "table/table_properties.cc",
        "table/two_level_iterator.cc",
-        "test_util/sync_point.cc",
-        "test_util/sync_point_impl.cc",
-        "test_util/transaction_test_util.cc",
        "tools/dump/db_dump_tool.cc",
        "tools/ldb_cmd.cc",
        "tools/ldb_tool.cc",
        "tools/sst_dump_tool.cc",
-        "trace_replay/block_cache_tracer.cc",
-        "trace_replay/trace_replay.cc",
+        "util/arena.cc",
+        "util/auto_roll_logger.cc",
        "util/bloom.cc",
        "util/build_version.cc",
        "util/coding.cc",
        "util/compaction_job_stats_impl.cc",
        "util/comparator.cc",
-        "util/compression_context_cache.cc",
-        "util/concurrent_task_limiter_impl.cc",
+        "util/concurrent_arena.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/log_buffer.cc",
        "util/murmurhash.cc",
        "util/random.cc",
        "util/rate_limiter.cc",
        "util/slice.cc",
+        "util/sst_file_manager_impl.cc",
        "util/status.cc",
+        "util/status_message.cc",
        "util/string_util.cc",
+        "util/sync_point.cc",
+        "util/sync_point_impl.cc",
        "util/thread_local.cc",
        "util/threadpool_imp.cc",
+        "util/transaction_test_util.cc",
        "util/xxhash.cc",
        "utilities/backupable/backupable_db.cc",
        "utilities/blob_db/blob_compaction_filter.cc",
        "utilities/blob_db/blob_db.cc",
        "utilities/blob_db/blob_db_impl.cc",
-        "utilities/blob_db/blob_db_impl_filesnapshot.cc",
        "utilities/blob_db/blob_dump_tool.cc",
        "utilities/blob_db/blob_file.cc",
        "utilities/blob_db/blob_log_format.cc",
        "utilities/blob_db/blob_log_reader.cc",
        "utilities/blob_db/blob_log_writer.cc",
+        "utilities/blob_db/ttl_extractor.cc",
        "utilities/cassandra/cassandra_compaction_filter.cc",
        "utilities/cassandra/format.cc",
        "utilities/cassandra/merge_operator.cc",
        "utilities/checkpoint/checkpoint_impl.cc",
        "utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc",
        "utilities/convenience/info_log_finder.cc",
+        "utilities/date_tiered/date_tiered_db_impl.cc",
        "utilities/debug.cc",
+        "utilities/document/document_db.cc",
+        "utilities/document/json_document.cc",
+        "utilities/document/json_document_builder.cc",
        "utilities/env_mirror.cc",
        "utilities/env_timed.cc",
+        "utilities/geodb/geodb_impl.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",
@@ -282,10 +265,10 @@ cpp_library(
        "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/redis/redis_lists.cc",
        "utilities/simulator_cache/sim_cache.cc",
+        "utilities/spatialdb/spatial_db.cc",
        "utilities/table_properties_collectors/compact_on_deletion_collector.cc",
-        "utilities/trace/file_trace_reader_writer.cc",
        "utilities/transactions/optimistic_transaction.cc",
        "utilities/transactions/optimistic_transaction_db_impl.cc",
        "utilities/transactions/pessimistic_transaction.cc",
@@ -303,12 +286,12 @@ cpp_library(
        "utilities/write_batch_with_index/write_batch_with_index.cc",
        "utilities/write_batch_with_index/write_batch_with_index_internal.cc",
    ],
-    auto_headers = AutoHeaders.RECURSIVE_GLOB,
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    headers = AutoHeaders.RECURSIVE_GLOB,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
    deps = [],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    external_deps = rocksdb_external_deps,
 )

 cpp_library(
@@ -316,63 +299,57 @@ cpp_library(
    srcs = [
        "db/db_test_util.cc",
        "table/mock_table.cc",
-        "test_util/fault_injection_test_env.cc",
-        "test_util/testharness.cc",
-        "test_util/testutil.cc",
-        "tools/block_cache_trace_analyzer.cc",
-        "tools/trace_analyzer_tool.cc",
+        "util/fault_injection_test_env.cc",
+        "util/testharness.cc",
+        "util/testutil.cc",
        "utilities/cassandra/test_utils.cc",
+        "utilities/col_buf_decoder.cc",
+        "utilities/col_buf_encoder.cc",
+        "utilities/column_aware_encoding_util.cc",
    ],
-    auto_headers = AutoHeaders.RECURSIVE_GLOB,
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    headers = AutoHeaders.RECURSIVE_GLOB,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
    deps = [":rocksdb_lib"],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    external_deps = rocksdb_external_deps,
 )

 cpp_library(
    name = "rocksdb_tools_lib",
    srcs = [
-        "test_util/testutil.cc",
-        "tools/block_cache_trace_analyzer.cc",
        "tools/db_bench_tool.cc",
-        "tools/trace_analyzer_tool.cc",
+        "util/testutil.cc",
    ],
-    auto_headers = AutoHeaders.RECURSIVE_GLOB,
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    headers = AutoHeaders.RECURSIVE_GLOB,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
    deps = [":rocksdb_lib"],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    external_deps = rocksdb_external_deps,
 )

 cpp_library(
    name = "env_basic_test_lib",
    srcs = ["env/env_basic_test.cc"],
-    auto_headers = AutoHeaders.RECURSIVE_GLOB,
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    headers = AutoHeaders.RECURSIVE_GLOB,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
    deps = [":rocksdb_test_lib"],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    external_deps = rocksdb_external_deps,
 )

 # [test_name, test_src, test_type]
 ROCKS_TESTS = [
    [
        "arena_test",
-        "memory/arena_test.cc",
+        "util/arena_test.cc",
        "serial",
    ],
    [
        "auto_roll_logger_test",
-        "logging/auto_roll_logger_test.cc",
-        "serial",
-    ],
-    [
-        "env_logger_test",
-        "logging/env_logger_test.cc",
+        "util/auto_roll_logger_test.cc",
        "serial",
    ],
    [
@@ -392,22 +369,12 @@ ROCKS_TESTS = [
    ],
    [
        "block_based_filter_block_test",
-        "table/block_based/block_based_filter_block_test.cc",
-        "serial",
-    ],
-    [
-        "block_cache_trace_analyzer_test",
-        "tools/block_cache_trace_analyzer_test.cc",
-        "serial",
-    ],
-    [
-        "block_cache_tracer_test",
-        "trace_replay/block_cache_tracer_test.cc",
+        "table/block_based_filter_block_test.cc",
        "serial",
    ],
    [
        "block_test",
-        "table/block_based/block_test.cc",
+        "table/block_test.cc",
        "serial",
    ],
    [
@@ -425,11 +392,6 @@ ROCKS_TESTS = [
        "cache/cache_test.cc",
        "serial",
    ],
-    [
-        "cache_simulator_test",
-        "utilities/simulator_cache/cache_simulator_test.cc",
-        "serial",
-    ],
    [
        "cassandra_format_test",
        "utilities/cassandra/cassandra_format_test.cc",
@@ -465,6 +427,11 @@ ROCKS_TESTS = [
        "util/coding_test.cc",
        "serial",
    ],
+    [
+        "column_aware_encoding_test",
+        "utilities/column_aware_encoding_test.cc",
+        "serial",
+    ],
    [
        "column_family_test",
        "db/column_family_test.cc",
@@ -482,22 +449,22 @@ ROCKS_TESTS = [
    ],
    [
        "compaction_iterator_test",
-        "db/compaction/compaction_iterator_test.cc",
+        "db/compaction_iterator_test.cc",
        "serial",
    ],
    [
        "compaction_job_stats_test",
-        "db/compaction/compaction_job_stats_test.cc",
+        "db/compaction_job_stats_test.cc",
        "serial",
    ],
    [
        "compaction_job_test",
-        "db/compaction/compaction_job_test.cc",
+        "db/compaction_job_test.cc",
        "serial",
    ],
    [
        "compaction_picker_test",
-        "db/compaction/compaction_picker_test.cc",
+        "db/compaction_picker_test.cc",
        "serial",
    ],
    [
@@ -517,7 +484,7 @@ ROCKS_TESTS = [
    ],
    [
        "cuckoo_table_builder_test",
-        "table/cuckoo/cuckoo_table_builder_test.cc",
+        "table/cuckoo_table_builder_test.cc",
        "serial",
    ],
    [
@@ -527,12 +494,12 @@ ROCKS_TESTS = [
    ],
    [
        "cuckoo_table_reader_test",
-        "table/cuckoo/cuckoo_table_reader_test.cc",
+        "table/cuckoo_table_reader_test.cc",
        "serial",
    ],
    [
-        "data_block_hash_index_test",
-        "table/block_based/data_block_hash_index_test.cc",
+        "date_tiered_test",
+        "utilities/date_tiered/date_tiered_test.cc",
        "serial",
    ],
    [
@@ -553,7 +520,7 @@ ROCKS_TESTS = [
    [
        "db_bloom_filter_test",
        "db/db_bloom_filter_test.cc",
-        "parallel",
+        "serial",
    ],
    [
        "db_compaction_filter_test",
@@ -591,13 +558,13 @@ ROCKS_TESTS = [
        "serial",
    ],
    [
-        "db_iter_stress_test",
-        "db/db_iter_stress_test.cc",
+        "db_iter_test",
+        "db/db_iter_test.cc",
        "serial",
    ],
    [
-        "db_iter_test",
-        "db/db_iter_test.cc",
+        "db_iter_stress_test",
+        "db/db_iter_stress_test.cc",
        "serial",
    ],
    [
@@ -635,11 +602,6 @@ ROCKS_TESTS = [
        "db/db_range_del_test.cc",
        "serial",
    ],
-    [
-        "db_secondary_test",
-        "db/db_impl/db_secondary_test.cc",
-        "serial",
-    ],
    [
        "db_sst_test",
        "db/db_sst_test.cc",
@@ -692,7 +654,7 @@ ROCKS_TESTS = [
    ],
    [
        "delete_scheduler_test",
-        "file/delete_scheduler_test.cc",
+        "util/delete_scheduler_test.cc",
        "serial",
    ],
    [
@@ -700,6 +662,11 @@ ROCKS_TESTS = [
        "db/deletefile_test.cc",
        "serial",
    ],
+    [
+        "document_db_test",
+        "utilities/document/document_db_test.cc",
+        "serial",
+    ],
    [
        "dynamic_bloom_test",
        "util/dynamic_bloom_test.cc",
@@ -720,14 +687,9 @@ ROCKS_TESTS = [
        "utilities/env_timed_test.cc",
        "serial",
    ],
-    [
-        "error_handler_test",
-        "db/error_handler_test.cc",
-        "serial",
-    ],
    [
        "event_logger_test",
-        "logging/event_logger_test.cc",
+        "util/event_logger_test.cc",
        "serial",
    ],
    [
@@ -772,7 +734,12 @@ ROCKS_TESTS = [
    ],
    [
        "full_filter_block_test",
-        "table/block_based/full_filter_block_test.cc",
+        "table/full_filter_block_test.cc",
+        "serial",
+    ],
+    [
+        "geodb_test",
+        "utilities/geodb/geodb_test.cc",
        "serial",
    ],
    [
@@ -805,6 +772,11 @@ ROCKS_TESTS = [
        "monitoring/iostats_context_test.cc",
        "serial",
    ],
+    [
+        "json_document_test",
+        "utilities/document/json_document_test.cc",
+        "serial",
+    ],
    [
        "ldb_cmd_test",
        "tools/ldb_cmd_test.cc",
@@ -902,7 +874,7 @@ ROCKS_TESTS = [
    ],
    [
        "partitioned_filter_block_test",
-        "table/block_based/partitioned_filter_block_test.cc",
+        "table/partitioned_filter_block_test.cc",
        "serial",
    ],
    [
@@ -930,11 +902,6 @@ ROCKS_TESTS = [
        "db/range_del_aggregator_test.cc",
        "serial",
    ],
-    [
-        "range_tombstone_fragmenter_test",
-        "db/range_tombstone_fragmenter_test.cc",
-        "serial",
-    ],
    [
        "rate_limiter_test",
        "util/rate_limiter_test.cc",
@@ -950,11 +917,6 @@ ROCKS_TESTS = [
        "db/repair_test.cc",
        "serial",
    ],
-    [
-        "repeatable_thread_test",
-        "util/repeatable_thread_test.cc",
-        "serial",
-    ],
    [
        "sim_cache_test",
        "utilities/simulator_cache/sim_cache_test.cc",
@@ -970,26 +932,21 @@ ROCKS_TESTS = [
        "util/slice_transform_test.cc",
        "serial",
    ],
+    [
+        "spatial_db_test",
+        "utilities/spatialdb/spatial_db_test.cc",
+        "serial",
+    ],
    [
        "sst_dump_test",
        "tools/sst_dump_test.cc",
        "serial",
    ],
-    [
-        "sst_file_reader_test",
-        "table/sst_file_reader_test.cc",
-        "serial",
-    ],
    [
        "statistics_test",
        "monitoring/statistics_test.cc",
        "serial",
    ],
-    [
-        "stats_history_test",
-        "monitoring/stats_history_test.cc",
-        "serial",
-    ],
    [
        "stringappend_test",
        "utilities/merge_operators/string_append/stringappend_test.cc",
@@ -1020,11 +977,6 @@ ROCKS_TESTS = [
        "util/timer_queue_test.cc",
        "serial",
    ],
-    [
-        "trace_analyzer_test",
-        "tools/trace_analyzer_test.cc",
-        "serial",
-    ],
    [
        "transaction_test",
        "utilities/transactions/transaction_test.cc",
@@ -1090,26 +1042,43 @@ ROCKS_TESTS = [
        "utilities/transactions/write_prepared_transaction_test.cc",
        "parallel",
    ],
-    [
-        "write_unprepared_transaction_test",
-        "utilities/transactions/write_unprepared_transaction_test.cc",
-        "parallel",
-    ],
 ]

 # Generate a test rule for each entry in ROCKS_TESTS
 # Do not build the tests in opt mode, since SyncPoint and other test code
 # will not be included.
-[
-    test_binary(
-        parallelism = parallelism,
-        rocksdb_arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-        rocksdb_compiler_flags = ROCKSDB_COMPILER_FLAGS,
-        rocksdb_external_deps = ROCKSDB_EXTERNAL_DEPS,
-        rocksdb_preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-        test_cc = test_cc,
-        test_name = test_name,
-    )
-    for test_name, test_cc, parallelism in ROCKS_TESTS
-    if not is_opt_mode
-]
+if not is_opt_mode:
+    for test_cfg in ROCKS_TESTS:
+        test_name = test_cfg[0]
+        test_cc = test_cfg[1]
+        ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
+        test_bin = test_name + "_bin"
+
+        cpp_binary (
+          name = test_bin,
+          srcs = [test_cc],
+          deps = [":rocksdb_test_lib"],
+          preprocessor_flags = rocksdb_preprocessor_flags,
+          arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+          compiler_flags = rocksdb_compiler_flags,
+          external_deps = rocksdb_external_deps,
+        )
+
+        custom_unittest(
+          name = test_name,
+          type = ttype,
+          deps = [":" + test_bin],
+          command = [TEST_RUNNER, BUCK_BINS + test_bin]
+        )
+
+custom_unittest(
+    name = "make_rocksdbjavastatic",
+    command = ["internal_repo_rocksdb/make_rocksdbjavastatic.sh"],
+    type = "simple",
+)
+
+custom_unittest(
+    name = "make_rocksdb_lite_release",
+    command = ["internal_repo_rocksdb/make_rocksdb_lite_release.sh"],
+    type = "simple",
+)
@@ -12,7 +12,6 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
 6. LogDevice -- a distributed data store for logs [2]

 [1] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
-
 [2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/

 ## LinkedIn
@@ -27,7 +26,7 @@ Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasu
 Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa. Learn more about it here: http://yahooeng.tumblr.com/post/120730204806/sherpa-scales-new-heights

 ## CockroachDB
-CockroachDB is an open-source geo-replicated transactional database. They are using RocksDB as their storage engine. Check out their github: https://github.com/cockroachdb/cockroach
+CockroachDB is an open-source geo-replicated transactional database (still in development). They are using RocksDB as their storage engine. Check out their github: https://github.com/cockroachdb/cockroach

 ## DNANexus
 DNANexus is using RocksDB to speed up processing of genomics data.
@@ -50,10 +49,6 @@ 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

@@ -93,6 +88,3 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed

 ## ProfaneDB
 [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.
@@ -43,9 +43,9 @@ 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.
+* `printf %z` specification is not supported on Windows. To imitate existing standards we came up with a string macro `ROCKSDB_PRIszt` which expands to `%z` on posix systems and to Iu on windows.
 * in class member initialization were moved to a __ctors in some cases
 * `constexpr` is not supported. We had to replace `std::numeric_limits<>::max/min()` to its C macros for constants. Sometimes we had to make class members `static const` and place a definition within a .cc file.
 * `constexpr` for functions was replaced to a template specialization (1 place)
@@ -1,67 +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
-
-install:
-  - md %THIRDPARTY_HOME%
-  - echo "Building Snappy dependency..."
-  - cd %THIRDPARTY_HOME%
-  - curl -fsSL -o snappy-1.1.7.zip 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 -DCMAKE_GENERATOR_PLATFORM=x64 ..
-  - 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 -fsSL -o lz4-1.8.3.zip 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="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $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 -fsSL -o zstd-1.4.0.zip 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="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $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 "Visual Studio 15 Win64" -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 ..
+- 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_test2,db_test,env_basic_test,env_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

@@ -1,14 +1,16 @@
-# 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
 from targets_builder import TARGETSBuilder
+from optparse import OptionParser
 import os
 import fnmatch
 import sys
+import tempfile

 from util import ColorString
+import util

 # tests to export as libraries for inclusion in other projects
 _EXPORTED_TEST_LIBS = ["env_basic_test"]
@@ -82,7 +84,7 @@ def get_tests(repo_path):
            else:
                # we consumed all the parallel tests
                break
-
+    
    return tests


@@ -110,15 +112,13 @@ def generate_targets(repo_path):
        "rocksdb_test_lib",
        src_mk.get("MOCK_LIB_SOURCES", []) +
        src_mk.get("TEST_LIB_SOURCES", []) +
-        src_mk.get("EXP_LIB_SOURCES", []) +
-        src_mk.get("ANALYZER_LIB_SOURCES", []),
+        src_mk.get("EXP_LIB_SOURCES", []),
        [":rocksdb_lib"])
    # rocksdb_tools_lib
    TARGETS.add_library(
        "rocksdb_tools_lib",
        src_mk.get("BENCH_LIB_SOURCES", []) +
-        src_mk.get("ANALYZER_LIB_SOURCES", []) +
-        ["test_util/testutil.cc"],
+        ["util/testutil.cc"],
        [":rocksdb_lib"])

    # test for every test we found in the Makefile
@@ -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
@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
@@ -11,7 +10,7 @@ def pretty_list(lst, indent=8):

    if len(lst) == 1:
        return "\"%s\"" % lst[0]
-
+    
    separator = "\",\n%s\"" % (" " * indent)
    res = separator.join(sorted(lst))
    res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 4))
@@ -32,16 +31,13 @@ class TARGETSBuilder:
        self.targets_file.close()

    def add_library(self, name, srcs, deps=None, headers=None):
-        headers_attr_prefix = ""
        if headers is None:
-            headers_attr_prefix = "auto_"
            headers = "AutoHeaders.RECURSIVE_GLOB"
-        self.targets_file.write(targets_cfg.library_template.format(
-            name=name,
-            srcs=pretty_list(srcs),
-            headers_attr_prefix=headers_attr_prefix,
-            headers=headers,
-            deps=pretty_list(deps)))
+        self.targets_file.write(targets_cfg.library_template % (
+            name,
+            pretty_list(srcs),
+            headers,
+            pretty_list(deps)))
        self.total_lib = self.total_lib + 1

    def add_binary(self, name, srcs, deps=None):
@@ -1,15 +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
-rocksdb_target_header = """load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
-load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
-load(":defs.bzl", "test_binary")
+rocksdb_target_header = """REPO_PATH = package_name() + "/"

-REPO_PATH = package_name() + "/"
+BUCK_BINS = "buck-out/gen/" + REPO_PATH

-ROCKSDB_COMPILER_FLAGS = [
+TEST_RUNNER = REPO_PATH + "buckifier/rocks_test_runner.sh"
+
+rocksdb_compiler_flags = [
    "-fno-builtin-memcmp",
    "-DROCKSDB_PLATFORM_POSIX",
    "-DROCKSDB_LIB_IO_POSIX",
@@ -25,7 +24,6 @@ ROCKSDB_COMPILER_FLAGS = [
    "-DBZIP2",
    "-DLZ4",
    "-DZSTD",
-    "-DZSTD_STATIC_LINKING_ONLY",
    "-DGFLAGS=gflags",
    "-DNUMA",
    "-DTBB",
@@ -34,11 +32,10 @@ ROCKSDB_COMPILER_FLAGS = [
    # Added missing flags from output of build_detect_platform
    "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
    "-DROCKSDB_BACKTRACE",
-    "-Wnarrowing",
-    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
+    "-Wshorten-64-to-32",
 ]

-ROCKSDB_EXTERNAL_DEPS = [
+rocksdb_external_deps = [
    ("bzip2", None, "bz2"),
    ("snappy", None, "snappy"),
    ("zlib", None, "z"),
@@ -50,13 +47,13 @@ ROCKSDB_EXTERNAL_DEPS = [
    ("googletest", None, "gtest"),
 ]

-ROCKSDB_PREPROCESSOR_FLAGS = [
+rocksdb_preprocessor_flags = [
    # Directories with files for #include
    "-I" + REPO_PATH + "include/",
    "-I" + REPO_PATH,
 ]

-ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
+rocksdb_arch_preprocessor_flags = {
    "x86_64": [
        "-DHAVE_SSE42",
        "-DHAVE_PCLMUL",
@@ -69,28 +66,21 @@ is_opt_mode = build_mode.startswith("opt")

 # -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
 # doesn't harm and avoid forgetting to add it.
-ROCKSDB_COMPILER_FLAGS += (["-DNDEBUG"] if is_opt_mode else [])
-
-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_COMPILER_FLAGS += (["-DROCKSDB_JEMALLOC"] if sanitizer == "" else [])
-
-ROCKSDB_EXTERNAL_DEPS += ([("jemalloc", None, "headers")] if sanitizer == "" else [])
+if is_opt_mode:
+    rocksdb_compiler_flags.append("-DNDEBUG")
 """


 library_template = """
 cpp_library(
-    name = "{name}",
-    srcs = [{srcs}],
-    {headers_attr_prefix}headers = {headers},
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-    deps = [{deps}],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    name = "%s",
+    srcs = [%s],
+    headers = %s,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
+    deps = [%s],
+    external_deps = rocksdb_external_deps,
 )
 """

@@ -98,11 +88,11 @@ binary_template = """
 cpp_binary(
    name = "%s",
    srcs = [%s],
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+    compiler_flags = rocksdb_compiler_flags,
+    preprocessor_flags = rocksdb_preprocessor_flags,
    deps = [%s],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
+    external_deps = rocksdb_external_deps,
 )
 """

@@ -121,17 +111,39 @@ ROCKS_TESTS = [
 # Generate a test rule for each entry in ROCKS_TESTS
 # Do not build the tests in opt mode, since SyncPoint and other test code
 # will not be included.
-[
-    test_binary(
-        parallelism = parallelism,
-        rocksdb_arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-        rocksdb_compiler_flags = ROCKSDB_COMPILER_FLAGS,
-        rocksdb_external_deps = ROCKSDB_EXTERNAL_DEPS,
-        rocksdb_preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-        test_cc = test_cc,
-        test_name = test_name,
-    )
-    for test_name, test_cc, parallelism in ROCKS_TESTS
-    if not is_opt_mode
-]
+if not is_opt_mode:
+    for test_cfg in ROCKS_TESTS:
+        test_name = test_cfg[0]
+        test_cc = test_cfg[1]
+        ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
+        test_bin = test_name + "_bin"
+
+        cpp_binary (
+          name = test_bin,
+          srcs = [test_cc],
+          deps = [":rocksdb_test_lib"],
+          preprocessor_flags = rocksdb_preprocessor_flags,
+          arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+          compiler_flags = rocksdb_compiler_flags,
+          external_deps = rocksdb_external_deps,
+        )
+
+        custom_unittest(
+          name = test_name,
+          type = ttype,
+          deps = [":" + test_bin],
+          command = [TEST_RUNNER, BUCK_BINS + test_bin]
+        )
+
+custom_unittest(
+    name = "make_rocksdbjavastatic",
+    command = ["internal_repo_rocksdb/make_rocksdbjavastatic.sh"],
+    type = "simple",
+)
+
+custom_unittest(
+    name = "make_rocksdb_lite_release",
+    command = ["internal_repo_rocksdb/make_rocksdb_lite_release.sh"],
+    type = "simple",
+)
 """
@@ -1,4 +1,3 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 """
 This module keeps commonly used components.
 """
@@ -7,12 +7,12 @@
 // 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";
+define("ENV_POST_RECEIVE_HOOK", "POST_RECEIVE_HOOK");
+define("ENV_HTTPS_APP_VALUE", "HTTPS_APP_VALUE");
+define("ENV_HTTPS_TOKEN_VALUE", "HTTPS_TOKEN_VALUE");

-const PRIMARY_TOKEN_FILE = '/home/krad/.sandcastle';
-const CONT_RUN_ALIAS = "leveldb";
+define("PRIMARY_TOKEN_FILE", '/home/krad/.sandcastle');
+define("CONT_RUN_ALIAS", "leveldb");

 //////////////////////////////////////////////////////////////////////
 /*  Run tests in sandcastle */
@@ -97,7 +97,7 @@ function getSteps($applyDiff, $diffID, $username, $test) {
  }

  // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
-  // Git thinks it is an uncommitted change.
+  // Git thinks it is an uncommited change.
  $fix_git_ignore = array(
    "name" => "Fix git ignore",
    "shell" => "echo fbcode >> .git/info/exclude",
@@ -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.
@@ -53,13 +53,11 @@ if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
    FBCODE_BUILD="true"
    # If we're compiling with TSAN we need pic build
    PIC_BUILD=$COMPILE_WITH_TSAN
-    if [ -n "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
+    if [ -z "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
+      source "$PWD/build_tools/fbcode_config.sh"
+    else
      # we need this to build with MySQL. Don't use for other purposes.
      source "$PWD/build_tools/fbcode_config4.8.1.sh"
-    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007" ]; then
-      source "$PWD/build_tools/fbcode_config_platform007.sh"
-    else
-      source "$PWD/build_tools/fbcode_config.sh"
    fi
 fi

@@ -234,7 +232,7 @@ 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 [ "$?" = 0 ]; then
@@ -370,16 +368,6 @@ EOF
            # JEMALLOC can be enabled either using the flag (like here) or by
            # providing direct link to the jemalloc library
            WITH_JEMALLOC_FLAG=1
-            # check for JEMALLOC installed with HomeBrew
-            if [ "$PLATFORM" == "OS_MACOSX" ]; then
-                if hash brew 2>/dev/null && brew ls --versions jemalloc > /dev/null; then
-                    JEMALLOC_VER=$(brew ls --versions jemalloc | tail -n 1 | cut -f 2 -d ' ')
-                    JEMALLOC_INCLUDE="-I/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/include"
-                    JEMALLOC_LIB="/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/lib/libjemalloc_pic.a"
-                    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS $JEMALLOC_LIB"
-                    JAVA_STATIC_LDFLAGS="$JAVA_STATIC_LDFLAGS $JEMALLOC_LIB"
-                fi
-            fi
        fi
    fi
    if ! test $JEMALLOC && ! test $ROCKSDB_DISABLE_TCMALLOC; then
@@ -397,7 +385,6 @@ EOF
          #include <malloc.h>
          int main() {
            size_t res = malloc_usable_size(0);
-            (void)res;
            return 0;
          }
 EOF
@@ -412,7 +399,6 @@ EOF
          #include <pthread.h>
          int main() {
            int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-            (void)x;
            return 0;
          }
 EOF
@@ -424,7 +410,7 @@ EOF
    if ! test $ROCKSDB_DISABLE_BACKTRACE; then
        # Test whether backtrace is available
        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <execinfo.h>
+          #include <execinfo.h>>
          int main() {
            void* frames[1];
            backtrace_symbols(frames, backtrace(frames, 1));
@@ -482,24 +468,12 @@ EOF
          #include <sched.h>
          int main() {
            int cpuid = sched_getcpu();
-            (void)cpuid;
          }
 EOF
        if [ "$?" = 0 ]; then
            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SCHED_GETCPU_PRESENT"
        fi
    fi
-
-    if ! test $ROCKSDB_DISABLE_ALIGNED_NEW; then
-        # Test whether c++17 aligned-new is supported
-        $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
-            struct alignas(1024) t {int a;};
-            int main() {}
-EOF
-        if [ "$?" = 0 ]; then
-            PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS -faligned-new -DHAVE_ALIGNED_NEW"
-        fi
-    fi
 fi

 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.
@@ -518,11 +492,11 @@ 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 $HDFS_CCFLAGS"
@@ -537,11 +511,9 @@ if test -z "$PORTABLE"; then
    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
@@ -558,13 +530,12 @@ $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <nmmintrin.h>
  int main() {
    volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
  }
 EOF
 if [ "$?" = 0 ]; then
  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

@@ -576,13 +547,12 @@ $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
    const auto b = _mm_set_epi64x(0, 0);
    const auto c = _mm_clmulepi64_si128(a, b, 0x00);
    auto d = _mm_cvtsi128_si64(c);
-    (void)d;
  }
 EOF
 if [ "$?" = 0 ]; then
  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_PCLMUL"
 elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
+  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling"
  exit 1
 fi

@@ -596,7 +566,6 @@ if [ "$PLATFORM" != IOS ]; then
  #endif
  int main() {
    static __thread int tls;
-    (void)tls;
  }
 EOF
  if [ "$?" = 0 ]; then
@@ -604,19 +573,6 @@ 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"

@@ -1,19 +1,19 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-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/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/lz4/907b498203d297947f3bb70b9466f47e100f1873/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/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
+# shellcheck disable=SC2148
+GCC_BASE=/mnt/gvfs/third-party2/gcc/8219ec1bcedf8ad9da05e121e193364de2cc4f61/5.x/centos6-native/c447969
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/64d8d58e3d84f8bde7a029763d4f5baf39d0d5b9/stable/centos6-native/6aaf4de
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/ba9be983c81de7299b59fe71950c664a84dcb5f8/5.x/gcc-5-glibc-2.23/339d858
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/f20197cf3d4bd50339c9777aaa0b2ccadad9e2cb/2.23/gcc-5-glibc-2.23/ca1d1c0
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/6427ce8c7496e4ab06c2da81543b94c0de8be3d0/1.1.3/gcc-5-glibc-2.23/9bc6787
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/8f1e8b867d26efef93eac2fabbdb2e1d512665d7/1.2.8/gcc-5-glibc-2.23/9bc6787
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/70471c0571559fe0af7db6d7e8860b93a7eadfe1/1.0.6/gcc-5-glibc-2.23/9bc6787
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/453c89d6f0e68cdf1c151c769197fabedad9cac8/r131/gcc-5-glibc-2.23/9bc6787
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/00a40fa5f8bd2cd0622f2e868552793aef37ccf4/1.3.0/gcc-5-glibc-2.23/03859b5
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/47eef08f9acb77de982fbda6047c26d330739538/2.2.0/gcc-5-glibc-2.23/9bc6787
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/4414ddc78df8008b35cc4adac23590ad29148584/master/gcc-5-glibc-2.23/d506c82
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9d7ae2693d05d62f9a579cb21e6b717cf257a75d/2.0.11/gcc-5-glibc-2.23/9bc6787
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/2b2dd58e3a52ccf2c1d827def59e5f740de0ad15/1.2/gcc-5-glibc-2.23/b443de1
+TBB_BASE=/mnt/gvfs/third-party2/tbb/379addf7ab2468a2b4293b47456cfcd1c9cb318d/4.3/gcc-5-glibc-2.23/9bc6787
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/3f68f5fe65a85b7c2d3e66852268fbd1efdb3151/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/b9fab0aec99d9c36408e810b2677e91c12807afd/2.28/centos6-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/423431d61786b20bcc3bde8972901130cb29e6b3/3.11.0/gcc-5-glibc-2.23/9bc6787
+LUA_BASE=/mnt/gvfs/third-party2/lua/3b0bb3bd9a0f690a069c479fcc0f7424fc7456d2/5.2.3/gcc-5-glibc-2.23/65372bd
@@ -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
@@ -1,19 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-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/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/lz4/907b498203d297947f3bb70b9466f47e100f1873/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/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
@@ -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
@@ -64,12 +64,8 @@ class MatchErrorParser(ErrorParserBase):

 class CompilerErrorParser(MatchErrorParser):
    def __init__(self):
-        # format (compile error):
-        #   '<filename>:<line #>:<column #>: error: <error msg>'
-        # format (link error):
-        #   '<filename>:<line #>: error: <error msg>'
-        # The below regex catches both
-        super(CompilerErrorParser, self).__init__(r'\S+:\d+: error:')
+        # format: '<filename>:<line #>:<column #>: error: <error msg>'
+        super(CompilerErrorParser, self).__init__(r'\S+:\d+:\d+: error:')


 class ScanBuildErrorParser(MatchErrorParser):
@@ -132,14 +128,11 @@ _TEST_NAME_TO_PARSERS = {
    'lite': [CompilerErrorParser],
    'lite_test': [CompilerErrorParser, GTestErrorParser],
    'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_atomic_flush': [CompilerErrorParser, DbCrashErrorParser],
    'write_stress': [CompilerErrorParser, WriteStressErrorParser],
    'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
    'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_atomic_flush': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
    'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
    'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_atomic_flush': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
    'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
    'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
    'format_compatible': [CompilerErrorParser, CompatErrorParser],
@@ -1,5 +1,5 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+
 # fail early
 set -e

@@ -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
@@ -44,15 +43,11 @@ if test -z $PIC_BUILD; then
  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
  CFLAGS+=" -DLZ4"
-fi

-ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-if test -z $PIC_BUILD; then
+  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-else
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
+  CFLAGS+=" -DZSTD"
 fi
-CFLAGS+=" -DZSTD -DZSTD_STATIC_LINKING_ONLY"

 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
@@ -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
@@ -1,158 +0,0 @@
-#!/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
-# uses jemalloc
-# Environment variables that change the behavior of this script:
-# PIC_BUILD -- if true, it will only take pic versions of libraries from fbcode. libraries that don't have pic variant will not be included
-
-
-BASEDIR=`dirname $BASH_SOURCE`
-source "$BASEDIR/dependencies_platform007.sh"
-
-CFLAGS=""
-
-# libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/7.3.0"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
-
-# glibc
-GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIBC_BASE/lib"
-
-# snappy
-SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-if test -z $PIC_BUILD; then
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
-else
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
-fi
-CFLAGS+=" -DSNAPPY"
-
-if test -z $PIC_BUILD; then
-  # location of zlib headers and libraries
-  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-  ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
-  CFLAGS+=" -DZLIB"
-
-  # location of bzip headers and libraries
-  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
-  CFLAGS+=" -DBZIP2"
-
-  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
-  CFLAGS+=" -DLZ4"
-fi
-
-ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-if test -z $PIC_BUILD; then
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-else
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
-fi
-CFLAGS+=" -DZSTD"
-
-# location of gflags headers and libraries
-GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
-if test -z $PIC_BUILD; then
-  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
-else
-  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags_pic.a"
-fi
-CFLAGS+=" -DGFLAGS=gflags"
-
-# location of jemalloc
-JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
-JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc.a"
-
-if test -z $PIC_BUILD; then
-  # location of numa
-  NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-  NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
-  CFLAGS+=" -DNUMA"
-
-  # location of libunwind
-  LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
-fi
-
-# location of TBB
-TBB_INCLUDE=" -isystem $TBB_BASE/include/"
-if test -z $PIC_BUILD; then
-  TBB_LIBS="$TBB_BASE/lib/libtbb.a"
-else
-  TBB_LIBS="$TBB_BASE/lib/libtbb_pic.a"
-fi
-CFLAGS+=" -DTBB"
-
-# use Intel SSE support for checksum calculations
-export USE_SSE=1
-export PORTABLE=1
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"
-
-STDLIBS="-L $GCC_BASE/lib64"
-
-CLANG_BIN="$CLANG_BASE/bin"
-CLANG_LIB="$CLANG_BASE/lib"
-CLANG_SRC="$CLANG_BASE/../../src"
-
-CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_SRC/llvm/tools/clang/tools/scan-build/bin/scan-build"
-
-if [ -z "$USE_CLANG" ]; then
-  # gcc
-  CC="$GCC_BASE/bin/gcc"
-  CXX="$GCC_BASE/bin/g++"
-
-  CFLAGS+=" -B$BINUTILS/gold"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  JEMALLOC=1
-else
-  # clang
-  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
-  CC="$CLANG_BIN/clang"
-  CXX="$CLANG_BIN/clang++"
-
-  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
-
-  CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x/x86_64-facebook-linux "
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $CLANG_INCLUDE"
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
-  CFLAGS+=" -Wno-expansion-to-defined "
-  CXXFLAGS="-nostdinc++"
-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"
-CXXFLAGS+=" $CFLAGS"
-
-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+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform007/lib"
-# required by libtbb
-EXEC_LDFLAGS+=" -ldl"
-
-PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
-
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-# lua not supported because it's on track for deprecation, I think
-LUA_PATH=
-LUA_LIB=
-
-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
@@ -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 ]
@@ -5082,8 +5082,8 @@ sub openoutputfiles {
 	# Set reading FD if using --group (--ungroup does not need)
 	for my $fdno (1,2) {
 	    # Re-open the file for reading
-	    # so fdw can be closed separately
-	    # and fdr can be seeked separately (for --line-buffer)
+	    # so fdw can be closed seperately
+	    # and fdr can be seeked seperately (for --line-buffer)
 	    open(my $fdr,"<", $self->fh($fdno,'name')) ||
 		::die_bug("fdr: Cannot open ".$self->fh($fdno,'name'));
 	    $self->set_fh($fdno,'r',$fdr);
@@ -1,6 +1,5 @@
 # shellcheck disable=SC1113
 #/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 set -e

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

 from __future__ import absolute_import
 from __future__ import division
@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 set -e

@@ -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
@@ -100,12 +85,9 @@ NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-# in gcc-5 there are known problems with TSAN like https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71090.
-# using platform007 gives us gcc-8 or higher which has that bug fixed.
-TSAN="ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007=1 COMPILE_WITH_TSAN=1"
+LITE="OPT=\"-DROCKSDB_LITE -g\""
+TSAN="COMPILE_WITH_TSAN=1"
 UBSAN="COMPILE_WITH_UBSAN=1"
-TSAN_CRASH='CRASH_TEST_EXT_ARGS="--compression_type=zstd --log2_keys_per_lock=22"'
-NON_TSAN_CRASH="CRASH_TEST_EXT_ARGS=--compression_type=zstd"
 DISABLE_JEMALLOC="DISABLE_JEMALLOC=1"
 HTTP_PROXY="https_proxy=http://fwdproxy.29.prn1:8080 http_proxy=http://fwdproxy.29.prn1:8080 ftp_proxy=http://fwdproxy.29.prn1:8080"
 SETUP_JAVA_ENV="export $HTTP_PROXY; export JAVA_HOME=/usr/local/jdk-8u60-64/; export PATH=\$JAVA_HOME/bin:\$PATH"
@@ -124,6 +106,13 @@ else
  TASK_CREATION_TOOL="false"
 fi

+ARTIFACTS=" 'artifacts': [
+    {
+        'name':'database',
+        'paths':[ '/dev/shm/rocksdb' ],
+    }
+]"
+
 #
 # A mechanism to disable tests temporarily
 #
@@ -148,7 +137,6 @@ UNIT_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -169,7 +157,6 @@ UNIT_TEST_NON_SHM_COMMANDS="[
    {
        'name':'Rocksdb Unit Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -192,7 +179,6 @@ RELEASE_BUILD_COMMANDS="[
    {
        'name':'Rocksdb Release Build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -213,7 +199,6 @@ UNIT_TEST_COMMANDS_481="[
    {
        'name':'Rocksdb Unit Test on GCC 4.8.1',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -234,7 +219,6 @@ RELEASE_BUILD_COMMANDS_481="[
    {
        'name':'Rocksdb Release on GCC 4.8.1',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -255,7 +239,6 @@ CLANG_UNIT_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -276,7 +259,6 @@ CLANG_RELEASE_BUILD_COMMANDS="[
    {
        'name':'Rocksdb CLANG Release Build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -297,7 +279,6 @@ CLANG_ANALYZE_COMMANDS="[
    {
        'name':'Rocksdb analyze',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -318,7 +299,6 @@ CODE_COV_COMMANDS="[
    {
        'name':'Rocksdb Unit Test Code Coverage',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -339,7 +319,6 @@ UNITY_COMMANDS="[
    {
        'name':'Rocksdb Unity',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -360,12 +339,11 @@ LITE_BUILD_COMMANDS="[
    {
        'name':'Rocksdb Lite build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
                'name':'Build RocksDB debug version',
-                'shell':'make J=1 LITE=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
+                'shell':'$LITE make J=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -380,7 +358,6 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
    {
        'name':'Rocksdb Lite Binary Size',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -396,56 +373,26 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
 #
 STRESS_CRASH_TEST_COMMANDS="[
    {
-        'name':'Rocksdb Stress and Crash Test',
+        'name':'Rocksdb Stress/Crash Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
            {
                'name':'Build and run RocksDB debug crash tests',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            }
        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test with atomic flush
-#
-STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with atomic flush',
-        'oncall':'$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,
-        ],
+        $ARTIFACTS,
        $REPORT
    }
 ]"
@@ -457,7 +404,6 @@ WRITE_STRESS_COMMANDS="[
    {
        'name':'Rocksdb Write Stress Test',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -480,7 +426,6 @@ ASAN_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under ASAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -501,14 +446,13 @@ ASAN_CRASH_TEST_COMMANDS="[
    {
        'name':'Rocksdb crash test under ASAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug asan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -517,30 +461,6 @@ ASAN_CRASH_TEST_COMMANDS="[
    }
 ]"

-#
-# 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB test under undefined behavior sanitizer
 #
@@ -548,7 +468,6 @@ UBSAN_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under UBSAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -569,14 +488,13 @@ UBSAN_CRASH_TEST_COMMANDS="[
    {
        'name':'Rocksdb crash test under UBSAN',
        'oncall':'$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 make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -585,30 +503,6 @@ UBSAN_CRASH_TEST_COMMANDS="[
    }
 ]"

-#
-# 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 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB unit test under valgrind
 #
@@ -616,7 +510,6 @@ VALGRIND_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under valgrind',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -639,7 +532,6 @@ TSAN_UNIT_TEST_COMMANDS="[
    {
        'name':'Rocksdb Unit Test under TSAN',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'timeout': 86400,
        'steps': [
            $CLEANUP_ENV,
@@ -662,14 +554,13 @@ TSAN_CRASH_TEST_COMMANDS="[
    {
        'name':'Rocksdb Crash Test under TSAN',
        'oncall':'$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 || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $DEBUG $TSAN CRASH_TEST_KILL_ODD=1887 CRASH_TEST_EXT_ARGS=--log2_keys_per_lock=22  make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -678,30 +569,6 @@ TSAN_CRASH_TEST_COMMANDS="[
    }
 ]"

-#
-# 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,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB format compatible
 #
@@ -719,7 +586,6 @@ FORMAT_COMPATIBLE_COMMANDS="[
    {
        'name':'Rocksdb Format Compatible tests',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -742,7 +608,7 @@ run_no_compression()
  rm -rf /dev/shm/rocksdb
  mkdir /dev/shm/rocksdb
  make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzstd | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
+  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
  mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
  cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
  mv .tmp.Makefile Makefile
@@ -753,7 +619,6 @@ NO_COMPRESSION_COMMANDS="[
    {
        'name':'Rocksdb No Compression tests',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -796,12 +661,12 @@ run_regression()

  # === lite build ===
  make clean
-  make LITE=1 -j$(nproc) static_lib
+  OPT=-DROCKSDB_LITE make -j$(nproc) static_lib
  send_size_to_ods static_lib_lite $(stat --printf="%s" librocksdb.a)
  strip librocksdb.a
  send_size_to_ods static_lib_lite_stripped $(stat --printf="%s" librocksdb.a)

-  make LITE=1 -j$(nproc) shared_lib
+  OPT=-DROCKSDB_LITE make -j$(nproc) shared_lib
  send_size_to_ods shared_lib_lite $(stat --printf="%s" `readlink -f librocksdb.so`)
  strip `readlink -f librocksdb.so`
  send_size_to_ods shared_lib_lite_stripped $(stat --printf="%s" `readlink -f librocksdb.so`)
@@ -831,7 +696,6 @@ JAVA_BUILD_TEST_COMMANDS="[
    {
        'name':'Rocksdb Java Build',
        'oncall':'$ONCALL',
-        'executeLocal': 'true',
        'steps': [
            $CLEANUP_ENV,
            {
@@ -886,9 +750,6 @@ case $1 in
  stress_crash)
    echo $STRESS_CRASH_TEST_COMMANDS
    ;;
-  stress_crash_with_atomic_flush)
-    echo $STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
  write_stress)
    echo $WRITE_STRESS_COMMANDS
    ;;
@@ -898,18 +759,12 @@ case $1 in
  asan_crash)
    echo $ASAN_CRASH_TEST_COMMANDS
    ;;
-  asan_crash_with_atomic_flush)
-    echo $ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_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
-    ;;
  valgrind)
    echo $VALGRIND_TEST_COMMANDS
    ;;
@@ -919,9 +774,6 @@ case $1 in
  tsan_crash)
    echo $TSAN_CRASH_TEST_COMMANDS
    ;;
-  tsan_crash_with_atomic_flush)
-    echo $TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
-    ;;
  format_compatible)
    echo $FORMAT_COMPATIBLE_COMMANDS
    ;;
@@ -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(
@@ -1,5 +1,4 @@
 #!/bin/bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 set -e

 ROCKSDB_VERSION="5.10.3"
@@ -1,5 +1,4 @@
 #!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 #
 # Update dependencies.sh file with the latest avaliable versions

@@ -54,45 +53,6 @@ function get_lib_base()
  log_variable $__res_var
 }

-###########################################################
-#                platform007 dependencies                 #
-###########################################################
-
-OUTPUT="$BASEDIR/dependencies_platform007.sh"
-
-rm -f "$OUTPUT"
-touch "$OUTPUT"
-
-echo "Writing dependencies to $OUTPUT"
-
-# Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/7.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
-
-log_variable GCC_BASE
-log_variable CLANG_BASE
-
-# Libraries locations
-get_lib_base libgcc     7.x     platform007
-get_lib_base glibc      2.26    platform007
-get_lib_base snappy     LATEST  platform007
-get_lib_base zlib       LATEST  platform007
-get_lib_base bzip2      LATEST  platform007
-get_lib_base lz4        LATEST  platform007
-get_lib_base zstd       LATEST  platform007
-get_lib_base gflags     LATEST  platform007
-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 kernel-headers fb platform007
-get_lib_base binutils   LATEST centos7-native
-get_lib_base valgrind   LATEST platform007
-get_lib_base lua        5.3.4  platform007
-
-git diff $OUTPUT
-
 ###########################################################
 #                   5.x dependencies                      #
 ###########################################################
@@ -105,8 +65,8 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"

 # Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos6-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`

 log_variable GCC_BASE
 log_variable CLANG_BASE
@@ -126,7 +86,7 @@ get_lib_base libunwind  LATEST  gcc-5-glibc-2.23
 get_lib_base tbb        LATEST  gcc-5-glibc-2.23

 get_lib_base kernel-headers 4.0.9-36_fbk5_2933_gd092e3f gcc-5-glibc-2.23
-get_lib_base binutils   LATEST centos7-native
+get_lib_base binutils   LATEST centos6-native 
 get_lib_base valgrind   LATEST gcc-5-glibc-2.23
 get_lib_base lua        5.2.3 gcc-5-glibc-2.23

@@ -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
@@ -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() {
@@ -11,7 +14,7 @@ int main() {
 }
 #else

-#include <cinttypes>
+#include <inttypes.h>
 #include <sys/types.h>
 #include <stdio.h>

@@ -16,9 +16,9 @@
 #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 {

@@ -64,8 +64,8 @@ class CacheTest : public testing::TestWithParam<std::string> {

  std::vector<int> deleted_keys_;
  std::vector<int> deleted_values_;
-  std::shared_ptr<Cache> cache_;
-  std::shared_ptr<Cache> cache2_;
+  shared_ptr<Cache> cache_;
+  shared_ptr<Cache> cache2_;

