Integrated BlobDB for backup/restore support (#8129 )

Summary: Add support for blob files for backup/restore like table files. Since DB session ID is currently not supported for blob files (there is no place to store it in the header), so for blob files uses the kLegacyCrc32cAndFileSize naming scheme even if share_files_with_checksum_naming is set to kUseDbSessionId. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8129 Test Plan: Add new test units Reviewed By: ltamasi Differential Revision: D27408510 Pulled By: akankshamahajan15 fbshipit-source-id: b27434d189a639ef3e6ad165c61a143a2daaf06e
Fix read-only DB writing to filesystem with write_dbid_to_manifest (#8164 )
2026-07-07 22:55:23 +08:00 · 2021-04-07 13:38:54 -07:00 · 2021-04-07 10:26:47 -07:00 · 2021-04-06 23:31:51 -07:00 · 2021-04-06 16:02:04 -07:00 · 2021-04-06 14:37:53 -07:00
471 changed files with 20306 additions and 8354 deletions
@@ -103,6 +103,13 @@ commands:
            git clone --single-branch --branch master --depth 1 https://github.com/google/gtest-parallel.git ~/gtest-parallel
            echo 'export PATH=$HOME/gtest-parallel:$PATH' >> $BASH_ENV

+  install-compression-libs:
+    steps:
+      - run:
+          name: Install compression libs
+          command: |
+            sudo apt-get update -y && sudo apt-get install -y libsnappy-dev zlib1g-dev libbz2-dev liblz4-dev libzstd-dev
+
 executors:
  windows-2xlarge:
    machine:
@@ -171,7 +178,7 @@ jobs:
    steps:
      - pre-steps
      - install-gflags
-      - run: ASSERT_STATUS_CHECKED=1 TEST_UINT128_COMPAT=1 ROCKSDB_MODIFY_NPHASH=1 LIB_MODE=shared OPT="-DROCKSDB_NAMESPACE=alternative_rocksdb_ns" make V=1 -j32 all check_some | .circleci/cat_ignore_eagain
+      - run: ASSERT_STATUS_CHECKED=1 TEST_UINT128_COMPAT=1 ROCKSDB_MODIFY_NPHASH=1 LIB_MODE=shared OPT="-DROCKSDB_NAMESPACE=alternative_rocksdb_ns" make V=1 -j32 check | .circleci/cat_ignore_eagain
      - post-steps

  build-linux-release:
@@ -565,7 +572,25 @@ jobs:
            gtest-parallel $(</tmp/test_list) --output_dir=/tmp | cat  # pipe to cat to continuously output status on circleci UI. Otherwise, no status will be printed while the job is running.
      - post-steps

+  build-format-compatible:
+    machine:
+      image: ubuntu-1604:202007-01
+    resource_class: 2xlarge
+    steps:
+      - pre-steps
+      - install-gflags
+      - install-compression-libs
+      - run:
+          name: "test"
+          command: |
+            export TEST_TMPDIR=/dev/shm/rocksdb
+            rm -rf /dev/shm/rocksdb
+            mkdir /dev/shm/rocksdb
+            tools/check_format_compatible.sh
+      - post-steps
+
 workflows:
+  version: 2
  build-linux:
    jobs:
      - build-linux
@@ -666,3 +691,13 @@ workflows:
  build-cmake-mingw:
    jobs:
      - build-cmake-mingw
+  nightly:
+    triggers:
+      - schedule:
+          cron: "0 0 * * *"
+          filters:
+            branches:
+              only:
+