  CacheTest()
      : cache_(NewCache(kCacheSize, kNumShardBits, false)),
@@ -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();
@@ -90,7 +91,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
                                  bool strict_capacity_limit) {
    auto type = GetParam();
    if (type == kLRU) {
-      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit, 0.0);
+      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit);
    }
    if (type == kClock) {
      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit);
@@ -98,7 +99,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
    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) {
@@ -107,16 +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);
  }
@@ -144,7 +145,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
 CacheTest* CacheTest::current_;

 TEST_P(CacheTest, UsageTest) {
-  // cache is std::shared_ptr and will be automatically cleaned up.
+  // cache is shared_ptr and will be automatically cleaned up.
  const uint64_t kCapacity = 100000;
  auto cache = NewCache(kCapacity, 8, false);

@@ -172,7 +173,7 @@ TEST_P(CacheTest, UsageTest) {
 }

 TEST_P(CacheTest, PinnedUsageTest) {
-  // cache is std::shared_ptr and will be automatically cleaned up.
+  // cache is shared_ptr and will be automatically cleaned up.
  const uint64_t kCapacity = 100000;
  auto cache = NewCache(kCapacity, 8, false);

@@ -306,7 +307,7 @@ TEST_P(CacheTest, EvictionPolicy) {
  Insert(200, 201);

  // Frequently used entry must be kept around
-  for (int i = 0; i < kCacheSize + 200; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
    Insert(1000+i, 2000+i);
    ASSERT_EQ(101, Lookup(100));
  }
@@ -359,7 +360,7 @@ TEST_P(CacheTest, EvictionPolicyRef) {
  Insert(303, 104);

  // Insert entries much more than Cache capacity
-  for (int i = 0; i < kCacheSize + 200; i++) {
+  for (int i = 0; i < kCacheSize + 100; i++) {
    Insert(1000 + i, 2000 + i);
  }

@@ -562,7 +563,6 @@ TEST_P(CacheTest, 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";
@@ -572,7 +572,6 @@ TEST_P(CacheTest, 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]);
@@ -593,7 +592,7 @@ TEST_P(CacheTest, 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++) {
@@ -688,17 +687,8 @@ 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) = NewClockCache;
+shared_ptr<Cache> (*new_clock_cache_func)(size_t, int, bool) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                        testing::Values(kLRU, kClock));
 #else
@@ -234,35 +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;
@@ -672,7 +675,7 @@ 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)
      : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
@@ -682,31 +685,31 @@ class ClockCache final : public ShardedCache {
    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_;
@@ -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>
@@ -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();
    }
  });
@@ -96,16 +100,14 @@ void LRUHandleTable::Resize() {
 }

 LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                             double high_pri_pool_ratio,
-                             bool use_adaptive_mutex)
+                             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) {
+      lru_usage_(0) {
  // Make empty circular linked list
  lru_.next = &lru_;
  lru_.prev = &lru_;
@@ -113,17 +115,29 @@ 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);
+      Unref(old);
      usage_ -= old->charge;
      last_reference_list.push_back(old);
    }
@@ -136,27 +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_) {
@@ -224,13 +233,14 @@ void LRUCacheShard::MaintainPoolSize() {

 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);
+    Unref(old);
    usage_ -= old->charge;
    deleted->push_back(old);
  }
@@ -244,8 +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();
  }
@@ -261,22 +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;
 }

@@ -295,27 +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()) {
-      // The item is still in cache, and nobody else holds a reference to it
-      if (usage_ > capacity_ || force_erase) {
-        // The LRU list must be empty since the cache is full
-        assert(lru_.next == &lru_ || force_erase);
-        // Take this opportunity and remove the item
-        table_.Remove(e->key(), e->hash);
-        e->SetInCache(false);
-      } else {
-        // Put the item back on the LRU list, and don't free it
-        LRU_Insert(e);
-        last_reference = false;
-      }
-    }
+    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(!(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 on the list to be potentially freed
+        LRU_Insert(e);
+      }
+    }
  }

-  // Free the entry here outside of mutex for performance reasons
+  // free outside of mutex
  if (last_reference) {
    e->Free();
  }
@@ -331,7 +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;
@@ -340,7 +353,9 @@ 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);
@@ -353,12 +368,11 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
    // is freed or the lru list is empty
    EvictFromLRU(charge, &last_reference_list);

-    if ((usage_ + 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);
@@ -366,30 +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_ += 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
-          LRU_Remove(old);
+        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);
          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();
  }
@@ -404,18 +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);
+      last_reference = Unref(e);
+      if (last_reference) {
        usage_ -= e->charge;
-        last_reference = true;
      }
+      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();
@@ -445,19 +461,15 @@ 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)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
-                   std::move(allocator)) {
+                   bool strict_capacity_limit, double high_pri_pool_ratio)
+    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
  num_shards_ = 1 << num_shard_bits;
  shards_ = reinterpret_cast<LRUCacheShard*>(
      port::cacheline_aligned_alloc(sizeof(LRUCacheShard) * num_shards_));
  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);
+        LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio);
  }
 }

@@ -493,17 +505,10 @@ uint32_t LRUCache::GetHash(Handle* handle) const {

 void LRUCache::DisownData() {
 // Do not drop data if compile with ASAN to suppress leak warning.
-#if defined(__clang__)
-#if !defined(__has_feature) || !__has_feature(address_sanitizer)
-  shards_ = nullptr;
-  num_shards_ = 0;
-#endif
-#else  // __clang__
 #ifndef __SANITIZE_ADDRESS__
  shards_ = nullptr;
  num_shards_ = 0;
 #endif  // !__SANITIZE_ADDRESS__
-#endif  // __clang__
 }

 size_t LRUCache::TEST_GetLRUSize() {
@@ -525,16 +530,12 @@ double LRUCache::GetHighPriPoolRatio() {
 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.high_pri_pool_ratio);
 }

-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) {
+std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
+                                   bool strict_capacity_limit,
+                                   double high_pri_pool_ratio) {
  if (num_shard_bits >= 20) {
    return nullptr;  // the cache cannot be sharded into too many fine pieces
  }
@@ -546,9 +547,7 @@ std::shared_ptr<Cache> NewLRUCache(
    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);
+                                    strict_capacity_limit, high_pri_pool_ratio);
 }

 }  // namespace rocksdb
@@ -17,34 +17,31 @@

 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;
@@ -54,75 +51,62 @@ 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);
    }
@@ -173,11 +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);
-  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
@@ -233,6 +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
@@ -288,16 +276,10 @@ 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);
+           double high_pri_pool_ratio);
  virtual ~LRUCache();
  virtual const char* Name() const override { return "LRUCache"; }
  virtual CacheShard* GetShard(int shard) override;
@@ -8,14 +8,14 @@
 #include <string>
 #include <vector>
 #include "port/port.h"
-#include "test_util/testharness.h"
+#include "util/testharness.h"

 namespace rocksdb {

 class LRUCacheTest : public testing::Test {
 public:
  LRUCacheTest() {}
-  ~LRUCacheTest() override { DeleteCache(); }
+  ~LRUCacheTest() { DeleteCache(); }

  void DeleteCache() {
    if (cache_ != nullptr) {
@@ -25,13 +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);
+                               high_pri_pool_ratio);
  }

  void Insert(const std::string& key,
@@ -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/sharded_cache.h"

 #include <string>
@@ -16,10 +20,8 @@
 namespace rocksdb {

 ShardedCache::ShardedCache(size_t capacity, int num_shard_bits,
-                           bool strict_capacity_limit,
-                           std::shared_ptr<MemoryAllocator> allocator)
-    : Cache(std::move(allocator)),
-      num_shard_bits_(num_shard_bits),
+                           bool strict_capacity_limit)
+    : num_shard_bits_(num_shard_bits),
      capacity_(capacity),
      strict_capacity_limit_(strict_capacity_limit),
      last_id_(1) {}
@@ -140,9 +142,6 @@ std::string ShardedCache::GetPrintableOptions() const {
             strict_capacity_limit_);
    ret.append(buffer);
  }
-  snprintf(buffer, kBufferSize, "    memory_allocator : %s\n",
-           memory_allocator() ? memory_allocator()->Name() : "None");
-  ret.append(buffer);
  ret.append(GetShard(0)->GetPrintableOptions());
  return ret;
 }
@@ -47,15 +47,13 @@ class CacheShard {
 // Keys are sharded by the highest num_shard_bits bits of hash value.
 class ShardedCache : public Cache {
 public:
-  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-               std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
+  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit);
  virtual ~ShardedCache() = default;
  virtual const char* Name() const override = 0;
  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;

@@ -84,7 +82,7 @@ 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) {
@@ -0,0 +1,21 @@
+# - Find zlib
+# Find the zlib compression library and includes
+#
+# ZLIB_INCLUDE_DIR - where to find zlib.h, etc.
+# ZLIB_LIBRARIES - List of libraries when using zlib.
+# ZLIB_FOUND - True if zlib found.
+
+find_path(ZLIB_INCLUDE_DIR
+  NAMES zlib.h
+  HINTS ${ZLIB_ROOT_DIR}/include)
+
+find_library(ZLIB_LIBRARIES
+  NAMES z
+  HINTS ${ZLIB_ROOT_DIR}/lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(zlib DEFAULT_MSG ZLIB_LIBRARIES ZLIB_INCLUDE_DIR)
+
+mark_as_advanced(
+  ZLIB_LIBRARIES
+  ZLIB_INCLUDE_DIR)
@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.

 # Exit on error.
 set -e
@@ -1,5 +1,4 @@
-#!/usr/bin/env python2
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+import optparse
 import re
 import sys

@@ -13,15 +13,13 @@
 #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"
 #include "db/merge_helper.h"
-#include "db/range_del_aggregator.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
-#include "file/filename.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -29,12 +27,12 @@
 #include "rocksdb/iterator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
-#include "table/block_based/block_based_table_builder.h"
-#include "table/format.h"
+#include "table/block_based_table_builder.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 {

@@ -47,20 +45,18 @@ 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);
 }

@@ -68,21 +64,19 @@ Status BuildTable(
    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,
-    FileMetaData* meta, const InternalKeyComparator& internal_comparator,
+    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
+    const InternalKeyComparator& internal_comparator,
    const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
        int_tbl_prop_collector_factories,
    uint32_t column_family_id, const std::string& column_family_name,
    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());
@@ -91,10 +85,12 @@ Status BuildTable(
  Status s;
  meta->fd.file_size = 0;
  iter->SeekToFirst();
-  std::unique_ptr<CompactionRangeDelAggregator> range_del_agg(
-      new CompactionRangeDelAggregator(&internal_comparator, snapshots));
-  for (auto& range_del_iter : range_del_iters) {
-    range_del_agg->AddTombstones(std::move(range_del_iter));
+  std::unique_ptr<RangeDelAggregator> range_del_agg(
+      new RangeDelAggregator(internal_comparator, snapshots));
+  s = range_del_agg->AddTombstones(std::move(range_del_iter));
+  if (!s.ok()) {
+    // may be non-ok if a range tombstone key is unparsable
+    return s;
  }

  std::string fname = TableFileName(ioptions.cf_paths, meta->fd.GetNumber(),
@@ -105,16 +101,11 @@ Status BuildTable(
 #endif  // !ROCKSDB_LITE
  TableProperties tp;

-  if (iter->Valid() || !range_del_agg->IsEmpty()) {
+  if (iter->Valid() || range_del_agg->ShouldAddTombstones()) {
    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;
+    unique_ptr<WritableFileWriter> file_writer;
    {
-      std::unique_ptr<WritableFile> file;
+      unique_ptr<WritableFile> file;
 #ifndef NDEBUG
      bool use_direct_writes = env_options.use_direct_writes;
      TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
@@ -129,16 +120,14 @@ Status BuildTable(
      file->SetIOPriority(io_priority);
      file->SetWriteLifeTimeHint(write_hint);

-      file_writer.reset(
-          new WritableFileWriter(std::move(file), fname, env_options, env,
-                                 ioptions.statistics, ioptions.listeners));
+      file_writer.reset(new WritableFileWriter(std::move(file), env_options,
+                                               ioptions.statistics));
      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(),
@@ -150,7 +139,6 @@ Status BuildTable(
    CompactionIterator c_iter(
        iter, internal_comparator.user_comparator(), &merge, kMaxSequenceNumber,
        &snapshots, earliest_write_conflict_snapshot, snapshot_checker, env,
-        ShouldReportDetailedTime(env, ioptions.statistics),
        true /* internal key corruption is not ok */, range_del_agg.get());
    c_iter.SeekToFirst();
    for (; c_iter.Valid(); c_iter.Next()) {
@@ -166,20 +154,12 @@ Status BuildTable(
            ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
      }
    }
-
-    auto range_del_it = range_del_agg->NewIterator();
-    for (range_del_it->SeekToFirst(); range_del_it->Valid();
-         range_del_it->Next()) {
-      auto tombstone = range_del_it->Tombstone();
-      auto kv = tombstone.Serialize();
-      builder->Add(kv.first.Encode(), kv.second);
-      meta->UpdateBoundariesForRange(kv.first, tombstone.SerializeEndKey(),
-                                     tombstone.seq_, internal_comparator);
-    }
+    // nullptr for table_{min,max} so all range tombstones will be flushed
+    range_del_agg->AddToBuilder(builder, nullptr /* lower_bound */,
+                                nullptr /* upper_bound */, meta);

    // Finish and check for builder errors
-    tp = builder->GetTableProperties();
-    bool empty = builder->NumEntries() == 0 && tp.num_range_deletions == 0;
+    bool empty = builder->NumEntries() == 0;
    s = c_iter.status();
    if (!s.ok() || empty) {
      builder->Abandon();
@@ -192,7 +172,7 @@ Status BuildTable(
      meta->fd.file_size = file_size;
      meta->marked_for_compaction = builder->NeedCompact();
      assert(meta->fd.GetFileSize() > 0);
-      tp = builder->GetTableProperties(); // refresh now that builder is finished
+      tp = builder->GetTableProperties();
      if (table_properties) {
        *table_properties = tp;
      }
@@ -216,14 +196,13 @@ 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(), env_options, internal_comparator, *meta,
+          ReadOptions(), env_options, internal_comparator, meta->fd,
          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()) {
@@ -9,9 +9,7 @@
 #include <string>
 #include <utility>
 #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"
@@ -21,6 +19,7 @@
 #include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
+#include "util/event_logger.h"

 namespace rocksdb {

@@ -36,10 +35,13 @@ class VersionEdit;
 class TableBuilder;
 class WritableFileWriter;
 class InternalStats;
+class InternalIterator;

 // @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
@@ -65,23 +66,20 @@ extern Status BuildTable(
    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,
-    FileMetaData* meta, const InternalKeyComparator& internal_comparator,
+    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
+    const InternalKeyComparator& internal_comparator,
    const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
        int_tbl_prop_collector_factories,
    uint32_t column_family_id, const std::string& column_family_name,
    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
@@ -33,7 +33,6 @@
 #include "rocksdb/utilities/backupable_db.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/db_ttl.h"
-#include "rocksdb/utilities/memory_util.h"
 #include "rocksdb/utilities/optimistic_transaction_db.h"
 #include "rocksdb/utilities/transaction.h"
 #include "rocksdb/utilities/transaction_db.h"
@@ -42,10 +41,6 @@
 #include "rocksdb/perf_context.h"
 #include "utilities/merge_operators.h"

-#include <vector>
-#include <unordered_set>
-#include <map>
-
 using rocksdb::BytewiseComparator;
 using rocksdb::Cache;
 using rocksdb::ColumnFamilyDescriptor;
@@ -98,7 +93,6 @@ using rocksdb::BackupInfo;
 using rocksdb::BackupID;
 using rocksdb::RestoreOptions;
 using rocksdb::CompactRangeOptions;
-using rocksdb::BottommostLevelCompaction;
 using rocksdb::RateLimiter;
 using rocksdb::NewGenericRateLimiter;
 using rocksdb::PinnableSlice;
@@ -113,12 +107,8 @@ using rocksdb::TransactionLogIterator;
 using rocksdb::BatchResult;
 using rocksdb::PerfLevel;
 using rocksdb::PerfContext;
-using rocksdb::MemoryUtil;

 using std::shared_ptr;
-using std::vector;
-using std::unordered_set;
-using std::map;

 extern "C" {

@@ -151,20 +141,14 @@ struct rocksdb_writablefile_t    { WritableFile*     rep; };
 struct rocksdb_wal_iterator_t { TransactionLogIterator* rep; };
 struct rocksdb_wal_readoptions_t { TransactionLogIterator::ReadOptions rep; };
 struct rocksdb_filelock_t        { FileLock*         rep; };
-struct rocksdb_logger_t {
-  std::shared_ptr<Logger> rep;
-};
-struct rocksdb_cache_t {
-  std::shared_ptr<Cache> rep;
-};
+struct rocksdb_logger_t          { shared_ptr<Logger>  rep; };
+struct rocksdb_cache_t           { shared_ptr<Cache>   rep; };
 struct rocksdb_livefiles_t       { std::vector<LiveFileMetaData> rep; };
 struct rocksdb_column_family_handle_t  { ColumnFamilyHandle* rep; };
 struct rocksdb_envoptions_t      { EnvOptions        rep; };
 struct rocksdb_ingestexternalfileoptions_t  { IngestExternalFileOptions rep; };
 struct rocksdb_sstfilewriter_t   { SstFileWriter*    rep; };
-struct rocksdb_ratelimiter_t {
-  std::shared_ptr<RateLimiter> rep;
-};
+struct rocksdb_ratelimiter_t     { shared_ptr<RateLimiter>      rep; };
 struct rocksdb_perfcontext_t     { PerfContext*      rep; };
 struct rocksdb_pinnableslice_t {
  PinnableSlice rep;
@@ -208,10 +192,13 @@ 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 +215,9 @@ 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 +227,9 @@ 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 +237,7 @@ 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 +249,20 @@ 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 +282,14 @@ 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 +307,8 @@ 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 +333,14 @@ 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 +374,10 @@ 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);
@@ -432,21 +428,23 @@ 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());
  }
 };
@@ -517,21 +515,6 @@ 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;
@@ -732,37 +715,6 @@ 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** 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.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,
@@ -1034,7 +986,7 @@ 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;
  }
@@ -1116,18 +1068,6 @@ 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,
@@ -1241,14 +1181,6 @@ 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) {
@@ -1547,10 +1479,10 @@ 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());
  }
 };
@@ -1836,11 +1768,11 @@ rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base(
 }

 rocksdb_iterator_t* rocksdb_writebatch_wi_create_iterator_with_base_cf(
-    rocksdb_writebatch_wi_t* wbwi, rocksdb_iterator_t* base_iterator,
+    rocksdb_writebatch_wi_t* wbwi,
+    rocksdb_iterator_t* base_iterator,
    rocksdb_column_family_handle_t* column_family) {
  rocksdb_iterator_t* result = new rocksdb_iterator_t;
-  result->rep =
-      wbwi->rep->NewIteratorWithBase(column_family->rep, base_iterator->rep);
+  result->rep = wbwi->rep->NewIteratorWithBase(column_family->rep, base_iterator->rep);
  delete base_iterator;
  return result;
 }
@@ -2052,11 +1984,6 @@ void rocksdb_block_based_options_set_pin_l0_filter_and_index_blocks_in_cache(
  options->rep.pin_l0_filter_and_index_blocks_in_cache = v;
 }

-void rocksdb_block_based_options_set_pin_top_level_index_and_filter(
-    rocksdb_block_based_table_options_t* options, unsigned char v) {
-  options->rep.pin_top_level_index_and_filter = v;
-}
-
 void rocksdb_options_set_block_based_table_factory(
    rocksdb_options_t *opt,
    rocksdb_block_based_table_options_t* table_options) {
@@ -2119,15 +2046,6 @@ void rocksdb_set_options(
            db->rep->SetOptions(options_map));
    }

-void rocksdb_set_options_cf(
-    rocksdb_t* db, rocksdb_column_family_handle_t* handle, int count, const char* const keys[], const char* const values[], char** errptr) {
-        std::unordered_map<std::string, std::string> options_map;
-        for (int i=0; i<count; i++)
-            options_map[keys[i]] = values[i];
-        SaveError(errptr,
-            db->rep->SetOptions(handle->rep, options_map));
-    }
-
 rocksdb_options_t* rocksdb_options_create() {
  return new rocksdb_options_t;
 }
@@ -2272,11 +2190,6 @@ void rocksdb_options_set_max_bytes_for_level_base(
  opt->rep.max_bytes_for_level_base = n;
 }

-void rocksdb_options_set_snap_refresh_nanos(rocksdb_options_t* opt,
-                                            uint64_t n) {
-  opt->rep.snap_refresh_nanos = n;
-}
-
 void rocksdb_options_set_level_compaction_dynamic_level_bytes(
    rocksdb_options_t* opt, unsigned char v) {
  opt->rep.level_compaction_dynamic_level_bytes = v;
@@ -2349,18 +2262,6 @@ void rocksdb_options_set_compression_per_level(rocksdb_options_t* opt,
  }
 }

-void rocksdb_options_set_bottommost_compression_options(rocksdb_options_t* opt,
-                                                        int w_bits, int level,
-                                                        int strategy,
-                                                        int max_dict_bytes,
-                                                        bool enabled) {
-  opt->rep.bottommost_compression_opts.window_bits = w_bits;
-  opt->rep.bottommost_compression_opts.level = level;
-  opt->rep.bottommost_compression_opts.strategy = strategy;
-  opt->rep.bottommost_compression_opts.max_dict_bytes = max_dict_bytes;
-  opt->rep.bottommost_compression_opts.enabled = enabled;
-}
-
 void rocksdb_options_set_compression_options(rocksdb_options_t* opt, int w_bits,
                                             int level, int strategy,
                                             int max_dict_bytes) {
@@ -2483,7 +2384,7 @@ void rocksdb_options_set_bytes_per_sync(

 void rocksdb_options_set_writable_file_max_buffer_size(rocksdb_options_t* opt,
                                                       uint64_t v) {
-  opt->rep.writable_file_max_buffer_size = static_cast<size_t>(v);
+  opt->rep.writable_file_max_buffer_size = v;
 }

 void rocksdb_options_set_allow_concurrent_memtable_write(rocksdb_options_t* opt,
@@ -2514,25 +2415,6 @@ void rocksdb_options_set_max_write_buffer_number_to_maintain(
  opt->rep.max_write_buffer_number_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;
-}
-
-void rocksdb_options_set_max_background_jobs(rocksdb_options_t* opt, int n) {
-  opt->rep.max_background_jobs = n;
-}
-
 void rocksdb_options_set_max_background_compactions(rocksdb_options_t* opt, int n) {
  opt->rep.max_background_compactions = n;
 }
@@ -2928,7 +2810,7 @@ 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;
 }
@@ -3028,7 +2910,7 @@ 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 {
@@ -3227,11 +3109,6 @@ void rocksdb_compactoptions_destroy(rocksdb_compactoptions_t* opt) {
  delete opt;
 }

-void rocksdb_compactoptions_set_bottommost_level_compaction(
-    rocksdb_compactoptions_t* opt, unsigned char v) {
-  opt->rep.bottommost_level_compaction = static_cast<BottommostLevelCompaction>(v);
-}
-
 void rocksdb_compactoptions_set_exclusive_manual_compaction(
    rocksdb_compactoptions_t* opt, unsigned char v) {
  opt->rep.exclusive_manual_compaction = v;
@@ -3319,22 +3196,6 @@ 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;
@@ -3397,11 +3258,6 @@ void rocksdb_sstfilewriter_finish(rocksdb_sstfilewriter_t* writer,
  SaveError(errptr, writer->rep->Finish(nullptr));
 }

-void rocksdb_sstfilewriter_file_size(rocksdb_sstfilewriter_t* writer,
-                                  uint64_t* file_size) {
-  *file_size = writer->rep->FileSize();
-}
-
 void rocksdb_sstfilewriter_destroy(rocksdb_sstfilewriter_t* writer) {
  delete writer->rep;
  delete writer;
@@ -3469,10 +3325,6 @@ 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*),
@@ -3503,7 +3355,7 @@ 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);
@@ -3641,18 +3493,6 @@ const char* rocksdb_livefiles_largestkey(
  return lf->rep[index].largestkey.data();
 }

-uint64_t rocksdb_livefiles_entries(
-    const rocksdb_livefiles_t* lf,
-    int index) {
-  return lf->rep[index].num_entries;
-}
-
-uint64_t rocksdb_livefiles_deletions(
-    const rocksdb_livefiles_t* lf,
-    int index) {
-  return lf->rep[index].num_deletions;
-}
-
 extern void rocksdb_livefiles_destroy(
  const rocksdb_livefiles_t* lf) {
  delete lf;
@@ -3798,38 +3638,6 @@ 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** 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(
-        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;
@@ -3950,26 +3758,6 @@ 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,
@@ -4062,14 +3850,6 @@ 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,
@@ -4079,14 +3859,6 @@ 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) {
@@ -4139,14 +3911,6 @@ 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;
@@ -4295,98 +4059,6 @@ const char* rocksdb_pinnableslice_value(const rocksdb_pinnableslice_t* v,
  *vlen = v->rep.size();
  return v->rep.data();
 }
-
-// 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;
-};
-
-// initializes new container of memory consumers
-rocksdb_memory_consumers_t* rocksdb_memory_consumers_create() {
-  return new rocksdb_memory_consumers_t;
-}
-
-// adds datatabase to the container of memory consumers
-void rocksdb_memory_consumers_add_db(rocksdb_memory_consumers_t* consumers,
-                                     rocksdb_t* db) {
-  consumers->dbs.push_back(db);
-}
-
-// adds cache to the container of memory consumers
-void rocksdb_memory_consumers_add_cache(rocksdb_memory_consumers_t* consumers,
-                                        rocksdb_cache_t* cache) {
-  consumers->caches.insert(cache);
-}
-
-// deletes container with memory consumers
-void rocksdb_memory_consumers_destroy(rocksdb_memory_consumers_t* consumers) {
-  delete consumers;
-}
-
-// contains memory usage statistics provided by rocksdb::MemoryUtil
-struct rocksdb_memory_usage_t {
-  uint64_t mem_table_total;
-  uint64_t mem_table_unflushed;
-  uint64_t mem_table_readers_total;
-  uint64_t cache_total;
-};
-
-// estimates amount of memory occupied by consumers (dbs and caches)
-rocksdb_memory_usage_t* rocksdb_approximate_memory_usage_create(
-    rocksdb_memory_consumers_t* consumers, char** errptr) {
-
-  vector<DB*> dbs;
-  for (auto db : consumers->dbs) {
-    dbs.push_back(db->rep);
-  }
-
-  unordered_set<const Cache*> cache_set;
-  for (auto cache : consumers->caches) {
-    cache_set.insert(const_cast<const Cache*>(cache->rep.get()));
-  }
-
-  std::map<rocksdb::MemoryUtil::UsageType, uint64_t> usage_by_type;
-
-  auto status = MemoryUtil::GetApproximateMemoryUsageByType(dbs, cache_set,
-                                                            &usage_by_type);
-  if (SaveError(errptr, status)) {
-    return nullptr;
-  }
-
-  auto result = new rocksdb_memory_usage_t;
-  result->mem_table_total = usage_by_type[MemoryUtil::kMemTableTotal];
-  result->mem_table_unflushed = usage_by_type[MemoryUtil::kMemTableUnFlushed];
-  result->mem_table_readers_total = usage_by_type[MemoryUtil::kTableReadersTotal];
-  result->cache_total = usage_by_type[MemoryUtil::kCacheTotal];
-  return result;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_mem_table_total(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->mem_table_total;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_mem_table_unflushed(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->mem_table_unflushed;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_mem_table_readers_total(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->mem_table_readers_total;
-}
-
-uint64_t rocksdb_approximate_memory_usage_get_cache_total(
-    rocksdb_memory_usage_t* memory_usage) {
-  return memory_usage->cache_total;
-}
-
-// deletes container with memory usage estimates
-void rocksdb_approximate_memory_usage_destroy(rocksdb_memory_usage_t* usage) {
-  delete usage;
-}
-
 }  // end extern "C"

 #endif  // !ROCKSDB_LITE
@@ -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>

@@ -20,8 +19,11 @@

 // Can not use port/port.h macros as this is a c file
 #ifdef OS_WIN
+
 #include <windows.h>

+#define snprintf _snprintf
+
 // Ok for uniqueness
 int geteuid() {
  int result = 0;
@@ -32,11 +34,6 @@ int geteuid() {
  return result;
 }

-// VS < 2015
-#if defined(_MSC_VER) && (_MSC_VER < 1900)
-#define snprintf _snprintf
-#endif
-
 #endif

 const char* phase = "";
@@ -45,25 +42,17 @@ 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);
  phase = name;
 }
-#ifdef _MSC_VER
-#pragma warning(push)
-#pragma warning (disable: 4996) // getenv security warning
-#endif
 static const char* GetTempDir(void) {
    const char* ret = getenv("TEST_TMPDIR");
    if (ret == NULL || ret[0] == '\0')
        ret = "/tmp";
    return ret;
 }
-#ifdef _MSC_VER
-#pragma warning(pop)
-#endif

 #define CheckNoError(err)                                               \
  if ((err) != NULL) {                                                  \
@@ -654,7 +643,7 @@ int main(int argc, char** argv) {
    rocksdb_sstfilewriter_t* writer =
        rocksdb_sstfilewriter_create(env_opt, io_options);

-    remove(sstfilename);
+    unlink(sstfilename);
    rocksdb_sstfilewriter_open(writer, sstfilename, &err);
    CheckNoError(err);
    rocksdb_sstfilewriter_put(writer, "sstk1", 5, "v1", 2, &err);
@@ -675,7 +664,7 @@ int main(int argc, char** argv) {
    CheckGet(db, roptions, "sstk2", "v2");
    CheckGet(db, roptions, "sstk3", "v3");

-    remove(sstfilename);
+    unlink(sstfilename);
    rocksdb_sstfilewriter_open(writer, sstfilename, &err);
    CheckNoError(err);
    rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v4", 2, &err);
@@ -919,8 +908,7 @@ int main(int argc, char** argv) {
    rocksdb_writebatch_wi_t* wbi = rocksdb_writebatch_wi_create(0, 1);
    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
    rocksdb_writebatch_wi_delete(wbi, "foo", 3);
-    rocksdb_iterator_t* iter =
-        rocksdb_writebatch_wi_create_iterator_with_base(wbi, base_iter);
+    rocksdb_iterator_t* iter = rocksdb_writebatch_wi_create_iterator_with_base(wbi, base_iter);
    CheckCondition(!rocksdb_iter_valid(iter));
    rocksdb_iter_seek_to_first(iter);
    CheckCondition(rocksdb_iter_valid(iter));
@@ -1189,12 +1177,6 @@ int main(int argc, char** argv) {
    rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &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");

@@ -1352,47 +1334,6 @@ int main(int argc, char** argv) {
    rocksdb_destroy_db(options, dbname, &err);
  }

-  // Check memory usage stats
-  StartPhase("approximate_memory_usage");
-  {
-    // Create database
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_memory_consumers_t* consumers;
-    consumers = rocksdb_memory_consumers_create();
-    rocksdb_memory_consumers_add_db(consumers, db);
-    rocksdb_memory_consumers_add_cache(consumers, cache);
-
-    // take memory usage report before write-read operation
-    rocksdb_memory_usage_t* mu1;
-    mu1 = rocksdb_approximate_memory_usage_create(consumers, &err);
-    CheckNoError(err);
-
-    // Put data (this should affect memtables)
-    rocksdb_put(db, woptions, "memory", 6, "test", 4, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "memory", "test");
-
-    // take memory usage report after write-read operation
-    rocksdb_memory_usage_t* mu2;
-    mu2 = rocksdb_approximate_memory_usage_create(consumers, &err);
-    CheckNoError(err);
-
-    // amount of memory used within memtables should grow
-    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_total(mu2) >=
-                   rocksdb_approximate_memory_usage_get_mem_table_total(mu1));
-    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu2) >=
-                   rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu1));
-
-    rocksdb_memory_consumers_destroy(consumers);
-    rocksdb_approximate_memory_usage_destroy(mu1);
-    rocksdb_approximate_memory_usage_destroy(mu2);
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-  }
-
  StartPhase("cuckoo_options");
  {
    rocksdb_cuckoo_table_options_t* cuckoo_options;
@@ -1536,7 +1477,7 @@ int main(int argc, char** argv) {
    const rocksdb_snapshot_t* snapshot;
    snapshot = rocksdb_transactiondb_create_snapshot(txn_db);
    rocksdb_readoptions_set_snapshot(roptions, snapshot);
-
+  
    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hey", 3,  &err);
    CheckNoError(err);

@@ -1723,59 +1664,6 @@ 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");
  {
@@ -1787,7 +1675,7 @@ int main(int argc, char** argv) {
    db = rocksdb_open(options, dbname, &err);
    CheckNoError(err);
  }
-
+  
  StartPhase("cleanup");
  rocksdb_close(db);
  rocksdb_options_destroy(options);
@@ -9,31 +9,32 @@

 #include "db/column_family.h"

-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <vector>
 #include <string>
 #include <algorithm>
 #include <limits>

-#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 "db/compaction_picker.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 "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 {

@@ -60,24 +61,12 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
    JobContext job_context(0);
    mutex_->Lock();
    if (cfd_->Unref()) {
-      bool dropped = cfd_->IsDropped();
-
      delete cfd_;
-
-      if (dropped) {
-        db_->FindObsoleteFiles(&job_context, false, true);
-      }
    }
+    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();
  }
@@ -116,6 +105,9 @@ void GetIntTblPropCollectorFactory(
    int_tbl_prop_collector_factories->emplace_back(
        new UserKeyTablePropertiesCollectorFactory(collector_factories[i]));
  }
+  // Add collector to collect internal key statistics
+  int_tbl_prop_collector_factories->emplace_back(
+      new InternalKeyPropertiesCollectorFactory);
 }

 Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
@@ -138,10 +130,14 @@ Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
    }
  }
  if (cf_options.compression_opts.zstd_max_train_bytes > 0) {
-    if (!ZSTD_TrainDictionarySupported()) {
+    if (!CompressionTypeSupported(CompressionType::kZSTD)) {
+      // Dictionary trainer is available since v0.6.1, but ZSTD was marked
+      // stable only since v0.8.0. For now we enable the feature in stable
+      // versions only.
      return Status::InvalidArgument(
-          "zstd dictionary trainer cannot be used because ZSTD 1.1.3+ "
-          "is not linked with the binary.");
+          "zstd dictionary trainer cannot be used because " +
+          CompressionTypeToString(CompressionType::kZSTD) +
+          " is not linked with the binary.");
    }
    if (cf_options.compression_opts.max_dict_bytes == 0) {
      return Status::InvalidArgument(
@@ -405,8 +401,7 @@ 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 EnvOptions& env_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),
@@ -446,8 +441,7 @@ ColumnFamilyData::ColumnFamilyData(
  if (_dummy_versions != nullptr) {
    internal_stats_.reset(
        new InternalStats(ioptions_.num_levels, db_options.env, this));
-    table_cache_.reset(new TableCache(ioptions_, env_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_));
@@ -951,16 +945,26 @@ Status ColumnFamilyData::RangesOverlapWithMemtables(
  super_version->imm->AddIterators(read_opts, &merge_iter_builder);
  ScopedArenaIterator memtable_iter(merge_iter_builder.Finish());

-  auto read_seq = super_version->current->version_set()->LastSequence();
-  ReadRangeDelAggregator range_del_agg(&internal_comparator_, read_seq);
+  std::vector<InternalIterator*> memtable_range_del_iters;
  auto* active_range_del_iter =
-      super_version->mem->NewRangeTombstoneIterator(read_opts, read_seq);
-  range_del_agg.AddTombstones(
-      std::unique_ptr<FragmentedRangeTombstoneIterator>(active_range_del_iter));
-  super_version->imm->AddRangeTombstoneIterators(read_opts, nullptr /* arena */,
-                                                 &range_del_agg);
-
+      super_version->mem->NewRangeTombstoneIterator(read_opts);
+  if (active_range_del_iter != nullptr) {
+    memtable_range_del_iters.push_back(active_range_del_iter);
+  }
+  super_version->imm->AddRangeTombstoneIterators(read_opts,
+                                                 &memtable_range_del_iters);
+  RangeDelAggregator range_del_agg(internal_comparator_, {} /* snapshots */,
+                                   false /* collapse_deletions */);
  Status status;
+  {
+    std::unique_ptr<InternalIterator> memtable_range_del_iter(
+        NewMergingIterator(&internal_comparator_,
+                           memtable_range_del_iters.empty()
+                               ? nullptr
+                               : &memtable_range_del_iters[0],
+                           static_cast<int>(memtable_range_del_iters.size())));
+    status = range_del_agg.AddTombstones(std::move(memtable_range_del_iter));
+  }
  for (size_t i = 0; i < ranges.size() && status.ok() && !*overlap; ++i) {
    auto* vstorage = super_version->current->storage_info();
    auto* ucmp = vstorage->InternalComparator()->user_comparator();
@@ -993,14 +997,13 @@ 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_);
  }
@@ -1146,60 +1149,13 @@ 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()) {
-    s = CheckCFPathsSupported(db_options, cf_options);
-  }
-  if (!s.ok()) {
-    return s;
-  }
-
-  if (cf_options.ttl > 0) {
-    if (db_options.max_open_files != -1) {
-      return Status::NotSupported(
-          "TTL is only supported when files are always "
-          "kept open (set max_open_files = -1). ");
-    }
-    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) {
-    if (db_options.max_open_files != -1) {
-      return Status::NotSupported(
-          "Periodic Compaction is only supported when files are always "
-          "kept open (set max_open_files = -1). ");
-    }
-    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_);
@@ -1256,20 +1212,18 @@ ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                 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(
-          0, "", nullptr, nullptr, nullptr, ColumnFamilyOptions(), *db_options,
-          env_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),
      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_;
@@ -1337,7 +1291,7 @@ 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_, env_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);
@@ -24,7 +24,6 @@
 #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 {
@@ -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
@@ -339,13 +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

@@ -407,10 +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
@@ -495,8 +383,6 @@ class ColumnFamilyData {

  Directory* GetDataDir(size_t path_id) const;

-  ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
-
 private:
  friend class ColumnFamilySet;
  ColumnFamilyData(uint32_t id, const std::string& name,
@@ -505,8 +391,7 @@ class ColumnFamilyData {
                   const ColumnFamilyOptions& options,
                   const ImmutableDBOptions& db_options,
                   const EnvOptions& env_options,
-                   ColumnFamilySet* column_family_set,
-                   BlockCacheTracer* const block_cache_tracer);
+                   ColumnFamilySet* column_family_set);

  uint32_t id_;
  const std::string name_;
@@ -634,8 +519,7 @@ class ColumnFamilySet {
                  const ImmutableDBOptions* db_options,
                  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;
@@ -694,7 +578,6 @@ class ColumnFamilySet {
  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
@@ -10,13 +10,13 @@
 #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 {

@@ -24,7 +24,7 @@ class CompactFilesTest : public testing::Test {
 public:
  CompactFilesTest() {
    env_ = Env::Default();
-    db_name_ = test::PerThreadDBPath("compact_files_test");
+    db_name_ = test::TmpDir(env_) + "/compact_files_test";
  }

  std::string db_name_;
@@ -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);
  }
@@ -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_;
@@ -308,100 +308,6 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
  delete db;
 }

-TEST_F(CompactFilesTest, SentinelCompressionType) {
-  if (!Zlib_Supported()) {
-    fprintf(stderr, "zlib compression not supported, skip this test\n");
-    return;
-  }
-  if (!Snappy_Supported()) {
-    fprintf(stderr, "snappy compression not supported, skip this test\n");
-    return;
-  }
-  // Check that passing `CompressionType::kDisableCompressionOption` to
-  // `CompactFiles` causes it to use the column family compression options.
-  for (auto compaction_style :
-       {CompactionStyle::kCompactionStyleLevel,
-        CompactionStyle::kCompactionStyleUniversal,
-        CompactionStyle::kCompactionStyleNone}) {
-    DestroyDB(db_name_, Options());
-    Options options;
-    options.compaction_style = compaction_style;
-    // L0: Snappy, L1: ZSTD, L2: Snappy
-    options.compression_per_level = {CompressionType::kSnappyCompression,
-                                     CompressionType::kZlibCompression,
-                                     CompressionType::kSnappyCompression};
-    options.create_if_missing = true;
-    FlushedFileCollector* collector = new FlushedFileCollector();
-    options.listeners.emplace_back(collector);
-    DB* db = nullptr;
-    ASSERT_OK(DB::Open(options, db_name_, &db));
-
-    db->Put(WriteOptions(), "key", "val");
-    db->Flush(FlushOptions());
-
-    auto l0_files = collector->GetFlushedFiles();
-    ASSERT_EQ(1, l0_files.size());
-
-    // L0->L1 compaction, so output should be ZSTD-compressed
-    CompactionOptions compaction_opts;
-    compaction_opts.compression = CompressionType::kDisableCompressionOption;
-    ASSERT_OK(db->CompactFiles(compaction_opts, l0_files, 1));
-
-    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),
-                name_and_table_props.second->compression_name);
-    }
-    delete db;
-  }
-}
-
-TEST_F(CompactFilesTest, GetCompactionJobInfo) {
-  Options options;
-  options.create_if_missing = true;
-  // Disable RocksDB background compaction.
-  options.compaction_style = kCompactionStyleNone;
-  options.level0_slowdown_writes_trigger = 1000;
-  options.level0_stop_writes_trigger = 1000;
-  options.write_buffer_size = 65536;
-  options.max_write_buffer_number = 2;
-  options.compression = kNoCompression;
-  options.max_compaction_bytes = 5000;
-
-  // Add listener
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  // create couple files
-  for (int i = 0; i < 500; ++i) {
-    db->Put(WriteOptions(), ToString(i), std::string(1000, 'a' + (i % 26)));
-  }
-  reinterpret_cast<DBImpl*>(db)->TEST_WaitForFlushMemTable();
-  auto l0_files_1 = collector->GetFlushedFiles();
-  CompactionOptions co;
-  co.compression = CompressionType::kLZ4Compression;
-  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);
-  ASSERT_EQ(compaction_job_info.cf_id, db->DefaultColumnFamily()->GetID());
-  ASSERT_EQ(compaction_job_info.cf_name, db->DefaultColumnFamily()->GetName());
-  ASSERT_EQ(compaction_job_info.compaction_reason,
-            CompactionReason::kManualCompaction);
-  ASSERT_EQ(compaction_job_info.compression, CompressionType::kLZ4Compression);
-  ASSERT_EQ(compaction_job_info.output_level, 0);
-  ASSERT_OK(compaction_job_info.status);
-  // no assertion failure
-  delete db;
-}
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -5,7 +5,7 @@

 #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"

@@ -25,12 +25,22 @@ CompactedDBImpl::~CompactedDBImpl() {
 }

 size_t CompactedDBImpl::FindFile(const Slice& key) {
+  size_t left = 0;
  size_t right = files_.num_files - 1;
-  auto cmp = [&](const FdWithKeyRange& f, const Slice& k) -> bool {
-    return user_comparator_->Compare(ExtractUserKey(f.largest_key), k) < 0;
-  };
-  return static_cast<size_t>(std::lower_bound(files_.files,
-                            files_.files + right, key, cmp) - files_.files);
+  while (left < right) {
+    size_t mid = (left + right) >> 1;
+    const FdWithKeyRange& f = files_.files[mid];
+    if (user_comparator_->Compare(ExtractUserKey(f.largest_key), key) < 0) {
+      // Key at "mid.largest" is < "target".  Therefore all
+      // files at or before "mid" are uninteresting.
+      left = mid + 1;
+    } else {
+      // Key at "mid.largest" is >= "target".  Therefore all files
+      // after "mid" are uninteresting.
+      right = mid;
+    }
+  }
+  return right;
 }

 Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
@@ -147,7 +157,6 @@ Status CompactedDBImpl::Open(const Options& options,
  std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
  Status s = db->Init(options);
  if (s.ok()) {
-    db->StartTimedTasks();
    ROCKS_LOG_INFO(db->immutable_db_options_.info_log,
                   "Opened the db as fully compacted mode");
    LogFlush(db->immutable_db_options_.info_log);
@@ -5,9 +5,9 @@

 #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 {

@@ -67,11 +67,10 @@ class CompactedDBImpl : public DBImpl {
  virtual Status EnableFileDeletions(bool /*force*/) override {
    return Status::NotSupported("Not supported in compacted db mode.");
  }
-  virtual Status GetLiveFiles(std::vector<std::string>& ret,
-                              uint64_t* manifest_file_size,
-                              bool /*flush_memtable*/) override {
-    return DBImpl::GetLiveFiles(ret, manifest_file_size,
-                                false /* flush_memtable */);
+  virtual Status GetLiveFiles(std::vector<std::string>&,
+                              uint64_t* /*manifest_file_size*/,
+                              bool /*flush_memtable*/ = true) override {
+    return Status::NotSupported("Not supported in compacted db mode.");
  }
  using DBImpl::Flush;
  virtual Status Flush(const FlushOptions& /*options*/,
@@ -85,15 +84,6 @@ 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;
@@ -7,54 +7,22 @@
 // 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 {

-const uint64_t kRangeTombstoneSentinel =
-    PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b) {
-  auto c = user_cmp->Compare(a.user_key(), b.user_key());
-  if (c != 0) {
-    return c;
-  }
-  auto a_footer = ExtractInternalKeyFooter(a.Encode());
-  auto b_footer = ExtractInternalKeyFooter(b.Encode());
-  if (a_footer == kRangeTombstoneSentinel) {
-    if (b_footer != kRangeTombstoneSentinel) {
-      return -1;
-    }
-  } else if (b_footer == kRangeTombstoneSentinel) {
-    return 1;
-  }
-  return 0;
-}
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
-                      const InternalKey& b) {
-  if (a == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, *a, b);
-}
-
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey* b) {
-  if (b == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, a, *b);
-}
-
 uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
  uint64_t sum = 0;
  for (size_t i = 0; i < files.size() && files[i]; i++) {
@@ -113,49 +81,6 @@ void Compaction::GetBoundaryKeys(
  }
 }

-std::vector<CompactionInputFiles> Compaction::PopulateWithAtomicBoundaries(
-    VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs) {
-  const Comparator* ucmp = vstorage->InternalComparator()->user_comparator();
-  for (size_t i = 0; i < inputs.size(); i++) {
-    if (inputs[i].level == 0 || inputs[i].files.empty()) {
-      continue;
-    }
-    inputs[i].atomic_compaction_unit_boundaries.reserve(inputs[i].files.size());
-    AtomicCompactionUnitBoundary cur_boundary;
-    size_t first_atomic_idx = 0;
-    auto add_unit_boundary = [&](size_t to) {
-      if (first_atomic_idx == to) return;
-      for (size_t k = first_atomic_idx; k < to; k++) {
-        inputs[i].atomic_compaction_unit_boundaries.push_back(cur_boundary);
-      }
-      first_atomic_idx = to;
-    };
-    for (size_t j = 0; j < inputs[i].files.size(); j++) {
-      const auto* f = inputs[i].files[j];
-      if (j == 0) {
-        // First file in a level.
-        cur_boundary.smallest = &f->smallest;
-        cur_boundary.largest = &f->largest;
-      } else if (sstableKeyCompare(ucmp, *cur_boundary.largest, f->smallest) ==
-                 0) {
-        // SSTs overlap but the end key of the previous file was not
-        // artificially extended by a range tombstone. Extend the current
-        // boundary.
-        cur_boundary.largest = &f->largest;
-      } else {
-        // Atomic compaction unit has ended.
-        add_unit_boundary(j);
-        cur_boundary.smallest = &f->smallest;
-        cur_boundary.largest = &f->largest;
-      }
-    }
-    add_unit_boundary(inputs[i].files.size());
-    assert(inputs[i].files.size() ==
-           inputs[i].atomic_compaction_unit_boundaries.size());
-  }
-  return inputs;
-}
-
 // helper function to determine if compaction is creating files at the
 // bottommost level
 bool Compaction::IsBottommostLevel(
@@ -209,7 +134,6 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
                       int _output_level, uint64_t _target_file_size,
                       uint64_t _max_compaction_bytes, uint32_t _output_path_id,
                       CompressionType _compression,
-                       CompressionOptions _compression_opts,
                       uint32_t _max_subcompactions,
                       std::vector<FileMetaData*> _grandparents,
                       bool _manual_compaction, double _score,
@@ -228,9 +152,8 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
      cfd_(nullptr),
      output_path_id_(_output_path_id),
      output_compression_(_compression),
-      output_compression_opts_(_compression_opts),
      deletion_compaction_(_deletion_compaction),
-      inputs_(PopulateWithAtomicBoundaries(vstorage, std::move(_inputs))),
+      inputs_(std::move(_inputs)),
      grandparents_(std::move(_grandparents)),
      score_(_score),
      bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
@@ -245,12 +168,6 @@ 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) {
@@ -374,8 +291,8 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
        if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
          // We've advanced far enough
          if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
-            // Key falls in this file's range, so it may
-            // exist beyond output level
+            // Key falls in this file's range, so definitely
+            // exists beyond output level
            return false;
          }
          break;
@@ -412,14 +329,12 @@ const char* Compaction::InputLevelSummary(
    if (!is_first) {
      len +=
          snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len, " + ");
-      len = std::min(len, static_cast<int>(sizeof(scratch->buffer)));
    } else {
      is_first = false;
    }
    len += snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
                    "%" ROCKSDB_PRIszt "@%d", input_level.size(),
                    input_level.level);
-    len = std::min(len, static_cast<int>(sizeof(scratch->buffer)));
  }
  snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
           " files to L%d", output_level());
@@ -9,51 +9,17 @@

 #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 {
-// The file contains class Compaction, as well as some helper functions
-// and data structures used by the class.
-
-// 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
-// than any key and b==null indicates a key that is greater than any key. Note
-// that the comparison is performed primarily on the user-key portion of the
-// key. If the user-keys compare equal, an additional test is made to sort
-// range tombstone sentinel keys before other keys with the same user-key. The
-// result is that 2 user-keys will compare equal if they differ purely on
-// their sequence number and value, but the range tombstone sentinel for that
-// user-key will compare not equal. This is necessary because the range
-// tombstone sentinel key is set as the largest key for an sstable even though
-// that key never appears in the database. We don't want adjacent sstables to
-// be considered overlapping if they are separated by the range tombstone
-// sentinel.
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b);
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
-                      const InternalKey& b);
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey* b);
-
-// An AtomicCompactionUnitBoundary represents a range of keys [smallest,
-// largest] that exactly spans one ore more neighbouring SSTs on the same
-// level. Every pair of  SSTs in this range "overlap" (i.e., the largest
-// user key of one file is the smallest user key of the next file). These
-// boundaries are propagated down to RangeDelAggregator during compaction
-// to provide safe truncation boundaries for range tombstones.
-struct AtomicCompactionUnitBoundary {
-  const InternalKey* smallest = nullptr;
-  const InternalKey* largest = nullptr;
-};

 // The structure that manages compaction input files associated
 // with the same physical level.
 struct CompactionInputFiles {
  int level;
  std::vector<FileMetaData*> files;
-  std::vector<AtomicCompactionUnitBoundary> atomic_compaction_unit_boundaries;
  inline bool empty() const { return files.empty(); }
  inline size_t size() const { return files.size(); }
  inline void clear() { files.clear(); }
@@ -65,7 +31,7 @@ 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,
@@ -74,7 +40,7 @@ class Compaction {
             std::vector<CompactionInputFiles> inputs, int output_level,
             uint64_t target_file_size, uint64_t max_compaction_bytes,
             uint32_t output_path_id, CompressionType compression,
-             CompressionOptions compression_opts, uint32_t max_subcompactions,
+             uint32_t max_subcompactions,
             std::vector<FileMetaData*> grandparents,
             bool manual_compaction = false, double score = -1,
             bool deletion_compaction = false,
@@ -130,12 +96,6 @@ class Compaction {
    return inputs_[compaction_input_level][i];
  }

-  const std::vector<AtomicCompactionUnitBoundary>* boundaries(
-      size_t compaction_input_level) const {
-    assert(compaction_input_level < inputs_.size());
-    return &inputs_[compaction_input_level].atomic_compaction_unit_boundaries;
-  }
-
  // Returns the list of file meta data of the specified compaction
  // input level.
  // REQUIREMENT: "compaction_input_level" must be >= 0 and
@@ -159,11 +119,6 @@ class Compaction {
  // What compression for output
  CompressionType output_compression() const { return output_compression_; }

-  // What compression options for output
-  CompressionOptions output_compression_opts() const {
-    return output_compression_opts_;
-  }
-
  // Whether need to write output file to second DB path.
  uint32_t output_path_id() const { return output_path_id_; }

@@ -302,13 +257,6 @@ class Compaction {
                              const std::vector<CompactionInputFiles>& inputs,
                              Slice* smallest_key, Slice* largest_key);

-  // Get the atomic file boundaries for all files in the compaction. Necessary
-  // in order to avoid the scenario described in
-  // https://github.com/facebook/rocksdb/pull/4432#discussion_r221072219 and plumb
-  // down appropriate key boundaries to RangeDelAggregator during compaction.
-  static std::vector<CompactionInputFiles> PopulateWithAtomicBoundaries(
-      VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs);
-
  // helper function to determine if compaction with inputs and storage is
  // bottommost
  static bool IsBottommostLevel(
@@ -335,7 +283,6 @@ class Compaction {

  const uint32_t output_path_id_;
  CompressionType output_compression_;
-  CompressionOptions output_compression_opts_;
  // If true, then the comaction can be done by simply deleting input files.
  const bool deletion_compaction_;

@@ -378,7 +325,7 @@ 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
@@ -1,232 +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/compaction/compaction_picker_fifo.h"
-#ifndef ROCKSDB_LITE
-
-#include <cinttypes>
-#include <string>
-#include <vector>
-#include "db/column_family.h"
-#include "logging/log_buffer.h"
-#include "util/string_util.h"
-
-namespace rocksdb {
-namespace {
-uint64_t GetTotalFilesSize(const std::vector<FileMetaData*>& files) {
-  uint64_t total_size = 0;
-  for (const auto& f : files) {
-    total_size += f->fd.file_size;
-  }
-  return total_size;
-}
-}  // anonymous namespace
-
-bool FIFOCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  const int kLevel0 = 0;
-  return vstorage->CompactionScore(kLevel0) >= 1;
-}
-
-Compaction* FIFOCompactionPicker::PickTTLCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(mutable_cf_options.ttl > 0);
-
-  const int kLevel0 = 0;
-  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
-  uint64_t total_size = GetTotalFilesSize(level_files);
-
-  int64_t _current_time;
-  auto status = ioptions_.env->GetCurrentTime(&_current_time);
-  if (!status.ok()) {
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: Couldn't get current time: %s. "
-                     "Not doing compactions based on TTL. ",
-                     cf_name.c_str(), status.ToString().c_str());
-    return nullptr;
-  }
-  const uint64_t current_time = static_cast<uint64_t>(_current_time);
-
-  std::vector<CompactionInputFiles> inputs;
-  inputs.emplace_back();
-  inputs[0].level = 0;
-
-  // avoid underflow
-  if (current_time > mutable_cf_options.ttl) {
-    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-      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.ttl)) {
-          break;
-        }
-        total_size -= f->compensated_file_size;
-        inputs[0].files.push_back(f);
-      }
-    }
-  }
-
-  // Return a nullptr and proceed to size-based FIFO compaction if:
-  // 1. there are no files older than ttl OR
-  // 2. there are a few files older than ttl, but deleting them will not bring
-  //    the total size to be less than max_table_files_size threshold.
-  if (inputs[0].files.empty() ||
-      total_size >
-          mutable_cf_options.compaction_options_fifo.max_table_files_size) {
-    return nullptr;
-  }
-
-  for (const auto& f : inputs[0].files) {
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: picking file %" PRIu64
-                     " with creation time %" PRIu64 " for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(),
-                     f->fd.table_reader->GetTableProperties()->creation_time);
-  }
-
-  Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
-      {}, /* is manual */ false, vstorage->CompactionScore(0),
-      /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::PickSizeCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  const int kLevel0 = 0;
-  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
-  uint64_t total_size = GetTotalFilesSize(level_files);
-
-  if (total_size <=
-          mutable_cf_options.compaction_options_fifo.max_table_files_size ||
-      level_files.size() == 0) {
-    // total size not exceeded
-    if (mutable_cf_options.compaction_options_fifo.allow_compaction &&
-        level_files.size() > 0) {
-      CompactionInputFiles comp_inputs;
-      // try to prevent same files from being compacted multiple times, which
-      // could produce large files that may never TTL-expire. Achieve this by
-      // disallowing compactions with files larger than memtable (inflate its
-      // size by 10% to account for uncompressed L0 files that may have size
-      // slightly greater than memtable size limit).
-      size_t max_compact_bytes_per_del_file =
-          static_cast<size_t>(MultiplyCheckOverflow(
-              static_cast<uint64_t>(mutable_cf_options.write_buffer_size),
-              1.1));
-      if (FindIntraL0Compaction(
-              level_files,
-              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)) {
-        Compaction* c = new Compaction(
-            vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
-            16 * 1024 * 1024 /* output file size limit */,
-            0 /* max compaction bytes, not applicable */,
-            0 /* output path ID */, mutable_cf_options.compression,
-            ioptions_.compression_opts, 0 /* max_subcompactions */, {},
-            /* is manual */ false, vstorage->CompactionScore(0),
-            /* is deletion compaction */ false,
-            CompactionReason::kFIFOReduceNumFiles);
-        return c;
-      }
-    }
-
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: nothing to do. Total size %" PRIu64
-        ", max size %" PRIu64 "\n",
-        cf_name.c_str(), total_size,
-        mutable_cf_options.compaction_options_fifo.max_table_files_size);
-    return nullptr;
-  }
-
-  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;
-
-  for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-    auto f = *ritr;
-    total_size -= f->compensated_file_size;
-    inputs[0].files.push_back(f);
-    char tmp_fsize[16];
-    AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: picking file %" PRIu64
-                     " with size %s for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
-    if (total_size <=
-        mutable_cf_options.compaction_options_fifo.max_table_files_size) {
-      break;
-    }
-  }
-
-  Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
-      {}, /* is manual */ false, vstorage->CompactionScore(0),
-      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(vstorage->num_levels() == 1);
-
-  Compaction* c = nullptr;
-  if (mutable_cf_options.ttl > 0) {
-    c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
-  }
-  if (c == nullptr) {
-    c = PickSizeCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
-  }
-  RegisterCompaction(c);
-  return c;
-}
-
-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*/,
-    const InternalKey* /*begin*/, const InternalKey* /*end*/,
-    InternalKey** compaction_end, bool* /*manual_conflict*/,
-    uint64_t /*max_file_num_to_ignore*/) {
-#ifdef NDEBUG
-  (void)input_level;
-  (void)output_level;
-#endif
-  assert(input_level == 0);
-  assert(output_level == 0);
-  *compaction_end = nullptr;
-  LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, ioptions_.info_log);
-  Compaction* c =
-      PickCompaction(cf_name, mutable_cf_options, vstorage, &log_buffer);
-  log_buffer.FlushBufferToLog();
-  return c;
-}
-
-}  // namespace rocksdb
-#endif  // !ROCKSDB_LITE
@@ -1,53 +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 {
-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) 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,
-      const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore) override;
-
-  // The maximum allowed output level.  Always returns 0.
-  virtual int MaxOutputLevel() const override { return 0; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-
- private:
-  Compaction* PickTTLCompaction(const std::string& cf_name,
-                                const MutableCFOptions& mutable_cf_options,
-                                VersionStorageInfo* version,
-                                LogBuffer* log_buffer);
-
-  Compaction* PickSizeCompaction(const std::string& cf_name,
-                                 const MutableCFOptions& mutable_cf_options,
-                                 VersionStorageInfo* version,
-                                 LogBuffer* log_buffer);
-};
-}  // namespace rocksdb
-#endif  // !ROCKSDB_LITE
@@ -1,553 +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 {
-
-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,
-                         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();
-
-  void PickFilesMarkedForPeriodicCompaction();
-
-  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::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_);
-}
-}  // 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
@@ -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 {
-// 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) override;
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-};
-
-}  // namespace rocksdb
@@ -3,28 +3,12 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

-#include "db/compaction/compaction_iterator.h"
+#include "db/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"
-
-#define DEFINITELY_IN_SNAPSHOT(seq, snapshot)                       \
-  ((seq) <= (snapshot) &&                                           \
-   (snapshot_checker_ == nullptr ||                                 \
-    LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) == \
-           SnapshotCheckerResult::kInSnapshot)))
-
-#define DEFINITELY_NOT_IN_SNAPSHOT(seq, snapshot)                     \
-  ((seq) > (snapshot) ||                                              \
-   (snapshot_checker_ != nullptr &&                                   \
-    UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) == \
-             SnapshotCheckerResult::kNotInSnapshot)))
-
-#define IN_EARLIEST_SNAPSHOT(seq) \
-  ((seq) <= earliest_snapshot_ && \
-   (snapshot_checker_ == nullptr || LIKELY(IsInEarliestSnapshot(seq))))

 namespace rocksdb {

@@ -33,33 +17,28 @@ CompactionIterator::CompactionIterator(
    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,
-    const CompactionFilter* compaction_filter,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
+    const Compaction* compaction, const CompactionFilter* compaction_filter,
    const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    SnapshotListFetchCallback* snap_list_callback)
+    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,
+          expect_valid_internal_key, range_del_agg,
          std::unique_ptr<CompactionProxy>(
              compaction ? new CompactionProxy(compaction) : nullptr),
-          compaction_filter, shutting_down, preserve_deletes_seqnum,
-          snap_list_callback) {}
+          compaction_filter, shutting_down, preserve_deletes_seqnum) {}

 CompactionIterator::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,
+    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
    std::unique_ptr<CompactionProxy> compaction,
    const CompactionFilter* compaction_filter,
    const std::atomic<bool>* shutting_down,
-    const SequenceNumber preserve_deletes_seqnum,
-    SnapshotListFetchCallback* snap_list_callback)
+    const SequenceNumber preserve_deletes_seqnum)
    : input_(input),
      cmp_(cmp),
      merge_helper_(merge_helper),
@@ -67,28 +46,42 @@ CompactionIterator::CompactionIterator(
      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
      snapshot_checker_(snapshot_checker),
      env_(env),
-      report_detailed_time_(report_detailed_time),
      expect_valid_internal_key_(expect_valid_internal_key),
      range_del_agg_(range_del_agg),
      compaction_(std::move(compaction)),
      compaction_filter_(compaction_filter),
      shutting_down_(shutting_down),
      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),
-      snap_list_callback_(snap_list_callback) {
+      current_key_committed_(false) {
  assert(compaction_filter_ == nullptr || compaction_ != nullptr);
-  assert(snapshots_ != nullptr);
  bottommost_level_ =
      compaction_ == nullptr ? false : compaction_->bottommost_level();
  if (compaction_ != nullptr) {
    level_ptrs_ = std::vector<size_t>(compaction_->number_levels(), 0);
  }
-  ProcessSnapshotList();
+
+  if (snapshots_->size() == 0) {
+    // optimize for fast path if there are no snapshots
+    visible_at_tip_ = true;
+    earliest_snapshot_ = kMaxSequenceNumber;
+    latest_snapshot_ = 0;
+  } else {
+    visible_at_tip_ = false;
+    earliest_snapshot_ = snapshots_->at(0);
+    latest_snapshot_ = snapshots_->back();
+  }
+  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());
 }

 CompactionIterator::~CompactionIterator() {
@@ -158,7 +151,12 @@ 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_ ||
+       ikey_.sequence > latest_snapshot_ ||
+       (snapshot_checker_ != nullptr &&
+        UNLIKELY(!snapshot_checker_->IsInSnapshot(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,
@@ -173,12 +171,12 @@ void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
    // to get sequence number.
    Slice& filter_key = ikey_.type == kTypeValue ? ikey_.user_key : key_;
    {
-      StopWatchNano timer(env_, report_detailed_time_);
+      StopWatchNano timer(env_, true);
      filter = compaction_filter_->FilterV2(
          compaction_->level(), filter_key, value_type, value_,
          &compaction_filter_value_, compaction_filter_skip_until_.rep());
      iter_stats_.total_filter_time +=
-          env_ != nullptr && report_detailed_time_ ? timer.ElapsedNanos() : 0;
+          env_ != nullptr ? timer.ElapsedNanos() : 0;
    }

    if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
@@ -208,28 +206,6 @@ void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
  }
 }

-void CompactionIterator::ProcessSnapshotList() {
-#ifndef NDEBUG
-  // findEarliestVisibleSnapshot assumes this ordering.
-  for (size_t i = 1; i < snapshots_->size(); ++i) {
-    assert(snapshots_->at(i - 1) < snapshots_->at(i));
-  }
-#endif
-  if (snapshots_->size() == 0) {
-    // optimize for fast path if there are no snapshots
-    visible_at_tip_ = true;
-    earliest_snapshot_iter_ = snapshots_->end();
-    earliest_snapshot_ = kMaxSequenceNumber;
-    latest_snapshot_ = 0;
-  } else {
-    visible_at_tip_ = false;
-    earliest_snapshot_iter_ = snapshots_->begin();
-    earliest_snapshot_ = snapshots_->at(0);
-    latest_snapshot_ = snapshots_->back();
-  }
-  released_snapshots_.clear();
-}
-
 void CompactionIterator::NextFromInput() {
  at_next_ = false;
  valid_ = false;
@@ -256,7 +232,6 @@ void CompactionIterator::NextFromInput() {
      valid_ = true;
      break;
    }
-    TEST_SYNC_POINT_CALLBACK("CompactionIterator:ProcessKV", &ikey_);

    // Update input statistics
    if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
@@ -277,13 +252,6 @@ void CompactionIterator::NextFromInput() {
    // compaction filter). ikey_.user_key is pointing to the copy.
    if (!has_current_user_key_ ||
        !cmp_->Equal(ikey_.user_key, current_user_key_)) {
-      num_keys_++;
-      // Use num_keys_ to reduce the overhead of reading current time
-      if (snap_list_callback_ && snapshots_->size() &&
-          snap_list_callback_->TimeToRefresh(num_keys_)) {
-        snap_list_callback_->Refresh(snapshots_, latest_snapshot_);
-        ProcessSnapshotList();
-      }
      // First occurrence of this user key
      // Copy key for output
      key_ = current_key_.SetInternalKey(key_, &ikey_);
@@ -292,7 +260,9 @@ void CompactionIterator::NextFromInput() {
      has_outputted_key_ = false;
      current_user_key_sequence_ = kMaxSequenceNumber;
      current_user_key_snapshot_ = 0;
-      current_key_committed_ = KeyCommitted(ikey_.sequence);
+      current_key_committed_ =
+          (snapshot_checker_ == nullptr ||
+           snapshot_checker_->IsInSnapshot(ikey_.sequence, kMaxSequenceNumber));

      // Apply the compaction filter to the first committed version of the user
      // key.
@@ -314,7 +284,8 @@ void CompactionIterator::NextFromInput() {
      // to query snapshot_checker_ in that case.
      if (UNLIKELY(!current_key_committed_)) {
        assert(snapshot_checker_ != nullptr);
-        current_key_committed_ = KeyCommitted(ikey_.sequence);
+        current_key_committed_ =
+            snapshot_checker_->IsInSnapshot(ikey_.sequence, kMaxSequenceNumber);
        // Apply the compaction filter to the first committed version of the
        // user key.
        if (current_key_committed_) {
@@ -398,8 +369,10 @@ void CompactionIterator::NextFromInput() {
          cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
        // Check whether the next key belongs to the same snapshot as the
        // SingleDelete.
-        if (prev_snapshot == 0 ||
-            DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot)) {
+        if (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot ||
+            (snapshot_checker_ != nullptr &&
+             UNLIKELY(!snapshot_checker_->IsInSnapshot(next_ikey.sequence,
+                                                       prev_snapshot)))) {
          if (next_ikey.type == kTypeSingleDeletion) {
            // We encountered two SingleDeletes in a row.  This could be due to
            // unexpected user input.
@@ -411,8 +384,11 @@ void CompactionIterator::NextFromInput() {
            ++iter_stats_.num_record_drop_obsolete;
            ++iter_stats_.num_single_del_mismatch;
          } else if (has_outputted_key_ ||
-                     DEFINITELY_IN_SNAPSHOT(
-                         ikey_.sequence, earliest_write_conflict_snapshot_)) {
+                     (ikey_.sequence <= earliest_write_conflict_snapshot_ &&
+                      (snapshot_checker_ == nullptr ||
+                       LIKELY(snapshot_checker_->IsInSnapshot(
+                           ikey_.sequence,
+                           earliest_write_conflict_snapshot_))))) {
            // Found a matching value, we can drop the single delete and the
            // value.  It is safe to drop both records since we've already
            // outputted a key in this snapshot, or there is no earlier
@@ -422,8 +398,7 @@ void CompactionIterator::NextFromInput() {
            // is an unexpected Merge or Delete.  We will compact it out
            // either way. We will maintain counts of how many mismatches
            // happened
-            if (next_ikey.type != kTypeValue &&
-                next_ikey.type != kTypeBlobIndex) {
+            if (next_ikey.type != kTypeValue) {
              ++iter_stats_.num_single_del_mismatch;
            }

@@ -460,7 +435,10 @@ void CompactionIterator::NextFromInput() {
        // iteration. If the next key is corrupt, we return before the
        // comparison, so the value of has_current_user_key does not matter.
        has_current_user_key_ = false;
-        if (compaction_ != nullptr && IN_EARLIEST_SNAPSHOT(ikey_.sequence) &&
+        if (compaction_ != nullptr && ikey_.sequence <= earliest_snapshot_ &&
+            (snapshot_checker_ == nullptr ||
+             LIKELY(snapshot_checker_->IsInSnapshot(ikey_.sequence,
+                                                    earliest_snapshot_))) &&
            compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                       &level_ptrs_)) {
          // Key doesn't exist outside of this range.
@@ -479,23 +457,24 @@ void CompactionIterator::NextFromInput() {
      if (valid_) {
        at_next_ = true;
      }
-    } else if (last_snapshot == current_user_key_snapshot_ ||
-               (last_snapshot > 0 &&
-                last_snapshot < current_user_key_snapshot_)) {
+    } else if (last_snapshot == current_user_key_snapshot_) {
      // If the earliest snapshot is which this key is visible in
      // is the same as the visibility of a previous instance of the
      // same key, then this kv is not visible in any snapshot.
      // Hidden by an newer entry for same user key
+      // TODO(noetzli): why not > ?
      //
      // Note: Dropping this key will not affect TransactionDB write-conflict
      // checking since there has already been a record returned for this key
      // in this snapshot.
      assert(last_sequence >= current_user_key_sequence_);
-
      ++iter_stats_.num_record_drop_hidden;  // (A)
      input_->Next();
    } else if (compaction_ != nullptr && ikey_.type == kTypeDeletion &&
-               IN_EARLIEST_SNAPSHOT(ikey_.sequence) &&
+               ikey_.sequence <= earliest_snapshot_ &&
+               (snapshot_checker_ == nullptr ||
+                LIKELY(snapshot_checker_->IsInSnapshot(ikey_.sequence,
+                                                       earliest_snapshot_))) &&
               ikeyNotNeededForIncrementalSnapshot() &&
               compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                          &level_ptrs_)) {
@@ -523,28 +502,6 @@ void CompactionIterator::NextFromInput() {
        ++iter_stats_.num_optimized_del_drop_obsolete;
      }
      input_->Next();
-    } else if ((ikey_.type == kTypeDeletion) && bottommost_level_ &&
-               ikeyNotNeededForIncrementalSnapshot()) {
-      // Handle the case where we have a delete key at the bottom most level
-      // We can skip outputting the key iff there are no subsequent puts for this
-      // key
-      ParsedInternalKey next_ikey;
-      input_->Next();
-      // Skip over all versions of this key that happen to occur in the same snapshot
-      // range as the delete
-      while (input_->Valid() && ParseInternalKey(input_->key(), &next_ikey) &&
-             cmp_->Equal(ikey_.user_key, next_ikey.user_key) &&
-             (prev_snapshot == 0 ||
-              DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot))) {
-        input_->Next();
-      }
-      // If you find you still need to output a row with this key, we need to output the
-      // delete too
-      if (input_->Valid() && ParseInternalKey(input_->key(), &next_ikey) &&
-          cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
-        valid_ = true;
-        at_next_ = true;
-      }
    } else if (ikey_.type == kTypeMerge) {
      if (!merge_helper_->HasOperator()) {
        status_ = Status::InvalidArgument(
@@ -594,7 +551,7 @@ void CompactionIterator::NextFromInput() {
      // 1. new user key -OR-
      // 2. different snapshot stripe
      bool should_delete = range_del_agg_->ShouldDelete(
-          key_, RangeDelPositioningMode::kForwardTraversal);
+          key_, RangeDelAggregator::RangePositioningMode::kForwardTraversal);
      if (should_delete) {
        ++iter_stats_.num_record_drop_hidden;
        ++iter_stats_.num_record_drop_range_del;
@@ -626,9 +583,14 @@ void CompactionIterator::PrepareOutput() {
  //
  // 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) {
+  if ((compaction_ != nullptr &&
+      !compaction_->allow_ingest_behind()) &&
+      ikeyNotNeededForIncrementalSnapshot() &&
+      bottommost_level_ && valid_ && ikey_.sequence <= earliest_snapshot_ &&
+      (snapshot_checker_ == nullptr || LIKELY(snapshot_checker_->IsInSnapshot(
+        ikey_.sequence, earliest_snapshot_))) &&
+      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);
@@ -638,34 +600,18 @@ void CompactionIterator::PrepareOutput() {
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
    SequenceNumber in, SequenceNumber* prev_snapshot) {
  assert(snapshots_->size());
-  auto snapshots_iter = std::lower_bound(
-      snapshots_->begin(), snapshots_->end(), in);
-  if (snapshots_iter == snapshots_->begin()) {
-    *prev_snapshot = 0;
-  } else {
-    *prev_snapshot = *std::prev(snapshots_iter);
-    assert(*prev_snapshot < in);
-  }
-  if (snapshot_checker_ == nullptr) {
-    return snapshots_iter != snapshots_->end()
-      ? *snapshots_iter : kMaxSequenceNumber;
-  }
-  bool has_released_snapshot = !released_snapshots_.empty();
-  for (; snapshots_iter != snapshots_->end(); ++snapshots_iter) {
-    auto cur = *snapshots_iter;
-    assert(in <= cur);
-    // Skip if cur is in released_snapshots.
-    if (has_released_snapshot && released_snapshots_.count(cur) > 0) {
-      continue;
-    }
-    auto res = snapshot_checker_->CheckInSnapshot(in, cur);
-    if (res == SnapshotCheckerResult::kInSnapshot) {
+  SequenceNumber prev = kMaxSequenceNumber;
+  for (const auto cur : *snapshots_) {
+    assert(prev == kMaxSequenceNumber || prev <= cur);
+    if (cur >= in && (snapshot_checker_ == nullptr ||
+                      snapshot_checker_->IsInSnapshot(in, cur))) {
+      *prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
      return cur;
-    } else if (res == SnapshotCheckerResult::kSnapshotReleased) {
-      released_snapshots_.insert(cur);
    }
-    *prev_snapshot = cur;
+    prev = cur;
+    assert(prev < kMaxSequenceNumber);
  }
+  *prev_snapshot = prev;
  return kMaxSequenceNumber;
 }

@@ -676,30 +622,4 @@ inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
         (ikey_.sequence < preserve_deletes_seqnum_);
 }

-bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
-  assert(snapshot_checker_ != nullptr);
-  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)) {
-    // Avoid the the current earliest_snapshot_ being return as
-    // earliest visible snapshot for the next value. So if a value's sequence
-    // is zero-ed out by PrepareOutput(), the next value will be compact out.
-    released_snapshots_.insert(earliest_snapshot_);
-    earliest_snapshot_iter_++;
-
-    if (earliest_snapshot_iter_ == snapshots_->end()) {
-      earliest_snapshot_ = kMaxSequenceNumber;
-    } else {
-      earliest_snapshot_ = *earliest_snapshot_iter_;
-    }
-    in_snapshot =
-        snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
-  }
-  assert(in_snapshot != SnapshotCheckerResult::kSnapshotReleased);
-  return in_snapshot == SnapshotCheckerResult::kInSnapshot;
-}
-
 }  // namespace rocksdb
@@ -7,11 +7,10 @@
 #include <algorithm>
 #include <deque>
 #include <string>
-#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"
@@ -21,53 +20,6 @@

 namespace rocksdb {

-// This callback can be used to refresh the snapshot list from the db. It
-// includes logics to exponentially decrease the refresh rate to limit the
-// overhead of refresh.
-class SnapshotListFetchCallback {
- public:
-  SnapshotListFetchCallback(Env* env, uint64_t snap_refresh_nanos,
-                            size_t every_nth_key = 1024)
-      : timer_(env, /*auto restart*/ true),
-        snap_refresh_nanos_(snap_refresh_nanos),
-        every_nth_key_minus_one_(every_nth_key - 1) {
-    assert(every_nth_key > 0);
-    assert((ceil(log2(every_nth_key)) == floor(log2(every_nth_key))));
-  }
-  // Refresh the snapshot list. snapshots will bre replacted with the new list.
-  // max is the upper bound. Note: this function will acquire the db_mutex_.
-  virtual void Refresh(std::vector<SequenceNumber>* snapshots,
-                       SequenceNumber max) = 0;
-  inline bool TimeToRefresh(const size_t key_index) {
-    // skip the key if key_index % every_nth_key (which is of power 2) is not 0.
-    if ((key_index & every_nth_key_minus_one_) != 0) {
-      return false;
-    }
-    const uint64_t elapsed = timer_.ElapsedNanos();
-    auto ret = elapsed > snap_refresh_nanos_;
-    // pre-compute the next time threshold
-    if (ret) {
-      // inc next refresh period exponentially (by x4)
-      auto next_refresh_threshold = snap_refresh_nanos_ << 2;
-      // make sure the shift has not overflown the highest 1 bit
-      snap_refresh_nanos_ =
-          std::max(snap_refresh_nanos_, next_refresh_threshold);
-    }
-    return ret;
-  }
-  static constexpr SnapshotListFetchCallback* kDisabled = nullptr;
-
-  virtual ~SnapshotListFetchCallback() {}
-
- private:
-  // Time since the callback was created
-  StopWatchNano timer_;
-  // The delay before calling ::Refresh. To be increased exponentially.
-  uint64_t snap_refresh_nanos_;
-  // Skip evey nth key. Number n if of power 2. The math will require n-1.
-  const uint64_t every_nth_key_minus_one_;
-};
-
 class CompactionIterator {
 public:
  // A wrapper around Compaction. Has a much smaller interface, only what
@@ -111,13 +63,12 @@ class CompactionIterator {
                     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,
+                     bool expect_valid_internal_key,
+                     RangeDelAggregator* 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,
-                     SnapshotListFetchCallback* snap_list_callback = nullptr);
+                     const SequenceNumber preserve_deletes_seqnum = 0);

  // Constructor with custom CompactionProxy, used for tests.
  CompactionIterator(InternalIterator* input, const Comparator* cmp,
@@ -125,13 +76,12 @@ class CompactionIterator {
                     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,
+                     bool expect_valid_internal_key,
+                     RangeDelAggregator* 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,
-                     SnapshotListFetchCallback* snap_list_callback = nullptr);
+                     const SequenceNumber preserve_deletes_seqnum = 0);

  ~CompactionIterator();

@@ -159,8 +109,6 @@ class CompactionIterator {
 private:
  // Processes the input stream to find the next output
  void NextFromInput();
-  // Process snapshots_ and assign related variables
-  void ProcessSnapshotList();

  // Do last preparations before presenting the output to the callee. At this
  // point this only zeroes out the sequence number if possible for better
@@ -184,31 +132,15 @@ class CompactionIterator {
  // or seqnum be zero-ed out even if all other conditions for it are met.
  inline bool ikeyNotNeededForIncrementalSnapshot();

-  inline bool KeyCommitted(SequenceNumber sequence) {
-    return snapshot_checker_ == nullptr ||
-           snapshot_checker_->CheckInSnapshot(sequence, kMaxSequenceNumber) ==
-               SnapshotCheckerResult::kInSnapshot;
-  }
-
-  bool IsInEarliestSnapshot(SequenceNumber sequence);
-
  InternalIterator* input_;
  const Comparator* cmp_;
  MergeHelper* merge_helper_;
-  std::vector<SequenceNumber>* snapshots_;
-  // List of snapshots released during compaction.
-  // findEarliestVisibleSnapshot() find them out from return of
-  // snapshot_checker, and make sure they will not be returned as
-  // earliest visible snapshot of an older value.
-  // See WritePreparedTransactionTest::ReleaseSnapshotDuringCompaction3.
-  std::unordered_set<SequenceNumber> released_snapshots_;
-  std::vector<SequenceNumber>::const_iterator earliest_snapshot_iter_;
+  const std::vector<SequenceNumber>* snapshots_;
  const SequenceNumber earliest_write_conflict_snapshot_;
  const SnapshotChecker* const snapshot_checker_;
  Env* env_;
-  bool report_detailed_time_;
  bool expect_valid_internal_key_;
-  CompactionRangeDelAggregator* range_del_agg_;
+  RangeDelAggregator* range_del_agg_;
  std::unique_ptr<CompactionProxy> compaction_;
  const CompactionFilter* compaction_filter_;
  const std::atomic<bool>* shutting_down_;
@@ -218,6 +150,7 @@ class CompactionIterator {
  bool visible_at_tip_;
  SequenceNumber earliest_snapshot_;
  SequenceNumber latest_snapshot_;
+  bool ignore_snapshots_;

  // State
  //
@@ -270,9 +203,6 @@ class CompactionIterator {
  // Used to avoid purging uncommitted values. The application can specify
  // uncommitted values by providing a SnapshotChecker object.
  bool current_key_committed_;
-  SnapshotListFetchCallback* snap_list_callback_;
-  // number of distinct keys processed
-  size_t num_keys_ = 0;

  bool IsShuttingDown() {
    // This is a best-effort facility, so memory_order_relaxed is sufficient.
@@ -3,15 +3,15 @@
 //  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 {
@@ -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;

@@ -188,17 +190,13 @@ class TestSnapshotChecker : public SnapshotChecker {
      : last_committed_sequence_(last_committed_sequence),
        snapshots_(snapshots) {}

-  SnapshotCheckerResult CheckInSnapshot(
-      SequenceNumber seq, SequenceNumber snapshot_seq) const override {
+  bool IsInSnapshot(SequenceNumber seq,
+                    SequenceNumber snapshot_seq) const override {
    if (snapshot_seq == kMaxSequenceNumber) {
-      return seq <= last_committed_sequence_
-                 ? SnapshotCheckerResult::kInSnapshot
-                 : SnapshotCheckerResult::kNotInSnapshot;
+      return seq <= last_committed_sequence_;
    }
    assert(snapshots_.count(snapshot_seq) > 0);
-    return seq <= snapshots_.at(snapshot_seq)
-               ? SnapshotCheckerResult::kInSnapshot
-               : SnapshotCheckerResult::kNotInSnapshot;
+    return seq <= snapshots_.at(snapshot_seq);
  }

 private:
@@ -223,15 +221,10 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
      MergeOperator* merge_op = nullptr, CompactionFilter* filter = nullptr,
      bool bottommost_level = false,
      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
-    std::unique_ptr<InternalIterator> unfragmented_range_del_iter(
+    std::unique_ptr<InternalIterator> range_del_iter(
        new test::VectorIterator(range_del_ks, range_del_vs));
-    auto tombstone_list = std::make_shared<FragmentedRangeTombstoneList>(
-        std::move(unfragmented_range_del_iter), icmp_);
-    std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
-        new FragmentedRangeTombstoneIterator(tombstone_list, icmp_,
-                                             kMaxSequenceNumber));
-    range_del_agg_.reset(new CompactionRangeDelAggregator(&icmp_, snapshots_));
-    range_del_agg_->AddTombstones(std::move(range_del_iter));
+    range_del_agg_.reset(new RangeDelAggregator(icmp_, snapshots_));
+    ASSERT_OK(range_del_agg_->AddTombstones(std::move(range_del_iter)));

    std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
    if (filter || bottommost_level) {
@@ -254,8 +247,8 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
    c_iter_.reset(new CompactionIterator(
        iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
        earliest_write_conflict_snapshot, snapshot_checker_.get(),
-        Env::Default(), false /* report_detailed_time */, false,
-        range_del_agg_.get(), std::move(compaction), filter, &shutting_down_));
+        Env::Default(), false, range_del_agg_.get(), std::move(compaction),
+        filter, &shutting_down_));
  }

  void AddSnapshot(SequenceNumber snapshot,
@@ -299,7 +292,7 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
  std::unique_ptr<MergeHelper> merge_helper_;
  std::unique_ptr<LoggingForwardVectorIterator> iter_;
  std::unique_ptr<CompactionIterator> c_iter_;
-  std::unique_ptr<CompactionRangeDelAggregator> range_del_agg_;
+  std::unique_ptr<RangeDelAggregator> range_del_agg_;
  std::unique_ptr<SnapshotChecker> snapshot_checker_;
  std::atomic<bool> shutting_down_{false};
  FakeCompaction* compaction_proxy_;
@@ -375,9 +368,10 @@ 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
@@ -557,9 +551,10 @@ 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();

@@ -676,12 +671,8 @@ TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
 TEST_P(CompactionIteratorTest, RemoveDeletionAtBottomLevel) {
  AddSnapshot(1);
  RunTest({test::KeyStr("a", 1, kTypeDeletion),
-           test::KeyStr("b", 3, kTypeDeletion),
-           test::KeyStr("b", 1, kTypeValue)},
-          {"", "", ""},
-          {test::KeyStr("b", 3, kTypeDeletion),
-           test::KeyStr("b", 0, kTypeValue)},
-          {"", ""},
+           test::KeyStr("b", 2, kTypeDeletion)},
+          {"", ""}, {test::KeyStr("b", 2, kTypeDeletion)}, {""},
          kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
          nullptr /*compaction_filter*/, true /*bottommost_level*/);
 }
@@ -850,26 +841,13 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
      {test::KeyStr("a", 1, kTypeDeletion), test::KeyStr("b", 2, kTypeDeletion),
       test::KeyStr("c", 3, kTypeDeletion)},
      {"", "", ""},
-      {},
+      {test::KeyStr("b", 2, kTypeDeletion),
+       test::KeyStr("c", 3, kTypeDeletion)},
      {"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
      nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
      true /*bottommost_level*/);
 }

-TEST_F(CompactionIteratorWithSnapshotCheckerTest,
-       NotRemoveDeletionIfValuePresentToEarlierSnapshot) {
-  AddSnapshot(2,1);
-  RunTest(
-      {test::KeyStr("a", 4, kTypeDeletion), test::KeyStr("a", 1, kTypeValue),
-          test::KeyStr("b", 3, kTypeValue)},
-      {"", "", ""},
-      {test::KeyStr("a", 4, kTypeDeletion), test::KeyStr("a", 0, kTypeValue),
-            test::KeyStr("b", 3, kTypeValue)},
-      {"", "", ""}, kMaxSequenceNumber /*last_commited_seq*/,
-      nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
-      true /*bottommost_level*/);
-}
-
 TEST_F(CompactionIteratorWithSnapshotCheckerTest,
       NotRemoveSingleDeletionIfNotVisibleToEarliestSnapshot) {
  AddSnapshot(2, 1);
@@ -7,7 +7,13 @@
 // 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_job.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
 #include <functional>
 #include <list>
@@ -19,11 +25,8 @@
 #include <vector>

 #include "db/builder.h"
-#include "db/compaction/compaction_job.h"
-#include "db/db_impl/db_impl.h"
 #include "db/db_iter.h"
 #include "db/dbformat.h"
-#include "db/error_handler.h"
 #include "db/event_helpers.h"
 #include "db/log_reader.h"
 #include "db/log_writer.h"
@@ -31,12 +34,7 @@
 #include "db/memtable_list.h"
 #include "db/merge_context.h"
 #include "db/merge_helper.h"
-#include "db/range_del_aggregator.h"
 #include "db/version_set.h"
-#include "file/filename.h"
-#include "file/sst_file_manager_impl.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"
@@ -46,17 +44,21 @@
 #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 {

@@ -92,8 +94,6 @@ const char* GetCompactionReasonString(CompactionReason compaction_reason) {
      return "Flush";
    case CompactionReason::kExternalSstIngestion:
      return "ExternalSstIngestion";
-    case CompactionReason::kPeriodicCompaction:
-      return "PeriodicCompaction";
    case CompactionReason::kNumOfReasons:
      // fall through
    default:
@@ -154,6 +154,7 @@ 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)
@@ -169,7 +170,8 @@ struct CompactionJob::SubcompactionState {
        approx_size(size),
        grandparent_index(0),
        overlapped_bytes(0),
-        seen_key(false) {
+        seen_key(false),
+        compression_dict() {
    assert(compaction != nullptr);
  }

@@ -192,10 +194,11 @@ struct CompactionJob::SubcompactionState {
    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;
  }

-  // Because member std::unique_ptrs do not have these.
+  // Because member unique_ptrs do not have these.
  SubcompactionState(const SubcompactionState&) = delete;

  SubcompactionState& operator=(const SubcompactionState&) = delete;
@@ -304,13 +307,12 @@ CompactionJob::CompactionJob(
    const std::atomic<bool>* shutting_down,
    const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
    Directory* db_directory, Directory* output_directory, Statistics* stats,
-    InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
+    InstrumentedMutex* db_mutex, Status* db_bg_error,
    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, SnapshotListFetchCallback* snap_list_callback)
+    const std::string& dbname, CompactionJobStats* compaction_job_stats)
    : job_id_(job_id),
      compact_(new CompactionState(compaction)),
      compaction_job_stats_(compaction_job_stats),
@@ -319,7 +321,7 @@ CompactionJob::CompactionJob(
      db_options_(db_options),
      env_options_(env_options),
      env_(db_options.env),
-      env_options_for_read_(
+      env_optiosn_for_read_(
          env_->OptimizeForCompactionTableRead(env_options, db_options_)),
      versions_(versions),
      shutting_down_(shutting_down),
@@ -329,9 +331,8 @@ CompactionJob::CompactionJob(
      output_directory_(output_directory),
      stats_(stats),
      db_mutex_(db_mutex),
-      db_error_handler_(db_error_handler),
+      db_bg_error_(db_bg_error),
      existing_snapshots_(std::move(existing_snapshots)),
-      snap_list_callback_(snap_list_callback),
      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
      snapshot_checker_(snapshot_checker),
      table_cache_(std::move(table_cache)),
@@ -339,8 +340,7 @@ 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,
@@ -410,13 +410,15 @@ 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++) {
@@ -424,8 +426,8 @@ 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);
  }
@@ -439,6 +441,11 @@ 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();
@@ -502,27 +509,17 @@ void CompactionJob::GenSubcompactionBoundaries() {
  // size of data covered by keys in that range
  uint64_t sum = 0;
  std::vector<RangeWithSize> ranges;
-  // Get input version from CompactionState since it's already referenced
-  // earlier in SetInputVersioCompaction::SetInputVersion and will not change
-  // when db_mutex_ is released below
-  auto* v = compact_->compaction->input_version();
+  auto* v = cfd->current();
  for (auto it = bounds.begin();;) {
    const Slice a = *it;
-    ++it;
+    it++;

    if (it == bounds.end()) {
      break;
    }

    const Slice b = *it;
-
-    // ApproximateSize could potentially create table reader iterator to seek
-    // 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(v, a, b, start_lvl, out_lvl + 1,
-                                               TableReaderCaller::kCompaction);
-    db_mutex_->Lock();
+    uint64_t size = versions_->ApproximateSize(v, a, b, start_lvl, out_lvl + 1);
    ranges.emplace_back(a, b, size);
    sum += size;
  }
@@ -594,18 +591,12 @@ Status CompactionJob::Run() {
    thread.join();
  }

-  compaction_stats_.micros = env_->NowMicros() - start_micros;
-  compaction_stats_.cpu_micros = 0;
-  for (size_t i = 0; i < compact_->sub_compact_states.size(); i++) {
-    compaction_stats_.cpu_micros +=
-        compact_->sub_compact_states[i].compaction_job_stats.cpu_micros;
+  if (output_directory_) {
+    output_directory_->Fsync();
  }

-  RecordTimeToHistogram(stats_, COMPACTION_TIME, compaction_stats_.micros);
-  RecordTimeToHistogram(stats_, COMPACTION_CPU_TIME,
-                        compaction_stats_.cpu_micros);
-
-  TEST_SYNC_POINT("CompactionJob::Run:BeforeVerify");
+  compaction_stats_.micros = env_->NowMicros() - start_micros;
+  MeasureTime(stats_, COMPACTION_TIME, compaction_stats_.micros);

  // Check if any thread encountered an error during execution
  Status status;
@@ -616,75 +607,6 @@ Status CompactionJob::Run() {
    }
  }

-  if (status.ok() && output_directory_) {
-    status = output_directory_->Fsync();
-  }
-
-  if (status.ok()) {
-    thread_pool.clear();
-    std::vector<const FileMetaData*> files_meta;
-    for (const auto& state : compact_->sub_compact_states) {
-      for (const auto& output : state.outputs) {
-        files_meta.emplace_back(&output.meta);
-      }
-    }
-    ColumnFamilyData* cfd = compact_->compaction->column_family_data();
-    auto prefix_extractor =
-        compact_->compaction->mutable_cf_options()->prefix_extractor.get();
-    std::atomic<size_t> next_file_meta_idx(0);
-    auto verify_table = [&](Status& output_status) {
-      while (true) {
-        size_t file_idx = next_file_meta_idx.fetch_add(1);
-        if (file_idx >= files_meta.size()) {
-          break;
-        }
-        // Verify that the table is usable
-        // We set for_compaction to false and don't OptimizeForCompactionTableRead
-        // here because this is a special case after we finish the table building
-        // No matter whether use_direct_io_for_flush_and_compaction is true,
-        // we will regard this verification as user reads since the goal is
-        // to cache it here for further user reads
-        InternalIterator* iter = cfd->table_cache()->NewIterator(
-            ReadOptions(), env_options_, cfd->internal_comparator(),
-            *files_meta[file_idx], /*range_del_agg=*/nullptr, prefix_extractor,
-            /*table_reader_ptr=*/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);
-        auto s = iter->status();
-
-        if (s.ok() && paranoid_file_checks_) {
-          for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {}
-          s = iter->status();
-        }
-
-        delete iter;
-
-        if (!s.ok()) {
-          output_status = s;
-          break;
-        }
-      }
-    };
-    for (size_t i = 1; i < compact_->sub_compact_states.size(); i++) {
-      thread_pool.emplace_back(verify_table,
-                               std::ref(compact_->sub_compact_states[i].status));
-    }
-    verify_table(compact_->sub_compact_states[0].status);
-    for (auto& thread : thread_pool) {
-      thread.join();
-    }
-    for (const auto& state : compact_->sub_compact_states) {
-      if (!state.status.ok()) {
-        status = state.status;
-        break;
-      }
-    }
-  }
-
  TablePropertiesCollection tp;
  for (const auto& state : compact_->sub_compact_states) {
    for (const auto& output : state.outputs) {
@@ -714,7 +636,7 @@ 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);
@@ -768,7 +690,6 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
  stream << "job" << job_id_ << "event"
         << "compaction_finished"
         << "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"
@@ -806,35 +727,11 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {

 void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  assert(sub_compact != nullptr);
-
-  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<RangeDelAggregator> range_del_agg(
+      new RangeDelAggregator(cfd->internal_comparator(), existing_snapshots_));
  std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
-      sub_compact->compaction, &range_del_agg, env_options_for_read_));
+      sub_compact->compaction, range_del_agg.get(), env_optiosn_for_read_));

  AutoThreadOperationStageUpdater stage_updater(
      ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -846,19 +743,55 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  uint64_t prev_fsync_nanos = 0;
  uint64_t prev_range_sync_nanos = 0;
  uint64_t prev_prepare_write_nanos = 0;
-  uint64_t prev_cpu_write_nanos = 0;
-  uint64_t prev_cpu_read_nanos = 0;
  if (measure_io_stats_) {
    prev_perf_level = GetPerfLevel();
-    SetPerfLevel(PerfLevel::kEnableTimeAndCPUTimeExceptForMutex);
+    SetPerfLevel(PerfLevel::kEnableTime);
    prev_write_nanos = IOSTATS(write_nanos);
    prev_fsync_nanos = IOSTATS(fsync_nanos);
    prev_range_sync_nanos = IOSTATS(range_sync_nanos);
    prev_prepare_write_nanos = IOSTATS(prepare_write_nanos);
-    prev_cpu_write_nanos = IOSTATS(cpu_write_nanos);
-    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 =
+      cfd->ioptions()->compression_opts.zstd_max_train_bytes > 0;
+  const size_t kSampleBytes =
+      kUseZstdTrainer ? cfd->ioptions()->compression_opts.zstd_max_train_bytes
+                      : cfd->ioptions()->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(),
@@ -883,11 +816,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  sub_compact->c_iter.reset(new CompactionIterator(
      input.get(), cfd->user_comparator(), &merge, versions_->LastSequence(),
      &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_,
-      // Currently range_del_agg is incompatible with snapshot refresh feature.
-      range_del_agg.IsEmpty() ? snap_list_callback_ : nullptr));
+      snapshot_checker_, env_, false, range_del_agg.get(),
+      sub_compact->compaction, compaction_filter, 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 +829,12 @@ 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()
@@ -933,6 +870,55 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
        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.
@@ -969,11 +955,22 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
        next_key = &c_iter->key();
      }
      CompactionIterationStats range_del_out_stats;
-      status =
-          FinishCompactionOutputFile(input_status, sub_compact, &range_del_agg,
-                                     &range_del_out_stats, next_key);
+      status = FinishCompactionOutputFile(input_status, sub_compact,
+                                          range_del_agg.get(),
+                                          &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,
+              cfd->ioptions()->compression_opts.max_dict_bytes);
+        } else {
+          sub_compact->compression_dict = std::move(dict_sample_data);
+        }
+      }
    }
  }

@@ -996,13 +993,10 @@ 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() &&
+      (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();
@@ -1012,7 +1006,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  }

  if (status.ok() && sub_compact->builder == nullptr &&
-      sub_compact->outputs.size() == 0 && !range_del_agg.IsEmpty()) {
+      sub_compact->outputs.size() == 0 &&
+      range_del_agg->ShouldAddTombstones(bottommost_level_)) {
    // handle subcompaction containing only range deletions
    status = OpenCompactionOutputFile(sub_compact);
  }
@@ -1021,17 +1016,14 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  // close the output file.
  if (sub_compact->builder != nullptr) {
    CompactionIterationStats range_del_out_stats;
-    Status s = FinishCompactionOutputFile(status, sub_compact, &range_del_agg,
-                                          &range_del_out_stats);
+    Status s = FinishCompactionOutputFile(
+        status, sub_compact, range_del_agg.get(), &range_del_out_stats);
    if (status.ok()) {
      status = s;
    }
    RecordDroppedKeys(range_del_out_stats, &sub_compact->compaction_job_stats);
  }

-  sub_compact->compaction_job_stats.cpu_micros =
-      env_->NowCPUNanos() / 1000 - prev_cpu_micros;
-
  if (measure_io_stats_) {
    sub_compact->compaction_job_stats.file_write_nanos +=
        IOSTATS(write_nanos) - prev_write_nanos;
@@ -1041,11 +1033,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
        IOSTATS(range_sync_nanos) - prev_range_sync_nanos;
    sub_compact->compaction_job_stats.file_prepare_write_nanos +=
        IOSTATS(prepare_write_nanos) - prev_prepare_write_nanos;
-    sub_compact->compaction_job_stats.cpu_micros -=
-        (IOSTATS(cpu_write_nanos) - prev_cpu_write_nanos +
-         IOSTATS(cpu_read_nanos) - prev_cpu_read_nanos) /
-        1000;
-    if (prev_perf_level != PerfLevel::kEnableTimeAndCPUTimeExceptForMutex) {
+    if (prev_perf_level != PerfLevel::kEnableTime) {
      SetPerfLevel(prev_perf_level);
    }
  }
@@ -1094,7 +1082,7 @@ void CompactionJob::RecordDroppedKeys(

 Status CompactionJob::FinishCompactionOutputFile(
    const Status& input_status, SubcompactionState* sub_compact,
-    CompactionRangeDelAggregator* range_del_agg,
+    RangeDelAggregator* range_del_agg,
    CompactionIterationStats* range_del_out_stats,
    const Slice* next_table_min_key /* = nullptr */) {
  AutoThreadOperationStageUpdater stage_updater(
@@ -1107,23 +1095,17 @@ Status CompactionJob::FinishCompactionOutputFile(
  uint64_t output_number = sub_compact->current_output()->meta.fd.GetNumber();
  assert(output_number != 0);

-  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-  const Comparator* ucmp = cfd->user_comparator();
-
  // Check for iterator errors
  Status s = input_status;
  auto meta = &sub_compact->current_output()->meta;
-  assert(meta != nullptr);
  if (s.ok()) {
    Slice lower_bound_guard, upper_bound_guard;
    std::string smallest_user_key;
    const Slice *lower_bound, *upper_bound;
-    bool lower_bound_from_sub_compact = false;
    if (sub_compact->outputs.size() == 1) {
      // For the first output table, include range tombstones before the min key
      // but after the subcompaction boundary.
      lower_bound = sub_compact->start;
-      lower_bound_from_sub_compact = true;
    } else if (meta->smallest.size() > 0) {
      // For subsequent output tables, only include range tombstones from min
      // key onwards since the previous file was extended to contain range
@@ -1135,145 +1117,18 @@ 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.
      upper_bound = sub_compact->end;
    }
-    auto earliest_snapshot = kMaxSequenceNumber;
-    if (existing_snapshots_.size() > 0) {
-      earliest_snapshot = existing_snapshots_[0];
-    }
-    bool has_overlapping_endpoints;
-    if (upper_bound != nullptr && meta->largest.size() > 0) {
-      has_overlapping_endpoints =
-          ucmp->Compare(meta->largest.user_key(), *upper_bound) == 0;
-    } else {
-      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
-    // fragments that are entirely out of range, so make sure that we do not
-    // include those.
-    if (lower_bound != nullptr) {
-      it->Seek(*lower_bound);
-    } else {
-      it->SeekToFirst();
-    }
-    for (; it->Valid(); it->Next()) {
-      auto tombstone = it->Tombstone();
-      if (upper_bound != nullptr) {
-        int cmp = ucmp->Compare(*upper_bound, tombstone.start_key_);
-        if ((has_overlapping_endpoints && cmp < 0) ||
-            (!has_overlapping_endpoints && cmp <= 0)) {
-          // Tombstones starting after upper_bound only need to be included in
-          // the next table. If the current SST ends before upper_bound, i.e.,
-          // `has_overlapping_endpoints == false`, we can also skip over range
-          // tombstones that start exactly at upper_bound. Such range tombstones
-          // will be included in the next file and are not relevant to the point
-          // keys or endpoints of the current file.
-          break;
-        }
-      }
-
-      if (bottommost_level_ && tombstone.seq_ <= earliest_snapshot) {
-        // TODO(andrewkr): tombstones that span multiple output files are
-        // counted for each compaction output file, so lots of double counting.
-        range_del_out_stats->num_range_del_drop_obsolete++;
-        range_del_out_stats->num_record_drop_obsolete++;
-        continue;
-      }
-
-      auto kv = tombstone.Serialize();
-      assert(lower_bound == nullptr ||
-             ucmp->Compare(*lower_bound, kv.second) < 0);
-      sub_compact->builder->Add(kv.first.Encode(), kv.second);
-      InternalKey smallest_candidate = std::move(kv.first);
-      if (lower_bound != nullptr &&
-          ucmp->Compare(smallest_candidate.user_key(), *lower_bound) <= 0) {
-        // Pretend the smallest key has the same user key as lower_bound
-        // (the max key in the previous table or subcompaction) in order for
-        // files to appear key-space partitioned.
-        //
-        // When lower_bound is chosen by a subcompaction, we know that
-        // subcompactions over smaller keys cannot contain any keys at
-        // lower_bound. We also know that smaller subcompactions exist, because
-        // otherwise the subcompaction woud be unbounded on the left. As a
-        // result, we know that no other files on the output level will contain
-        // actual keys at lower_bound (an output file may have a largest key of
-        // lower_bound@kMaxSequenceNumber, but this only indicates a large range
-        // tombstone was truncated). Therefore, it is safe to use the
-        // tombstone's sequence number, to ensure that keys at lower_bound at
-        // lower levels are covered by truncated tombstones.
-        //
-        // If lower_bound was chosen by the smallest data key in the file,
-        // choose lowest seqnum so this file's smallest internal key comes after
-        // the previous file's largest. The fake seqnum is OK because the read
-        // path's file-picking code only considers user key.
-        smallest_candidate = InternalKey(
-            *lower_bound, lower_bound_from_sub_compact ? tombstone.seq_ : 0,
-            kTypeRangeDeletion);
-      }
-      InternalKey largest_candidate = tombstone.SerializeEndKey();
-      if (upper_bound != nullptr &&
-          ucmp->Compare(*upper_bound, largest_candidate.user_key()) <= 0) {
-        // Pretend the largest key has the same user key as upper_bound (the
-        // min key in the following table or subcompaction) in order for files
-        // to appear key-space partitioned.
-        //
-        // Choose highest seqnum so this file's largest internal key comes
-        // before the next file's/subcompaction's smallest. The fake seqnum is
-        // OK because the read path's file-picking code only considers the user
-        // key portion.
-        //
-        // Note Seek() also creates InternalKey with (user_key,
-        // kMaxSequenceNumber), but with kTypeDeletion (0x7) instead of
-        // kTypeRangeDeletion (0xF), so the range tombstone comes before the
-        // Seek() key in InternalKey's ordering. So Seek() will look in the
-        // next file for the user key.
-        largest_candidate =
-            InternalKey(*upper_bound, kMaxSequenceNumber, kTypeRangeDeletion);
-      }
-#ifndef NDEBUG
-      SequenceNumber smallest_ikey_seqnum = kMaxSequenceNumber;
-      if (meta->smallest.size() > 0) {
-        smallest_ikey_seqnum = GetInternalKeySeqno(meta->smallest.Encode());
-      }
-#endif
-      meta->UpdateBoundariesForRange(smallest_candidate, largest_candidate,
-                                     tombstone.seq_,
-                                     cfd->internal_comparator());
-
-      // The smallest key in a file is used for range tombstone truncation, so
-      // it cannot have a seqnum of 0 (unless the smallest data key in a file
-      // has a seqnum of 0). Otherwise, the truncated tombstone may expose
-      // deleted keys at lower levels.
-      assert(smallest_ikey_seqnum == 0 ||
-             ExtractInternalKeyFooter(meta->smallest.Encode()) !=
-                 PackSequenceAndType(0, kTypeRangeDeletion));
-    }
+    range_del_agg->AddToBuilder(sub_compact->builder.get(), lower_bound,
+                                upper_bound, meta, range_del_out_stats,
+                                bottommost_level_);
    meta->marked_for_compaction = sub_compact->builder->NeedCompact();
  }
  const uint64_t current_entries = sub_compact->builder->NumEntries();
@@ -1299,12 +1154,7 @@ Status CompactionJob::FinishCompactionOutputFile(
  }
  sub_compact->outfile.reset();

-  TableProperties tp;
-  if (s.ok()) {
-    tp = sub_compact->builder->GetTableProperties();
-  }
-
-  if (s.ok() && current_entries == 0 && tp.num_range_deletions == 0) {
+  if (s.ok() && current_entries == 0) {
    // If there is nothing to output, no necessary to generate a sst file.
    // This happens when the output level is bottom level, at the same time
    // the sub_compact output nothing.
@@ -1317,19 +1167,51 @@ Status CompactionJob::FinishCompactionOutputFile(
    // VersionEdit.
    assert(!sub_compact->outputs.empty());
    sub_compact->outputs.pop_back();
-    meta = nullptr;
+    sub_compact->builder.reset();
+    sub_compact->current_output_file_size = 0;
+    return s;
  }

-  if (s.ok() && (current_entries > 0 || tp.num_range_deletions > 0)) {
+  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
+  TableProperties tp;
+  if (s.ok() && current_entries > 0) {
+    // Verify that the table is usable
+    // We set for_compaction to false and don't OptimizeForCompactionTableRead
+    // here because this is a special case after we finish the table building
+    // No matter whether use_direct_io_for_flush_and_compaction is true,
+    // we will regard this verification as user reads since the goal is
+    // to cache it here for further user reads
+    InternalIterator* iter = cfd->table_cache()->NewIterator(
+        ReadOptions(), env_options_, cfd->internal_comparator(), meta->fd,
+        nullptr /* range_del_agg */,
+        sub_compact->compaction->mutable_cf_options()->prefix_extractor.get(),
+        nullptr,
+        cfd->internal_stats()->GetFileReadHist(
+            compact_->compaction->output_level()),
+        false, nullptr /* arena */, false /* skip_filters */,
+        compact_->compaction->output_level());
+    s = iter->status();
+
+    if (s.ok() && paranoid_file_checks_) {
+      for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
+      }
+      s = iter->status();
+    }
+
+    delete iter;
+
    // Output to event logger and fire events.
-    sub_compact->current_output()->table_properties =
-        std::make_shared<TableProperties>(tp);
-    ROCKS_LOG_INFO(db_options_.info_log,
-                   "[%s] [JOB %d] Generated table #%" PRIu64 ": %" PRIu64
-                   " keys, %" PRIu64 " bytes%s",
-                   cfd->GetName().c_str(), job_id_, output_number,
-                   current_entries, current_bytes,
-                   meta->marked_for_compaction ? " (need compaction)" : "");
+    if (s.ok()) {
+      tp = sub_compact->builder->GetTableProperties();
+      sub_compact->current_output()->table_properties =
+          std::make_shared<TableProperties>(tp);
+      ROCKS_LOG_INFO(db_options_.info_log,
+                     "[%s] [JOB %d] Generated table #%" PRIu64 ": %" PRIu64
+                     " keys, %" PRIu64 " bytes%s",
+                     cfd->GetName().c_str(), job_id_, output_number,
+                     current_entries, current_bytes,
+                     meta->marked_for_compaction ? " (need compaction)" : "");
+    }
  }
  std::string fname;
  FileDescriptor output_fd;
@@ -1350,16 +1232,28 @@ Status CompactionJob::FinishCompactionOutputFile(
  auto sfm =
      static_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
  if (sfm && meta != nullptr && meta->fd.GetPathId() == 0) {
-    sfm->OnAddFile(fname);
+    auto fn =
+        TableFileName(sub_compact->compaction->immutable_cf_options()->cf_paths,
+                      meta->fd.GetNumber(), meta->fd.GetPathId());
+    sfm->OnAddFile(fn);
    if (sfm->IsMaxAllowedSpaceReached()) {
      // TODO(ajkr): should we return OK() if max space was reached by the final
      // compaction output file (similarly to how flush works when full)?
-      s = Status::SpaceLimit("Max allowed space was reached");
+      s = Status::NoSpace("Max allowed space was reached");
      TEST_SYNC_POINT(
          "CompactionJob::FinishCompactionOutputFile:"
          "MaxAllowedSpaceReached");
      InstrumentedMutexLock l(db_mutex_);
-      db_error_handler_->SetBGError(s, BackgroundErrorReason::kCompaction);
+      if (db_bg_error_->ok()) {
+        Status new_bg_error = s;
+        // may temporarily unlock and lock the mutex.
+        EventHelpers::NotifyOnBackgroundError(
+            cfd->ioptions()->listeners, BackgroundErrorReason::kCompaction,
+            &new_bg_error, db_mutex_);
+        if (!new_bg_error.ok()) {
+          *db_bg_error_ = new_bg_error;
+        }
+      }
    }
  }
 #endif
@@ -1436,7 +1330,7 @@ Status CompactionJob::OpenCompactionOutputFile(
      TableFileCreationReason::kCompaction);
 #endif  // !ROCKSDB_LITE
  // Make the output file
-  std::unique_ptr<WritableFile> writable_file;
+  unique_ptr<WritableFile> writable_file;
 #ifndef NDEBUG
  bool syncpoint_arg = env_options_.use_direct_writes;
  TEST_SYNC_POINT_CALLBACK("CompactionJob::OpenCompactionOutputFile",
@@ -1468,11 +1362,8 @@ Status CompactionJob::OpenCompactionOutputFile(
  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, env_options_,
-                             env_, db_options_.statistics.get(), listeners));
+  sub_compact->outfile.reset(new WritableFileWriter(
+      std::move(writable_file), env_options_, db_options_.statistics.get()));

  // If the Column family flag is to only optimize filters for hits,
  // we can skip creating filters if this is the bottommost_level where
@@ -1480,20 +1371,20 @@ Status CompactionJob::OpenCompactionOutputFile(
  bool skip_filters =
      cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;

-  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 latest_key_time =
+  uint64_t output_file_creation_time =
      sub_compact->compaction->MaxInputFileCreationTime();
-  if (latest_key_time == 0) {
-    latest_key_time = current_time;
+  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(
@@ -1501,11 +1392,9 @@ Status CompactionJob::OpenCompactionOutputFile(
      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, latest_key_time,
-      0 /* oldest_key_time */, sub_compact->compaction->max_output_file_size(),
-      current_time));
+      cfd->ioptions()->compression_opts,
+      sub_compact->compaction->output_level(), &sub_compact->compression_dict,
+      skip_filters, output_file_creation_time));
  LogFlush(db_options_.info_log);
  return s;
 }
@@ -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"
@@ -29,9 +29,8 @@
 #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 "options/cf_options.h"
 #include "port/port.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/compaction_job_stats.h"
@@ -41,13 +40,13 @@
 #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 {

 class Arena;
-class ErrorHandler;
 class MemTable;
 class SnapshotChecker;
 class TableCache;
@@ -55,27 +54,24 @@ 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 EnvOptions env_options, VersionSet* versions,
-      const std::atomic<bool>* shutting_down,
-      const SequenceNumber preserve_deletes_seqnum, 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, SnapshotListFetchCallback* snap_list_callback);
+  CompactionJob(int job_id, Compaction* compaction,
+                const ImmutableDBOptions& db_options,
+                const EnvOptions env_options, VersionSet* versions,
+                const std::atomic<bool>* shutting_down,
+                const SequenceNumber preserve_deletes_seqnum,
+                LogBuffer* log_buffer,
+                Directory* db_directory, Directory* output_directory,
+                Statistics* stats, InstrumentedMutex* db_mutex,
+                Status* db_bg_error,
+                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);

  ~CompactionJob();

@@ -85,28 +81,17 @@ 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.
@@ -118,7 +103,7 @@ class CompactionJob {

  Status FinishCompactionOutputFile(
      const Status& input_status, SubcompactionState* sub_compact,
-      CompactionRangeDelAggregator* range_del_agg,
+      RangeDelAggregator* range_del_agg,
      CompactionIterationStats* range_del_out_stats,
      const Slice* next_table_min_key = nullptr);
  Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
@@ -151,7 +136,7 @@ class CompactionJob {

  Env* env_;
  // env_option optimized for compaction table reads
-  EnvOptions env_options_for_read_;
+  EnvOptions env_optiosn_for_read_;
  VersionSet* versions_;
  const std::atomic<bool>* shutting_down_;
  const SequenceNumber preserve_deletes_seqnum_;
@@ -160,13 +145,12 @@ class CompactionJob {
  Directory* output_directory_;
  Statistics* stats_;
  InstrumentedMutex* db_mutex_;
-  ErrorHandler* db_error_handler_;
+  Status* db_bg_error_;
  // If there were two snapshots with seq numbers s1 and
  // s2 and s1 < s2, and if we find two instances of a key k1 then lies
  // entirely within s1 and s2, then the earlier version of k1 can be safely
  // deleted because that version is not visible in any snapshot.
  std::vector<SequenceNumber> existing_snapshots_;
-  SnapshotListFetchCallback* snap_list_callback_;

  // This is the earliest snapshot that could be used for write-conflict
  // checking by a transaction.  For any user-key newer than this snapshot, we
@@ -179,7 +163,6 @@ 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_;
@@ -188,7 +171,6 @@ 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
@@ -7,7 +7,11 @@
 // 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>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <algorithm>
 #include <iostream>
 #include <mutex>
@@ -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"
@@ -45,18 +47,20 @@
 #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)
@@ -94,7 +98,7 @@ class CompactionJobStatsTest : public testing::Test,
  CompactionJobStatsTest() : env_(Env::Default()) {
    env_->SetBackgroundThreads(1, Env::LOW);
    env_->SetBackgroundThreads(1, Env::HIGH);
-    dbname_ = test::PerThreadDBPath("compaction_job_stats_test");
+    dbname_ = test::TmpDir(env_) + "/compaction_job_stats_test";
    alternative_wal_dir_ = dbname_ + "/wal";
    Options options;
    options.create_if_missing = true;
@@ -109,7 +113,7 @@ class CompactionJobStatsTest : public testing::Test,
    Reopen(options);
  }

-  ~CompactionJobStatsTest() override {
+  ~CompactionJobStatsTest() {
    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
    rocksdb::SyncPoint::GetInstance()->LoadDependency({});
    rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -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);
@@ -5,26 +5,23 @@

 #ifndef ROCKSDB_LITE

-#include <cinttypes>
 #include <algorithm>
-#include <array>
 #include <map>
 #include <string>
 #include <tuple>

 #include "db/column_family.h"
-#include "db/compaction/compaction_job.h"
-#include "db/error_handler.h"
+#include "db/compaction_job.h"
 #include "db/version_set.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 {
@@ -70,19 +67,17 @@ class CompactionJobTest : public testing::Test {
 public:
  CompactionJobTest()
      : env_(Env::Default()),
-        dbname_(test::PerThreadDBPath("compaction_job_test")),
+        dbname_(test::TmpDir() + "/compaction_job_test"),
        db_options_(),
        mutable_cf_options_(cf_options_),
        table_cache_(NewLRUCache(50000, 16)),
        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_) {
+        mock_table_factory_(new mock::MockTableFactory()) {
    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
    db_options_.db_paths.emplace_back(dbname_,
                                      std::numeric_limits<uint64_t>::max());
@@ -175,7 +170,7 @@ 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);
@@ -197,26 +192,18 @@ 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();
-
    VersionEdit new_db;
    new_db.SetLogNumber(0);
    new_db.SetNextFile(2);
    new_db.SetLastSequence(0);

    const std::string manifest = DescriptorFileName(dbname_, 1);
-    std::unique_ptr<WritableFile> file;
+    unique_ptr<WritableFile> file;
    Status s = env_->NewWritableFile(
        manifest, &file, env_->OptimizeForManifestWrite(env_options_));
    ASSERT_OK(s);
-    std::unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), manifest, env_options_));
+    unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), env_options_));
    {
      log::Writer log(std::move(file_writer), 0, false);
      std::string record;
@@ -241,10 +228,7 @@ 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,
-      SnapshotListFetchCallback* snapshot_fetcher =
-          SnapshotListFetchCallback::kDisabled) {
+      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
    auto cfd = versions_->GetColumnFamilySet()->GetDefault();

    size_t num_input_files = 0;
@@ -261,9 +245,8 @@ class CompactionJobTest : public testing::Test {

    Compaction compaction(cfd->current()->storage_info(), *cfd->ioptions(),
                          *cfd->GetLatestMutableCFOptions(),
-                          compaction_input_files, output_level, 1024 * 1024,
-                          10 * 1024 * 1024, 0, kNoCompression,
-                          cfd->ioptions()->compression_opts, 0, {}, true);
+                          compaction_input_files, 1, 1024 * 1024,
+                          10 * 1024 * 1024, 0, kNoCompression, 0, {}, true);
    compaction.SetInputVersion(cfd->current());

    LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
@@ -271,13 +254,13 @@ class CompactionJobTest : public testing::Test {
    EventLogger event_logger(db_options_.info_log.get());
    // TODO(yiwu) add a mock snapshot checker and add test for it.
    SnapshotChecker* snapshot_checker = nullptr;
-    CompactionJob compaction_job(
-        0, &compaction, db_options_, env_options_, versions_.get(),
-        &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, snapshot_fetcher);
+    CompactionJob compaction_job(0, &compaction, db_options_, env_options_,
+                                 versions_.get(), &shutting_down_,
+                                 preserve_deletes_seqnum_, &log_buffer,
+                                 nullptr, nullptr, nullptr, &mutex_, &bg_error_,
+                                 snapshots, earliest_write_conflict_snapshot,
+                                 snapshot_checker, table_cache_, &event_logger,
+                                 false, false, dbname_, &compaction_job_stats_);
    VerifyInitializationOfCompactionJobStats(compaction_job_stats_);

    compaction_job.Prepare();
@@ -289,17 +272,15 @@ 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);
-        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);
-      }
+    if (expected_results.size() == 0) {
+      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, 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);
    }
  }

@@ -321,7 +302,7 @@ class CompactionJobTest : public testing::Test {
  ColumnFamilyData* cfd_;
  std::unique_ptr<CompactionFilter> compaction_filter_;
  std::shared_ptr<MergeOperator> merge_op_;
-  ErrorHandler error_handler_;
+  Status bg_error_;
 };

 TEST_F(CompactionJobTest, Simple) {
@@ -396,7 +377,7 @@ 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);
@@ -449,7 +430,7 @@ 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);
@@ -473,7 +454,8 @@ 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, kTypeMerge), "2"},
+                          {KeyStr("b", 1U, kTypeMerge), "1"}});

  SetLastSequence(5U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -500,7 +482,7 @@ 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, kTypeMerge), test::EncodeInt(2U)}});

  SetLastSequence(5U);
  auto files = cfd_->current()->storage_info()->LevelFiles(0);
@@ -763,7 +745,7 @@ TEST_F(CompactionJobTest, SingleDeleteZeroSeq) {
  AddMockFile(file2);

  auto expected_results = mock::MakeMockFile({
-      {KeyStr("dummy", 0U, kTypeValue), "val2"},
+      {KeyStr("dummy", 5U, kTypeValue), "val2"},
  });

  SetLastSequence(22U);
@@ -947,112 +929,13 @@ 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 the snapshot fetcher in compaction
-TEST_F(CompactionJobTest, SnapshotRefresh) {
-  uint64_t time_seed = env_->NowMicros();
-  printf("time_seed is %" PRIu64 "\n", time_seed);  // would help to reproduce
-  Random64 rand(time_seed);
-  std::vector<SequenceNumber> db_snapshots;
-  class SnapshotListFetchCallbackTest : public SnapshotListFetchCallback {
-   public:
-    SnapshotListFetchCallbackTest(Env* env, Random64& rand,
-                                  std::vector<SequenceNumber>* snapshots)
-        : SnapshotListFetchCallback(env, 0 /*no time delay*/,
-                                    1 /*fetch after each key*/),
-          rand_(rand),
-          snapshots_(snapshots) {}
-    virtual void Refresh(std::vector<SequenceNumber>* snapshots,
-                         SequenceNumber) override {
-      assert(snapshots->size());
-      assert(snapshots_->size());
-      assert(snapshots_->size() == snapshots->size());
-      if (rand_.OneIn(2)) {
-        uint64_t release_index = rand_.Uniform(snapshots_->size());
-        snapshots_->erase(snapshots_->begin() + release_index);
-        *snapshots = *snapshots_;
-      }
-    }
-
-   private:
-    Random64 rand_;
-    std::vector<SequenceNumber>* snapshots_;
-  } snapshot_fetcher(env_, rand, &db_snapshots);
-
-  std::vector<std::pair<const std::string, std::string>> file1_kvs, file2_kvs;
-  std::array<ValueType, 4> types = {kTypeValue, kTypeDeletion,
-                                    kTypeSingleDeletion};
-  SequenceNumber last_seq = 0;
-  for (int i = 1; i < 100; i++) {
-    SequenceNumber seq = last_seq + 1;
-    last_seq = seq;
-    if (rand.OneIn(2)) {
-      auto type = types[rand.Uniform(types.size())];
-      file1_kvs.push_back(
-          {test::KeyStr("k" + ToString(i), seq, type), "v" + ToString(i)});
-    }
-  }
-  auto file1 = mock::MakeMockFile(file1_kvs);
-  for (int i = 1; i < 100; i++) {
-    SequenceNumber seq = last_seq + 1;
-    last_seq++;
-    if (rand.OneIn(2)) {
-      auto type = types[rand.Uniform(types.size())];
-      file2_kvs.push_back(
-          {test::KeyStr("k" + ToString(i), seq, type), "v" + ToString(i)});
-    }
-  }
-  auto file2 = mock::MakeMockFile(file2_kvs);
-  for (SequenceNumber i = 1; i < last_seq + 1; i++) {
-    if (rand.OneIn(5)) {
-      db_snapshots.push_back(i);
-    }
-  }
-
-  const bool kVerify = true;
-  const int output_level_0 = 0;
-  NewDB();
-  AddMockFile(file1);
-  AddMockFile(file2);
-  SetLastSequence(last_seq);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  // put the output on L0 since it is easier to feed them again to the 2nd
-  // compaction
-  RunCompaction({files}, file1, db_snapshots, kMaxSequenceNumber,
-                output_level_0, !kVerify, &snapshot_fetcher);
-
-  // Now db_snapshots are changed. Run the compaction again without snapshot
-  // fetcher but with the updated snapshot list.
-  compaction_job_stats_.Reset();
-  files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, file1, db_snapshots, kMaxSequenceNumber,
-                output_level_0 + 1, !kVerify);
-  // The result should be what we get if we run compaction without snapshot
-  // fetcher on the updated list of snapshots
-  auto expected = mock_table_factory_->output();
-
-  NewDB();
-  AddMockFile(file1);
-  AddMockFile(file2);
-  SetLastSequence(last_seq);
-  files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected, db_snapshots, kMaxSequenceNumber,
-                output_level_0, !kVerify);
-  // The 2nd compaction above would get rid of useless delete markers. To get
-  // the output here exactly as what we got above after two compactions, we also
-  // run the compaction for 2nd time.
-  compaction_job_stats_.Reset();
-  files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected, db_snapshots, kMaxSequenceNumber,
-                output_level_0 + 1, !kVerify);
-}
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -7,21 +7,24 @@
 // 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 {

@@ -33,28 +36,23 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
  }
  return sum;
 }
-}  // anonymous namespace

 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) {
  size_t compact_bytes = static_cast<size_t>(level_files[0]->fd.file_size);
-  uint64_t compensated_compact_bytes = level_files[0]->compensated_file_size;
  size_t compact_bytes_per_del_file = port::kMaxSizet;
-  // Compaction range will be [0, span_len).
+  // 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 or maximum total compaction size is reached.
+  // pull in files until the amount of compaction work per deleted file begins
+  // increasing.
  size_t new_compact_bytes_per_del_file = 0;
  for (span_len = 1; span_len < level_files.size(); ++span_len) {
-    compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
-    compensated_compact_bytes += level_files[span_len]->compensated_file_size;
+    compact_bytes += 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 ||
-        compensated_compact_bytes > max_compaction_bytes) {
+        new_compact_bytes_per_del_file > compact_bytes_per_del_file) {
      break;
    }
    compact_bytes_per_del_file = new_compact_bytes_per_del_file;
@@ -71,6 +69,7 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
  }
  return false;
 }
+}  // anonymous namespace

 // Determine compression type, based on user options, level of the output
 // file and whether compression is disabled.
@@ -111,24 +110,6 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
  }
 }

-CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
-                                         const VersionStorageInfo* vstorage,
-                                         int level,
-                                         const bool enable_compression) {
-  if (!enable_compression) {
-    return ioptions.compression_opts;
-  }
-  // If bottommost_compression is set and we are compacting to the
-  // bottommost level then we should use the specified compression options
-  // for the bottmomost_compression.
-  if (ioptions.bottommost_compression != kDisableCompressionOption &&
-      level >= (vstorage->num_non_empty_levels() - 1) &&
-      ioptions.bottommost_compression_opts.enabled) {
-    return ioptions.bottommost_compression_opts;
-  }
-  return ioptions.compression_opts;
-}
-
 CompactionPicker::CompactionPicker(const ImmutableCFOptions& ioptions,
                                   const InternalKeyComparator* icmp)
    : ioptions_(ioptions), icmp_(icmp) {}
@@ -220,8 +201,7 @@ void CompactionPicker::GetRange(const std::vector<CompactionInputFiles>& inputs,

 bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
                                              VersionStorageInfo* vstorage,
-                                              CompactionInputFiles* inputs,
-                                              InternalKey** next_smallest) {
+                                              CompactionInputFiles* inputs) {
  // This isn't good compaction
  assert(!inputs->empty());

@@ -244,8 +224,7 @@ bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
    GetRange(*inputs, &smallest, &largest);
    inputs->clear();
    vstorage->GetOverlappingInputs(level, &smallest, &largest, &inputs->files,
-                                   hint_index, &hint_index, true,
-                                   next_smallest);
+                                   hint_index, &hint_index);
  } while (inputs->size() > old_size);

  // we started off with inputs non-empty and the previous loop only grew
@@ -318,29 +297,13 @@ Compaction* CompactionPicker::CompactFiles(
  // shouldn't have been released since.
  assert(!FilesRangeOverlapWithCompaction(input_files, output_level));

-  CompressionType compression_type;
-  if (compact_options.compression == kDisableCompressionOption) {
-    int base_level;
-    if (ioptions_.compaction_style == kCompactionStyleLevel) {
-      base_level = vstorage->base_level();
-    } else {
-      base_level = 1;
-    }
-    compression_type =
-        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
-                           output_level, base_level);
-  } else {
-    // TODO(ajkr): `CompactionOptions` offers configurable `CompressionType`
-    // without configurable `CompressionOptions`, which is inconsistent.
-    compression_type = compact_options.compression;
-  }
-  auto c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, input_files, output_level,
-      compact_options.output_file_size_limit,
-      mutable_cf_options.max_compaction_bytes, output_path_id, compression_type,
-      GetCompressionOptions(ioptions_, vstorage, output_level),
-      compact_options.max_subcompactions,
-      /* grandparents */ {}, true);
+  auto c =
+      new Compaction(vstorage, ioptions_, mutable_cf_options, input_files,
+                     output_level, compact_options.output_file_size_limit,
+                     mutable_cf_options.max_compaction_bytes, output_path_id,
+                     compact_options.compression,
+                     compact_options.max_subcompactions,
+                     /* grandparents */ {}, true);
  RegisterCompaction(c);
  return c;
 }
@@ -543,9 +506,9 @@ 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);

@@ -606,16 +569,12 @@ Compaction* CompactionPicker::CompactRange(

    Compaction* c = new Compaction(
        vstorage, ioptions_, mutable_cf_options, std::move(inputs),
-        output_level,
-        MaxFileSizeForLevel(mutable_cf_options, output_level,
-                            ioptions_.compaction_style),
-        /* max_compaction_bytes */ LLONG_MAX,
-        compact_range_options.target_path_id,
+        output_level, MaxFileSizeForLevel(mutable_cf_options, output_level,
+            ioptions_.compaction_style),
+        /* 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;
  }
@@ -654,54 +613,16 @@ Compaction* CompactionPicker::CompactRange(
      uint64_t s = inputs[i]->compensated_file_size;
      total += s;
      if (total >= limit) {
+        **compaction_end = inputs[i + 1]->smallest;
        covering_the_whole_range = false;
        inputs.files.resize(i + 1);
        break;
      }
    }
  }
-  assert(compact_range_options.target_path_id <
-         static_cast<uint32_t>(ioptions_.cf_paths.size()));
+  assert(output_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;
-      }
-    }
-  }
-
-  InternalKey key_storage;
-  InternalKey* next_smallest = &key_storage;
-  if (ExpandInputsToCleanCut(cf_name, vstorage, &inputs, &next_smallest) ==
-      false) {
+  if (ExpandInputsToCleanCut(cf_name, vstorage, &inputs) == false) {
    // manual compaction is now multi-threaded, so it can
    // happen that ExpandWhileOverlapping fails
    // we handle it higher in RunManualCompaction
@@ -709,10 +630,8 @@ Compaction* CompactionPicker::CompactRange(
    return nullptr;
  }

-  if (covering_the_whole_range || !next_smallest) {
+  if (covering_the_whole_range) {
    *compaction_end = nullptr;
-  } else {
-    **compaction_end = *next_smallest;
  }

  CompactionInputFiles output_level_inputs;
@@ -760,14 +679,12 @@ Compaction* CompactionPicker::CompactRange(
      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,
-      compact_range_options.target_path_id,
+          ioptions_.compaction_style, vstorage->base_level(),
+          ioptions_.level_compaction_dynamic_level_bytes),
+      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 */ 0, std::move(grandparents),
      /* is manual compaction */ true);

  TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);
@@ -936,11 +853,6 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
      }
    }
  }
-  if (RangeOverlapWithCompaction(smallestkey, largestkey, output_level)) {
-    return Status::Aborted(
-        "A running compaction is writing to the same output level in an "
-        "overlapping key range");
-  }
  return Status::OK();
 }

@@ -983,8 +895,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
  // any currently-existing files.
  for (auto file_num : *input_files) {
    bool found = false;
-    for (const auto& level_meta : cf_meta.levels) {
-      for (const auto& file_meta : level_meta.files) {
+    for (auto level_meta : cf_meta.levels) {
+      for (auto file_meta : level_meta.files) {
        if (file_num == TableFileNameToNumber(file_meta.name)) {
          if (file_meta.being_compacted) {
            return Status::Aborted("Specified compaction input file " +
@@ -1107,4 +1019,695 @@ bool CompactionPicker::GetOverlappingL0Files(
  return true;
 }

+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()),
+      /* 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();
+}
+
+#ifndef ROCKSDB_LITE
+bool FIFOCompactionPicker::NeedsCompaction(
+    const VersionStorageInfo* vstorage) const {
+  const int kLevel0 = 0;
+  return vstorage->CompactionScore(kLevel0) >= 1;
+}
+
+namespace {
+uint64_t GetTotalFilesSize(
+    const std::vector<FileMetaData*>& files) {
+  uint64_t total_size = 0;
+  for (const auto& f : files) {
+    total_size += f->fd.file_size;
+  }
+  return total_size;
+}
+}  // anonymous namespace
+
+Compaction* FIFOCompactionPicker::PickTTLCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  assert(mutable_cf_options.compaction_options_fifo.ttl > 0);
+
+  const int kLevel0 = 0;
+  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  uint64_t total_size = GetTotalFilesSize(level_files);
+
+  int64_t _current_time;
+  auto status = ioptions_.env->GetCurrentTime(&_current_time);
+  if (!status.ok()) {
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: Couldn't get current time: %s. "
+                     "Not doing compactions based on TTL. ",
+                     cf_name.c_str(), status.ToString().c_str());
+    return nullptr;
+  }
+  const uint64_t current_time = static_cast<uint64_t>(_current_time);
+
+  std::vector<CompactionInputFiles> inputs;
+  inputs.emplace_back();
+  inputs[0].level = 0;
+
+  // avoid underflow
+  if (current_time > mutable_cf_options.compaction_options_fifo.ttl) {
+    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
+      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);
+      }
+    }
+  }
+
+  // Return a nullptr and proceed to size-based FIFO compaction if:
+  // 1. there are no files older than ttl OR
+  // 2. there are a few files older than ttl, but deleting them will not bring
+  //    the total size to be less than max_table_files_size threshold.
+  if (inputs[0].files.empty() ||
+      total_size >
+          mutable_cf_options.compaction_options_fifo.max_table_files_size) {
+    return nullptr;
+  }
+
+  for (const auto& f : inputs[0].files) {
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: picking file %" PRIu64
+                     " with creation time %" PRIu64 " for deletion",
+                     cf_name.c_str(), f->fd.GetNumber(),
+                     f->fd.table_reader->GetTableProperties()->creation_time);
+  }
+
+  Compaction* c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
+      kNoCompression, /* max_subcompactions */ 0, {}, /* is manual */ false,
+      vstorage->CompactionScore(0), /* is deletion compaction */ true,
+      CompactionReason::kFIFOTtl);
+  return c;
+}
+
+Compaction* FIFOCompactionPicker::PickSizeCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  const int kLevel0 = 0;
+  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  uint64_t total_size = GetTotalFilesSize(level_files);
+
+  if (total_size <=
+          mutable_cf_options.compaction_options_fifo.max_table_files_size ||
+      level_files.size() == 0) {
+    // total size not exceeded
+    if (mutable_cf_options.compaction_options_fifo.allow_compaction &&
+        level_files.size() > 0) {
+      CompactionInputFiles comp_inputs;
+      // try to prevent same files from being compacted multiple times, which
+      // could produce large files that may never TTL-expire. Achieve this by
+      // disallowing compactions with files larger than memtable (inflate its
+      // size by 10% to account for uncompressed L0 files that may have size
+      // slightly greater than memtable size limit).
+      size_t max_compact_bytes_per_del_file =
+          static_cast<size_t>(MultiplyCheckOverflow(
+              static_cast<uint64_t>(mutable_cf_options.write_buffer_size),
+              1.1));
+      if (FindIntraL0Compaction(
+              level_files,
+              mutable_cf_options
+                  .level0_file_num_compaction_trigger /* min_files_to_compact */
+              ,
+              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 */,
+            0 /* max compaction bytes, not applicable */,
+            0 /* output path ID */, mutable_cf_options.compression,
+            0 /* max_subcompactions */, {}, /* is manual */ false,
+            vstorage->CompactionScore(0), /* is deletion compaction */ false,
+            CompactionReason::kFIFOReduceNumFiles);
+        return c;
+      }
+    }
+
+    ROCKS_LOG_BUFFER(
+        log_buffer,
+        "[%s] FIFO compaction: nothing to do. Total size %" PRIu64
+        ", max size %" PRIu64 "\n",
+        cf_name.c_str(), total_size,
+        mutable_cf_options.compaction_options_fifo.max_table_files_size);
+    return nullptr;
+  }
+
+  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;
+
+  for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
+    auto f = *ritr;
+    total_size -= f->compensated_file_size;
+    inputs[0].files.push_back(f);
+    char tmp_fsize[16];
+    AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: picking file %" PRIu64
+                     " with size %s for deletion",
+                     cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
+    if (total_size <=
+        mutable_cf_options.compaction_options_fifo.max_table_files_size) {
+      break;
+    }
+  }
+
+  Compaction* c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
+      kNoCompression, /* max_subcompactions */ 0, {}, /* is manual */ false,
+      vstorage->CompactionScore(0), /* is deletion compaction */ true,
+      CompactionReason::kFIFOMaxSize);
+  return c;
+}
+
+Compaction* FIFOCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  assert(vstorage->num_levels() == 1);
+
+  Compaction* c = nullptr;
+  if (mutable_cf_options.compaction_options_fifo.ttl > 0) {
+    c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
+  }
+  if (c == nullptr) {
+    c = PickSizeCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
+  }
+  RegisterCompaction(c);
+  return c;
+}
+
+Compaction* FIFOCompactionPicker::CompactRange(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, int input_level, int output_level,
+    uint32_t /*output_path_id*/, uint32_t /*max_subcompactions*/,
+    const InternalKey* /*begin*/, const InternalKey* /*end*/,
+    InternalKey** compaction_end, bool* /*manual_conflict*/) {
+#ifdef NDEBUG
+  (void)input_level;
+  (void)output_level;
+#endif
+  assert(input_level == 0);
+  assert(output_level == 0);
+  *compaction_end = nullptr;
+  LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, ioptions_.info_log);
+  Compaction* c =
+      PickCompaction(cf_name, mutable_cf_options, vstorage, &log_buffer);
+  log_buffer.FlushBufferToLog();
+  return c;
+}
+
+#endif  // !ROCKSDB_LITE
+
 }  // namespace rocksdb
@@ -15,7 +15,7 @@
 #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"
@@ -24,26 +24,11 @@

 namespace rocksdb {

-// The file contains an abstract class CompactionPicker, and its two
-// sub-classes LevelCompactionPicker and NullCompactionPicker, as
-// well as some helper functions used by them.
-
 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,
@@ -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; }
@@ -167,8 +151,7 @@ class CompactionPicker {
  // Will return false if it is impossible to apply this compaction.
  bool ExpandInputsToCleanCut(const std::string& cf_name,
                              VersionStorageInfo* vstorage,
-                              CompactionInputFiles* inputs,
-                              InternalKey** next_smallest = nullptr);
+                              CompactionInputFiles* inputs);

  // Returns true if any one of the parent files are being compacted
  bool IsRangeInCompaction(VersionStorageInfo* vstorage,
@@ -236,9 +219,57 @@ 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 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) override;
+
+  virtual Compaction* CompactRange(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, int input_level, int output_level,
+      uint32_t output_path_id, uint32_t max_subcompactions,
+      const InternalKey* begin, const InternalKey* end,
+      InternalKey** compaction_end, bool* manual_conflict) override;
+
+  // The maximum allowed output level.  Always returns 0.
+  virtual int MaxOutputLevel() const override { return 0; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+
+ private:
+  Compaction* PickTTLCompaction(const std::string& cf_name,
+                                const MutableCFOptions& mutable_cf_options,
+                                VersionStorageInfo* version,
+                                LogBuffer* log_buffer);
+
+  Compaction* PickSizeCompaction(const std::string& cf_name,
+                                 const MutableCFOptions& mutable_cf_options,
+                                 VersionStorageInfo* version,
+                                 LogBuffer* log_buffer);
+};
+
 class NullCompactionPicker : public CompactionPicker {
 public:
  NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -259,12 +290,12 @@ 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;
  }

@@ -276,37 +307,10 @@ 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);
-
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
                                   const VersionStorageInfo* vstorage,
                                   const MutableCFOptions& mutable_cf_options,
                                   int level, int base_level,
                                   const bool enable_compression = true);

-CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
-                                         const VersionStorageInfo* vstorage,
-                                         int level,
-                                         const bool enable_compression = true);
-
 }  // namespace rocksdb
@@ -3,26 +3,26 @@
 //  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_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 {

 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;
 };

@@ -57,16 +57,14 @@ class CompactionPickerTest : public testing::Test {
        log_buffer_(InfoLogLevel::INFO_LEVEL, &logger_),
        file_num_(1),
        vstorage_(nullptr) {
-    // ioptions_.compaction_pri = kMinOverlappingRatio has its own set of
-    // tests to cover.
-    ioptions_.compaction_pri = kByCompensatedSize;
    fifo_options_.max_table_files_size = 1;
    mutable_cf_options_.RefreshDerivedOptions(ioptions_);
    ioptions_.cf_paths.emplace_back("dummy",
                                    std::numeric_limits<uint64_t>::max());
  }

-  ~CompactionPickerTest() override {}
+  ~CompactionPickerTest() {
+  }

  void NewVersionStorage(int num_levels, CompactionStyle style) {
    DeleteVersionStorage();
@@ -85,17 +83,16 @@ class CompactionPickerTest : public testing::Test {

  void Add(int level, uint32_t file_number, const char* smallest,
           const char* largest, uint64_t file_size = 1, uint32_t path_id = 0,
-           SequenceNumber smallest_seq = 100, SequenceNumber largest_seq = 100,
-           size_t compensated_file_size = 0) {
+           SequenceNumber smallest_seq = 100,
+           SequenceNumber largest_seq = 100) {
    assert(level < vstorage_->num_levels());
    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->smallest_seqno = smallest_seq;
+    f->largest_seqno = largest_seq;
+    f->compensated_file_size = file_size;
    f->refs = 0;
    vstorage_->AddFile(level, f);
    files_.emplace_back(f);
@@ -618,35 +615,6 @@ TEST_F(CompactionPickerTest, CompactionPriMinOverlapping3) {
  ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
 }

-TEST_F(CompactionPickerTest, CompactionPriMinOverlapping4) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.max_bytes_for_level_base = 10000000;
-  mutable_cf_options_.max_bytes_for_level_multiplier = 10;
-
-  // file 7 and 8 over lap with the same file, but file 8 is smaller so
-  // it will be picked.
-  // Overlaps with file 26, 27. And the file is compensated so will be
-  // picked up.
-  Add(2, 6U, "150", "167", 60000000U, 0, 100, 100, 180000000U);
-  Add(2, 7U, "168", "169", 60000000U);  // Overlaps with file 27
-  Add(2, 8U, "201", "300", 61000000U);  // Overlaps with file 28
-
-  Add(3, 26U, "160", "165", 60000000U);
-  // Boosted file size in output level is not considered.
-  Add(3, 27U, "166", "170", 60000000U, 0, 100, 100, 260000000U);
-  Add(3, 28U, "180", "400", 60000000U);
-  Add(3, 29U, "401", "500", 60000000U);
-  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_files(0));
-  // Picking file 8 because overlapping ratio is the biggest.
-  ASSERT_EQ(6U, compaction->input(0, 0)->fd.GetNumber());
-}
-
 // This test exhibits the bug where we don't properly reset parent_index in
 // PickCompaction()
 TEST_F(CompactionPickerTest, ParentIndexResetBug) {
@@ -1478,65 +1446,6 @@ 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);
-  Add(0, 2U, "151", "200", 200000U);
-  Add(0, 3U, "201", "250", 200000U);
-  Add(0, 4U, "251", "300", 200000U);
-  Add(0, 5U, "301", "350", 200000U);
-  Add(1, 6U, "100", "350", 200000U);
-  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(0U, 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);
-  Add(0, 2U, "151", "200", 200000U);
-  Add(0, 3U, "201", "250", 200000U);
-  Add(0, 4U, "251", "300", 200000U);
-  Add(0, 5U, "301", "350", 200000U);
-  Add(1, 6U, "100", "350", 200000U);
-  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(0U, compaction->output_level());
-}
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -7,21 +7,25 @@
 // 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_universal.h"
+#include "db/compaction_picker_universal.h"
 #ifndef ROCKSDB_LITE

-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <limits>
 #include <queue>
 #include <string>
 #include <utility>
 #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 {
@@ -93,17 +97,17 @@ void GetSmallestLargestSeqno(const std::vector<FileMetaData*>& files,
                             SequenceNumber* largest_seqno) {
  bool is_first = true;
  for (FileMetaData* f : files) {
-    assert(f->fd.smallest_seqno <= f->fd.largest_seqno);
+    assert(f->smallest_seqno <= f->largest_seqno);
    if (is_first) {
      is_first = false;
-      *smallest_seqno = f->fd.smallest_seqno;
-      *largest_seqno = f->fd.largest_seqno;
+      *smallest_seqno = f->smallest_seqno;
+      *largest_seqno = f->largest_seqno;
    } else {
-      if (f->fd.smallest_seqno < *smallest_seqno) {
-        *smallest_seqno = f->fd.smallest_seqno;
+      if (f->smallest_seqno < *smallest_seqno) {
+        *smallest_seqno = f->smallest_seqno;
      }
-      if (f->fd.largest_seqno > *largest_seqno) {
-        *largest_seqno = f->fd.largest_seqno;
+      if (f->largest_seqno > *largest_seqno) {
+        *largest_seqno = f->largest_seqno;
      }
    }
  }
@@ -361,11 +365,11 @@ Compaction* UniversalCompactionPicker::PickCompaction(
  size_t level_index = 0U;
  if (c->start_level() == 0) {
    for (auto f : *c->inputs(0)) {
-      assert(f->fd.smallest_seqno <= f->fd.largest_seqno);
+      assert(f->smallest_seqno <= f->largest_seqno);
      if (is_first) {
        is_first = false;
      }
-      prev_smallest_seqno = f->fd.smallest_seqno;
+      prev_smallest_seqno = f->smallest_seqno;
    }
    level_index = 1U;
  }
@@ -391,8 +395,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
  }
 #endif
  // update statistics
-  RecordInHistogram(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
-                    c->inputs(0)->size());
+  MeasureTime(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
+              c->inputs(0)->size());

  RegisterCompaction(c);
  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
@@ -632,8 +636,6 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
      LLONG_MAX, path_id,
      GetCompressionType(ioptions_, vstorage, mutable_cf_options, start_level,
                         1, enable_compression),
-      GetCompressionOptions(ioptions_, vstorage, start_level,
-                            enable_compression),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
      score, false /* deletion_compaction */, compaction_reason);
 }
@@ -657,10 +659,6 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
  size_t start_index = 0;
  const SortedRun* sr = nullptr;

-  if (sorted_runs.back().being_compacted) {
-    return nullptr;
-  }
-
  // Skip files that are already being compacted
  for (size_t loop = 0; loop < sorted_runs.size() - 1; loop++) {
    sr = &sorted_runs[loop];
@@ -767,13 +765,12 @@ Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
  }

  return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
-      MaxFileSizeForLevel(mutable_cf_options, output_level,
-                          kCompactionStyleUniversal),
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs),
+      output_level, MaxFileSizeForLevel(mutable_cf_options, output_level,
+          kCompactionStyleUniversal),
      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
-                         1),
-      GetCompressionOptions(ioptions_, vstorage, output_level),
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options,
+                         output_level, 1),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
      score, false /* deletion_compaction */,
      CompactionReason::kUniversalSizeAmplification);
@@ -893,7 +890,6 @@ Compaction* UniversalCompactionPicker::PickDeleteTriggeredCompaction(
      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                         1),
-      GetCompressionOptions(ioptions_, vstorage, output_level),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ true,
      score, false /* deletion_compaction */,
      CompactionReason::kFilesMarkedForCompaction);
@@ -10,7 +10,7 @@
 #pragma once
 #ifndef ROCKSDB_LITE

-#include "db/compaction/compaction_picker.h"
+#include "db/compaction_picker.h"

 namespace rocksdb {
 class UniversalCompactionPicker : public CompactionPicker {
@@ -9,11 +9,11 @@
 #include "memtable/stl_wrappers.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/hash.h"
 #include "util/kv_map.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
 #include "utilities/merge_operators.h"

 using std::unique_ptr;
@@ -27,24 +27,24 @@ class KVIter : public Iterator {
 public:
  explicit KVIter(const stl_wrappers::KVMap* map)
      : map_(map), iter_(map_->end()) {}
-  bool Valid() const override { return iter_ != map_->end(); }
-  void SeekToFirst() override { iter_ = map_->begin(); }
-  void SeekToLast() override {
+  virtual bool Valid() const override { return iter_ != map_->end(); }
+  virtual void SeekToFirst() override { iter_ = map_->begin(); }
+  virtual void SeekToLast() override {
    if (map_->empty()) {
      iter_ = map_->end();
    } else {
      iter_ = map_->find(map_->rbegin()->first);
    }
  }
-  void Seek(const Slice& k) override {
+  virtual void Seek(const Slice& k) override {
    iter_ = map_->lower_bound(k.ToString());
  }
-  void SeekForPrev(const Slice& k) override {
+  virtual void SeekForPrev(const Slice& k) override {
    iter_ = map_->upper_bound(k.ToString());
    Prev();
  }
-  void Next() override { ++iter_; }
-  void Prev() override {
+  virtual void Next() override { ++iter_; }
+  virtual void Prev() override {
    if (iter_ == map_->begin()) {
      iter_ = map_->end();
      return;
@@ -52,9 +52,9 @@ class KVIter : public Iterator {
    --iter_;
  }

-  Slice key() const override { return iter_->first; }
-  Slice value() const override { return iter_->second; }
-  Status status() const override { return Status::OK(); }
+  virtual Slice key() const override { return iter_->first; }
+  virtual Slice value() const override { return iter_->second; }
+  virtual Status status() const override { return Status::OK(); }

 private:
  const stl_wrappers::KVMap* const map_;
@@ -171,9 +171,9 @@ class DoubleComparator : public Comparator {
 public:
  DoubleComparator() {}

-  const char* Name() const override { return "DoubleComparator"; }
+  virtual const char* Name() const override { return "DoubleComparator"; }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
 #ifndef CYGWIN
    double da = std::stod(a.ToString());
    double db = std::stod(b.ToString());
@@ -189,19 +189,19 @@ class DoubleComparator : public Comparator {
      return -1;
    }
  }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}

-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };

 class HashComparator : public Comparator {
 public:
  HashComparator() {}

-  const char* Name() const override { return "HashComparator"; }
+  virtual const char* Name() const override { return "HashComparator"; }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
    uint32_t ha = Hash(a.data(), a.size(), 66);
    uint32_t hb = Hash(b.data(), b.size(), 66);
    if (ha == hb) {
@@ -212,19 +212,19 @@ class HashComparator : public Comparator {
      return -1;
    }
  }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}

-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };

 class TwoStrComparator : public Comparator {
 public:
  TwoStrComparator() {}

-  const char* Name() const override { return "TwoStrComparator"; }
+  virtual const char* Name() const override { return "TwoStrComparator"; }

-  int Compare(const Slice& a, const Slice& b) const override {
+  virtual int Compare(const Slice& a, const Slice& b) const override {
    assert(a.size() >= 2);
    assert(b.size() >= 2);
    size_t size_a1 = static_cast<size_t>(a[0]);
@@ -244,16 +244,14 @@ class TwoStrComparator : public Comparator {
    }
    return a2.compare(b2);
  }
-  void FindShortestSeparator(std::string* /*start*/,
-                             const Slice& /*limit*/) const override {}
+  virtual void FindShortestSeparator(std::string* /*start*/,
+                                     const Slice& /*limit*/) const override {}

-  void FindShortSuccessor(std::string* /*key*/) const override {}
+  virtual void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 }  // namespace

-class ComparatorDBTest
-    : public testing::Test,
-      virtual public ::testing::WithParamInterface<uint32_t> {
+class ComparatorDBTest : public testing::Test {
 private:
  std::string dbname_;
  Env* env_;
@@ -264,15 +262,11 @@ class ComparatorDBTest
 public:
  ComparatorDBTest() : env_(Env::Default()), db_(nullptr) {
    comparator = BytewiseComparator();
-    dbname_ = test::PerThreadDBPath("comparator_db_test");
-    BlockBasedTableOptions toptions;
-    toptions.format_version = GetParam();
-    last_options_.table_factory.reset(
-        rocksdb::NewBlockBasedTableFactory(toptions));
+    dbname_ = test::TmpDir() + "/comparator_db_test";
    EXPECT_OK(DestroyDB(dbname_, last_options_));
  }

-  ~ComparatorDBTest() override {
+  ~ComparatorDBTest() {
    delete db_;
    EXPECT_OK(DestroyDB(dbname_, last_options_));
    comparator = BytewiseComparator();
@@ -280,12 +274,8 @@ class ComparatorDBTest

  DB* GetDB() { return db_; }

-  void SetOwnedComparator(const Comparator* cmp, bool owner = true) {
-    if (owner) {
-      comparator_guard.reset(cmp);
-    } else {
-      comparator_guard.reset();
-    }
+  void SetOwnedComparator(const Comparator* cmp) {
+    comparator_guard.reset(cmp);
    comparator = cmp;
    last_options_.comparator = cmp;
  }
@@ -314,12 +304,7 @@ class ComparatorDBTest
  }
 };

-INSTANTIATE_TEST_CASE_P(FormatDef, ComparatorDBTest,
-                        testing::Values(test::kDefaultFormatVersion));
-INSTANTIATE_TEST_CASE_P(FormatLatest, ComparatorDBTest,
-                        testing::Values(test::kLatestFormatVersion));
-
-TEST_P(ComparatorDBTest, Bytewise) {
+TEST_F(ComparatorDBTest, Bytewise) {
  for (int rand_seed = 301; rand_seed < 306; rand_seed++) {
    DestroyAndReopen();
    Random rnd(rand_seed);
@@ -329,7 +314,7 @@ TEST_P(ComparatorDBTest, Bytewise) {
  }
 }

-TEST_P(ComparatorDBTest, SimpleSuffixReverseComparator) {
+TEST_F(ComparatorDBTest, SimpleSuffixReverseComparator) {
  SetOwnedComparator(new test::SimpleSuffixReverseComparator());

  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -355,8 +340,8 @@ TEST_P(ComparatorDBTest, SimpleSuffixReverseComparator) {
  }
 }

-TEST_P(ComparatorDBTest, Uint64Comparator) {
-  SetOwnedComparator(test::Uint64Comparator(), false /* owner */);
+TEST_F(ComparatorDBTest, Uint64Comparator) {
+  SetOwnedComparator(test::Uint64Comparator());

  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
    Options* opt = GetOptions();
@@ -379,7 +364,7 @@ TEST_P(ComparatorDBTest, Uint64Comparator) {
  }
 }

-TEST_P(ComparatorDBTest, DoubleComparator) {
+TEST_F(ComparatorDBTest, DoubleComparator) {
  SetOwnedComparator(new DoubleComparator());

  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -404,7 +389,7 @@ TEST_P(ComparatorDBTest, DoubleComparator) {
  }
 }

-TEST_P(ComparatorDBTest, HashComparator) {
+TEST_F(ComparatorDBTest, HashComparator) {
  SetOwnedComparator(new HashComparator());

  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -423,7 +408,7 @@ TEST_P(ComparatorDBTest, HashComparator) {
  }
 }

-TEST_P(ComparatorDBTest, TwoStrComparator) {
+TEST_F(ComparatorDBTest, TwoStrComparator) {
  SetOwnedComparator(new TwoStrComparator());

  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
@@ -449,71 +434,7 @@ TEST_P(ComparatorDBTest, TwoStrComparator) {
  }
 }

-TEST_P(ComparatorDBTest, IsSameLengthImmediateSuccessor) {
-  {
-    // different length
-    Slice s("abcxy");
-    Slice t("abcxyz");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    Slice s("abcxyz");
-    Slice t("abcxy");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    // not last byte different
-    Slice s("abc1xyz");
-    Slice t("abc2xyz");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    // same string
-    Slice s("abcxyz");
-    Slice t("abcxyz");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    Slice s("abcxy");
-    Slice t("abcxz");
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    Slice s("abcxz");
-    Slice t("abcxy");
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xac";
-    const char t_array[] = "\x50\x8a\xad";
-    Slice s(s_array);
-    Slice t(t_array);
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xff";
-    const char t_array[] = "\x50\x8b\x00";
-    Slice s(s_array, 3);
-    Slice t(t_array, 3);
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xff\xff";
-    const char t_array[] = "\x50\x8b\x00\x00";
-    Slice s(s_array, 4);
-    Slice t(t_array, 4);
-    ASSERT_TRUE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-  {
-    const char s_array[] = "\x50\x8a\xff\xff";
-    const char t_array[] = "\x50\x8b\x00\x01";
-    Slice s(s_array, 4);
-    Slice t(t_array, 4);
-    ASSERT_FALSE(BytewiseComparator()->IsSameLengthImmediateSuccessor(s, t));
-  }
-}
-
-TEST_P(ComparatorDBTest, FindShortestSeparator) {
+TEST_F(ComparatorDBTest, FindShortestSeparator) {
  std::string s1 = "abc1xyz";
  std::string s2 = "abc3xy";

@@ -547,7 +468,7 @@ TEST_P(ComparatorDBTest, FindShortestSeparator) {
  ASSERT_TRUE(s1 > s2);
 }

-TEST_P(ComparatorDBTest, SeparatorSuccessorRandomizeTest) {
+TEST_F(ComparatorDBTest, SeparatorSuccessorRandomizeTest) {
  // Char list for boundary cases.
  std::array<unsigned char, 6> char_list{{0, 1, 2, 253, 254, 255}};
  Random rnd(301);
@@ -8,7 +8,7 @@

 #include "rocksdb/convenience.h"

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "util/cast_util.h"

 namespace rocksdb {
@@ -35,7 +35,7 @@ Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
 Status VerifySstFileChecksum(const Options& options,
                             const EnvOptions& env_options,
                             const std::string& file_path) {
-  std::unique_ptr<RandomAccessFile> file;
+  unique_ptr<RandomAccessFile> file;
  uint64_t file_size;
  InternalKeyComparator internal_comparator(options.comparator);
  ImmutableCFOptions ioptions(options);
@@ -46,20 +46,19 @@ Status VerifySstFileChecksum(const Options& options,
  } else {
    return s;
  }
-  std::unique_ptr<TableReader> table_reader;
+  unique_ptr<TableReader> table_reader;
  std::unique_ptr<RandomAccessFileReader> file_reader(
      new RandomAccessFileReader(std::move(file), file_path));
-  const bool kImmortal = true;
  s = ioptions.table_factory->NewTableReader(
      TableReaderOptions(ioptions, options.prefix_extractor.get(), env_options,
                         internal_comparator, false /* skip_filters */,
-                         !kImmortal, -1 /* level */),
+                         -1 /* level */),
      std::move(file_reader), file_size, &table_reader,
      false /* prefetch_index_and_filter_in_cache */);
  if (!s.ok()) {
    return s;
  }
-  s = table_reader->VerifyChecksum(TableReaderCaller::kUserVerifyChecksum);
+  s = table_reader->VerifyChecksum();
  return s;
 }

@@ -13,23 +13,21 @@

 #include <errno.h>
 #include <fcntl.h>
-#include <cinttypes>
+#include <inttypes.h>
 #include <sys/stat.h>
 #include <sys/types.h>
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "file/filename.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/convenience.h"
 #include "rocksdb/env.h"
 #include "rocksdb/table.h"
 #include "rocksdb/write_batch.h"
-#include "table/block_based/block_based_table_builder.h"
-#include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
+#include "util/filename.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"

 namespace rocksdb {

@@ -39,7 +37,7 @@ class CorruptionTest : public testing::Test {
 public:
  test::ErrorEnv env_;
  std::string dbname_;
-  std::shared_ptr<Cache> tiny_cache_;
+  shared_ptr<Cache> tiny_cache_;
  Options options_;
  DB* db_;

@@ -50,7 +48,7 @@ class CorruptionTest : public testing::Test {
    tiny_cache_ = NewLRUCache(100, 4);
    options_.wal_recovery_mode = WALRecoveryMode::kTolerateCorruptedTailRecords;
    options_.env = &env_;
-    dbname_ = test::PerThreadDBPath("corruption_test");
+    dbname_ = test::TmpDir() + "/corruption_test";
    DestroyDB(dbname_, options_);

    db_ = nullptr;
@@ -62,9 +60,9 @@ class CorruptionTest : public testing::Test {
    options_.create_if_missing = false;
  }

-  ~CorruptionTest() override {
-    delete db_;
-    DestroyDB(dbname_, Options());
+  ~CorruptionTest() {
+     delete db_;
+     DestroyDB(dbname_, Options());
  }

  void CloseDb() {
@@ -469,39 +467,6 @@ TEST_F(CorruptionTest, UnrelatedKeys) {
  ASSERT_EQ(Value(1000, &tmp2).ToString(), v);
 }

-TEST_F(CorruptionTest, RangeDeletionCorrupted) {
-  ASSERT_OK(
-      db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), "a", "b"));
-  ASSERT_OK(db_->Flush(FlushOptions()));
-  std::vector<LiveFileMetaData> metadata;
-  db_->GetLiveFilesMetaData(&metadata);
-  ASSERT_EQ(static_cast<size_t>(1), metadata.size());
-  std::string filename = dbname_ + metadata[0].name;
-
-  std::unique_ptr<RandomAccessFile> file;
-  ASSERT_OK(options_.env->NewRandomAccessFile(filename, &file, EnvOptions()));
-  std::unique_ptr<RandomAccessFileReader> file_reader(
-      new RandomAccessFileReader(std::move(file), filename));
-
-  uint64_t file_size;
-  ASSERT_OK(options_.env->GetFileSize(filename, &file_size));
-
-  BlockHandle range_del_handle;
-  ASSERT_OK(FindMetaBlock(
-      file_reader.get(), file_size, kBlockBasedTableMagicNumber,
-      ImmutableCFOptions(options_), kRangeDelBlock, &range_del_handle));
-
-  ASSERT_OK(TryReopen());
-  CorruptFile(filename, static_cast<int>(range_del_handle.offset()), 1);
-  // The test case does not fail on TryReopen because failure to preload table
-  // handlers is not considered critical.
-  ASSERT_OK(TryReopen());
-  std::string val;
-  // However, it does fail on any read involving that file since that file
-  // cannot be opened with a corrupt range deletion meta-block.
-  ASSERT_TRUE(db_->Get(ReadOptions(), "a", &val).IsCorruption());
-}
-
 TEST_F(CorruptionTest, FileSystemStateCorrupted) {
  for (int iter = 0; iter < 2; ++iter) {
    Options options;
@@ -520,7 +485,7 @@ TEST_F(CorruptionTest, FileSystemStateCorrupted) {
    db_ = nullptr;

    if (iter == 0) {  // corrupt file size
-      std::unique_ptr<WritableFile> file;
+      unique_ptr<WritableFile> file;
      env_.NewWritableFile(filename, &file, EnvOptions());
      file->Append(Slice("corrupted sst"));
      file.reset();
@@ -5,15 +5,15 @@

 #ifndef ROCKSDB_LITE

-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "table/cuckoo/cuckoo_table_factory.h"
-#include "table/cuckoo/cuckoo_table_reader.h"
+#include "table/cuckoo_table_factory.h"
+#include "table/cuckoo_table_reader.h"
 #include "table/meta_blocks.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
 #include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"

 namespace rocksdb {

@@ -25,13 +25,13 @@ class CuckooTableDBTest : public testing::Test {

 public:
  CuckooTableDBTest() : env_(Env::Default()) {
-    dbname_ = test::PerThreadDBPath("cuckoo_table_db_test");
+    dbname_ = test::TmpDir() + "/cuckoo_table_db_test";
    EXPECT_OK(DestroyDB(dbname_, Options()));
    db_ = nullptr;
    Reopen();
  }

-  ~CuckooTableDBTest() override {
+  ~CuckooTableDBTest() {
    delete db_;
    EXPECT_OK(DestroyDB(dbname_, Options()));
  }
@@ -6,15 +6,12 @@
 // 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 <iostream>
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
 #include "rocksdb/perf_context.h"
-#include "rocksdb/utilities/debug.h"
-#include "table/block_based/block_builder.h"
-#include "test_util/fault_injection_test_env.h"
+#include "util/fault_injection_test_env.h"
 #if !defined(ROCKSDB_LITE)
-#include "test_util/sync_point.h"
+#include "util/sync_point.h"
 #endif

 namespace rocksdb {
@@ -217,11 +214,11 @@ TEST_F(DBBasicTest, PutSingleDeleteGet) {
    ASSERT_EQ("v2", Get(1, "foo2"));
    ASSERT_OK(SingleDelete(1, "foo"));
    ASSERT_EQ("NOT_FOUND", Get(1, "foo"));
-    // Ski FIFO and universal compaction because they do not apply to the test
-    // case. Skip MergePut because single delete does not get removed when it
-    // encounters a merge.
-  } while (ChangeOptions(kSkipFIFOCompaction | kSkipUniversalCompaction |
-                         kSkipMergePut));
+    // Skip HashCuckooRep as it does not support single delete. FIFO and
+    // universal compaction do not apply to the test case. Skip MergePut
+    // because single delete does not get removed when it encounters a merge.
+  } while (ChangeOptions(kSkipHashCuckoo | kSkipFIFOCompaction |
+                         kSkipUniversalCompaction | kSkipMergePut));
 }

 TEST_F(DBBasicTest, EmptyFlush) {
@@ -239,11 +236,11 @@ TEST_F(DBBasicTest, EmptyFlush) {
    ASSERT_OK(Flush(1));

    ASSERT_EQ("[ ]", AllEntriesFor("a", 1));
-    // Skip FIFO and  universal compaction as they do not apply to the test
-    // case. Skip MergePut because merges cannot be combined with single
-    // deletions.
-  } while (ChangeOptions(kSkipFIFOCompaction | kSkipUniversalCompaction |
-                         kSkipMergePut));
+    // Skip HashCuckooRep as it does not support single delete. FIFO and
+    // universal compaction do not apply to the test case. Skip MergePut
+    // because merges cannot be combined with single deletions.
+  } while (ChangeOptions(kSkipHashCuckoo | kSkipFIFOCompaction |
+                         kSkipUniversalCompaction | kSkipMergePut));
 }

 TEST_F(DBBasicTest, GetFromVersions) {
@@ -267,6 +264,11 @@ TEST_F(DBBasicTest, GetSnapshot) {
      std::string key = (i == 0) ? std::string("foo") : std::string(200, 'x');
      ASSERT_OK(Put(1, key, "v1"));
      const Snapshot* s1 = db_->GetSnapshot();
+      if (option_config_ == kHashCuckoo) {
+        // Unsupported case.
+        ASSERT_TRUE(s1 == nullptr);
+        break;
+      }
      ASSERT_OK(Put(1, key, "v2"));
      ASSERT_EQ("v2", Get(1, key));
      ASSERT_EQ("v1", Get(1, key, s1));
@@ -507,7 +509,7 @@ TEST_F(DBBasicTest, Snapshot) {
    ASSERT_EQ(0U, GetNumSnapshots());
    ASSERT_EQ("0v4", Get(0, "foo"));
    ASSERT_EQ("1v4", Get(1, "foo"));
-  } while (ChangeOptions());
+  } while (ChangeOptions(kSkipHashCuckoo));
 }

 #endif  // ROCKSDB_LITE
@@ -563,7 +565,8 @@ TEST_F(DBBasicTest, CompactBetweenSnapshots) {
                           nullptr);
    ASSERT_EQ("sixth", Get(1, "foo"));
    ASSERT_EQ(AllEntriesFor("foo", 1), "[ sixth ]");
-  } while (ChangeOptions(kSkipFIFOCompaction));
+    // skip HashCuckooRep as it does not support snapshot
+  } while (ChangeOptions(kSkipHashCuckoo | kSkipFIFOCompaction));
 }

 TEST_F(DBBasicTest, DBOpen_Options) {
@@ -791,7 +794,7 @@ TEST_F(DBBasicTest, ChecksumTest) {
  BlockBasedTableOptions table_options;
  Options options = CurrentOptions();
  // change when new checksum type added
-  int max_checksum = static_cast<int>(kxxHash64);
+  int max_checksum = static_cast<int>(kxxHash);
  const int kNumPerFile = 2;

  // generate one table with each type of checksum
@@ -806,7 +809,7 @@ TEST_F(DBBasicTest, ChecksumTest) {
  }

  // verify data with each type of checksum
-  for (int i = 0; i <= kxxHash64; ++i) {
+  for (int i = 0; i <= kxxHash; ++i) {
    table_options.checksum = static_cast<ChecksumType>(i);
    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
    Reopen(options);
@@ -854,17 +857,18 @@ class TestEnv : public EnvWrapper {
      public:
        using Logger::Logv;
        TestLogger(TestEnv *env_ptr) : Logger() { env = env_ptr; }
-        ~TestLogger() override {
+        ~TestLogger() {
          if (!closed_) {
            CloseHelper();
          }
        }
-        void Logv(const char* /*format*/, va_list /*ap*/) override{};
+        virtual void Logv(const char* /*format*/, va_list /*ap*/) override{};

       protected:
-        Status CloseImpl() override { return CloseHelper(); }
-
-       private:
+        virtual Status CloseImpl() override {
+          return CloseHelper();
+        }
+      private:
        Status CloseHelper() {
          env->CloseCountInc();;
          return Status::IOError();
@@ -876,8 +880,8 @@ class TestEnv : public EnvWrapper {

    int GetCloseCount() { return close_count; }

-    Status NewLogger(const std::string& /*fname*/,
-                     std::shared_ptr<Logger>* result) override {
+    virtual Status NewLogger(const std::string& /*fname*/,
+                             shared_ptr<Logger>* result) {
      result->reset(new TestLogger(this));
      return Status::OK();
    }
@@ -888,7 +892,7 @@ class TestEnv : public EnvWrapper {

 TEST_F(DBBasicTest, DBClose) {
  Options options = GetDefaultOptions();
-  std::string dbname = test::PerThreadDBPath("db_close_test");
+  std::string dbname = test::TmpDir(env_) + "/db_close_test";
  ASSERT_OK(DestroyDB(dbname, options));

  DB* db = nullptr;
@@ -952,828 +956,6 @@ TEST_F(DBBasicTest, DBCloseFlushError) {
  Destroy(options);
 }

-TEST_F(DBBasicTest, MultiGetMultiCF) {
-  Options options = CurrentOptions();
-  CreateAndReopenWithCF({"pikachu", "ilya", "muromec", "dobrynia", "nikitich",
-                         "alyosha", "popovich"},
-                        options);
-
-  for (int i = 0; i < 8; ++i) {
-    ASSERT_OK(Put(i, "cf" + std::to_string(i) + "_key",
-                  "cf" + std::to_string(i) + "_val"));
-  }
-
-  int get_sv_count = 0;
-  rocksdb::DBImpl* db = reinterpret_cast<DBImpl*>(db_);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::MultiGet::AfterRefSV", [&](void* /*arg*/) {
-        if (++get_sv_count == 2) {
-          // After MultiGet refs a couple of CFs, flush all CFs so MultiGet
-          // is forced to repeat the process
-          for (int i = 0; i < 8; ++i) {
-            ASSERT_OK(Flush(i));
-            ASSERT_OK(Put(i, "cf" + std::to_string(i) + "_key",
-                          "cf" + std::to_string(i) + "_val2"));
-          }
-        }
-        if (get_sv_count == 11) {
-          for (int i = 0; i < 8; ++i) {
-            auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(
-                            db->GetColumnFamilyHandle(i))
-                            ->cfd();
-            ASSERT_EQ(cfd->TEST_GetLocalSV()->Get(), SuperVersion::kSVInUse);
-          }
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  std::vector<int> cfs;
-  std::vector<std::string> keys;
-  std::vector<std::string> values;
-
-  for (int i = 0; i < 8; ++i) {
-    cfs.push_back(i);
-    keys.push_back("cf" + std::to_string(i) + "_key");
-  }
-
-  values = MultiGet(cfs, keys, nullptr);
-  ASSERT_EQ(values.size(), 8);
-  for (unsigned int j = 0; j < values.size(); ++j) {
-    ASSERT_EQ(values[j], "cf" + std::to_string(j) + "_val2");
-  }
-  for (int i = 0; i < 8; ++i) {
-    auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(
-                    reinterpret_cast<DBImpl*>(db_)->GetColumnFamilyHandle(i))
-                    ->cfd();
-    ASSERT_NE(cfd->TEST_GetLocalSV()->Get(), SuperVersion::kSVInUse);
-    ASSERT_NE(cfd->TEST_GetLocalSV()->Get(), SuperVersion::kSVObsolete);
-  }
-}
-
-TEST_F(DBBasicTest, MultiGetMultiCFMutex) {
-  Options options = CurrentOptions();
-  CreateAndReopenWithCF({"pikachu", "ilya", "muromec", "dobrynia", "nikitich",
-                         "alyosha", "popovich"},
-                        options);
-
-  for (int i = 0; i < 8; ++i) {
-    ASSERT_OK(Put(i, "cf" + std::to_string(i) + "_key",
-                  "cf" + std::to_string(i) + "_val"));
-  }
-
-  int get_sv_count = 0;
-  int retries = 0;
-  bool last_try = false;
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::MultiGet::LastTry", [&](void* /*arg*/) {
-        last_try = true;
-        rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-      });
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::MultiGet::AfterRefSV", [&](void* /*arg*/) {
-        if (last_try) {
-          return;
-        }
-        if (++get_sv_count == 2) {
-          ++retries;
-          get_sv_count = 0;
-          for (int i = 0; i < 8; ++i) {
-            ASSERT_OK(Flush(i));
-            ASSERT_OK(Put(
-                i, "cf" + std::to_string(i) + "_key",
-                "cf" + std::to_string(i) + "_val" + std::to_string(retries)));
-          }
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  std::vector<int> cfs;
-  std::vector<std::string> keys;
-  std::vector<std::string> values;
-
-  for (int i = 0; i < 8; ++i) {
-    cfs.push_back(i);
-    keys.push_back("cf" + std::to_string(i) + "_key");
-  }
-
-  values = MultiGet(cfs, keys, nullptr);
-  ASSERT_TRUE(last_try);
-  ASSERT_EQ(values.size(), 8);
-  for (unsigned int j = 0; j < values.size(); ++j) {
-    ASSERT_EQ(values[j],
-              "cf" + std::to_string(j) + "_val" + std::to_string(retries));
-  }
-  for (int i = 0; i < 8; ++i) {
-    auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(
-                    reinterpret_cast<DBImpl*>(db_)->GetColumnFamilyHandle(i))
-                    ->cfd();
-    ASSERT_NE(cfd->TEST_GetLocalSV()->Get(), SuperVersion::kSVInUse);
-  }
-}
-
-TEST_F(DBBasicTest, MultiGetMultiCFSnapshot) {
-  Options options = CurrentOptions();
-  CreateAndReopenWithCF({"pikachu", "ilya", "muromec", "dobrynia", "nikitich",
-                         "alyosha", "popovich"},
-                        options);
-
-  for (int i = 0; i < 8; ++i) {
-    ASSERT_OK(Put(i, "cf" + std::to_string(i) + "_key",
-                  "cf" + std::to_string(i) + "_val"));
-  }
-
-  int get_sv_count = 0;
-  rocksdb::DBImpl* db = reinterpret_cast<DBImpl*>(db_);
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::MultiGet::AfterRefSV", [&](void* /*arg*/) {
-        if (++get_sv_count == 2) {
-          for (int i = 0; i < 8; ++i) {
-            ASSERT_OK(Flush(i));
-            ASSERT_OK(Put(i, "cf" + std::to_string(i) + "_key",
-                          "cf" + std::to_string(i) + "_val2"));
-          }
-        }
-        if (get_sv_count == 8) {
-          for (int i = 0; i < 8; ++i) {
-            auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(
-                            db->GetColumnFamilyHandle(i))
-                            ->cfd();
-            ASSERT_TRUE(
-                (cfd->TEST_GetLocalSV()->Get() == SuperVersion::kSVInUse) ||
-                (cfd->TEST_GetLocalSV()->Get() == SuperVersion::kSVObsolete));
-          }
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  std::vector<int> cfs;
-  std::vector<std::string> keys;
-  std::vector<std::string> values;
-
-  for (int i = 0; i < 8; ++i) {
-    cfs.push_back(i);
-    keys.push_back("cf" + std::to_string(i) + "_key");
-  }
-
-  const Snapshot* snapshot = db_->GetSnapshot();
-  values = MultiGet(cfs, keys, snapshot);
-  db_->ReleaseSnapshot(snapshot);
-  ASSERT_EQ(values.size(), 8);
-  for (unsigned int j = 0; j < values.size(); ++j) {
-    ASSERT_EQ(values[j], "cf" + std::to_string(j) + "_val");
-  }
-  for (int i = 0; i < 8; ++i) {
-    auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(
-                    reinterpret_cast<DBImpl*>(db_)->GetColumnFamilyHandle(i))
-                    ->cfd();
-    ASSERT_NE(cfd->TEST_GetLocalSV()->Get(), SuperVersion::kSVInUse);
-  }
-}
-
-TEST_F(DBBasicTest, MultiGetBatchedSimpleUnsorted) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    SetPerfLevel(kEnableCount);
-    ASSERT_OK(Put(1, "k1", "v1"));
-    ASSERT_OK(Put(1, "k2", "v2"));
-    ASSERT_OK(Put(1, "k3", "v3"));
-    ASSERT_OK(Put(1, "k4", "v4"));
-    ASSERT_OK(Delete(1, "k4"));
-    ASSERT_OK(Put(1, "k5", "v5"));
-    ASSERT_OK(Delete(1, "no_key"));
-
-    get_perf_context()->Reset();
-
-    std::vector<Slice> keys({"no_key", "k5", "k4", "k3", "k2", "k1"});
-    std::vector<PinnableSlice> values(keys.size());
-    std::vector<ColumnFamilyHandle*> cfs(keys.size(), handles_[1]);
-    std::vector<Status> s(keys.size());
-
-    db_->MultiGet(ReadOptions(), handles_[1], keys.size(), keys.data(),
-                  values.data(), s.data(), false);
-
-    ASSERT_EQ(values.size(), keys.size());
-    ASSERT_EQ(std::string(values[5].data(), values[5].size()), "v1");
-    ASSERT_EQ(std::string(values[4].data(), values[4].size()), "v2");
-    ASSERT_EQ(std::string(values[3].data(), values[3].size()), "v3");
-    ASSERT_EQ(std::string(values[1].data(), values[1].size()), "v5");
-    // four kv pairs * two bytes per value
-    ASSERT_EQ(8, (int)get_perf_context()->multiget_read_bytes);
-
-    ASSERT_TRUE(s[0].IsNotFound());
-    ASSERT_OK(s[1]);
-    ASSERT_TRUE(s[2].IsNotFound());
-    ASSERT_OK(s[3]);
-    ASSERT_OK(s[4]);
-    ASSERT_OK(s[5]);
-
-    SetPerfLevel(kDisable);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, MultiGetBatchedSimpleSorted) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    SetPerfLevel(kEnableCount);
-    ASSERT_OK(Put(1, "k1", "v1"));
-    ASSERT_OK(Put(1, "k2", "v2"));
-    ASSERT_OK(Put(1, "k3", "v3"));
-    ASSERT_OK(Put(1, "k4", "v4"));
-    ASSERT_OK(Delete(1, "k4"));
-    ASSERT_OK(Put(1, "k5", "v5"));
-    ASSERT_OK(Delete(1, "no_key"));
-
-    get_perf_context()->Reset();
-
-    std::vector<Slice> keys({"k1", "k2", "k3", "k4", "k5", "no_key"});
-    std::vector<PinnableSlice> values(keys.size());
-    std::vector<ColumnFamilyHandle*> cfs(keys.size(), handles_[1]);
-    std::vector<Status> s(keys.size());
-
-    db_->MultiGet(ReadOptions(), handles_[1], keys.size(), keys.data(),
-                  values.data(), s.data(), true);
-
-    ASSERT_EQ(values.size(), keys.size());
-    ASSERT_EQ(std::string(values[0].data(), values[0].size()), "v1");
-    ASSERT_EQ(std::string(values[1].data(), values[1].size()), "v2");
-    ASSERT_EQ(std::string(values[2].data(), values[2].size()), "v3");
-    ASSERT_EQ(std::string(values[4].data(), values[4].size()), "v5");
-    // four kv pairs * two bytes per value
-    ASSERT_EQ(8, (int)get_perf_context()->multiget_read_bytes);
-
-    ASSERT_OK(s[0]);
-    ASSERT_OK(s[1]);
-    ASSERT_OK(s[2]);
-    ASSERT_TRUE(s[3].IsNotFound());
-    ASSERT_OK(s[4]);
-    ASSERT_TRUE(s[5].IsNotFound());
-
-    SetPerfLevel(kDisable);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, MultiGetBatchedMultiLevel) {
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  Reopen(options);
-  int num_keys = 0;
-
-  for (int i = 0; i < 128; ++i) {
-    ASSERT_OK(Put("key_" + std::to_string(i), "val_l2_" + std::to_string(i)));
-    num_keys++;
-    if (num_keys == 8) {
-      Flush();
-      num_keys = 0;
-    }
-  }
-  if (num_keys > 0) {
-    Flush();
-    num_keys = 0;
-  }
-  MoveFilesToLevel(2);
-
-  for (int i = 0; i < 128; i += 3) {
-    ASSERT_OK(Put("key_" + std::to_string(i), "val_l1_" + std::to_string(i)));
-    num_keys++;
-    if (num_keys == 8) {
-      Flush();
-      num_keys = 0;
-    }
-  }
-  if (num_keys > 0) {
-    Flush();
-    num_keys = 0;
-  }
-  MoveFilesToLevel(1);
-
-  for (int i = 0; i < 128; i += 5) {
-    ASSERT_OK(Put("key_" + std::to_string(i), "val_l0_" + std::to_string(i)));
-    num_keys++;
-    if (num_keys == 8) {
-      Flush();
-      num_keys = 0;
-    }
-  }
-  if (num_keys > 0) {
-    Flush();
-    num_keys = 0;
-  }
-  ASSERT_EQ(0, num_keys);
-
-  for (int i = 0; i < 128; i += 9) {
-    ASSERT_OK(Put("key_" + std::to_string(i), "val_mem_" + std::to_string(i)));
-  }
-
-  std::vector<std::string> keys;
-  std::vector<std::string> values;
-
-  for (int i = 64; i < 80; ++i) {
-    keys.push_back("key_" + std::to_string(i));
-  }
-
-  values = MultiGet(keys, nullptr);
-  ASSERT_EQ(values.size(), 16);
-  for (unsigned int j = 0; j < values.size(); ++j) {
-    int key = j + 64;
-    if (key % 9 == 0) {
-      ASSERT_EQ(values[j], "val_mem_" + std::to_string(key));
-    } else if (key % 5 == 0) {
-      ASSERT_EQ(values[j], "val_l0_" + std::to_string(key));
-    } else if (key % 3 == 0) {
-      ASSERT_EQ(values[j], "val_l1_" + std::to_string(key));
-    } else {
-      ASSERT_EQ(values[j], "val_l2_" + std::to_string(key));
-    }
-  }
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBBasicTest, GetAllKeyVersions) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.disable_auto_compactions = true;
-  CreateAndReopenWithCF({"pikachu"}, options);
-  ASSERT_EQ(2, handles_.size());
-  const size_t kNumInserts = 4;
-  const size_t kNumDeletes = 4;
-  const size_t kNumUpdates = 4;
-
-  // Check default column family
-  for (size_t i = 0; i != kNumInserts; ++i) {
-    ASSERT_OK(Put(std::to_string(i), "value"));
-  }
-  for (size_t i = 0; i != kNumUpdates; ++i) {
-    ASSERT_OK(Put(std::to_string(i), "value1"));
-  }
-  for (size_t i = 0; i != kNumDeletes; ++i) {
-    ASSERT_OK(Delete(std::to_string(i)));
-  }
-  std::vector<KeyVersion> key_versions;
-  ASSERT_OK(rocksdb::GetAllKeyVersions(db_, Slice(), Slice(),
-                                       std::numeric_limits<size_t>::max(),
-                                       &key_versions));
-  ASSERT_EQ(kNumInserts + kNumDeletes + kNumUpdates, key_versions.size());
-  ASSERT_OK(rocksdb::GetAllKeyVersions(db_, handles_[0], Slice(), Slice(),
-                                       std::numeric_limits<size_t>::max(),
-                                       &key_versions));
-  ASSERT_EQ(kNumInserts + kNumDeletes + kNumUpdates, key_versions.size());
-
-  // Check non-default column family
-  for (size_t i = 0; i != kNumInserts - 1; ++i) {
-    ASSERT_OK(Put(1, std::to_string(i), "value"));
-  }
-  for (size_t i = 0; i != kNumUpdates - 1; ++i) {
-    ASSERT_OK(Put(1, std::to_string(i), "value1"));
-  }
-  for (size_t i = 0; i != kNumDeletes - 1; ++i) {
-    ASSERT_OK(Delete(1, std::to_string(i)));
-  }
-  ASSERT_OK(rocksdb::GetAllKeyVersions(db_, handles_[1], Slice(), Slice(),
-                                       std::numeric_limits<size_t>::max(),
-                                       &key_versions));
-  ASSERT_EQ(kNumInserts + kNumDeletes + kNumUpdates - 3, key_versions.size());
-}
-#endif  // !ROCKSDB_LITE
-
-class DBBasicTestWithParallelIO
-    : public DBTestBase,
-      public testing::WithParamInterface<std::tuple<bool,bool,bool,bool>> {
- public:
-  DBBasicTestWithParallelIO()
-      : DBTestBase("/db_basic_test_with_parallel_io") {
-    bool compressed_cache = std::get<0>(GetParam());
-    bool uncompressed_cache = std::get<1>(GetParam());
-    compression_enabled_ = std::get<2>(GetParam());
-    fill_cache_ = std::get<3>(GetParam());
-
-    if (compressed_cache) {
-      std::shared_ptr<Cache> cache = NewLRUCache(1048576);
-      compressed_cache_ = std::make_shared<MyBlockCache>(cache);
-    }
-    if (uncompressed_cache) {
-      std::shared_ptr<Cache> cache = NewLRUCache(1048576);
-      uncompressed_cache_ = std::make_shared<MyBlockCache>(cache);
-    }
-
-    env_->count_random_reads_ = true;
-
-    Options options = CurrentOptions();
-    Random rnd(301);
-    BlockBasedTableOptions table_options;
-    table_options.pin_l0_filter_and_index_blocks_in_cache = true;
-    table_options.block_cache = uncompressed_cache_;
-    table_options.block_cache_compressed = compressed_cache_;
-    table_options.flush_block_policy_factory.reset(
-                      new MyFlushBlockPolicyFactory());
-    options.table_factory.reset(new BlockBasedTableFactory(table_options));
-    if (!compression_enabled_) {
-      options.compression = kNoCompression;
-    }
-    Reopen(options);
-
-    std::string zero_str(128, '\0');
-    for (int i = 0; i < 100; ++i) {
-      // Make the value compressible. A purely random string doesn't compress
-      // and the resultant data block will not be compressed
-      values_.emplace_back(RandomString(&rnd, 128) + zero_str);
-      assert(Put(Key(i), values_[i]) == Status::OK());
-    }
-    Flush();
-  }
-
-  bool CheckValue(int i, const std::string& value) {
-    if (values_[i].compare(value) == 0) {
-      return true;
-    }
-    return false;
-  }
-
-  int num_lookups() { return uncompressed_cache_->num_lookups(); }
-  int num_found() { return uncompressed_cache_->num_found(); }
-  int num_inserts() { return uncompressed_cache_->num_inserts(); }
-
-  int num_lookups_compressed() {
-    return compressed_cache_->num_lookups();
-  }
-  int num_found_compressed() {
-    return compressed_cache_->num_found();
-  }
-  int num_inserts_compressed() {
-    return compressed_cache_->num_inserts();
-  }
-
-  bool fill_cache() { return fill_cache_; }
-
-  static void SetUpTestCase() {}
-  static void TearDownTestCase() {}
-
- private:
-  class MyFlushBlockPolicyFactory
-    : public FlushBlockPolicyFactory {
-   public:
-    MyFlushBlockPolicyFactory() {}
-
-    virtual const char* Name() const override {
-      return "MyFlushBlockPolicyFactory";
-    }
-
-    virtual FlushBlockPolicy* NewFlushBlockPolicy(
-        const BlockBasedTableOptions& /*table_options*/,
-        const BlockBuilder& data_block_builder) const override {
-      return new MyFlushBlockPolicy(data_block_builder);
-    }
-  };
-
-  class MyFlushBlockPolicy
-    : public FlushBlockPolicy {
-   public:
-    explicit MyFlushBlockPolicy(const BlockBuilder& data_block_builder)
-      : num_keys_(0), data_block_builder_(data_block_builder) {}
-
-    bool Update(const Slice& /*key*/, const Slice& /*value*/) override {
-      if (data_block_builder_.empty()) {
-        // First key in this block
-        num_keys_ = 1;
-        return false;
-      }
-      // Flush every 10 keys
-      if (num_keys_ == 10) {
-        num_keys_ = 1;
-        return true;
-      }
-      num_keys_++;
-      return false;
-    }
-
-   private:
-    int num_keys_;
-    const BlockBuilder& data_block_builder_;
-  };
-
-  class MyBlockCache
-    : public Cache {
-   public:
-    explicit MyBlockCache(std::shared_ptr<Cache>& target)
-      : target_(target), num_lookups_(0), num_found_(0), num_inserts_(0) {}
-
-    virtual const char* Name() const override { return "MyBlockCache"; }
-
-    virtual Status Insert(const Slice& key, void* value, size_t charge,
-                          void (*deleter)(const Slice& key, void* value),
-                          Handle** handle = nullptr,
-                          Priority priority = Priority::LOW) override {
-      num_inserts_++;
-      return target_->Insert(key, value, charge, deleter, handle, priority);
-    }
-
-    virtual Handle* Lookup(const Slice& key,
-                           Statistics* stats = nullptr) override {
-      num_lookups_++;
-      Handle* handle = target_->Lookup(key, stats);
-      if (handle != nullptr) {
-        num_found_++;
-      }
-      return handle;
-    }
-
-    virtual bool Ref(Handle* handle) override {
-      return target_->Ref(handle);
-    }
-
-    virtual bool Release(Handle* handle, bool force_erase = false) override {
-      return target_->Release(handle, force_erase);
-    }
-
-    virtual void* Value(Handle* handle) override {
-      return target_->Value(handle);
-    }
-
-    virtual void Erase(const Slice& key) override {
-      target_->Erase(key);
-    }
-    virtual uint64_t NewId() override {
-      return target_->NewId();
-    }
-
-    virtual void SetCapacity(size_t capacity) override {
-      target_->SetCapacity(capacity);
-    }
-
-    virtual void SetStrictCapacityLimit(bool strict_capacity_limit) override {
-      target_->SetStrictCapacityLimit(strict_capacity_limit);
-    }
-
-    virtual bool HasStrictCapacityLimit() const override {
-      return target_->HasStrictCapacityLimit();
-    }
-
-    virtual size_t GetCapacity() const override {
-      return target_->GetCapacity();
-    }
-
-    virtual size_t GetUsage() const override {
-      return target_->GetUsage();
-    }
-
-    virtual size_t GetUsage(Handle* handle) const override {
-      return target_->GetUsage(handle);
-    }
-
-    virtual size_t GetPinnedUsage() const override {
-      return target_->GetPinnedUsage();
-    }
-
-    virtual size_t GetCharge(Handle* /*handle*/) const override { return 0; }
-
-    virtual void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
-                                        bool thread_safe) override {
-      return target_->ApplyToAllCacheEntries(callback, thread_safe);
-    }
-
-    virtual void EraseUnRefEntries() override {
-      return target_->EraseUnRefEntries();
-    }
-
-    int num_lookups() { return num_lookups_; }
-
-    int num_found() { return num_found_; }
-
-    int num_inserts() { return num_inserts_; }
-   private:
-    std::shared_ptr<Cache> target_;
-    int num_lookups_;
-    int num_found_;
-    int num_inserts_;
-  };
-
-  std::shared_ptr<MyBlockCache> compressed_cache_;
-  std::shared_ptr<MyBlockCache> uncompressed_cache_;
-  bool compression_enabled_;
-  std::vector<std::string> values_;
-  bool fill_cache_;
-};
-
-TEST_P(DBBasicTestWithParallelIO, MultiGet) {
-  std::vector<std::string> key_data(10);
-  std::vector<Slice> keys;
-  // We cannot resize a PinnableSlice vector, so just set initial size to
-  // largest we think we will need
-  std::vector<PinnableSlice> values(10);
-  std::vector<Status> statuses;
-  ReadOptions ro;
-  ro.fill_cache = fill_cache();
-
-  // Warm up the cache first
-  key_data.emplace_back(Key(0));
-  keys.emplace_back(Slice(key_data.back()));
-  key_data.emplace_back(Key(50));
-  keys.emplace_back(Slice(key_data.back()));
-  statuses.resize(keys.size());
-
-  dbfull()->MultiGet(ro, dbfull()->DefaultColumnFamily(), keys.size(),
-           keys.data(), values.data(), statuses.data(), true);
-  ASSERT_TRUE(CheckValue(0, values[0].ToString()));
-  ASSERT_TRUE(CheckValue(50, values[1].ToString()));
-
-  int random_reads = env_->random_read_counter_.Read();
-  key_data[0] = Key(1);
-  key_data[1] = Key(51);
-  keys[0] = Slice(key_data[0]);
-  keys[1] = Slice(key_data[1]);
-  values[0].Reset();
-  values[1].Reset();
-  dbfull()->MultiGet(ro, dbfull()->DefaultColumnFamily(), keys.size(),
-           keys.data(), values.data(), statuses.data(), true);
-  ASSERT_TRUE(CheckValue(1, values[0].ToString()));
-  ASSERT_TRUE(CheckValue(51, values[1].ToString()));
-
-  int expected_reads = random_reads + (fill_cache() ? 0 : 2);
-  ASSERT_EQ(env_->random_read_counter_.Read(), expected_reads);
-
-  keys.resize(10);
-  statuses.resize(10);
-  std::vector<int> key_ints{1,2,15,16,55,81,82,83,84,85};
-  for (size_t i = 0; i < key_ints.size(); ++i) {
-    key_data[i] = Key(key_ints[i]);
-    keys[i] = Slice(key_data[i]);
-    statuses[i] = Status::OK();
-    values[i].Reset();
-  }
-  dbfull()->MultiGet(ro, dbfull()->DefaultColumnFamily(), keys.size(),
-           keys.data(), values.data(), statuses.data(), true);
-  for (size_t i = 0; i < key_ints.size(); ++i) {
-    ASSERT_OK(statuses[i]);
-    ASSERT_TRUE(CheckValue(key_ints[i], values[i].ToString()));
-  }
-  expected_reads += (fill_cache() ? 2 : 4);
-  ASSERT_EQ(env_->random_read_counter_.Read(), expected_reads);
-}
-
-INSTANTIATE_TEST_CASE_P(
-    ParallelIO, DBBasicTestWithParallelIO,
-    // Params are as follows -
-    // Param 0 - Compressed cache enabled
-    // Param 1 - Uncompressed cache enabled
-    // Param 2 - Data compression enabled
-    // Param 3 - ReadOptions::fill_cache
-    ::testing::Values(std::make_tuple(false, true, true, true),
-                      std::make_tuple(true, true, true, true),
-                      std::make_tuple(false, true, false, true),
-                      std::make_tuple(false, true, true, false),
-                      std::make_tuple(true, true, true, false),
-                      std::make_tuple(false, true, false, false)));
-
-class DBBasicTestWithTimestampWithParam
-    : public DBTestBase,
-      public testing::WithParamInterface<bool> {
- public:
-  DBBasicTestWithTimestampWithParam()
-      : DBTestBase("/db_basic_test_with_timestamp") {}
-
- protected:
-  class TestComparator : public Comparator {
-   private:
-    const Comparator* cmp_without_ts_;
-
-   public:
-    explicit TestComparator(size_t ts_sz)
-        : Comparator(ts_sz), cmp_without_ts_(nullptr) {
-      cmp_without_ts_ = BytewiseComparator();
-    }
-
-    const char* Name() const override { return "TestComparator"; }
-
-    void FindShortSuccessor(std::string*) const override {}
-
-    void FindShortestSeparator(std::string*, const Slice&) const override {}
-
-    int Compare(const Slice& a, const Slice& b) const override {
-      int r = CompareWithoutTimestamp(a, b);
-      if (r != 0 || 0 == timestamp_size()) {
-        return r;
-      }
-      return CompareTimestamp(
-          Slice(a.data() + a.size() - timestamp_size(), timestamp_size()),
-          Slice(b.data() + b.size() - timestamp_size(), timestamp_size()));
-    }
-
-    int CompareWithoutTimestamp(const Slice& a, const Slice& b) const override {
-      assert(a.size() >= timestamp_size());
-      assert(b.size() >= timestamp_size());
-      Slice k1 = StripTimestampFromUserKey(a, timestamp_size());
-      Slice k2 = StripTimestampFromUserKey(b, timestamp_size());
-
-      return cmp_without_ts_->Compare(k1, k2);
-    }
-
-    int CompareTimestamp(const Slice& ts1, const Slice& ts2) const override {
-      if (!ts1.data() && !ts2.data()) {
-        return 0;
-      } else if (ts1.data() && !ts2.data()) {
-        return 1;
-      } else if (!ts1.data() && ts2.data()) {
-        return -1;
-      }
-      assert(ts1.size() == ts2.size());
-      uint64_t low1 = 0;
-      uint64_t low2 = 0;
-      uint64_t high1 = 0;
-      uint64_t high2 = 0;
-      auto* ptr1 = const_cast<Slice*>(&ts1);
-      auto* ptr2 = const_cast<Slice*>(&ts2);
-      if (!GetFixed64(ptr1, &low1) || !GetFixed64(ptr1, &high1) ||
-          !GetFixed64(ptr2, &low2) || !GetFixed64(ptr2, &high2)) {
-        assert(false);
-      }
-      if (high1 < high2) {
-        return 1;
-      } else if (high1 > high2) {
-        return -1;
-      }
-      if (low1 < low2) {
-        return 1;
-      } else if (low1 > low2) {
-        return -1;
-      }
-      return 0;
-    }
-  };
-
-  Slice EncodeTimestamp(uint64_t low, uint64_t high, std::string* ts) {
-    assert(nullptr != ts);
-    ts->clear();
-    PutFixed64(ts, low);
-    PutFixed64(ts, high);
-    assert(ts->size() == sizeof(low) + sizeof(high));
-    return Slice(*ts);
-  }
-};
-
-TEST_P(DBBasicTestWithTimestampWithParam, PutAndGet) {
-  const int kNumKeysPerFile = 8192;
-  const size_t kNumTimestamps = 6;
-  bool memtable_only = GetParam();
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.env = env_;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  std::string tmp;
-  size_t ts_sz = EncodeTimestamp(0, 0, &tmp).size();
-  TestComparator test_cmp(ts_sz);
-  options.comparator = &test_cmp;
-  BlockBasedTableOptions bbto;
-  bbto.filter_policy.reset(NewBloomFilterPolicy(
-      10 /*bits_per_key*/, false /*use_block_based_builder*/));
-  bbto.whole_key_filtering = true;
-  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(2, num_cfs);
-  std::vector<std::string> write_ts_strs(kNumTimestamps);
-  std::vector<std::string> read_ts_strs(kNumTimestamps);
-  std::vector<Slice> write_ts_list;
-  std::vector<Slice> read_ts_list;
-
-  for (size_t i = 0; i != kNumTimestamps; ++i) {
-    write_ts_list.emplace_back(EncodeTimestamp(i * 2, 0, &write_ts_strs[i]));
-    read_ts_list.emplace_back(EncodeTimestamp(1 + i * 2, 0, &read_ts_strs[i]));
-    const Slice& write_ts = write_ts_list.back();
-    WriteOptions wopts;
-    wopts.timestamp = &write_ts;
-    for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-      for (size_t j = 0; j != (kNumKeysPerFile - 1) / kNumTimestamps; ++j) {
-        ASSERT_OK(Put(cf, "key" + std::to_string(j),
-                      "value_" + std::to_string(j) + "_" + std::to_string(i),
-                      wopts));
-      }
-      if (!memtable_only) {
-        ASSERT_OK(Flush(cf));
-      }
-    }
-  }
-  const auto& verify_db_func = [&]() {
-    for (size_t i = 0; i != kNumTimestamps; ++i) {
-      ReadOptions ropts;
-      ropts.timestamp = &read_ts_list[i];
-      for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-        ColumnFamilyHandle* cfh = handles_[cf];
-        for (size_t j = 0; j != (kNumKeysPerFile - 1) / kNumTimestamps; ++j) {
-          std::string value;
-          ASSERT_OK(db_->Get(ropts, cfh, "key" + std::to_string(j), &value));
-          ASSERT_EQ("value_" + std::to_string(j) + "_" + std::to_string(i),
-                    value);
-        }
-      }
-    }
-  };
-  verify_db_func();
-}
-
-INSTANTIATE_TEST_CASE_P(Timestamp, DBBasicTestWithTimestampWithParam,
-                        ::testing::Bool());
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -173,7 +173,7 @@ TEST_F(DBBlockCacheTest, TestWithoutCompressedBlockCache) {
  delete iter;
  iter = nullptr;

-  // Release iterators and access cache again.
+  // Release interators and access cache again.
  for (size_t i = 0; i < kNumBlocks - 1; i++) {
    iterators[i].reset();
    CheckCacheCounters(options, 0, 0, 0, 0);
@@ -346,14 +346,14 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
  options.statistics = rocksdb::CreateDBStatistics();
  BlockBasedTableOptions table_options;
  table_options.cache_index_and_filter_blocks = true;
-  // 500 bytes are enough to hold the first two blocks
-  std::shared_ptr<Cache> cache = NewLRUCache(500, 0, false);
+  // 200 bytes are enough to hold the first two blocks
+  std::shared_ptr<Cache> cache = NewLRUCache(200, 0, false);
  table_options.block_cache = cache;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20, true));
+  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
  options.table_factory.reset(new BlockBasedTableFactory(table_options));
  CreateAndReopenWithCF({"pikachu"}, options);

-  ASSERT_OK(Put(1, "longer_key", "val"));
+  ASSERT_OK(Put(1, "key", "val"));
  // Create a new table
  ASSERT_OK(Flush(1));
  size_t index_bytes_insert =
@@ -365,14 +365,9 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
  ASSERT_EQ(cache->GetUsage(), index_bytes_insert + filter_bytes_insert);
  // set the cache capacity to the current usage
  cache->SetCapacity(index_bytes_insert + filter_bytes_insert);
-  // The index and filter eviction statistics were broken by the refactoring
-  // that moved the readers out of the block cache. Disabling these until we can
-  // bring the stats back.
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT), 0);
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT), 0);
-  // Note that the second key needs to be no longer than the first one.
-  // Otherwise the second index block may not fit in cache.
-  ASSERT_OK(Put(1, "key", "val"));
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT), 0);
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT), 0);
+  ASSERT_OK(Put(1, "key2", "val"));
  // Create a new table
  ASSERT_OK(Flush(1));
  // cache evicted old index and block entries
@@ -380,13 +375,10 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
            index_bytes_insert);
  ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_INSERT),
            filter_bytes_insert);
-  // The index and filter eviction statistics were broken by the refactoring
-  // that moved the readers out of the block cache. Disabling these until we can
-  // bring the stats back.
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT),
-  //           index_bytes_insert);
-  // ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT),
-  //           filter_bytes_insert);
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT),
+            index_bytes_insert);
+  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT),
+            filter_bytes_insert);
 }

 namespace {
@@ -403,9 +395,9 @@ class MockCache : public LRUCache {
                 false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/) {
  }

-  Status Insert(const Slice& key, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value), Handle** handle,
-                Priority priority) override {
+  virtual Status Insert(const Slice& key, void* value, size_t charge,
+                        void (*deleter)(const Slice& key, void* value),
+                        Handle** handle, Priority priority) override {
    if (priority == Priority::LOW) {
      low_pri_insert_count++;
    } else {
@@ -639,74 +631,6 @@ TEST_F(DBBlockCacheTest, CompressedCache) {
  }
 }

-TEST_F(DBBlockCacheTest, CacheCompressionDict) {
-  const int kNumFiles = 4;
-  const int kNumEntriesPerFile = 128;
-  const int kNumBytesPerEntry = 1024;
-
-  // Try all the available libraries that support dictionary compression
-  std::vector<CompressionType> compression_types;
-#ifdef ZLIB
-  compression_types.push_back(kZlibCompression);
-#endif  // ZLIB
-#if LZ4_VERSION_NUMBER >= 10400
-  compression_types.push_back(kLZ4Compression);
-  compression_types.push_back(kLZ4HCCompression);
-#endif  // LZ4_VERSION_NUMBER >= 10400
-#if ZSTD_VERSION_NUMBER >= 500
-  compression_types.push_back(kZSTD);
-#endif  // ZSTD_VERSION_NUMBER >= 500
-  Random rnd(301);
-  for (auto compression_type : compression_types) {
-    Options options = CurrentOptions();
-    options.compression = compression_type;
-    options.compression_opts.max_dict_bytes = 4096;
-    options.create_if_missing = true;
-    options.num_levels = 2;
-    options.statistics = rocksdb::CreateDBStatistics();
-    options.target_file_size_base = kNumEntriesPerFile * kNumBytesPerEntry;
-    BlockBasedTableOptions table_options;
-    table_options.cache_index_and_filter_blocks = true;
-    table_options.block_cache.reset(new MockCache());
-    options.table_factory.reset(new BlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    for (int i = 0; i < kNumFiles; ++i) {
-      ASSERT_EQ(i, NumTableFilesAtLevel(0, 0));
-      for (int j = 0; j < kNumEntriesPerFile; ++j) {
-        std::string value = RandomString(&rnd, kNumBytesPerEntry);
-        ASSERT_OK(Put(Key(j * kNumFiles + i), value.c_str()));
-      }
-      ASSERT_OK(Flush());
-    }
-    dbfull()->TEST_WaitForCompact();
-    ASSERT_EQ(0, NumTableFilesAtLevel(0));
-    ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(1));
-
-    // Seek to a key in a file. It should cause the SST's dictionary meta-block
-    // to be read.
-    RecordCacheCounters(options);
-    ASSERT_EQ(0,
-              TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_ADD));
-    ASSERT_EQ(
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
-        0);
-    ReadOptions read_options;
-    ASSERT_NE("NOT_FOUND", Get(Key(kNumFiles * kNumEntriesPerFile - 1)));
-    // Two blocks missed/added: dictionary and data block
-    // One block hit: index since it's prefetched
-    CheckCacheCounters(options, 2 /* expected_misses */, 1 /* expected_hits */,
-                       2 /* expected_inserts */, 0 /* expected_failures */);
-    ASSERT_EQ(1,
-              TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_ADD));
-    ASSERT_GT(
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
-        0);
-  }
-}
-
 #endif  // ROCKSDB_LITE

 }  // namespace rocksdb
@@ -22,51 +22,27 @@ class DBBloomFilterTest : public DBTestBase {

 class DBBloomFilterTestWithParam
    : public DBTestBase,
-      public testing::WithParamInterface<std::tuple<bool, bool, uint32_t>> {
+      public testing::WithParamInterface<std::tuple<bool, bool>> {
  //                             public testing::WithParamInterface<bool> {
 protected:
  bool use_block_based_filter_;
  bool partition_filters_;
-  uint32_t format_version_;

 public:
  DBBloomFilterTestWithParam() : DBTestBase("/db_bloom_filter_tests") {}

-  ~DBBloomFilterTestWithParam() override {}
+  ~DBBloomFilterTestWithParam() {}

  void SetUp() override {
    use_block_based_filter_ = std::get<0>(GetParam());
    partition_filters_ = std::get<1>(GetParam());
-    format_version_ = std::get<2>(GetParam());
-  }
-};
-
-class DBBloomFilterTestDefFormatVersion : public DBBloomFilterTestWithParam {};
-
-class SliceTransformLimitedDomainGeneric : public SliceTransform {
-  const char* Name() const override {
-    return "SliceTransformLimitedDomainGeneric";
-  }
-
-  Slice Transform(const Slice& src) const override {
-    return Slice(src.data(), 5);
-  }
-
-  bool InDomain(const Slice& src) const override {
-    // prefix will be x????
-    return src.size() >= 5;
-  }
-
-  bool InRange(const Slice& dst) const override {
-    // prefix will be x????
-    return dst.size() == 5;
  }
 };

 // KeyMayExist can lead to a few false positives, but not false negatives.
 // To make test deterministic, use a much larger number of bits per key-20 than
 // bits in the key, so that false positives are eliminated
-TEST_P(DBBloomFilterTestDefFormatVersion, KeyMayExist) {
+TEST_P(DBBloomFilterTestWithParam, KeyMayExist) {
  do {
    ReadOptions ropts;
    std::string value;
@@ -141,79 +117,11 @@ TEST_P(DBBloomFilterTestDefFormatVersion, KeyMayExist) {
      ChangeOptions(kSkipPlainTable | kSkipHashIndex | kSkipFIFOCompaction));
 }

-TEST_F(DBBloomFilterTest, GetFilterByPrefixBloomCustomPrefixExtractor) {
-  for (bool partition_filters : {true, false}) {
-    Options options = last_options_;
-    options.prefix_extractor =
-        std::make_shared<SliceTransformLimitedDomainGeneric>();
-    options.statistics = rocksdb::CreateDBStatistics();
-    get_perf_context()->EnablePerLevelPerfContext();
-    BlockBasedTableOptions bbto;
-    bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
-    if (partition_filters) {
-      bbto.partition_filters = true;
-      bbto.index_type = BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-    }
-    bbto.whole_key_filtering = false;
-    options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-    DestroyAndReopen(options);
-
-    WriteOptions wo;
-    ReadOptions ro;
-    FlushOptions fo;
-    fo.wait = true;
-    std::string value;
-
-    ASSERT_OK(dbfull()->Put(wo, "barbarbar", "foo"));
-    ASSERT_OK(dbfull()->Put(wo, "barbarbar2", "foo2"));
-    ASSERT_OK(dbfull()->Put(wo, "foofoofoo", "bar"));
-
-    dbfull()->Flush(fo);
-
-    ASSERT_EQ("foo", Get("barbarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ(
-        0,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-    ASSERT_EQ("foo2", Get("barbarbar2"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ(
-        0,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-    ASSERT_EQ("NOT_FOUND", Get("barbarbar3"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
-    ASSERT_EQ(
-        0,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-
-    ASSERT_EQ("NOT_FOUND", Get("barfoofoo"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
-    ASSERT_EQ(
-        1,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-
-    ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
-    ASSERT_EQ(
-        2,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-
-    ro.total_order_seek = true;
-    ASSERT_TRUE(db_->Get(ro, "foobarbar", &value).IsNotFound());
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
-    ASSERT_EQ(
-        2,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-    get_perf_context()->Reset();
-  }
-}
-
 TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
  for (bool partition_filters : {true, false}) {
    Options options = last_options_;
    options.prefix_extractor.reset(NewFixedPrefixTransform(8));
    options.statistics = rocksdb::CreateDBStatistics();
-    get_perf_context()->EnablePerLevelPerfContext();
    BlockBasedTableOptions bbto;
    bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
    if (partition_filters) {
@@ -252,10 +160,6 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
    ro.total_order_seek = true;
    ASSERT_TRUE(db_->Get(ro, "foobarbar", &value).IsNotFound());
    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
-    ASSERT_EQ(
-        2,
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
-    get_perf_context()->Reset();
  }
 }

@@ -264,7 +168,6 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
    Options options = last_options_;
    options.prefix_extractor.reset(NewFixedPrefixTransform(3));
    options.statistics = rocksdb::CreateDBStatistics();
-    get_perf_context()->EnablePerLevelPerfContext();

    BlockBasedTableOptions bbto;
    bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
@@ -412,14 +315,6 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
    ASSERT_EQ("bar", Get("barfoo"));
    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
-    uint64_t bloom_filter_useful_all_levels = 0;
-    for (auto& kv : (*(get_perf_context()->level_to_perf_context))) {
-      if (kv.second.bloom_filter_useful > 0) {
-        bloom_filter_useful_all_levels += kv.second.bloom_filter_useful;
-      }
-    }
-    ASSERT_EQ(12, bloom_filter_useful_all_levels);
-    get_perf_context()->Reset();
  }
 }

@@ -439,11 +334,6 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
      table_options.index_type =
          BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
    }
-    table_options.format_version = format_version_;
-    if (format_version_ >= 4) {
-      // value delta encoding challenged more with index interval > 1
-      table_options.index_block_restart_interval = 8;
-    }
    table_options.metadata_block_size = 32;
    options.table_factory.reset(NewBlockBasedTableFactory(table_options));

@@ -499,34 +389,15 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
  } while (ChangeCompactOptions());
 }

-#ifndef ROCKSDB_VALGRIND_RUN
-INSTANTIATE_TEST_CASE_P(
-    FormatDef, DBBloomFilterTestDefFormatVersion,
-    ::testing::Values(std::make_tuple(true, false, test::kDefaultFormatVersion),
-                      std::make_tuple(false, true, test::kDefaultFormatVersion),
-                      std::make_tuple(false, false,
-                                      test::kDefaultFormatVersion)));
-
-INSTANTIATE_TEST_CASE_P(
-    FormatDef, DBBloomFilterTestWithParam,
-    ::testing::Values(std::make_tuple(true, false, test::kDefaultFormatVersion),
-                      std::make_tuple(false, true, test::kDefaultFormatVersion),
-                      std::make_tuple(false, false,
-                                      test::kDefaultFormatVersion)));
-
-INSTANTIATE_TEST_CASE_P(
-    FormatLatest, DBBloomFilterTestWithParam,
-    ::testing::Values(std::make_tuple(true, false, test::kLatestFormatVersion),
-                      std::make_tuple(false, true, test::kLatestFormatVersion),
-                      std::make_tuple(false, false,
-                                      test::kLatestFormatVersion)));
-#endif  // ROCKSDB_VALGRIND_RUN
+INSTANTIATE_TEST_CASE_P(DBBloomFilterTestWithParam, DBBloomFilterTestWithParam,
+                        ::testing::Values(std::make_tuple(true, false),
+                                          std::make_tuple(false, true),
+                                          std::make_tuple(false, false)));

 TEST_F(DBBloomFilterTest, BloomFilterRate) {
  while (ChangeFilterOptions()) {
    Options options = CurrentOptions();
    options.statistics = rocksdb::CreateDBStatistics();
-    get_perf_context()->EnablePerLevelPerfContext();
    CreateAndReopenWithCF({"pikachu"}, options);

    const int maxKey = 10000;
@@ -548,10 +419,6 @@ TEST_F(DBBloomFilterTest, BloomFilterRate) {
      ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
    }
    ASSERT_GE(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), maxKey * 0.98);
-    ASSERT_GE(
-        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful,
-        maxKey * 0.98);
-    get_perf_context()->Reset();
  }
 }

@@ -642,7 +509,7 @@ class WrappedBloom : public FilterPolicy {
  explicit WrappedBloom(int bits_per_key)
      : filter_(NewBloomFilterPolicy(bits_per_key)), counter_(0) {}

-  ~WrappedBloom() override { delete filter_; }
+  ~WrappedBloom() { delete filter_; }

  const char* Name() const override { return "WrappedRocksDbFilterPolicy"; }

@@ -786,75 +653,6 @@ TEST_F(DBBloomFilterTest, PrefixExtractorBlockFilter) {
  delete iter;
 }

-TEST_F(DBBloomFilterTest, MemtableWholeKeyBloomFilter) {
-  // regression test for #2743. the range delete tombstones in memtable should
-  // be added even when Get() skips searching due to its prefix bloom filter
-  const int kMemtableSize = 1 << 20;              // 1MB
-  const int kMemtablePrefixFilterSize = 1 << 13;  // 8KB
-  const int kPrefixLen = 4;
-  Options options = CurrentOptions();
-  options.memtable_prefix_bloom_size_ratio =
-      static_cast<double>(kMemtablePrefixFilterSize) / kMemtableSize;
-  options.prefix_extractor.reset(rocksdb::NewFixedPrefixTransform(kPrefixLen));
-  options.write_buffer_size = kMemtableSize;
-  options.memtable_whole_key_filtering = false;
-  Reopen(options);
-  std::string key1("AAAABBBB");
-  std::string key2("AAAACCCC");  // not in DB
-  std::string key3("AAAADDDD");
-  std::string key4("AAAAEEEE");
-  std::string value1("Value1");
-  std::string value3("Value3");
-  std::string value4("Value4");
-
-  ASSERT_OK(Put(key1, value1, WriteOptions()));
-
-  // check memtable bloom stats
-  ASSERT_EQ("NOT_FOUND", Get(key2));
-  ASSERT_EQ(0, get_perf_context()->bloom_memtable_miss_count);
-  // same prefix, bloom filter false positive
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-
-  // enable whole key bloom filter
-  options.memtable_whole_key_filtering = true;
-  Reopen(options);
-  // check memtable bloom stats
-  ASSERT_OK(Put(key3, value3, WriteOptions()));
-  ASSERT_EQ("NOT_FOUND", Get(key2));
-  // whole key bloom filter kicks in and determines it's a miss
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_miss_count);
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-
-  // verify whole key filtering does not depend on prefix_extractor
-  options.prefix_extractor.reset();
-  Reopen(options);
-  // check memtable bloom stats
-  ASSERT_OK(Put(key4, value4, WriteOptions()));
-  ASSERT_EQ("NOT_FOUND", Get(key2));
-  // whole key bloom filter kicks in and determines it's a miss
-  ASSERT_EQ(2, get_perf_context()->bloom_memtable_miss_count);
-  ASSERT_EQ(1, get_perf_context()->bloom_memtable_hit_count);
-}
-
-TEST_F(DBBloomFilterTest, MemtablePrefixBloomOutOfDomain) {
-  constexpr size_t kPrefixSize = 8;
-  const std::string kKey = "key";
-  assert(kKey.size() < kPrefixSize);
-  Options options = CurrentOptions();
-  options.prefix_extractor.reset(NewFixedPrefixTransform(kPrefixSize));
-  options.memtable_prefix_bloom_size_ratio = 0.25;
-  Reopen(options);
-  ASSERT_OK(Put(kKey, "v"));
-  ASSERT_EQ("v", Get(kKey));
-  std::unique_ptr<Iterator> iter(dbfull()->NewIterator(ReadOptions()));
-  iter->Seek(kKey);
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ(kKey, iter->key());
-  iter->SeekForPrev(kKey);
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ(kKey, iter->key());
-}
-
 #ifndef ROCKSDB_LITE
 class BloomStatsTestWithParam
    : public DBBloomFilterTest,
@@ -892,7 +690,7 @@ class BloomStatsTestWithParam
    DestroyAndReopen(options_);
  }

-  ~BloomStatsTestWithParam() override {
+  ~BloomStatsTestWithParam() {
    get_perf_context()->Reset();
    Destroy(options_);
  }
@@ -966,7 +764,7 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
  ASSERT_OK(Put(key1, value1, WriteOptions()));
  ASSERT_OK(Put(key3, value3, WriteOptions()));

-  std::unique_ptr<Iterator> iter(dbfull()->NewIterator(ReadOptions()));
+  unique_ptr<Iterator> iter(dbfull()->NewIterator(ReadOptions()));

  // check memtable bloom stats
  iter->Seek(key1);
@@ -1004,16 +802,13 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
  ASSERT_OK(iter->status());
  ASSERT_TRUE(iter->Valid());
  ASSERT_EQ(value3, iter->value().ToString());
-  // The seek doesn't check block-based bloom filter because last index key
-  // starts with the same prefix we're seeking to.
-  uint64_t expected_hits = use_block_based_builder_ ? 1 : 2;
-  ASSERT_EQ(expected_hits, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);

  iter->Seek(key2);
  ASSERT_OK(iter->status());
  ASSERT_TRUE(!iter->Valid());
  ASSERT_EQ(1, get_perf_context()->bloom_sst_miss_count);
-  ASSERT_EQ(expected_hits, get_perf_context()->bloom_sst_hit_count);
+  ASSERT_EQ(2, get_perf_context()->bloom_sst_hit_count);
 }

 INSTANTIATE_TEST_CASE_P(BloomStatsTestWithParam, BloomStatsTestWithParam,
@@ -1095,8 +890,6 @@ TEST_F(DBBloomFilterTest, PrefixScan) {
    options.max_background_compactions = 2;
    options.create_if_missing = true;
    options.memtable_factory.reset(NewHashSkipListRepFactory(16));
-    assert(!options.unordered_write);
-    // It is incompatible with allow_concurrent_memtable_write=false
    options.allow_concurrent_memtable_write = false;

    BlockBasedTableOptions table_options;
@@ -1147,7 +940,6 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  options.optimize_filters_for_hits = true;
  options.statistics = rocksdb::CreateDBStatistics();
-  get_perf_context()->EnablePerLevelPerfContext();
  CreateAndReopenWithCF({"mypikachu"}, options);

  int numkeys = 200000;
@@ -1194,14 +986,6 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
  // no bloom filter. Most keys be checked bloom filters twice.
  ASSERT_GT(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 65000 * 2);
  ASSERT_LT(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 120000 * 2);
-  uint64_t bloom_filter_useful_all_levels = 0;
-  for (auto& kv : (*(get_perf_context()->level_to_perf_context))) {
-    if (kv.second.bloom_filter_useful > 0) {
-      bloom_filter_useful_all_levels += kv.second.bloom_filter_useful;
-    }
-  }
-  ASSERT_GT(bloom_filter_useful_all_levels, 65000 * 2);
-  ASSERT_LT(bloom_filter_useful_all_levels, 120000 * 2);

  for (int i = 0; i < numkeys; i += 2) {
    ASSERT_EQ(Get(1, Key(i)), "val");
@@ -1311,416 +1095,6 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
  ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
  ASSERT_EQ(2 /* index and data block */,
            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-  get_perf_context()->Reset();
-}
-
-int CountIter(std::unique_ptr<Iterator>& iter, const Slice& key) {
-  int count = 0;
-  for (iter->Seek(key); iter->Valid() && iter->status() == Status::OK();
-       iter->Next()) {
-    count++;
-  }
-  return count;
-}
-
-// use iterate_upper_bound to hint compatiability of existing bloom filters.
-// The BF is considered compatible if 1) upper bound and seek key transform
-// into the same string, or 2) the transformed seek key is of the same length
-// as the upper bound and two keys are adjacent according to the comparator.
-TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
-  int iteration = 0;
-  for (bool use_block_based_builder : {true, false}) {
-    Options options;
-    options.create_if_missing = true;
-    options.prefix_extractor.reset(NewCappedPrefixTransform(4));
-    options.disable_auto_compactions = true;
-    options.statistics = CreateDBStatistics();
-    // Enable prefix bloom for SST files
-    BlockBasedTableOptions table_options;
-    table_options.cache_index_and_filter_blocks = true;
-    table_options.filter_policy.reset(
-        NewBloomFilterPolicy(10, use_block_based_builder));
-    table_options.index_shortening = BlockBasedTableOptions::
-        IndexShorteningMode::kShortenSeparatorsAndSuccessor;
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    ASSERT_OK(Put("abcdxxx0", "val1"));
-    ASSERT_OK(Put("abcdxxx1", "val2"));
-    ASSERT_OK(Put("abcdxxx2", "val3"));
-    ASSERT_OK(Put("abcdxxx3", "val4"));
-    dbfull()->Flush(FlushOptions());
-    {
-      // prefix_extractor has not changed, BF will always be read
-      Slice upper_bound("abce");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abcd0000"), 4);
-    }
-    {
-      Slice upper_bound("abcdzzzz");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abcd0000"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:5"}}));
-    ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                        "rocksdb.FixedPrefix.5"));
-    {
-      // BF changed, [abcdxx00, abce) is a valid bound, will trigger BF read
-      Slice upper_bound("abce");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abcdxx00"), 4);
-      // should check bloom filter since upper bound meets requirement
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + iteration);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    {
-      // [abcdxx01, abcey) is not valid bound since upper bound is too long for
-      // the BF in SST (capped:4)
-      Slice upper_bound("abcey");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abcdxx01"), 4);
-      // should skip bloom filter since upper bound is too long
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + iteration);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    {
-      // [abcdxx02, abcdy) is a valid bound since the prefix is the same
-      Slice upper_bound("abcdy");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abcdxx02"), 4);
-      // should check bloom filter since upper bound matches transformed seek
-      // key
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + iteration * 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    {
-      // [aaaaaaaa, abce) is not a valid bound since 1) they don't share the
-      // same prefix, 2) the prefixes are not consecutive
-      Slice upper_bound("abce");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "aaaaaaaa"), 0);
-      // should skip bloom filter since mismatch is found
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + iteration * 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:3"}}));
-    {
-      // [abc, abd) is not a valid bound since the upper bound is too short
-      // for BF (capped:4)
-      Slice upper_bound("abd");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abc"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + iteration * 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:4"}}));
-    {
-      // set back to capped:4 and verify BF is always read
-      Slice upper_bound("abd");
-      ReadOptions read_options;
-      read_options.prefix_same_as_start = true;
-      read_options.iterate_upper_bound = &upper_bound;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "abc"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                3 + iteration * 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
-    }
-    iteration++;
-  }
-}
-
-// Create multiple SST files each with a different prefix_extractor config,
-// verify iterators can read all SST files using the latest config.
-TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
-  int iteration = 0;
-  for (bool use_block_based_builder : {true, false}) {
-    Options options;
-    options.create_if_missing = true;
-    options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-    options.disable_auto_compactions = true;
-    options.statistics = CreateDBStatistics();
-    // Enable prefix bloom for SST files
-    BlockBasedTableOptions table_options;
-    table_options.filter_policy.reset(
-        NewBloomFilterPolicy(10, use_block_based_builder));
-    table_options.cache_index_and_filter_blocks = true;
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    Slice upper_bound("foz90000");
-    ReadOptions read_options;
-    read_options.prefix_same_as_start = true;
-
-    // first SST with fixed:1 BF
-    ASSERT_OK(Put("foo2", "bar2"));
-    ASSERT_OK(Put("foo", "bar"));
-    ASSERT_OK(Put("foq1", "bar1"));
-    ASSERT_OK(Put("fpa", "0"));
-    dbfull()->Flush(FlushOptions());
-    std::unique_ptr<Iterator> iter_old(db_->NewIterator(read_options));
-    ASSERT_EQ(CountIter(iter_old, "foo"), 4);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 1);
-
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
-    ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                        "rocksdb.CappedPrefix.3"));
-    read_options.iterate_upper_bound = &upper_bound;
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-    ASSERT_EQ(CountIter(iter, "foo"), 2);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              1 + iteration);
-    ASSERT_EQ(CountIter(iter, "gpk"), 0);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              1 + iteration);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-
-    // second SST with capped:3 BF
-    ASSERT_OK(Put("foo3", "bar3"));
-    ASSERT_OK(Put("foo4", "bar4"));
-    ASSERT_OK(Put("foq5", "bar5"));
-    ASSERT_OK(Put("fpb", "1"));
-    dbfull()->Flush(FlushOptions());
-    {
-      // BF is cappped:3 now
-      std::unique_ptr<Iterator> iter_tmp(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter_tmp, "foo"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + iteration * 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-      ASSERT_EQ(CountIter(iter_tmp, "gpk"), 0);
-      // both counters are incremented because BF is "not changed" for 1 of the
-      // 2 SST files, so filter is checked once and found no match.
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                3 + iteration * 2);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
-    }
-
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:2"}}));
-    ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                        "rocksdb.FixedPrefix.2"));
-    // third SST with fixed:2 BF
-    ASSERT_OK(Put("foo6", "bar6"));
-    ASSERT_OK(Put("foo7", "bar7"));
-    ASSERT_OK(Put("foq8", "bar8"));
-    ASSERT_OK(Put("fpc", "2"));
-    dbfull()->Flush(FlushOptions());
-    {
-      // BF is fixed:2 now
-      std::unique_ptr<Iterator> iter_tmp(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter_tmp, "foo"), 9);
-      // the first and last BF are checked
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                4 + iteration * 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
-      ASSERT_EQ(CountIter(iter_tmp, "gpk"), 0);
-      // only last BF is checked and not found
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                5 + iteration * 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
-    }
-
-    // iter_old can only see the first SST, so checked plus 1
-    ASSERT_EQ(CountIter(iter_old, "foo"), 4);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              6 + iteration * 3);
-    // iter was created after the first setoptions call so only full filter
-    // will check the filter
-    ASSERT_EQ(CountIter(iter, "foo"), 2);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              6 + iteration * 4);
-
-    {
-      // keys in all three SSTs are visible to iterator
-      // The range of [foo, foz90000] is compatible with (fixed:1) and (fixed:2)
-      // so +2 for checked counter
-      std::unique_ptr<Iterator> iter_all(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter_all, "foo"), 9);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                7 + iteration * 5);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
-      ASSERT_EQ(CountIter(iter_all, "gpk"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                8 + iteration * 5);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
-    }
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
-    ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                        "rocksdb.CappedPrefix.3"));
-    {
-      std::unique_ptr<Iterator> iter_all(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter_all, "foo"), 6);
-      // all three SST are checked because the current options has the same as
-      // the remaining SST (capped:3)
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                9 + iteration * 7);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
-      ASSERT_EQ(CountIter(iter_all, "gpk"), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                10 + iteration * 7);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 4);
-    }
-    // TODO(Zhongyi): Maybe also need to add Get calls to test point look up?
-    iteration++;
-  }
-}
-
-// Create a new column family in a running DB, change prefix_extractor
-// dynamically, verify the iterator created on the new column family behaves
-// as expected
-TEST_F(DBBloomFilterTest, DynamicBloomFilterNewColumnFamily) {
-  int iteration = 0;
-  for (bool use_block_based_builder : {true, false}) {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-    options.disable_auto_compactions = true;
-    options.statistics = CreateDBStatistics();
-    // Enable prefix bloom for SST files
-    BlockBasedTableOptions table_options;
-    table_options.cache_index_and_filter_blocks = true;
-    table_options.filter_policy.reset(
-        NewBloomFilterPolicy(10, use_block_based_builder));
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    CreateAndReopenWithCF({"pikachu" + std::to_string(iteration)}, options);
-    ReadOptions read_options;
-    read_options.prefix_same_as_start = true;
-    // create a new CF and set prefix_extractor dynamically
-    options.prefix_extractor.reset(NewCappedPrefixTransform(3));
-    CreateColumnFamilies({"ramen_dojo_" + std::to_string(iteration)}, options);
-    ASSERT_EQ(0,
-              strcmp(dbfull()->GetOptions(handles_[2]).prefix_extractor->Name(),
-                     "rocksdb.CappedPrefix.3"));
-    ASSERT_OK(Put(2, "foo3", "bar3"));
-    ASSERT_OK(Put(2, "foo4", "bar4"));
-    ASSERT_OK(Put(2, "foo5", "bar5"));
-    ASSERT_OK(Put(2, "foq6", "bar6"));
-    ASSERT_OK(Put(2, "fpq7", "bar7"));
-    dbfull()->Flush(FlushOptions());
-    {
-      std::unique_ptr<Iterator> iter(
-          db_->NewIterator(read_options, handles_[2]));
-      ASSERT_EQ(CountIter(iter, "foo"), 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    ASSERT_OK(
-        dbfull()->SetOptions(handles_[2], {{"prefix_extractor", "fixed:2"}}));
-    ASSERT_EQ(0,
-              strcmp(dbfull()->GetOptions(handles_[2]).prefix_extractor->Name(),
-                     "rocksdb.FixedPrefix.2"));
-    {
-      std::unique_ptr<Iterator> iter(
-          db_->NewIterator(read_options, handles_[2]));
-      ASSERT_EQ(CountIter(iter, "foo"), 4);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 0);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    ASSERT_OK(dbfull()->DropColumnFamily(handles_[2]));
-    dbfull()->DestroyColumnFamilyHandle(handles_[2]);
-    handles_[2] = nullptr;
-    ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-    dbfull()->DestroyColumnFamilyHandle(handles_[1]);
-    handles_[1] = nullptr;
-    iteration++;
-  }
-}
-
-// Verify it's possible to change prefix_extractor at runtime and iterators
-// behaves as expected
-TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
-  int iteration = 0;
-  for (bool use_block_based_builder : {true, false}) {
-    Options options;
-    options.create_if_missing = true;
-    options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-    options.disable_auto_compactions = true;
-    options.statistics = CreateDBStatistics();
-    // Enable prefix bloom for SST files
-    BlockBasedTableOptions table_options;
-    table_options.cache_index_and_filter_blocks = true;
-    table_options.filter_policy.reset(
-        NewBloomFilterPolicy(10, use_block_based_builder));
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    ASSERT_OK(Put("foo2", "bar2"));
-    ASSERT_OK(Put("foo", "bar"));
-    ASSERT_OK(Put("foo1", "bar1"));
-    ASSERT_OK(Put("fpa", "0"));
-    dbfull()->Flush(FlushOptions());
-    ASSERT_OK(Put("foo3", "bar3"));
-    ASSERT_OK(Put("foo4", "bar4"));
-    ASSERT_OK(Put("foo5", "bar5"));
-    ASSERT_OK(Put("fpb", "1"));
-    dbfull()->Flush(FlushOptions());
-    ASSERT_OK(Put("foo6", "bar6"));
-    ASSERT_OK(Put("foo7", "bar7"));
-    ASSERT_OK(Put("foo8", "bar8"));
-    ASSERT_OK(Put("fpc", "2"));
-    dbfull()->Flush(FlushOptions());
-
-    ReadOptions read_options;
-    read_options.prefix_same_as_start = true;
-    {
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      ASSERT_EQ(CountIter(iter, "foo"), 12);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 3);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-    std::unique_ptr<Iterator> iter_old(db_->NewIterator(read_options));
-    ASSERT_EQ(CountIter(iter_old, "foo"), 12);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 6);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-
-    ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
-    ASSERT_EQ(0, strcmp(dbfull()->GetOptions().prefix_extractor->Name(),
-                        "rocksdb.CappedPrefix.3"));
-    {
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-      // "fp*" should be skipped
-      ASSERT_EQ(CountIter(iter, "foo"), 9);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 6);
-      ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    }
-
-    // iterator created before should not be affected and see all keys
-    ASSERT_EQ(CountIter(iter_old, "foo"), 12);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 9);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
-    ASSERT_EQ(CountIter(iter_old, "abc"), 0);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 12);
-    ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
-    iteration++;
-  }
 }

 #endif  // ROCKSDB_LITE
@@ -63,33 +63,33 @@ INSTANTIATE_TEST_CASE_P(DBTestCompactionFilterWithCompactOption,

 class KeepFilter : 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 {
    cfilter_count++;
    return false;
  }

-  const char* Name() const override { return "KeepFilter"; }
+  virtual const char* Name() const override { return "KeepFilter"; }
 };

 class DeleteFilter : 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 {
    cfilter_count++;
    return true;
  }

-  const char* Name() const override { return "DeleteFilter"; }
+  virtual const char* Name() const override { return "DeleteFilter"; }
 };

 class DeleteISFilter : 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 {
    cfilter_count++;
    int i = std::stoi(key.ToString());
    if (i > 5 && i <= 105) {
@@ -98,18 +98,20 @@ class DeleteISFilter : public CompactionFilter {
    return false;
  }

-  bool IgnoreSnapshots() const override { return true; }
+  virtual bool IgnoreSnapshots() const override { return true; }

-  const char* Name() const override { return "DeleteFilter"; }
+  virtual const char* Name() const override { return "DeleteFilter"; }
 };

 // Skip x if floor(x/10) is even, use range skips. Requires that keys are
 // zero-padded to length 10.
 class SkipEvenFilter : public CompactionFilter {
 public:
-  Decision FilterV2(int /*level*/, const Slice& key, ValueType /*value_type*/,
-                    const Slice& /*existing_value*/, std::string* /*new_value*/,
-                    std::string* skip_until) const override {
+  virtual Decision FilterV2(int /*level*/, const Slice& key,
+                            ValueType /*value_type*/,
+                            const Slice& /*existing_value*/,
+                            std::string* /*new_value*/,
+                            std::string* skip_until) const override {
    cfilter_count++;
    int i = std::stoi(key.ToString());
    if (i / 10 % 2 == 0) {
@@ -122,22 +124,22 @@ class SkipEvenFilter : public CompactionFilter {
    return Decision::kKeep;
  }

-  bool IgnoreSnapshots() const override { return true; }
+  virtual bool IgnoreSnapshots() const override { return true; }

-  const char* Name() const override { return "DeleteFilter"; }
+  virtual const char* Name() const override { return "DeleteFilter"; }
 };

 class DelayFilter : public CompactionFilter {
 public:
  explicit DelayFilter(DBTestBase* d) : db_test(d) {}
-  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 {
    db_test->env_->addon_time_.fetch_add(1000);
    return true;
  }

-  const char* Name() const override { return "DelayFilter"; }
+  virtual const char* Name() const override { return "DelayFilter"; }

 private:
  DBTestBase* db_test;
@@ -147,13 +149,13 @@ class ConditionalFilter : public CompactionFilter {
 public:
  explicit ConditionalFilter(const std::string* filtered_value)
      : filtered_value_(filtered_value) {}
-  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 {
    return value.ToString() == *filtered_value_;
  }

-  const char* Name() const override { return "ConditionalFilter"; }
+  virtual const char* Name() const override { return "ConditionalFilter"; }

 private:
  const std::string* filtered_value_;
@@ -163,15 +165,16 @@ class ChangeFilter : public CompactionFilter {
 public:
  explicit ChangeFilter() {}

-  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 {
    assert(new_value != nullptr);
    *new_value = NEW_VALUE;
    *value_changed = true;
    return false;
  }

-  const char* Name() const override { return "ChangeFilter"; }
+  virtual const char* Name() const override { return "ChangeFilter"; }
 };

 class KeepFilterFactory : public CompactionFilterFactory {
@@ -182,7 +185,7 @@ class KeepFilterFactory : public CompactionFilterFactory {
        check_context_cf_id_(check_context_cf_id),
        compaction_filter_created_(false) {}

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (check_context_) {
      EXPECT_EQ(expect_full_compaction_.load(), context.is_full_compaction);
@@ -197,7 +200,7 @@ class KeepFilterFactory : public CompactionFilterFactory {

  bool compaction_filter_created() const { return compaction_filter_created_; }

-  const char* Name() const override { return "KeepFilterFactory"; }
+  virtual const char* Name() const override { return "KeepFilterFactory"; }
  bool check_context_;
  bool check_context_cf_id_;
  std::atomic_bool expect_full_compaction_;
@@ -208,7 +211,7 @@ class KeepFilterFactory : public CompactionFilterFactory {

 class DeleteFilterFactory : public CompactionFilterFactory {
 public:
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (context.is_manual_compaction) {
      return std::unique_ptr<CompactionFilter>(new DeleteFilter());
@@ -217,13 +220,13 @@ class DeleteFilterFactory : public CompactionFilterFactory {
    }
  }

-  const char* Name() const override { return "DeleteFilterFactory"; }
+  virtual const char* Name() const override { return "DeleteFilterFactory"; }
 };

 // Delete Filter Factory which ignores snapshots
 class DeleteISFilterFactory : public CompactionFilterFactory {
 public:
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (context.is_manual_compaction) {
      return std::unique_ptr<CompactionFilter>(new DeleteISFilter());
@@ -232,12 +235,12 @@ class DeleteISFilterFactory : public CompactionFilterFactory {
    }
  }

-  const char* Name() const override { return "DeleteFilterFactory"; }
+  virtual const char* Name() const override { return "DeleteFilterFactory"; }
 };

 class SkipEvenFilterFactory : public CompactionFilterFactory {
 public:
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& context) override {
    if (context.is_manual_compaction) {
      return std::unique_ptr<CompactionFilter>(new SkipEvenFilter());
@@ -246,18 +249,18 @@ class SkipEvenFilterFactory : public CompactionFilterFactory {
    }
  }

-  const char* Name() const override { return "SkipEvenFilterFactory"; }
+  virtual const char* Name() const override { return "SkipEvenFilterFactory"; }
 };

 class DelayFilterFactory : public CompactionFilterFactory {
 public:
  explicit DelayFilterFactory(DBTestBase* d) : db_test(d) {}
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
    return std::unique_ptr<CompactionFilter>(new DelayFilter(db_test));
  }

-  const char* Name() const override { return "DelayFilterFactory"; }
+  virtual const char* Name() const override { return "DelayFilterFactory"; }

 private:
  DBTestBase* db_test;
@@ -268,13 +271,15 @@ class ConditionalFilterFactory : public CompactionFilterFactory {
  explicit ConditionalFilterFactory(const Slice& filtered_value)
      : filtered_value_(filtered_value.ToString()) {}

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
    return std::unique_ptr<CompactionFilter>(
        new ConditionalFilter(&filtered_value_));
  }

-  const char* Name() const override { return "ConditionalFilterFactory"; }
+  virtual const char* Name() const override {
+    return "ConditionalFilterFactory";
+  }

 private:
  std::string filtered_value_;
@@ -284,12 +289,12 @@ class ChangeFilterFactory : public CompactionFilterFactory {
 public:
  explicit ChangeFilterFactory() {}

-  std::unique_ptr<CompactionFilter> CreateCompactionFilter(
+  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
    return std::unique_ptr<CompactionFilter>(new ChangeFilter());
  }

-  const char* Name() const override { return "ChangeFilterFactory"; }
+  virtual const char* Name() const override { return "ChangeFilterFactory"; }
 };

 #ifndef ROCKSDB_LITE
@@ -335,10 +340,9 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
  Arena arena;
  {
    InternalKeyComparator icmp(options.comparator);
-    ReadRangeDelAggregator range_del_agg(&icmp,
-                                         kMaxSequenceNumber /* upper_bound */);
-    ScopedArenaIterator iter(dbfull()->NewInternalIterator(
-        &arena, &range_del_agg, kMaxSequenceNumber, handles_[1]));
+    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
+    ScopedArenaIterator iter(
+        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[1]));
    iter->SeekToFirst();
    ASSERT_OK(iter->status());
    while (iter->Valid()) {
@@ -352,7 +356,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
    }
  }
  ASSERT_EQ(total, 100000);
-  ASSERT_EQ(count, 0);
+  ASSERT_EQ(count, 1);

  // overwrite all the 100K keys once again.
  for (int i = 0; i < 100000; i++) {
@@ -425,10 +429,9 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
  count = 0;
  {
    InternalKeyComparator icmp(options.comparator);
-    ReadRangeDelAggregator range_del_agg(&icmp,
-                                         kMaxSequenceNumber /* upper_bound */);
-    ScopedArenaIterator iter(dbfull()->NewInternalIterator(
-        &arena, &range_del_agg, kMaxSequenceNumber, handles_[1]));
+    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
+    ScopedArenaIterator iter(
+        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[1]));
    iter->SeekToFirst();
    ASSERT_OK(iter->status());
    while (iter->Valid()) {
@@ -643,10 +646,9 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
    int total = 0;
    Arena arena;
    InternalKeyComparator icmp(options.comparator);
-    ReadRangeDelAggregator range_del_agg(&icmp,
-                                         kMaxSequenceNumber /* snapshots */);
-    ScopedArenaIterator iter(dbfull()->NewInternalIterator(
-        &arena, &range_del_agg, kMaxSequenceNumber));
+    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
+    ScopedArenaIterator iter(
+        dbfull()->NewInternalIterator(&arena, &range_del_agg));
    iter->SeekToFirst();
    ASSERT_OK(iter->status());
    while (iter->Valid()) {
@@ -659,7 +661,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
      iter->Next();
    }
    ASSERT_EQ(total, 700);
-    ASSERT_EQ(count, 0);
+    ASSERT_EQ(count, 1);
  }
 }
 #endif  // ROCKSDB_LITE
@@ -694,7 +696,44 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextCfId) {
 }

 #ifndef ROCKSDB_LITE
-// Compaction filters aplies to all records, regardless snapshots.
+// Compaction filters should only be applied to records that are newer than the
+// latest snapshot. This test inserts records and applies a delete filter.
+TEST_F(DBTestCompactionFilter, CompactionFilterSnapshot) {
+  Options options = CurrentOptions();
+  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
+  options.disable_auto_compactions = true;
+  options.create_if_missing = true;
+  DestroyAndReopen(options);
+
+  // Put some data.
+  const Snapshot* snapshot = nullptr;
+  for (int table = 0; table < 4; ++table) {
+    for (int i = 0; i < 10; ++i) {
+      Put(ToString(table * 100 + i), "val");
+    }
+    Flush();
+
+    if (table == 0) {
+      snapshot = db_->GetSnapshot();
+    }
+  }
+  assert(snapshot != nullptr);
+
+  cfilter_count = 0;
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  // The filter should delete 10 records.
+  ASSERT_EQ(30U, cfilter_count);
+
+  // Release the snapshot and compact again -> now all records should be
+  // removed.
+  db_->ReleaseSnapshot(snapshot);
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  ASSERT_EQ(0U, CountLiveFiles());
+}
+
+// Compaction filters should only be applied to records that are newer than the
+// latest snapshot. However, if the compaction filter asks to ignore snapshots
+// records newer than the snapshot will also be processed
 TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
  std::string five = ToString(5);
  Options options = CurrentOptions();
@@ -809,7 +848,7 @@ TEST_F(DBTestCompactionFilter, SkipUntilWithBloomFilter) {
  DestroyAndReopen(options);

  Put("0000000010", "v10");
-  Put("0000000020", "v20");  // skipped
+  Put("0000000020", "v20"); // skipped
  Put("0000000050", "v50");
  Flush();

@@ -832,38 +871,6 @@ TEST_F(DBTestCompactionFilter, SkipUntilWithBloomFilter) {
  EXPECT_EQ("v50", val);
 }

-class TestNotSupportedFilter : public CompactionFilter {
- public:
-  bool Filter(int /*level*/, const Slice& /*key*/, const Slice& /*value*/,
-              std::string* /*new_value*/,
-              bool* /*value_changed*/) const override {
-    return true;
-  }
-
-  const char* Name() const override { return "NotSupported"; }
-  bool IgnoreSnapshots() const override { return false; }
-};
-
-TEST_F(DBTestCompactionFilter, IgnoreSnapshotsFalse) {
-  Options options = CurrentOptions();
-  options.compaction_filter = new TestNotSupportedFilter();
-  DestroyAndReopen(options);
-
-  Put("a", "v10");
-  Put("z", "v20");
-  Flush();
-
-  Put("a", "v10");
-  Put("z", "v20");
-  Flush();
-
-  // Comapction should fail because IgnoreSnapshots() = false
-  EXPECT_TRUE(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr)
-                  .IsNotSupported());
-
-  delete options.compaction_filter;
-}
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -27,7 +27,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
    return;
  }
  // Use InMemoryEnv, or it would be too slow.
-  std::unique_ptr<Env> env(new MockEnv(env_));
+  unique_ptr<Env> env(new MockEnv(env_));

  const int kNKeys = 1000;
  int keys[kNKeys];
@@ -125,7 +125,6 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
  int kMaxKey = 1000000;

  Options options = CurrentOptions();
-  options.compression = kNoCompression;
  options.create_if_missing = true;
  options.write_buffer_size = 20480;
  options.max_write_buffer_number = 2;
@@ -168,8 +167,8 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
  ASSERT_EQ(4U, int_prop);

-  // Insert extra about 28K to L0. After they are compacted to L4, the base
-  // level should be changed to L3.
+  // Insert extra about 28K to L0. After they are compacted to L4, base level
+  // should be changed to L3.
  ASSERT_OK(dbfull()->SetOptions({
      {"disable_auto_compactions", "true"},
  }));
@@ -190,7 +189,13 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
  ASSERT_EQ("0", str_prop);

-  // Write even more data while leaving the base level at L3.
+  // Trigger parallel compaction, and the first one would change the base
+  // level.
+  // Hold compaction jobs to make sure
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "CompactionJob::Run():Start",
+      [&](void* /*arg*/) { env_->SleepForMicroseconds(100000); });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
  ASSERT_OK(dbfull()->SetOptions({
      {"disable_auto_compactions", "true"},
  }));
@@ -203,12 +208,18 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
      {"disable_auto_compactions", "false"},
  }));
  Flush();
+  // Wait for 200 milliseconds before proceeding compactions to make sure two
+  // parallel ones are executed.
+  env_->SleepForMicroseconds(200000);
  dbfull()->TEST_WaitForCompact();
  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
  ASSERT_EQ(3U, int_prop);
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();

-  // Fill up L0, and then run an (auto) L0->Lmax compaction to raise the base
-  // level to 2.
+  // Trigger a condition that the compaction changes base level and L0->Lbase
+  // happens at the same time.
+  // We try to make last levels' targets to be 40K, 160K, 640K, add triggers
+  // another compaction from 40K->160K.
  ASSERT_OK(dbfull()->SetOptions({
      {"disable_auto_compactions", "true"},
  }));
@@ -218,31 +229,23 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
                  RandomString(&rnd, 380)));
  }
-
-  // Make sure that the compaction starts before the last bit of data is
-  // flushed, so that the base level isn't raised to L1.
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
-  });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
  ASSERT_OK(dbfull()->SetOptions({
      {"disable_auto_compactions", "false"},
  }));
-
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:0");
  Flush();
  dbfull()->TEST_WaitForCompact();
  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
  ASSERT_EQ(2U, int_prop);
+
+  // A manual compaction will trigger the base level to become L2
+  // Keep Writing data until base level changed 2->1. There will be L0->L2
+  // compaction going on at the same time.
  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();

-  // Write more data until the base level changes to L1. There will be
-  // a manual compaction going on at the same time.
  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:1"},
-      {"DynamicLevelMaxBytesBase2:2", "CompactionJob::Run():End"},
+      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
+      {"DynamicLevelMaxBytesBase2:1", "CompactionJob::Run():End"},
      {"DynamicLevelMaxBytesBase2:compact_range_finish",
       "FlushJob::WriteLevel0Table"},
  });
@@ -254,12 +257,12 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
    TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:compact_range_finish");
  });

-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:1");
+  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:0");
  for (int i = 0; i < 2; i++) {
    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
                  RandomString(&rnd, 380)));
  }
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:2");
+  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:1");

  Flush();

@@ -7,7 +7,7 @@
 #include "port/stack_trace.h"
 #include "rocksdb/perf_context.h"
 #if !defined(ROCKSDB_LITE)
-#include "test_util/sync_point.h"
+#include "util/sync_point.h"
 #endif
 #include <iostream>
 #include <string>
@@ -40,7 +40,7 @@ TEST_F(DBEncryptionTest, CheckEncrypted) {
      continue;
    }
    auto filePath = dbname_ + "/" + *it;
-    std::unique_ptr<SequentialFile> seqFile;
+    unique_ptr<SequentialFile> seqFile;
    auto envOptions = EnvOptions(CurrentOptions());
    status = defaultEnv->NewSequentialFile(filePath, &seqFile, envOptions);
    ASSERT_OK(status);
@@ -6,20 +6,24 @@

 #ifndef ROCKSDB_LITE

-#include <cinttypes>
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
 #include <stdint.h>
 #include <algorithm>
 #include <string>
-#include "db/db_impl/db_impl.h"
+#include "db/db_impl.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
-#include "file/file_util.h"
-#include "file/filename.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "test_util/sync_point.h"
+#include "util/file_util.h"
+#include "util/filename.h"
 #include "util/mutexlock.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -40,7 +44,7 @@ Status DBImpl::EnableFileDeletions(bool force) {
  // Job id == 0 means that this is not our background process, but rather
  // user thread
  JobContext job_context(0);
-  bool file_deletion_enabled = false;
+  bool should_purge_files = false;
  {
    InstrumentedMutexLock l(&mutex_);
    if (force) {
@@ -50,20 +54,19 @@ Status DBImpl::EnableFileDeletions(bool force) {
      --disable_delete_obsolete_files_;
    }
    if (disable_delete_obsolete_files_ == 0)  {
-      file_deletion_enabled = true;
+      ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Enabled");
+      should_purge_files = true;
      FindObsoleteFiles(&job_context, true);
      bg_cv_.SignalAll();
+    } else {
+      ROCKS_LOG_WARN(
+          immutable_db_options_.info_log,
+          "File Deletions Enable, but not really enabled. Counter: %d",
+          disable_delete_obsolete_files_);
    }
  }
-  if (file_deletion_enabled) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Enabled");
-    if (job_context.HaveSomethingToDelete()) {
-      PurgeObsoleteFiles(job_context);
-    }
-  } else {
-    ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                   "File Deletions Enable, but not really enabled. Counter: %d",
-                   disable_delete_obsolete_files_);
+  if (should_purge_files)  {
+    PurgeObsoleteFiles(job_context);
  }
  job_context.Clean();
  LogFlush(immutable_db_options_.info_log);
@@ -84,28 +87,19 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
  if (flush_memtable) {
    // flush all dirty data to disk.
    Status status;
-    if (immutable_db_options_.atomic_flush) {
-      autovector<ColumnFamilyData*> cfds;
-      SelectColumnFamiliesForAtomicFlush(&cfds);
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      if (cfd->IsDropped()) {
+        continue;
+      }
+      cfd->Ref();
      mutex_.Unlock();
-      status = AtomicFlushMemTables(cfds, FlushOptions(),
-                                    FlushReason::kGetLiveFiles);
+      status = FlushMemTable(cfd, FlushOptions(), FlushReason::kGetLiveFiles);
+      TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
+      TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
      mutex_.Lock();
-    } else {
-      for (auto cfd : *versions_->GetColumnFamilySet()) {
-        if (cfd->IsDropped()) {
-          continue;
-        }
-        cfd->Ref();
-        mutex_.Unlock();
-        status = FlushMemTable(cfd, FlushOptions(), FlushReason::kGetLiveFiles);
-        TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
-        TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
-        mutex_.Lock();
-        cfd->Unref();
-        if (!status.ok()) {
-          break;
-        }
+      cfd->Unref();
+      if (!status.ok()) {
+        break;
      }
    }
    versions_->GetColumnFamilySet()->FreeDeadColumnFamilies();
@@ -132,7 +126,7 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,

  // create names of the live files. The names are not absolute
  // paths, instead they are relative to dbname_;
-  for (const auto& live_file : live) {
+  for (auto live_file : live) {
    ret.push_back(MakeTableFileName("", live_file.GetNumber()));
  }

@@ -9,8 +9,8 @@

 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
-#include "test_util/fault_injection_test_env.h"
-#include "test_util/sync_point.h"
+#include "util/fault_injection_test_env.h"
+#include "util/sync_point.h"

 namespace rocksdb {

@@ -25,12 +25,6 @@ class DBFlushDirectIOTest : public DBFlushTest,
  DBFlushDirectIOTest() : DBFlushTest() {}
 };

-class DBAtomicFlushTest : public DBFlushTest,
-                          public ::testing::WithParamInterface<bool> {
- public:
-  DBAtomicFlushTest() : DBFlushTest() {}
-};
-
 // We had issue when two background threads trying to flush at the same time,
 // only one of them get committed. The test verifies the issue is fixed.
 TEST_F(DBFlushTest, FlushWhileWritingManifest) {
@@ -41,12 +35,11 @@ TEST_F(DBFlushTest, FlushWhileWritingManifest) {
  Reopen(options);
  FlushOptions no_wait;
  no_wait.wait = false;
-  no_wait.allow_write_stall=true;

  SyncPoint::GetInstance()->LoadDependency(
      {{"VersionSet::LogAndApply:WriteManifest",
        "DBFlushTest::FlushWhileWritingManifest:1"},
-       {"MemTableList::TryInstallMemtableFlushResults:InProgress",
+       {"MemTableList::InstallMemtableFlushResults:InProgress",
        "VersionSet::LogAndApply:WriteManifestDone"}});
  SyncPoint::GetInstance()->EnableProcessing();

@@ -62,8 +55,6 @@ TEST_F(DBFlushTest, FlushWhileWritingManifest) {
 #endif  // ROCKSDB_LITE
 }

-// Disable this test temporarily on Travis as it fails intermittently.
-// Github issue: #4151
 TEST_F(DBFlushTest, SyncFail) {
  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
      new FaultInjectionTestEnv(env_));
@@ -72,15 +63,11 @@ TEST_F(DBFlushTest, SyncFail) {
  options.env = fault_injection_env.get();

  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBFlushTest::SyncFail:GetVersionRefCount:1",
-        "DBImpl::FlushMemTableToOutputFile:BeforePickMemtables"},
-       {"DBImpl::FlushMemTableToOutputFile:AfterPickMemtables",
-        "DBFlushTest::SyncFail:GetVersionRefCount:2"},
-       {"DBFlushTest::SyncFail:1", "DBImpl::SyncClosedLogs:Start"},
+      {{"DBFlushTest::SyncFail:1", "DBImpl::SyncClosedLogs:Start"},
       {"DBImpl::SyncClosedLogs:Failed", "DBFlushTest::SyncFail:2"}});
  SyncPoint::GetInstance()->EnableProcessing();

-  CreateAndReopenWithCF({"pikachu"}, options);
+  Reopen(options);
  Put("key", "value");
  auto* cfd =
      reinterpret_cast<ColumnFamilyHandleImpl*>(db_->DefaultColumnFamily())
@@ -91,10 +78,6 @@ TEST_F(DBFlushTest, SyncFail) {
  // Flush installs a new super-version. Get the ref count after that.
  auto current_before = cfd->current();
  int refs_before = cfd->current()->TEST_refs();
-  TEST_SYNC_POINT("DBFlushTest::SyncFail:GetVersionRefCount:1");
-  TEST_SYNC_POINT("DBFlushTest::SyncFail:GetVersionRefCount:2");
-  int refs_after_picking_memtables = cfd->current()->TEST_refs();
-  ASSERT_EQ(refs_before + 1, refs_after_picking_memtables);
  fault_injection_env->SetFilesystemActive(false);
  TEST_SYNC_POINT("DBFlushTest::SyncFail:1");
  TEST_SYNC_POINT("DBFlushTest::SyncFail:2");
@@ -110,30 +93,6 @@ TEST_F(DBFlushTest, SyncFail) {
  Destroy(options);
 }

-TEST_F(DBFlushTest, SyncSkip) {
-  Options options = CurrentOptions();
-
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBFlushTest::SyncSkip:1", "DBImpl::SyncClosedLogs:Skip"},
-       {"DBImpl::SyncClosedLogs:Skip", "DBFlushTest::SyncSkip:2"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  Reopen(options);
-  Put("key", "value");
-
-  FlushOptions flush_options;
-  flush_options.wait = false;
-  ASSERT_OK(dbfull()->Flush(flush_options));
-
-  TEST_SYNC_POINT("DBFlushTest::SyncSkip:1");
-  TEST_SYNC_POINT("DBFlushTest::SyncSkip:2");
-
-  // Now the background job will do the flush; wait for it.
-  dbfull()->TEST_WaitForFlushMemTable();
-
-  Destroy(options);
-}
-
 TEST_F(DBFlushTest, FlushInLowPriThreadPool) {
  // Verify setting an empty high-pri (flush) thread pool causes flushes to be
  // scheduled in the low-pri (compaction) thread pool.
@@ -250,382 +209,9 @@ TEST_F(DBFlushTest, FlushError) {
  ASSERT_NE(s, Status::OK());
 }

-TEST_F(DBFlushTest, ManualFlushFailsInReadOnlyMode) {
-  // Regression test for bug where manual flush hangs forever when the DB
-  // is in read-only mode. Verify it now at least returns, despite failing.
-  Options options;
-  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
-      new FaultInjectionTestEnv(env_));
-  options.env = fault_injection_env.get();
-  options.max_write_buffer_number = 2;
-  Reopen(options);
-
-  // Trigger a first flush but don't let it run
-  ASSERT_OK(db_->PauseBackgroundWork());
-  ASSERT_OK(Put("key1", "value1"));
-  FlushOptions flush_opts;
-  flush_opts.wait = false;
-  ASSERT_OK(db_->Flush(flush_opts));
-
-  // Write a key to the second memtable so we have something to flush later
-  // after the DB is in read-only mode.
-  ASSERT_OK(Put("key2", "value2"));
-
-  // Let the first flush continue, hit an error, and put the DB in read-only
-  // mode.
-  fault_injection_env->SetFilesystemActive(false);
-  ASSERT_OK(db_->ContinueBackgroundWork());
-  dbfull()->TEST_WaitForFlushMemTable();
-#ifndef ROCKSDB_LITE
-  uint64_t num_bg_errors;
-  ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kBackgroundErrors,
-                                  &num_bg_errors));
-  ASSERT_GT(num_bg_errors, 0);
-#endif  // ROCKSDB_LITE
-
-  // In the bug scenario, triggering another flush would cause the second flush
-  // to hang forever. After the fix we expect it to return an error.
-  ASSERT_NOK(db_->Flush(FlushOptions()));
-
-  Close();
-}
-
-TEST_F(DBFlushTest, CFDropRaceWithWaitForFlushMemTables) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  CreateAndReopenWithCF({"pikachu"}, options);
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::FlushMemTable:AfterScheduleFlush",
-        "DBFlushTest::CFDropRaceWithWaitForFlushMemTables:BeforeDrop"},
-       {"DBFlushTest::CFDropRaceWithWaitForFlushMemTables:AfterFree",
-        "DBImpl::BackgroundCallFlush:start"},
-       {"DBImpl::BackgroundCallFlush:start",
-        "DBImpl::FlushMemTable:BeforeWaitForBgFlush"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_EQ(2, handles_.size());
-  ASSERT_OK(Put(1, "key", "value"));
-  auto* cfd = static_cast<ColumnFamilyHandleImpl*>(handles_[1])->cfd();
-  port::Thread drop_cf_thr([&]() {
-    TEST_SYNC_POINT(
-        "DBFlushTest::CFDropRaceWithWaitForFlushMemTables:BeforeDrop");
-    ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-    ASSERT_OK(dbfull()->DestroyColumnFamilyHandle(handles_[1]));
-    handles_.resize(1);
-    TEST_SYNC_POINT(
-        "DBFlushTest::CFDropRaceWithWaitForFlushMemTables:AfterFree");
-  });
-  FlushOptions flush_opts;
-  flush_opts.allow_write_stall = true;
-  ASSERT_NOK(dbfull()->TEST_FlushMemTable(cfd, flush_opts));
-  drop_cf_thr.join();
-  Close();
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
-TEST_P(DBAtomicFlushTest, ManualAtomicFlush) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = GetParam();
-  options.write_buffer_size = (static_cast<size_t>(64) << 20);
-
-  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(3, num_cfs);
-  WriteOptions wopts;
-  wopts.disableWAL = true;
-  for (size_t i = 0; i != num_cfs; ++i) {
-    ASSERT_OK(Put(static_cast<int>(i) /*cf*/, "key", "value", wopts));
-  }
-  std::vector<int> cf_ids;
-  for (size_t i = 0; i != num_cfs; ++i) {
-    cf_ids.emplace_back(static_cast<int>(i));
-  }
-  ASSERT_OK(Flush(cf_ids));
-  for (size_t i = 0; i != num_cfs; ++i) {
-    auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
-    ASSERT_EQ(0, cfh->cfd()->imm()->NumNotFlushed());
-    ASSERT_TRUE(cfh->cfd()->mem()->IsEmpty());
-  }
-}
-
-TEST_P(DBAtomicFlushTest, AtomicFlushTriggeredByMemTableFull) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = GetParam();
-  // 4KB so that we can easily trigger auto flush.
-  options.write_buffer_size = 4096;
-
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::BackgroundCallFlush:FlushFinish:0",
-        "DBAtomicFlushTest::AtomicFlushTriggeredByMemTableFull:BeforeCheck"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(3, num_cfs);
-  WriteOptions wopts;
-  wopts.disableWAL = true;
-  for (size_t i = 0; i != num_cfs; ++i) {
-    ASSERT_OK(Put(static_cast<int>(i) /*cf*/, "key", "value", wopts));
-  }
-  // Keep writing to one of them column families to trigger auto flush.
-  for (int i = 0; i != 4000; ++i) {
-    ASSERT_OK(Put(static_cast<int>(num_cfs) - 1 /*cf*/,
-                  "key" + std::to_string(i), "value" + std::to_string(i),
-                  wopts));
-  }
-
-  TEST_SYNC_POINT(
-      "DBAtomicFlushTest::AtomicFlushTriggeredByMemTableFull:BeforeCheck");
-  if (options.atomic_flush) {
-    for (size_t i = 0; i != num_cfs - 1; ++i) {
-      auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
-      ASSERT_EQ(0, cfh->cfd()->imm()->NumNotFlushed());
-      ASSERT_TRUE(cfh->cfd()->mem()->IsEmpty());
-    }
-  } else {
-    for (size_t i = 0; i != num_cfs - 1; ++i) {
-      auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
-      ASSERT_EQ(0, cfh->cfd()->imm()->NumNotFlushed());
-      ASSERT_FALSE(cfh->cfd()->mem()->IsEmpty());
-    }
-  }
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
-TEST_P(DBAtomicFlushTest, AtomicFlushRollbackSomeJobs) {
-  bool atomic_flush = GetParam();
-  if (!atomic_flush) {
-    return;
-  }
-  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
-      new FaultInjectionTestEnv(env_));
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-  options.env = fault_injection_env.get();
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::AtomicFlushMemTablesToOutputFiles:SomeFlushJobsComplete:1",
-        "DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:1"},
-       {"DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:2",
-        "DBImpl::AtomicFlushMemTablesToOutputFiles:SomeFlushJobsComplete:2"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(3, num_cfs);
-  WriteOptions wopts;
-  wopts.disableWAL = true;
-  for (size_t i = 0; i != num_cfs; ++i) {
-    int cf_id = static_cast<int>(i);
-    ASSERT_OK(Put(cf_id, "key", "value", wopts));
-  }
-  FlushOptions flush_opts;
-  flush_opts.wait = false;
-  ASSERT_OK(dbfull()->Flush(flush_opts, handles_));
-  TEST_SYNC_POINT("DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:1");
-  fault_injection_env->SetFilesystemActive(false);
-  TEST_SYNC_POINT("DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:2");
-  for (auto* cfh : handles_) {
-    dbfull()->TEST_WaitForFlushMemTable(cfh);
-  }
-  for (size_t i = 0; i != num_cfs; ++i) {
-    auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
-    ASSERT_EQ(1, cfh->cfd()->imm()->NumNotFlushed());
-    ASSERT_TRUE(cfh->cfd()->mem()->IsEmpty());
-  }
-  fault_injection_env->SetFilesystemActive(true);
-  Destroy(options);
-}
-
-TEST_P(DBAtomicFlushTest, FlushMultipleCFs_DropSomeBeforeRequestFlush) {
-  bool atomic_flush = GetParam();
-  if (!atomic_flush) {
-    return;
-  }
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(3, num_cfs);
-  WriteOptions wopts;
-  wopts.disableWAL = true;
-  std::vector<int> cf_ids;
-  for (size_t i = 0; i != num_cfs; ++i) {
-    int cf_id = static_cast<int>(i);
-    ASSERT_OK(Put(cf_id, "key", "value", wopts));
-    cf_ids.push_back(cf_id);
-  }
-  ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-  ASSERT_TRUE(Flush(cf_ids).IsColumnFamilyDropped());
-  Destroy(options);
-}
-
-TEST_P(DBAtomicFlushTest,
-       FlushMultipleCFs_DropSomeAfterScheduleFlushBeforeFlushJobRun) {
-  bool atomic_flush = GetParam();
-  if (!atomic_flush) {
-    return;
-  }
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-
-  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::AtomicFlushMemTables:AfterScheduleFlush",
-        "DBAtomicFlushTest::BeforeDropCF"},
-       {"DBAtomicFlushTest::AfterDropCF",
-        "DBImpl::BackgroundCallFlush:start"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(3, num_cfs);
-  WriteOptions wopts;
-  wopts.disableWAL = true;
-  for (size_t i = 0; i != num_cfs; ++i) {
-    int cf_id = static_cast<int>(i);
-    ASSERT_OK(Put(cf_id, "key", "value", wopts));
-  }
-  port::Thread user_thread([&]() {
-    TEST_SYNC_POINT("DBAtomicFlushTest::BeforeDropCF");
-    ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-    TEST_SYNC_POINT("DBAtomicFlushTest::AfterDropCF");
-  });
-  FlushOptions flush_opts;
-  flush_opts.wait = true;
-  ASSERT_OK(dbfull()->Flush(flush_opts, handles_));
-  user_thread.join();
-  for (size_t i = 0; i != num_cfs; ++i) {
-    int cf_id = static_cast<int>(i);
-    ASSERT_EQ("value", Get(cf_id, "key"));
-  }
-
-  ReopenWithColumnFamilies({kDefaultColumnFamilyName, "eevee"}, options);
-  num_cfs = handles_.size();
-  ASSERT_EQ(2, num_cfs);
-  for (size_t i = 0; i != num_cfs; ++i) {
-    int cf_id = static_cast<int>(i);
-    ASSERT_EQ("value", Get(cf_id, "key"));
-  }
-  Destroy(options);
-}
-
-TEST_P(DBAtomicFlushTest, TriggerFlushAndClose) {
-  bool atomic_flush = GetParam();
-  if (!atomic_flush) {
-    return;
-  }
-  const int kNumKeysTriggerFlush = 4;
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-  options.memtable_factory.reset(
-      new SpecialSkipListFactory(kNumKeysTriggerFlush));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  for (int i = 0; i != kNumKeysTriggerFlush; ++i) {
-    ASSERT_OK(Put(0, "key" + std::to_string(i), "value" + std::to_string(i)));
-  }
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_OK(Put(0, "key", "value"));
-  Close();
-
-  ReopenWithColumnFamilies({kDefaultColumnFamilyName, "pikachu"}, options);
-  ASSERT_EQ("value", Get(0, "key"));
-}
-
-TEST_P(DBAtomicFlushTest, PickMemtablesRaceWithBackgroundFlush) {
-  bool atomic_flush = GetParam();
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-  options.max_write_buffer_number = 4;
-  // Set min_write_buffer_number_to_merge to be greater than 1, so that
-  // a column family with one memtable in the imm will not cause IsFlushPending
-  // to return true when flush_requested_ is false.
-  options.min_write_buffer_number_to_merge = 2;
-  CreateAndReopenWithCF({"pikachu"}, options);
-  ASSERT_EQ(2, handles_.size());
-  ASSERT_OK(dbfull()->PauseBackgroundWork());
-  ASSERT_OK(Put(0, "key00", "value00"));
-  ASSERT_OK(Put(1, "key10", "value10"));
-  FlushOptions flush_opts;
-  flush_opts.wait = false;
-  ASSERT_OK(dbfull()->Flush(flush_opts, handles_));
-  ASSERT_OK(Put(0, "key01", "value01"));
-  // Since max_write_buffer_number is 4, the following flush won't cause write
-  // stall.
-  ASSERT_OK(dbfull()->Flush(flush_opts));
-  ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-  ASSERT_OK(dbfull()->DestroyColumnFamilyHandle(handles_[1]));
-  handles_[1] = nullptr;
-  ASSERT_OK(dbfull()->ContinueBackgroundWork());
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable(handles_[0]));
-  delete handles_[0];
-  handles_.clear();
-}
-
-TEST_P(DBAtomicFlushTest, CFDropRaceWithWaitForFlushMemTables) {
-  bool atomic_flush = GetParam();
-  if (!atomic_flush) {
-    return;
-  }
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-  CreateAndReopenWithCF({"pikachu"}, options);
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::AtomicFlushMemTables:AfterScheduleFlush",
-        "DBAtomicFlushTest::CFDropRaceWithWaitForFlushMemTables:BeforeDrop"},
-       {"DBAtomicFlushTest::CFDropRaceWithWaitForFlushMemTables:AfterFree",
-        "DBImpl::BackgroundCallFlush:start"},
-       {"DBImpl::BackgroundCallFlush:start",
-        "DBImpl::AtomicFlushMemTables:BeforeWaitForBgFlush"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_EQ(2, handles_.size());
-  ASSERT_OK(Put(0, "key", "value"));
-  ASSERT_OK(Put(1, "key", "value"));
-  auto* cfd_default =
-      static_cast<ColumnFamilyHandleImpl*>(dbfull()->DefaultColumnFamily())
-          ->cfd();
-  auto* cfd_pikachu = static_cast<ColumnFamilyHandleImpl*>(handles_[1])->cfd();
-  port::Thread drop_cf_thr([&]() {
-    TEST_SYNC_POINT(
-        "DBAtomicFlushTest::CFDropRaceWithWaitForFlushMemTables:BeforeDrop");
-    ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-    delete handles_[1];
-    handles_.resize(1);
-    TEST_SYNC_POINT(
-        "DBAtomicFlushTest::CFDropRaceWithWaitForFlushMemTables:AfterFree");
-  });
-  FlushOptions flush_opts;
-  flush_opts.allow_write_stall = true;
-  ASSERT_OK(dbfull()->TEST_AtomicFlushMemTables({cfd_default, cfd_pikachu},
-                                                flush_opts));
-  drop_cf_thr.join();
-  Close();
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
 INSTANTIATE_TEST_CASE_P(DBFlushDirectIOTest, DBFlushDirectIOTest,
                        testing::Bool());

-INSTANTIATE_TEST_CASE_P(DBAtomicFlushTest, DBAtomicFlushTest, testing::Bool());
-
 }  // namespace rocksdb

 int main(int argc, char** argv) {
@@ -1,648 +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/db_impl/db_impl_secondary.h"
-
-#include <cinttypes>
-
-#include "db/db_iter.h"
-#include "db/merge_context.h"
-#include "logging/auto_roll_logger.h"
-#include "monitoring/perf_context_imp.h"
-
-namespace rocksdb {
-
-#ifndef ROCKSDB_LITE
-DBImplSecondary::DBImplSecondary(const DBOptions& db_options,
-                                 const std::string& dbname)
-    : DBImpl(db_options, dbname) {
-  ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                 "Opening the db in secondary mode");
-  LogFlush(immutable_db_options_.info_log);
-}
-
-DBImplSecondary::~DBImplSecondary() {}
-
-Status DBImplSecondary::Recover(
-    const std::vector<ColumnFamilyDescriptor>& column_families,
-    bool /*readonly*/, bool /*error_if_log_file_exist*/,
-    bool /*error_if_data_exists_in_logs*/) {
-  mutex_.AssertHeld();
-
-  JobContext job_context(0);
-  Status s;
-  s = static_cast<ReactiveVersionSet*>(versions_.get())
-          ->Recover(column_families, &manifest_reader_, &manifest_reporter_,
-                    &manifest_reader_status_);
-  if (!s.ok()) {
-    return s;
-  }
-  if (immutable_db_options_.paranoid_checks && s.ok()) {
-    s = CheckConsistency();
-  }
-  // Initial max_total_in_memory_state_ before recovery logs.
-  max_total_in_memory_state_ = 0;
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    auto* mutable_cf_options = cfd->GetLatestMutableCFOptions();
-    max_total_in_memory_state_ += mutable_cf_options->write_buffer_size *
-                                  mutable_cf_options->max_write_buffer_number;
-  }
-  if (s.ok()) {
-    default_cf_handle_ = new ColumnFamilyHandleImpl(
-        versions_->GetColumnFamilySet()->GetDefault(), this, &mutex_);
-    default_cf_internal_stats_ = default_cf_handle_->cfd()->internal_stats();
-    single_column_family_mode_ =
-        versions_->GetColumnFamilySet()->NumberOfColumnFamilies() == 1;
-
-    std::unordered_set<ColumnFamilyData*> cfds_changed;
-    s = FindAndRecoverLogFiles(&cfds_changed, &job_context);
-  }
-
-  if (s.IsPathNotFound()) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                   "Secondary tries to read WAL, but WAL file(s) have already "
-                   "been purged by primary.");
-    s = Status::OK();
-  }
-  // TODO: update options_file_number_ needed?
-
-  job_context.Clean();
-  return s;
-}
-
-// find new WAL and apply them in order to the secondary instance
-Status DBImplSecondary::FindAndRecoverLogFiles(
-    std::unordered_set<ColumnFamilyData*>* cfds_changed,
-    JobContext* job_context) {
-  assert(nullptr != cfds_changed);
-  assert(nullptr != job_context);
-  Status s;
-  std::vector<uint64_t> logs;
-  s = FindNewLogNumbers(&logs);
-  if (s.ok() && !logs.empty()) {
-    SequenceNumber next_sequence(kMaxSequenceNumber);
-    s = RecoverLogFiles(logs, &next_sequence, cfds_changed, job_context);
-  }
-  return s;
-}
-
-// List wal_dir and find all new WALs, return these log numbers
-Status DBImplSecondary::FindNewLogNumbers(std::vector<uint64_t>* logs) {
-  assert(logs != nullptr);
-  std::vector<std::string> filenames;
-  Status s;
-  s = env_->GetChildren(immutable_db_options_.wal_dir, &filenames);
-  if (s.IsNotFound()) {
-    return Status::InvalidArgument("Failed to open wal_dir",
-                                   immutable_db_options_.wal_dir);
-  } else if (!s.ok()) {
-    return s;
-  }
-
-  // if log_readers_ is non-empty, it means we have applied all logs with log
-  // numbers smaller than the smallest log in log_readers_, so there is no
-  // need to pass these logs to RecoverLogFiles
-  uint64_t log_number_min = 0;
-  if (!log_readers_.empty()) {
-    log_number_min = log_readers_.begin()->first;
-  }
-  for (size_t i = 0; i < filenames.size(); i++) {
-    uint64_t number;
-    FileType type;
-    if (ParseFileName(filenames[i], &number, &type) && type == kLogFile &&
-        number >= log_number_min) {
-      logs->push_back(number);
-    }
-  }
-  // Recover logs in the order that they were generated
-  if (!logs->empty()) {
-    std::sort(logs->begin(), logs->end());
-  }
-  return s;
-}
-
-Status DBImplSecondary::MaybeInitLogReader(
-    uint64_t log_number, log::FragmentBufferedReader** log_reader) {
-  auto iter = log_readers_.find(log_number);
-  // make sure the log file is still present
-  if (iter == log_readers_.end() ||
-      iter->second->reader_->GetLogNumber() != log_number) {
-    // delete the obsolete log reader if log number mismatch
-    if (iter != log_readers_.end()) {
-      log_readers_.erase(iter);
-    }
-    // initialize log reader from log_number
-    // TODO: min_log_number_to_keep_2pc check needed?
-    // Open the log file
-    std::string fname = LogFileName(immutable_db_options_.wal_dir, log_number);
-    ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                   "Recovering log #%" PRIu64 " mode %d", log_number,
-                   static_cast<int>(immutable_db_options_.wal_recovery_mode));
-
-    std::unique_ptr<SequentialFileReader> file_reader;
-    {
-      std::unique_ptr<SequentialFile> file;
-      Status status = env_->NewSequentialFile(
-          fname, &file, env_->OptimizeForLogRead(env_options_));
-      if (!status.ok()) {
-        *log_reader = nullptr;
-        return status;
-      }
-      file_reader.reset(new SequentialFileReader(std::move(file), fname));
-    }
-
-    // Create the log reader.
-    LogReaderContainer* log_reader_container = new LogReaderContainer(
-        env_, immutable_db_options_.info_log, std::move(fname),
-        std::move(file_reader), log_number);
-    log_readers_.insert(std::make_pair(
-        log_number, std::unique_ptr<LogReaderContainer>(log_reader_container)));
-  }
-  iter = log_readers_.find(log_number);
-  assert(iter != log_readers_.end());
-  *log_reader = iter->second->reader_;
-  return Status::OK();
-}
-
-// After manifest recovery, replay WALs and refresh log_readers_ if necessary
-// REQUIRES: log_numbers are sorted in ascending order
-Status DBImplSecondary::RecoverLogFiles(
-    const std::vector<uint64_t>& log_numbers, SequenceNumber* next_sequence,
-    std::unordered_set<ColumnFamilyData*>* cfds_changed,
-    JobContext* job_context) {
-  assert(nullptr != cfds_changed);
-  assert(nullptr != job_context);
-  mutex_.AssertHeld();
-  Status status;
-  for (auto log_number : log_numbers) {
-    log::FragmentBufferedReader* reader = nullptr;
-    status = MaybeInitLogReader(log_number, &reader);
-    if (!status.ok()) {
-      return status;
-    }
-    assert(reader != nullptr);
-  }
-  for (auto log_number : log_numbers) {
-    auto it  = log_readers_.find(log_number);
-    assert(it != log_readers_.end());
-    log::FragmentBufferedReader* reader = it->second->reader_;
-    // Manually update the file number allocation counter in VersionSet.
-    versions_->MarkFileNumberUsed(log_number);
-
-    // Determine if we should tolerate incomplete records at the tail end of the
-    // Read all the records and add to a memtable
-    std::string scratch;
-    Slice record;
-    WriteBatch batch;
-
-    while (reader->ReadRecord(&record, &scratch,
-                              immutable_db_options_.wal_recovery_mode) &&
-           status.ok()) {
-      if (record.size() < WriteBatchInternal::kHeader) {
-        reader->GetReporter()->Corruption(
-            record.size(), Status::Corruption("log record too small"));
-        continue;
-      }
-      WriteBatchInternal::SetContents(&batch, record);
-      SequenceNumber seq_of_batch = WriteBatchInternal::Sequence(&batch);
-      std::vector<uint32_t> column_family_ids;
-      status = CollectColumnFamilyIdsFromWriteBatch(batch, &column_family_ids);
-      if (status.ok()) {
-        for (const auto id : column_family_ids) {
-          ColumnFamilyData* cfd =
-              versions_->GetColumnFamilySet()->GetColumnFamily(id);
-          if (cfd == nullptr) {
-            continue;
-          }
-          if (cfds_changed->count(cfd) == 0) {
-            cfds_changed->insert(cfd);
-          }
-          const std::vector<FileMetaData*>& l0_files =
-              cfd->current()->storage_info()->LevelFiles(0);
-          SequenceNumber seq =
-              l0_files.empty() ? 0 : l0_files.back()->fd.largest_seqno;
-          // If the write batch's sequence number is smaller than the last
-          // sequence number of the largest sequence persisted for this column
-          // family, then its data must reside in an SST that has already been
-          // added in the prior MANIFEST replay.
-          if (seq_of_batch <= seq) {
-            continue;
-          }
-          auto curr_log_num = port::kMaxUint64;
-          if (cfd_to_current_log_.count(cfd) > 0) {
-            curr_log_num = cfd_to_current_log_[cfd];
-          }
-          // If the active memtable contains records added by replaying an
-          // earlier WAL, then we need to seal the memtable, add it to the
-          // immutable memtable list and create a new active memtable.
-          if (!cfd->mem()->IsEmpty() && (curr_log_num == port::kMaxUint64 ||
-                                         curr_log_num != log_number)) {
-            const MutableCFOptions mutable_cf_options =
-                *cfd->GetLatestMutableCFOptions();
-            MemTable* new_mem =
-                cfd->ConstructNewMemtable(mutable_cf_options, seq_of_batch);
-            cfd->mem()->SetNextLogNumber(log_number);
-            cfd->imm()->Add(cfd->mem(), &job_context->memtables_to_free);
-            new_mem->Ref();
-            cfd->SetMemtable(new_mem);
-          }
-        }
-        bool has_valid_writes = false;
-        status = WriteBatchInternal::InsertInto(
-            &batch, column_family_memtables_.get(),
-            nullptr /* flush_scheduler */, true, log_number, this,
-            false /* concurrent_memtable_writes */, next_sequence,
-            &has_valid_writes, seq_per_batch_, batch_per_txn_);
-      }
-      // If column family was not found, it might mean that the WAL write
-      // batch references to the column family that was dropped after the
-      // insert. We don't want to fail the whole write batch in that case --
-      // we just ignore the update.
-      // That's why we set ignore missing column families to true
-      // passing null flush_scheduler will disable memtable flushing which is
-      // needed for secondary instances
-      if (status.ok()) {
-        for (const auto id : column_family_ids) {
-          ColumnFamilyData* cfd =
-              versions_->GetColumnFamilySet()->GetColumnFamily(id);
-          if (cfd == nullptr) {
-            continue;
-          }
-          std::unordered_map<ColumnFamilyData*, uint64_t>::iterator iter =
-              cfd_to_current_log_.find(cfd);
-          if (iter == cfd_to_current_log_.end()) {
-            cfd_to_current_log_.insert({cfd, log_number});
-          } else if (log_number > iter->second) {
-            iter->second = log_number;
-          }
-        }
-        auto last_sequence = *next_sequence - 1;
-        if ((*next_sequence != kMaxSequenceNumber) &&
-            (versions_->LastSequence() <= last_sequence)) {
-          versions_->SetLastAllocatedSequence(last_sequence);
-          versions_->SetLastPublishedSequence(last_sequence);
-          versions_->SetLastSequence(last_sequence);
-        }
-      } else {
-        // We are treating this as a failure while reading since we read valid
-        // blocks that do not form coherent data
-        reader->GetReporter()->Corruption(record.size(), status);
-      }
-    }
-    if (!status.ok()) {
-      return status;
-    }
-  }
-  // remove logreaders from map after successfully recovering the WAL
-  if (log_readers_.size() > 1) {
-    auto erase_iter = log_readers_.begin();
-    std::advance(erase_iter, log_readers_.size() - 1);
-    log_readers_.erase(log_readers_.begin(), erase_iter);
-  }
-  return status;
-}
-
-// Implementation of the DB interface
-Status DBImplSecondary::Get(const ReadOptions& read_options,
-                            ColumnFamilyHandle* column_family, const Slice& key,
-                            PinnableSlice* value) {
-  return GetImpl(read_options, column_family, key, value);
-}
-
-Status DBImplSecondary::GetImpl(const ReadOptions& read_options,
-                                ColumnFamilyHandle* column_family,
-                                const Slice& key, PinnableSlice* pinnable_val) {
-  assert(pinnable_val != nullptr);
-  PERF_CPU_TIMER_GUARD(get_cpu_nanos, env_);
-  StopWatch sw(env_, stats_, DB_GET);
-  PERF_TIMER_GUARD(get_snapshot_time);
-
-  auto cfh = static_cast<ColumnFamilyHandleImpl*>(column_family);
-  ColumnFamilyData* cfd = cfh->cfd();
-  if (tracer_) {
-    InstrumentedMutexLock lock(&trace_mutex_);
-    if (tracer_) {
-      tracer_->Get(column_family, key);
-    }
-  }
-  // Acquire SuperVersion
-  SuperVersion* super_version = GetAndRefSuperVersion(cfd);
-  SequenceNumber snapshot = versions_->LastSequence();
-  MergeContext merge_context;
-  SequenceNumber max_covering_tombstone_seq = 0;
-  Status s;
-  LookupKey lkey(key, snapshot);
-  PERF_TIMER_STOP(get_snapshot_time);
-
-  bool done = false;
-  if (super_version->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
-                              &max_covering_tombstone_seq, read_options)) {
-    done = true;
-    pinnable_val->PinSelf();
-    RecordTick(stats_, MEMTABLE_HIT);
-  } else if ((s.ok() || s.IsMergeInProgress()) &&
-             super_version->imm->Get(
-                 lkey, pinnable_val->GetSelf(), &s, &merge_context,
-                 &max_covering_tombstone_seq, read_options)) {
-    done = true;
-    pinnable_val->PinSelf();
-    RecordTick(stats_, MEMTABLE_HIT);
-  }
-  if (!done && !s.ok() && !s.IsMergeInProgress()) {
-    ReturnAndCleanupSuperVersion(cfd, super_version);
-    return s;
-  }
-  if (!done) {
-    PERF_TIMER_GUARD(get_from_output_files_time);
-    super_version->current->Get(read_options, lkey, pinnable_val, &s,
-                                &merge_context, &max_covering_tombstone_seq);
-    RecordTick(stats_, MEMTABLE_MISS);
-  }
-  {
-    PERF_TIMER_GUARD(get_post_process_time);
-    ReturnAndCleanupSuperVersion(cfd, super_version);
-    RecordTick(stats_, NUMBER_KEYS_READ);
-    size_t size = pinnable_val->size();
-    RecordTick(stats_, BYTES_READ, size);
-    RecordTimeToHistogram(stats_, BYTES_PER_READ, size);
-    PERF_COUNTER_ADD(get_read_bytes, size);
-  }
-  return s;
-}
-
-Iterator* DBImplSecondary::NewIterator(const ReadOptions& read_options,
-                                       ColumnFamilyHandle* column_family) {
-  if (read_options.managed) {
-    return NewErrorIterator(
-        Status::NotSupported("Managed iterator is not supported anymore."));
-  }
-  if (read_options.read_tier == kPersistedTier) {
-    return NewErrorIterator(Status::NotSupported(
-        "ReadTier::kPersistedData is not yet supported in iterators."));
-  }
-  Iterator* result = nullptr;
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  auto cfd = cfh->cfd();
-  ReadCallback* read_callback = nullptr;  // No read callback provided.
-  if (read_options.tailing) {
-    return NewErrorIterator(Status::NotSupported(
-        "tailing iterator not supported in secondary mode"));
-  } else if (read_options.snapshot != nullptr) {
-    // TODO (yanqin) support snapshot.
-    return NewErrorIterator(
-        Status::NotSupported("snapshot not supported in secondary mode"));
-  } else {
-    auto snapshot = versions_->LastSequence();
-    result = NewIteratorImpl(read_options, cfd, snapshot, read_callback);
-  }
-  return result;
-}
-
-ArenaWrappedDBIter* DBImplSecondary::NewIteratorImpl(
-    const ReadOptions& read_options, ColumnFamilyData* cfd,
-    SequenceNumber snapshot, ReadCallback* read_callback) {
-  assert(nullptr != cfd);
-  SuperVersion* super_version = cfd->GetReferencedSuperVersion(&mutex_);
-  auto db_iter = NewArenaWrappedDbIterator(
-      env_, read_options, *cfd->ioptions(), super_version->mutable_cf_options,
-      snapshot,
-      super_version->mutable_cf_options.max_sequential_skip_in_iterations,
-      super_version->version_number, read_callback);
-  auto internal_iter =
-      NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator(), snapshot);
-  db_iter->SetIterUnderDBIter(internal_iter);
-  return db_iter;
-}
-
-Status DBImplSecondary::NewIterators(
-    const ReadOptions& read_options,
-    const std::vector<ColumnFamilyHandle*>& column_families,
-    std::vector<Iterator*>* iterators) {
-  if (read_options.managed) {
-    return Status::NotSupported("Managed iterator is not supported anymore.");
-  }
-  if (read_options.read_tier == kPersistedTier) {
-    return Status::NotSupported(
-        "ReadTier::kPersistedData is not yet supported in iterators.");
-  }
-  ReadCallback* read_callback = nullptr;  // No read callback provided.
-  if (iterators == nullptr) {
-    return Status::InvalidArgument("iterators not allowed to be nullptr");
-  }
-  iterators->clear();
-  iterators->reserve(column_families.size());
-  if (read_options.tailing) {
-    return Status::NotSupported(
-        "tailing iterator not supported in secondary mode");
-  } else if (read_options.snapshot != nullptr) {
-    // TODO (yanqin) support snapshot.
-    return Status::NotSupported("snapshot not supported in secondary mode");
-  } else {
-    SequenceNumber read_seq = versions_->LastSequence();
-    for (auto cfh : column_families) {
-      ColumnFamilyData* cfd = static_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
-      iterators->push_back(
-          NewIteratorImpl(read_options, cfd, read_seq, read_callback));
-    }
-  }
-  return Status::OK();
-}
-
-Status DBImplSecondary::CheckConsistency() {
-  mutex_.AssertHeld();
-  Status s = DBImpl::CheckConsistency();
-  // If DBImpl::CheckConsistency() which is stricter returns success, then we
-  // do not need to give a second chance.
-  if (s.ok()) {
-    return s;
-  }
-  // It's possible that DBImpl::CheckConssitency() can fail because the primary
-  // may have removed certain files, causing the GetFileSize(name) call to
-  // fail and returning a PathNotFound. In this case, we take a best-effort
-  // approach and just proceed.
-  TEST_SYNC_POINT_CALLBACK(
-      "DBImplSecondary::CheckConsistency:AfterFirstAttempt", &s);
-  std::vector<LiveFileMetaData> metadata;
-  versions_->GetLiveFilesMetaData(&metadata);
-
-  std::string corruption_messages;
-  for (const auto& md : metadata) {
-    // md.name has a leading "/".
-    std::string file_path = md.db_path + md.name;
-
-    uint64_t fsize = 0;
-    s = env_->GetFileSize(file_path, &fsize);
-    if (!s.ok() &&
-        (env_->GetFileSize(Rocks2LevelTableFileName(file_path), &fsize).ok() ||
-         s.IsPathNotFound())) {
-      s = Status::OK();
-    }
-    if (!s.ok()) {
-      corruption_messages +=
-          "Can't access " + md.name + ": " + s.ToString() + "\n";
-    }
-  }
-  return corruption_messages.empty() ? Status::OK()
-                                     : Status::Corruption(corruption_messages);
-}
-
-Status DBImplSecondary::TryCatchUpWithPrimary() {
-  assert(versions_.get() != nullptr);
-  assert(manifest_reader_.get() != nullptr);
-  Status s;
-  // read the manifest and apply new changes to the secondary instance
-  std::unordered_set<ColumnFamilyData*> cfds_changed;
-  JobContext job_context(0, true /*create_superversion*/);
-  InstrumentedMutexLock lock_guard(&mutex_);
-  s = static_cast<ReactiveVersionSet*>(versions_.get())
-          ->ReadAndApply(&mutex_, &manifest_reader_, &cfds_changed);
-
-  ROCKS_LOG_INFO(immutable_db_options_.info_log, "Last sequence is %" PRIu64,
-                 static_cast<uint64_t>(versions_->LastSequence()));
-  for (ColumnFamilyData* cfd : cfds_changed) {
-    if (cfd->IsDropped()) {
-      ROCKS_LOG_DEBUG(immutable_db_options_.info_log, "[%s] is dropped\n",
-                      cfd->GetName().c_str());
-      continue;
-    }
-    VersionStorageInfo::LevelSummaryStorage tmp;
-    ROCKS_LOG_DEBUG(immutable_db_options_.info_log, "[%s] Level summary: %s\n",
-                    cfd->GetName().c_str(),
-                    cfd->current()->storage_info()->LevelSummary(&tmp));
-  }
-
-  // list wal_dir to discover new WALs and apply new changes to the secondary
-  // instance
-  if (s.ok()) {
-    s = FindAndRecoverLogFiles(&cfds_changed, &job_context);
-  }
-  if (s.IsPathNotFound()) {
-    ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                   "Secondary tries to read WAL, but WAL file(s) have already "
-                   "been purged by primary.");
-    s = Status::OK();
-  }
-  if (s.ok()) {
-    for (auto cfd : cfds_changed) {
-      cfd->imm()->RemoveOldMemTables(cfd->GetLogNumber(),
-                                     &job_context.memtables_to_free);
-      auto& sv_context = job_context.superversion_contexts.back();
-      cfd->InstallSuperVersion(&sv_context, &mutex_);
-      sv_context.NewSuperVersion();
-    }
-    job_context.Clean();
-  }
-  return s;
-}
-
-Status DB::OpenAsSecondary(const Options& options, const std::string& dbname,
-                           const std::string& secondary_path, DB** dbptr) {
-  *dbptr = nullptr;
-
-  DBOptions db_options(options);
-  ColumnFamilyOptions cf_options(options);
-  std::vector<ColumnFamilyDescriptor> column_families;
-  column_families.emplace_back(kDefaultColumnFamilyName, cf_options);
-  std::vector<ColumnFamilyHandle*> handles;
-
-  Status s = DB::OpenAsSecondary(db_options, dbname, secondary_path,
-                                 column_families, &handles, dbptr);
-  if (s.ok()) {
-    assert(handles.size() == 1);
-    delete handles[0];
-  }
-  return s;
-}
-
-Status DB::OpenAsSecondary(
-    const DBOptions& db_options, const std::string& dbname,
-    const std::string& secondary_path,
-    const std::vector<ColumnFamilyDescriptor>& column_families,
-    std::vector<ColumnFamilyHandle*>* handles, DB** dbptr) {
-  *dbptr = nullptr;
-  if (db_options.max_open_files != -1) {
-    // TODO (yanqin) maybe support max_open_files != -1 by creating hard links
-    // on SST files so that db secondary can still have access to old SSTs
-    // while primary instance may delete original.
-    return Status::InvalidArgument("require max_open_files to be -1");
-  }
-
-  DBOptions tmp_opts(db_options);
-  Status s;
-  if (nullptr == tmp_opts.info_log) {
-    s = CreateLoggerFromOptions(secondary_path, tmp_opts, &tmp_opts.info_log);
-    if (!s.ok()) {
-      tmp_opts.info_log = nullptr;
-    }
-  }
-
-  handles->clear();
-  DBImplSecondary* impl = new DBImplSecondary(tmp_opts, dbname);
-  impl->versions_.reset(new ReactiveVersionSet(
-      dbname, &impl->immutable_db_options_, impl->env_options_,
-      impl->table_cache_.get(), impl->write_buffer_manager_,
-      &impl->write_controller_));
-  impl->column_family_memtables_.reset(
-      new ColumnFamilyMemTablesImpl(impl->versions_->GetColumnFamilySet()));
-  impl->wal_in_db_path_ =
-      IsWalDirSameAsDBPath(&impl->immutable_db_options_);
-
-  impl->mutex_.Lock();
-  s = impl->Recover(column_families, true, false, false);
-  if (s.ok()) {
-    for (auto cf : column_families) {
-      auto cfd =
-          impl->versions_->GetColumnFamilySet()->GetColumnFamily(cf.name);
-      if (nullptr == cfd) {
-        s = Status::InvalidArgument("Column family not found: ", cf.name);
-        break;
-      }
-      handles->push_back(new ColumnFamilyHandleImpl(cfd, impl, &impl->mutex_));
-    }
-  }
-  SuperVersionContext sv_context(true /* create_superversion */);
-  if (s.ok()) {
-    for (auto cfd : *impl->versions_->GetColumnFamilySet()) {
-      sv_context.NewSuperVersion();
-      cfd->InstallSuperVersion(&sv_context, &impl->mutex_);
-    }
-  }
-  impl->mutex_.Unlock();
-  sv_context.Clean();
-  if (s.ok()) {
-    *dbptr = impl;
-    for (auto h : *handles) {
-      impl->NewThreadStatusCfInfo(
-          reinterpret_cast<ColumnFamilyHandleImpl*>(h)->cfd());
-    }
-  } else {
-    for (auto h : *handles) {
-      delete h;
-    }
-    handles->clear();
-    delete impl;
-  }
-  return s;
-}
-#else   // !ROCKSDB_LITE
-
-Status DB::OpenAsSecondary(const Options& /*options*/,
-                           const std::string& /*name*/,
-                           const std::string& /*secondary_path*/,
-                           DB** /*dbptr*/) {
-  return Status::NotSupported("Not supported in ROCKSDB_LITE.");
-}
-
-Status DB::OpenAsSecondary(
-    const DBOptions& /*db_options*/, const std::string& /*dbname*/,
-    const std::string& /*secondary_path*/,
-    const std::vector<ColumnFamilyDescriptor>& /*column_families*/,
-    std::vector<ColumnFamilyHandle*>* /*handles*/, DB** /*dbptr*/) {
-  return Status::NotSupported("Not supported in ROCKSDB_LITE.");
-}
-#endif  // !ROCKSDB_LITE
-
-}  // namespace rocksdb
@@ -1,306 +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
-
-#ifndef ROCKSDB_LITE
-
-#include <string>
-#include <vector>
-#include "db/db_impl/db_impl.h"
-
-namespace rocksdb {
-
-// A wrapper class to hold log reader, log reporter, log status.
-class LogReaderContainer {
- public:
-  LogReaderContainer()
-      : reader_(nullptr), reporter_(nullptr), status_(nullptr) {}
-  LogReaderContainer(Env* env, std::shared_ptr<Logger> info_log,
-                     std::string fname,
-                     std::unique_ptr<SequentialFileReader>&& file_reader,
-                     uint64_t log_number) {
-    LogReporter* reporter = new LogReporter();
-    status_ = new Status();
-    reporter->env = env;
-    reporter->info_log = info_log.get();
-    reporter->fname = std::move(fname);
-    reporter->status = status_;
-    reporter_ = reporter;
-    // We intentially make log::Reader do checksumming even if
-    // paranoid_checks==false so that corruptions cause entire commits
-    // to be skipped instead of propagating bad information (like overly
-    // large sequence numbers).
-    reader_ = new log::FragmentBufferedReader(info_log, std::move(file_reader),
-                                              reporter, true /*checksum*/,
-                                              log_number);
-  }
-  log::FragmentBufferedReader* reader_;
-  log::Reader::Reporter* reporter_;
-  Status* status_;
-  ~LogReaderContainer() {
-    delete reader_;
-    delete reporter_;
-    delete status_;
-  }
- private:
-  struct LogReporter : public log::Reader::Reporter {
-    Env* env;
-    Logger* info_log;
-    std::string fname;
-    Status* status;  // nullptr if immutable_db_options_.paranoid_checks==false
-    void Corruption(size_t bytes, const Status& s) override {
-      ROCKS_LOG_WARN(info_log, "%s%s: dropping %d bytes; %s",
-                     (this->status == nullptr ? "(ignoring error) " : ""),
-                     fname.c_str(), static_cast<int>(bytes),
-                     s.ToString().c_str());
-      if (this->status != nullptr && this->status->ok()) {
-        *this->status = s;
-      }
-    }
-  };
-};
-
-// The secondary instance shares access to the storage as the primary.
-// The secondary is able to read and replay changes described in both the
-// MANIFEST and the WAL files without coordination with the primary.
-// The secondary instance can be opened using `DB::OpenAsSecondary`. After
-// that, it can call `DBImplSecondary::TryCatchUpWithPrimary` to make best
-// effort attempts to catch up with the primary.
-class DBImplSecondary : public DBImpl {
- public:
-  DBImplSecondary(const DBOptions& options, const std::string& dbname);
-  ~DBImplSecondary() override;
-
-  // Recover by replaying MANIFEST and WAL. Also initialize manifest_reader_
-  // and log_readers_ to facilitate future operations.
-  Status Recover(const std::vector<ColumnFamilyDescriptor>& column_families,
-                 bool read_only, bool error_if_log_file_exist,
-                 bool error_if_data_exists_in_logs) override;
-
-  // Implementations of the DB interface
-  using DB::Get;
-  Status Get(const ReadOptions& options, ColumnFamilyHandle* column_family,
-             const Slice& key, PinnableSlice* value) override;
-
-  Status GetImpl(const ReadOptions& options, ColumnFamilyHandle* column_family,
-                 const Slice& key, PinnableSlice* value);
-
-  using DBImpl::NewIterator;
-  Iterator* NewIterator(const ReadOptions&,
-                        ColumnFamilyHandle* column_family) override;
-
-  ArenaWrappedDBIter* NewIteratorImpl(const ReadOptions& read_options,
-                                      ColumnFamilyData* cfd,
-                                      SequenceNumber snapshot,
-                                      ReadCallback* read_callback);
-
-  Status NewIterators(const ReadOptions& options,
-                      const std::vector<ColumnFamilyHandle*>& column_families,
-                      std::vector<Iterator*>* iterators) override;
-
-  using DBImpl::Put;
-  Status Put(const WriteOptions& /*options*/,
-             ColumnFamilyHandle* /*column_family*/, const Slice& /*key*/,
-             const Slice& /*value*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::Merge;
-  Status Merge(const WriteOptions& /*options*/,
-               ColumnFamilyHandle* /*column_family*/, const Slice& /*key*/,
-               const Slice& /*value*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::Delete;
-  Status Delete(const WriteOptions& /*options*/,
-                ColumnFamilyHandle* /*column_family*/,
-                const Slice& /*key*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::SingleDelete;
-  Status SingleDelete(const WriteOptions& /*options*/,
-                      ColumnFamilyHandle* /*column_family*/,
-                      const Slice& /*key*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  Status Write(const WriteOptions& /*options*/,
-               WriteBatch* /*updates*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::CompactRange;
-  Status CompactRange(const CompactRangeOptions& /*options*/,
-                      ColumnFamilyHandle* /*column_family*/,
-                      const Slice* /*begin*/, const Slice* /*end*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::CompactFiles;
-  Status CompactFiles(
-      const CompactionOptions& /*compact_options*/,
-      ColumnFamilyHandle* /*column_family*/,
-      const std::vector<std::string>& /*input_file_names*/,
-      const int /*output_level*/, const int /*output_path_id*/ = -1,
-      std::vector<std::string>* const /*output_file_names*/ = nullptr,
-      CompactionJobInfo* /*compaction_job_info*/ = nullptr) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  Status DisableFileDeletions() override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  Status EnableFileDeletions(bool /*force*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  Status GetLiveFiles(std::vector<std::string>&,
-                      uint64_t* /*manifest_file_size*/,
-                      bool /*flush_memtable*/ = true) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::Flush;
-  Status Flush(const FlushOptions& /*options*/,
-               ColumnFamilyHandle* /*column_family*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DBImpl::SyncWAL;
-  Status SyncWAL() override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  using DB::IngestExternalFile;
-  Status IngestExternalFile(
-      ColumnFamilyHandle* /*column_family*/,
-      const std::vector<std::string>& /*external_files*/,
-      const IngestExternalFileOptions& /*ingestion_options*/) override {
-    return Status::NotSupported("Not supported operation in secondary mode.");
-  }
-
-  // Try to catch up with the primary by reading as much as possible from the
-  // log files until there is nothing more to read or encounters an error. If
-  // the amount of information in the log files to process is huge, this
-  // method can take long time due to all the I/O and CPU costs.
-  Status TryCatchUpWithPrimary() override;
-
-
-  // Try to find log reader using log_number from log_readers_ map, initialize
-  // if it doesn't exist
-  Status MaybeInitLogReader(uint64_t log_number,
-                            log::FragmentBufferedReader** log_reader);
-
-  // Check if all live files exist on file system and that their file sizes
-  // matche to the in-memory records. It is possible that some live files may
-  // have been deleted by the primary. In this case, CheckConsistency() does
-  // not flag the missing file as inconsistency.
-  Status CheckConsistency() override;
-
- protected:
-  // ColumnFamilyCollector is a write batch handler which does nothing
-  // except recording unique column family IDs
-  class ColumnFamilyCollector : public WriteBatch::Handler {
-    std::unordered_set<uint32_t> column_family_ids_;
-
-    Status AddColumnFamilyId(uint32_t column_family_id) {
-      if (column_family_ids_.find(column_family_id) ==
-          column_family_ids_.end()) {
-        column_family_ids_.insert(column_family_id);
-      }
-      return Status::OK();
-    }
-
-   public:
-    explicit ColumnFamilyCollector() {}
-
-    ~ColumnFamilyCollector() override {}
-
-    Status PutCF(uint32_t column_family_id, const Slice&,
-                 const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status DeleteCF(uint32_t column_family_id, const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status SingleDeleteCF(uint32_t column_family_id, const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status DeleteRangeCF(uint32_t column_family_id, const Slice&,
-                         const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status MergeCF(uint32_t column_family_id, const Slice&,
-                   const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status PutBlobIndexCF(uint32_t column_family_id, const Slice&,
-                          const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    const std::unordered_set<uint32_t>& column_families() const {
-      return column_family_ids_;
-    }
-  };
-
-  Status CollectColumnFamilyIdsFromWriteBatch(
-      const WriteBatch& batch, std::vector<uint32_t>* column_family_ids) {
-    assert(column_family_ids != nullptr);
-    column_family_ids->clear();
-    ColumnFamilyCollector handler;
-    Status s = batch.Iterate(&handler);
-    if (s.ok()) {
-      for (const auto& cf : handler.column_families()) {
-        column_family_ids->push_back(cf);
-      }
-    }
-    return s;
-  }
-
- private:
-  friend class DB;
-
-  // No copying allowed
-  DBImplSecondary(const DBImplSecondary&);
-  void operator=(const DBImplSecondary&);
-
-  using DBImpl::Recover;
-
-  Status FindAndRecoverLogFiles(
-      std::unordered_set<ColumnFamilyData*>* cfds_changed,
-      JobContext* job_context);
-  Status FindNewLogNumbers(std::vector<uint64_t>* logs);
-  // After manifest recovery, replay WALs and refresh log_readers_ if necessary
-  // REQUIRES: log_numbers are sorted in ascending order
-  Status RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
-                         SequenceNumber* next_sequence,
-                         std::unordered_set<ColumnFamilyData*>* cfds_changed,
-                         JobContext* job_context);
-
-  std::unique_ptr<log::FragmentBufferedReader> manifest_reader_;
-  std::unique_ptr<log::Reader::Reporter> manifest_reporter_;
-  std::unique_ptr<Status> manifest_reader_status_;
-
-  // Cache log readers for each log number, used for continue WAL replay
-  // after recovery
-  std::map<uint64_t, std::unique_ptr<LogReaderContainer>> log_readers_;
-
-  // Current WAL number replayed for each column family.
-  std::unordered_map<ColumnFamilyData*, uint64_t> cfd_to_current_log_;
-};
-
-}  // namespace rocksdb
-
-#endif  // !ROCKSDB_LITE
@@ -1,784 +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/db_impl/db_impl_secondary.h"
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "test_util/fault_injection_test_env.h"
-#include "test_util/sync_point.h"
-
-namespace rocksdb {
-
-#ifndef ROCKSDB_LITE
-class DBSecondaryTest : public DBTestBase {
- public:
-  DBSecondaryTest()
-      : DBTestBase("/db_secondary_test"),
-        secondary_path_(),
-        handles_secondary_(),
-        db_secondary_(nullptr) {
-    secondary_path_ =
-        test::PerThreadDBPath(env_, "/db_secondary_test_secondary");
-  }
-
-  ~DBSecondaryTest() override {
-    CloseSecondary();
-    if (getenv("KEEP_DB") != nullptr) {
-      fprintf(stdout, "Secondary DB is still at %s\n", secondary_path_.c_str());
-    } else {
-      Options options;
-      options.env = env_;
-      EXPECT_OK(DestroyDB(secondary_path_, options));
-    }
-  }
-
- protected:
-  Status ReopenAsSecondary(const Options& options) {
-    return DB::OpenAsSecondary(options, dbname_, secondary_path_, &db_);
-  }
-
-  void OpenSecondary(const Options& options);
-
-  void OpenSecondaryWithColumnFamilies(
-      const std::vector<std::string>& column_families, const Options& options);
-
-  void CloseSecondary() {
-    for (auto h : handles_secondary_) {
-      db_secondary_->DestroyColumnFamilyHandle(h);
-    }
-    handles_secondary_.clear();
-    delete db_secondary_;
-    db_secondary_ = nullptr;
-  }
-
-  DBImplSecondary* db_secondary_full() {
-    return static_cast<DBImplSecondary*>(db_secondary_);
-  }
-
-  void CheckFileTypeCounts(const std::string& dir, int expected_log,
-                           int expected_sst, int expected_manifest) const;
-
-  std::string secondary_path_;
-  std::vector<ColumnFamilyHandle*> handles_secondary_;
-  DB* db_secondary_;
-};
-
-void DBSecondaryTest::OpenSecondary(const Options& options) {
-  Status s =
-      DB::OpenAsSecondary(options, dbname_, secondary_path_, &db_secondary_);
-  ASSERT_OK(s);
-}
-
-void DBSecondaryTest::OpenSecondaryWithColumnFamilies(
-    const std::vector<std::string>& column_families, const Options& options) {
-  std::vector<ColumnFamilyDescriptor> cf_descs;
-  cf_descs.emplace_back(kDefaultColumnFamilyName, options);
-  for (const auto& cf_name : column_families) {
-    cf_descs.emplace_back(cf_name, options);
-  }
-  Status s = DB::OpenAsSecondary(options, dbname_, secondary_path_, cf_descs,
-                                 &handles_secondary_, &db_secondary_);
-  ASSERT_OK(s);
-}
-
-void DBSecondaryTest::CheckFileTypeCounts(const std::string& dir,
-                                          int expected_log, int expected_sst,
-                                          int expected_manifest) const {
-  std::vector<std::string> filenames;
-  env_->GetChildren(dir, &filenames);
-
-  int log_cnt = 0, sst_cnt = 0, manifest_cnt = 0;
-  for (auto file : filenames) {
-    uint64_t number;
-    FileType type;
-    if (ParseFileName(file, &number, &type)) {
-      log_cnt += (type == kLogFile);
-      sst_cnt += (type == kTableFile);
-      manifest_cnt += (type == kDescriptorFile);
-    }
-  }
-  ASSERT_EQ(expected_log, log_cnt);
-  ASSERT_EQ(expected_sst, sst_cnt);
-  ASSERT_EQ(expected_manifest, manifest_cnt);
-}
-
-TEST_F(DBSecondaryTest, ReopenAsSecondary) {
-  Options options;
-  options.env = env_;
-  Reopen(options);
-  ASSERT_OK(Put("foo", "foo_value"));
-  ASSERT_OK(Put("bar", "bar_value"));
-  ASSERT_OK(dbfull()->Flush(FlushOptions()));
-  Close();
-
-  ASSERT_OK(ReopenAsSecondary(options));
-  ASSERT_EQ("foo_value", Get("foo"));
-  ASSERT_EQ("bar_value", Get("bar"));
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  auto db1 = static_cast<DBImplSecondary*>(db_);
-  ASSERT_NE(nullptr, db1);
-  Iterator* iter = db1->NewIterator(ropts);
-  ASSERT_NE(nullptr, iter);
-  size_t count = 0;
-  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    if (0 == count) {
-      ASSERT_EQ("bar", iter->key().ToString());
-      ASSERT_EQ("bar_value", iter->value().ToString());
-    } else if (1 == count) {
-      ASSERT_EQ("foo", iter->key().ToString());
-      ASSERT_EQ("foo_value", iter->value().ToString());
-    }
-    ++count;
-  }
-  delete iter;
-  ASSERT_EQ(2, count);
-}
-
-TEST_F(DBSecondaryTest, OpenAsSecondary) {
-  Options options;
-  options.env = env_;
-  options.level0_file_num_compaction_trigger = 4;
-  Reopen(options);
-  for (int i = 0; i < 3; ++i) {
-    ASSERT_OK(Put("foo", "foo_value" + std::to_string(i)));
-    ASSERT_OK(Put("bar", "bar_value" + std::to_string(i)));
-    ASSERT_OK(Flush());
-  }
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-  ASSERT_OK(dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  const auto verify_db_func = [&](const std::string& foo_val,
-                                  const std::string& bar_val) {
-    std::string value;
-    ASSERT_OK(db_secondary_->Get(ropts, "foo", &value));
-    ASSERT_EQ(foo_val, value);
-    ASSERT_OK(db_secondary_->Get(ropts, "bar", &value));
-    ASSERT_EQ(bar_val, value);
-    Iterator* iter = db_secondary_->NewIterator(ropts);
-    ASSERT_NE(nullptr, iter);
-    iter->Seek("foo");
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_EQ("foo", iter->key().ToString());
-    ASSERT_EQ(foo_val, iter->value().ToString());
-    iter->Seek("bar");
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_EQ("bar", iter->key().ToString());
-    ASSERT_EQ(bar_val, iter->value().ToString());
-    size_t count = 0;
-    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-      ++count;
-    }
-    ASSERT_EQ(2, count);
-    delete iter;
-  };
-
-  verify_db_func("foo_value2", "bar_value2");
-
-  ASSERT_OK(Put("foo", "new_foo_value"));
-  ASSERT_OK(Put("bar", "new_bar_value"));
-  ASSERT_OK(Flush());
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  verify_db_func("new_foo_value", "new_bar_value");
-}
-
-TEST_F(DBSecondaryTest, OpenAsSecondaryWALTailing) {
-  Options options;
-  options.env = env_;
-  options.level0_file_num_compaction_trigger = 4;
-  Reopen(options);
-  for (int i = 0; i < 3; ++i) {
-    ASSERT_OK(Put("foo", "foo_value" + std::to_string(i)));
-    ASSERT_OK(Put("bar", "bar_value" + std::to_string(i)));
-  }
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  const auto verify_db_func = [&](const std::string& foo_val,
-                                  const std::string& bar_val) {
-    std::string value;
-    ASSERT_OK(db_secondary_->Get(ropts, "foo", &value));
-    ASSERT_EQ(foo_val, value);
-    ASSERT_OK(db_secondary_->Get(ropts, "bar", &value));
-    ASSERT_EQ(bar_val, value);
-    Iterator* iter = db_secondary_->NewIterator(ropts);
-    ASSERT_NE(nullptr, iter);
-    iter->Seek("foo");
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_EQ("foo", iter->key().ToString());
-    ASSERT_EQ(foo_val, iter->value().ToString());
-    iter->Seek("bar");
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_EQ("bar", iter->key().ToString());
-    ASSERT_EQ(bar_val, iter->value().ToString());
-    size_t count = 0;
-    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-      ++count;
-    }
-    ASSERT_EQ(2, count);
-    delete iter;
-  };
-
-  verify_db_func("foo_value2", "bar_value2");
-
-  ASSERT_OK(Put("foo", "new_foo_value"));
-  ASSERT_OK(Put("bar", "new_bar_value"));
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  verify_db_func("new_foo_value", "new_bar_value");
-
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put("foo", "new_foo_value_1"));
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  verify_db_func("new_foo_value_1", "new_bar_value");
-}
-
-TEST_F(DBSecondaryTest, OpenWithNonExistColumnFamily) {
-  Options options;
-  options.env = env_;
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  std::vector<ColumnFamilyDescriptor> cf_descs;
-  cf_descs.emplace_back(kDefaultColumnFamilyName, options1);
-  cf_descs.emplace_back("pikachu", options1);
-  cf_descs.emplace_back("eevee", options1);
-  Status s = DB::OpenAsSecondary(options1, dbname_, secondary_path_, cf_descs,
-                                 &handles_secondary_, &db_secondary_);
-  ASSERT_NOK(s);
-}
-
-TEST_F(DBSecondaryTest, OpenWithSubsetOfColumnFamilies) {
-  Options options;
-  options.env = env_;
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-  ASSERT_EQ(0, handles_secondary_.size());
-  ASSERT_NE(nullptr, db_secondary_);
-
-  ASSERT_OK(Put(0 /*cf*/, "foo", "foo_value"));
-  ASSERT_OK(Put(1 /*cf*/, "foo", "foo_value"));
-  ASSERT_OK(Flush(0 /*cf*/));
-  ASSERT_OK(Flush(1 /*cf*/));
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  std::string value;
-  ASSERT_OK(db_secondary_->Get(ropts, "foo", &value));
-  ASSERT_EQ("foo_value", value);
-}
-
-TEST_F(DBSecondaryTest, SwitchToNewManifestDuringOpen) {
-  Options options;
-  options.env = env_;
-  Reopen(options);
-  Close();
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"ReactiveVersionSet::MaybeSwitchManifest:AfterGetCurrentManifestPath:0",
-        "VersionSet::ProcessManifestWrites:BeforeNewManifest"},
-       {"VersionSet::ProcessManifestWrites:AfterNewManifest",
-        "ReactiveVersionSet::MaybeSwitchManifest:AfterGetCurrentManifestPath:"
-        "1"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  // Make sure db calls RecoverLogFiles so as to trigger a manifest write,
-  // which causes the db to switch to a new MANIFEST upon start.
-  port::Thread ro_db_thread([&]() {
-    Options options1;
-    options1.env = env_;
-    options1.max_open_files = -1;
-    OpenSecondary(options1);
-    CloseSecondary();
-  });
-  Reopen(options);
-  ro_db_thread.join();
-}
-
-TEST_F(DBSecondaryTest, MissingTableFileDuringOpen) {
-  Options options;
-  options.env = env_;
-  options.level0_file_num_compaction_trigger = 4;
-  Reopen(options);
-  for (int i = 0; i != options.level0_file_num_compaction_trigger; ++i) {
-    ASSERT_OK(Put("foo", "foo_value" + std::to_string(i)));
-    ASSERT_OK(Put("bar", "bar_value" + std::to_string(i)));
-    ASSERT_OK(dbfull()->Flush(FlushOptions()));
-  }
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  std::string value;
-  ASSERT_OK(db_secondary_->Get(ropts, "foo", &value));
-  ASSERT_EQ("foo_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            value);
-  ASSERT_OK(db_secondary_->Get(ropts, "bar", &value));
-  ASSERT_EQ("bar_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            value);
-  Iterator* iter = db_secondary_->NewIterator(ropts);
-  ASSERT_NE(nullptr, iter);
-  iter->Seek("bar");
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ("bar", iter->key().ToString());
-  ASSERT_EQ("bar_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            iter->value().ToString());
-  iter->Seek("foo");
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ("foo", iter->key().ToString());
-  ASSERT_EQ("foo_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            iter->value().ToString());
-  size_t count = 0;
-  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    ++count;
-  }
-  ASSERT_EQ(2, count);
-  delete iter;
-}
-
-TEST_F(DBSecondaryTest, MissingTableFile) {
-  int table_files_not_exist = 0;
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->SetCallBack(
-      "ReactiveVersionSet::ApplyOneVersionEditToBuilder:AfterLoadTableHandlers",
-      [&](void* arg) {
-        Status s = *reinterpret_cast<Status*>(arg);
-        if (s.IsPathNotFound()) {
-          ++table_files_not_exist;
-        } else if (!s.ok()) {
-          assert(false);  // Should not reach here
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-  Options options;
-  options.env = env_;
-  options.level0_file_num_compaction_trigger = 4;
-  Reopen(options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-
-  for (int i = 0; i != options.level0_file_num_compaction_trigger; ++i) {
-    ASSERT_OK(Put("foo", "foo_value" + std::to_string(i)));
-    ASSERT_OK(Put("bar", "bar_value" + std::to_string(i)));
-    ASSERT_OK(dbfull()->Flush(FlushOptions()));
-  }
-  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-  ASSERT_NE(nullptr, db_secondary_full());
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  std::string value;
-  ASSERT_NOK(db_secondary_->Get(ropts, "foo", &value));
-  ASSERT_NOK(db_secondary_->Get(ropts, "bar", &value));
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  ASSERT_EQ(options.level0_file_num_compaction_trigger, table_files_not_exist);
-  ASSERT_OK(db_secondary_->Get(ropts, "foo", &value));
-  ASSERT_EQ("foo_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            value);
-  ASSERT_OK(db_secondary_->Get(ropts, "bar", &value));
-  ASSERT_EQ("bar_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            value);
-  Iterator* iter = db_secondary_->NewIterator(ropts);
-  ASSERT_NE(nullptr, iter);
-  iter->Seek("bar");
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ("bar", iter->key().ToString());
-  ASSERT_EQ("bar_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            iter->value().ToString());
-  iter->Seek("foo");
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ("foo", iter->key().ToString());
-  ASSERT_EQ("foo_value" +
-                std::to_string(options.level0_file_num_compaction_trigger - 1),
-            iter->value().ToString());
-  size_t count = 0;
-  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    ++count;
-  }
-  ASSERT_EQ(2, count);
-  delete iter;
-}
-
-TEST_F(DBSecondaryTest, PrimaryDropColumnFamily) {
-  Options options;
-  options.env = env_;
-  const std::string kCfName1 = "pikachu";
-  CreateAndReopenWithCF({kCfName1}, options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondaryWithColumnFamilies({kCfName1}, options1);
-  ASSERT_EQ(2, handles_secondary_.size());
-
-  ASSERT_OK(Put(1 /*cf*/, "foo", "foo_val_1"));
-  ASSERT_OK(Flush(1 /*cf*/));
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  std::string value;
-  ASSERT_OK(db_secondary_->Get(ropts, handles_secondary_[1], "foo", &value));
-  ASSERT_EQ("foo_val_1", value);
-
-  ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-  Close();
-  CheckFileTypeCounts(dbname_, 1, 0, 1);
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  value.clear();
-  ASSERT_OK(db_secondary_->Get(ropts, handles_secondary_[1], "foo", &value));
-  ASSERT_EQ("foo_val_1", value);
-}
-
-TEST_F(DBSecondaryTest, SwitchManifest) {
-  Options options;
-  options.env = env_;
-  options.level0_file_num_compaction_trigger = 4;
-  Reopen(options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-
-  const int kNumFiles = options.level0_file_num_compaction_trigger - 1;
-  // Keep it smaller than 10 so that key0, key1, ..., key9 are sorted as 0, 1,
-  // ..., 9.
-  const int kNumKeys = 10;
-  // Create two sst
-  for (int i = 0; i != kNumFiles; ++i) {
-    for (int j = 0; j != kNumKeys; ++j) {
-      ASSERT_OK(Put("key" + std::to_string(j), "value_" + std::to_string(i)));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  const auto& range_scan_db = [&]() {
-    ReadOptions tmp_ropts;
-    tmp_ropts.total_order_seek = true;
-    tmp_ropts.verify_checksums = true;
-    std::unique_ptr<Iterator> iter(db_secondary_->NewIterator(tmp_ropts));
-    int cnt = 0;
-    for (iter->SeekToFirst(); iter->Valid(); iter->Next(), ++cnt) {
-      ASSERT_EQ("key" + std::to_string(cnt), iter->key().ToString());
-      ASSERT_EQ("value_" + std::to_string(kNumFiles - 1),
-                iter->value().ToString());
-    }
-  };
-
-  range_scan_db();
-
-  // While secondary instance still keeps old MANIFEST open, we close primary,
-  // restart primary, performs full compaction, close again, restart again so
-  // that next time secondary tries to catch up with primary, the secondary
-  // will skip the MANIFEST in middle.
-  Reopen(options);
-  ASSERT_OK(dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-  Reopen(options);
-  ASSERT_OK(dbfull()->SetOptions({{"disable_auto_compactions", "false"}}));
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  range_scan_db();
-}
-
-// Here, "Snapshot" refers to the version edits written by
-// VersionSet::WriteSnapshot() at the beginning of the new MANIFEST after
-// switching from the old one.
-TEST_F(DBSecondaryTest, SkipSnapshotAfterManifestSwitch) {
-  Options options;
-  options.env = env_;
-  options.disable_auto_compactions = true;
-  Reopen(options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-
-  ASSERT_OK(Put("0", "value0"));
-  ASSERT_OK(Flush());
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  std::string value;
-  ReadOptions ropts;
-  ropts.verify_checksums = true;
-  ASSERT_OK(db_secondary_->Get(ropts, "0", &value));
-  ASSERT_EQ("value0", value);
-
-  Reopen(options);
-  ASSERT_OK(dbfull()->SetOptions({{"disable_auto_compactions", "false"}}));
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-}
-
-TEST_F(DBSecondaryTest, SwitchWAL) {
-  const int kNumKeysPerMemtable = 1;
-  Options options;
-  options.env = env_;
-  options.max_write_buffer_number = 4;
-  options.min_write_buffer_number_to_merge = 2;
-  options.memtable_factory.reset(
-      new SpecialSkipListFactory(kNumKeysPerMemtable));
-  Reopen(options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-
-  const auto& verify_db = [](DB* db1, DB* db2) {
-    ASSERT_NE(nullptr, db1);
-    ASSERT_NE(nullptr, db2);
-    ReadOptions read_opts;
-    read_opts.verify_checksums = true;
-    std::unique_ptr<Iterator> it1(db1->NewIterator(read_opts));
-    std::unique_ptr<Iterator> it2(db2->NewIterator(read_opts));
-    it1->SeekToFirst();
-    it2->SeekToFirst();
-    for (; it1->Valid() && it2->Valid(); it1->Next(), it2->Next()) {
-      ASSERT_EQ(it1->key(), it2->key());
-      ASSERT_EQ(it1->value(), it2->value());
-    }
-    ASSERT_FALSE(it1->Valid());
-    ASSERT_FALSE(it2->Valid());
-
-    for (it1->SeekToFirst(); it1->Valid(); it1->Next()) {
-      std::string value;
-      ASSERT_OK(db2->Get(read_opts, it1->key(), &value));
-      ASSERT_EQ(it1->value(), value);
-    }
-    for (it2->SeekToFirst(); it2->Valid(); it2->Next()) {
-      std::string value;
-      ASSERT_OK(db1->Get(read_opts, it2->key(), &value));
-      ASSERT_EQ(it2->value(), value);
-    }
-  };
-  for (int k = 0; k != 16; ++k) {
-    ASSERT_OK(Put("key" + std::to_string(k), "value" + std::to_string(k)));
-    ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-    verify_db(dbfull(), db_secondary_);
-  }
-}
-
-TEST_F(DBSecondaryTest, SwitchWALMultiColumnFamilies) {
-  const int kNumKeysPerMemtable = 1;
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->LoadDependency({
-      {"DBImpl::BackgroundCallFlush:ContextCleanedUp",
-       "DBSecondaryTest::SwitchWALMultipleColumnFamilies:BeforeCatchUp"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-  const std::string kCFName1 = "pikachu";
-  Options options;
-  options.env = env_;
-  options.max_write_buffer_number = 4;
-  options.min_write_buffer_number_to_merge = 2;
-  options.memtable_factory.reset(
-      new SpecialSkipListFactory(kNumKeysPerMemtable));
-  CreateAndReopenWithCF({kCFName1}, options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondaryWithColumnFamilies({kCFName1}, options1);
-  ASSERT_EQ(2, handles_secondary_.size());
-
-  const auto& verify_db = [](DB* db1,
-                             const std::vector<ColumnFamilyHandle*>& handles1,
-                             DB* db2,
-                             const std::vector<ColumnFamilyHandle*>& handles2) {
-    ASSERT_NE(nullptr, db1);
-    ASSERT_NE(nullptr, db2);
-    ReadOptions read_opts;
-    read_opts.verify_checksums = true;
-    ASSERT_EQ(handles1.size(), handles2.size());
-    for (size_t i = 0; i != handles1.size(); ++i) {
-      std::unique_ptr<Iterator> it1(db1->NewIterator(read_opts, handles1[i]));
-      std::unique_ptr<Iterator> it2(db2->NewIterator(read_opts, handles2[i]));
-      it1->SeekToFirst();
-      it2->SeekToFirst();
-      for (; it1->Valid() && it2->Valid(); it1->Next(), it2->Next()) {
-        ASSERT_EQ(it1->key(), it2->key());
-        ASSERT_EQ(it1->value(), it2->value());
-      }
-      ASSERT_FALSE(it1->Valid());
-      ASSERT_FALSE(it2->Valid());
-
-      for (it1->SeekToFirst(); it1->Valid(); it1->Next()) {
-        std::string value;
-        ASSERT_OK(db2->Get(read_opts, handles2[i], it1->key(), &value));
-        ASSERT_EQ(it1->value(), value);
-      }
-      for (it2->SeekToFirst(); it2->Valid(); it2->Next()) {
-        std::string value;
-        ASSERT_OK(db1->Get(read_opts, handles1[i], it2->key(), &value));
-        ASSERT_EQ(it2->value(), value);
-      }
-    }
-  };
-  for (int k = 0; k != 8; ++k) {
-    ASSERT_OK(
-        Put(0 /*cf*/, "key" + std::to_string(k), "value" + std::to_string(k)));
-    ASSERT_OK(
-        Put(1 /*cf*/, "key" + std::to_string(k), "value" + std::to_string(k)));
-    TEST_SYNC_POINT("DBSecondaryTest::SwitchWALMultipleColumnFamilies:BeforeCatchUp");
-    ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-    verify_db(dbfull(), handles_, db_secondary_, handles_secondary_);
-    SyncPoint::GetInstance()->ClearTrace();
-  }
-}
-
-TEST_F(DBSecondaryTest, CatchUpAfterFlush) {
-  const int kNumKeysPerMemtable = 16;
-  Options options;
-  options.env = env_;
-  options.max_write_buffer_number = 4;
-  options.min_write_buffer_number_to_merge = 2;
-  options.memtable_factory.reset(
-      new SpecialSkipListFactory(kNumKeysPerMemtable));
-  Reopen(options);
-
-  Options options1;
-  options1.env = env_;
-  options1.max_open_files = -1;
-  OpenSecondary(options1);
-
-  WriteOptions write_opts;
-  WriteBatch wb;
-  wb.Put("key0", "value0");
-  wb.Put("key1", "value1");
-  ASSERT_OK(dbfull()->Write(write_opts, &wb));
-  ReadOptions read_opts;
-  std::unique_ptr<Iterator> iter1(db_secondary_->NewIterator(read_opts));
-  iter1->Seek("key0");
-  ASSERT_FALSE(iter1->Valid());
-  iter1->Seek("key1");
-  ASSERT_FALSE(iter1->Valid());
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  iter1->Seek("key0");
-  ASSERT_FALSE(iter1->Valid());
-  iter1->Seek("key1");
-  ASSERT_FALSE(iter1->Valid());
-  std::unique_ptr<Iterator> iter2(db_secondary_->NewIterator(read_opts));
-  iter2->Seek("key0");
-  ASSERT_TRUE(iter2->Valid());
-  ASSERT_EQ("value0", iter2->value());
-  iter2->Seek("key1");
-  ASSERT_TRUE(iter2->Valid());
-  ASSERT_EQ("value1", iter2->value());
-
-  {
-    WriteBatch wb1;
-    wb1.Put("key0", "value01");
-    wb1.Put("key1", "value11");
-    ASSERT_OK(dbfull()->Write(write_opts, &wb1));
-  }
-
-  {
-    WriteBatch wb2;
-    wb2.Put("key0", "new_value0");
-    wb2.Delete("key1");
-    ASSERT_OK(dbfull()->Write(write_opts, &wb2));
-  }
-
-  ASSERT_OK(Flush());
-
-  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
-  std::unique_ptr<Iterator> iter3(db_secondary_->NewIterator(read_opts));
-  // iter3 should not see value01 and value11 at all.
-  iter3->Seek("key0");
-  ASSERT_TRUE(iter3->Valid());
-  ASSERT_EQ("new_value0", iter3->value());
-  iter3->Seek("key1");
-  ASSERT_FALSE(iter3->Valid());
-}
-
-TEST_F(DBSecondaryTest, CheckConsistencyWhenOpen) {
-  bool called = false;
-  Options options;
-  options.env = env_;
-  options.disable_auto_compactions = true;
-  Reopen(options);
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->SetCallBack(
-      "DBImplSecondary::CheckConsistency:AfterFirstAttempt", [&](void* arg) {
-        ASSERT_NE(nullptr, arg);
-        called = true;
-        auto* s = reinterpret_cast<Status*>(arg);
-        ASSERT_NOK(*s);
-      });
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::CheckConsistency:AfterGetLiveFilesMetaData",
-        "BackgroundCallCompaction:0"},
-       {"DBImpl::BackgroundCallCompaction:PurgedObsoleteFiles",
-        "DBImpl::CheckConsistency:BeforeGetFileSize"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("a", "value0"));
-  ASSERT_OK(Put("c", "value0"));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put("b", "value1"));
-  ASSERT_OK(Put("d", "value1"));
-  ASSERT_OK(Flush());
-  port::Thread thread([this]() {
-    Options opts;
-    opts.env = env_;
-    opts.max_open_files = -1;
-    OpenSecondary(opts);
-  });
-  ASSERT_OK(dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  thread.join();
-  ASSERT_TRUE(called);
-}
-#endif  //! ROCKSDB_LITE
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -9,8 +9,7 @@

 #ifndef NDEBUG

-#include "db/db_impl/db_impl.h"
-#include "db/error_handler.h"
+#include "db/db_impl.h"
 #include "monitoring/thread_status_updater.h"

 namespace rocksdb {
@@ -26,16 +25,10 @@ void DBImpl::TEST_SwitchWAL() {
  SwitchWAL(&write_context);
 }

-bool DBImpl::TEST_WALBufferIsEmpty(bool lock) {
-  if (lock) {
-    log_write_mutex_.Lock();
-  }
+bool DBImpl::TEST_WALBufferIsEmpty() {
+  InstrumentedMutexLock wl(&log_write_mutex_);
  log::Writer* cur_log_writer = logs_.back().writer;
-  auto res = cur_log_writer->TEST_BufferIsEmpty();
-  if (lock) {
-    log_write_mutex_.Unlock();
-  }
-  return res;
+  return cur_log_writer->TEST_BufferIsEmpty();
 }

 int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
@@ -93,9 +86,8 @@ Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
       cfd->ioptions()->compaction_style == kCompactionStyleFIFO)
          ? level
          : level + 1;
-  return RunManualCompaction(cfd, level, output_level, CompactRangeOptions(),
-                             begin, end, true, disallow_trivial_move,
-                             port::kMaxUint64 /*max_file_num_to_ignore*/);
+  return RunManualCompaction(cfd, level, output_level, 0, 0, begin, end, true,
+                             disallow_trivial_move);
 }

 Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
@@ -107,11 +99,9 @@ Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
  return SwitchMemtable(cfd, &write_context);
 }

-Status DBImpl::TEST_FlushMemTable(bool wait, bool allow_write_stall,
-                                  ColumnFamilyHandle* cfh) {
+Status DBImpl::TEST_FlushMemTable(bool wait, ColumnFamilyHandle* cfh) {
  FlushOptions fo;
  fo.wait = wait;
-  fo.allow_write_stall = allow_write_stall;
  ColumnFamilyData* cfd;
  if (cfh == nullptr) {
    cfd = default_cf_handle_->cfd();
@@ -122,16 +112,6 @@ Status DBImpl::TEST_FlushMemTable(bool wait, bool allow_write_stall,
  return FlushMemTable(cfd, fo, FlushReason::kTest);
 }

-Status DBImpl::TEST_FlushMemTable(ColumnFamilyData* cfd,
-                                  const FlushOptions& flush_opts) {
-  return FlushMemTable(cfd, flush_opts, FlushReason::kTest);
-}
-
-Status DBImpl::TEST_AtomicFlushMemTables(
-    const autovector<ColumnFamilyData*>& cfds, const FlushOptions& flush_opts) {
-  return AtomicFlushMemTables(cfds, flush_opts, FlushReason::kTest);
-}
-
 Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
  ColumnFamilyData* cfd;
  if (column_family == nullptr) {
@@ -140,7 +120,7 @@ Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
    cfd = cfh->cfd();
  }
-  return WaitForFlushMemTable(cfd, nullptr, false);
+  return WaitForFlushMemTable(cfd);
 }

 Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
@@ -154,15 +134,19 @@ Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
  while ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
          bg_flush_scheduled_ ||
          (wait_unscheduled && unscheduled_compactions_)) &&
-         (error_handler_.GetBGError() == Status::OK())) {
+         bg_error_.ok()) {
    bg_cv_.Wait();
  }
-  return error_handler_.GetBGError();
+  return bg_error_;
 }

-void DBImpl::TEST_LockMutex() { mutex_.Lock(); }
+void DBImpl::TEST_LockMutex() {
+  mutex_.Lock();
+}

-void DBImpl::TEST_UnlockMutex() { mutex_.Unlock(); }
+void DBImpl::TEST_UnlockMutex() {
+  mutex_.Unlock();
+}

 void* DBImpl::TEST_BeginWrite() {
  auto w = new WriteThread::Writer();
@@ -250,30 +234,5 @@ SequenceNumber DBImpl::TEST_GetLastVisibleSequence() const {
  }
 }

-size_t DBImpl::TEST_GetWalPreallocateBlockSize(
-    uint64_t write_buffer_size) const {
-  InstrumentedMutexLock l(&mutex_);
-  return GetWalPreallocateBlockSize(write_buffer_size);
-}
-
-void DBImpl::TEST_WaitForDumpStatsRun(std::function<void()> callback) const {
-  if (thread_dump_stats_ != nullptr) {
-    thread_dump_stats_->TEST_WaitForRun(callback);
-  }
-}
-
-void DBImpl::TEST_WaitForPersistStatsRun(std::function<void()> callback) const {
-  if (thread_persist_stats_ != nullptr) {
-    thread_persist_stats_->TEST_WaitForRun(callback);
-  }
-}
-
-bool DBImpl::TEST_IsPersistentStatsEnabled() const {
-  return thread_persist_stats_ && thread_persist_stats_->IsRunning();
-}
-
-size_t DBImpl::TEST_EstimateInMemoryStatsHistorySize() const {
-  return EstimateInMemoryStatsHistorySize();
-}
 }  // namespace rocksdb
 #endif  // NDEBUG
--- a/Show More
+++ b/Show More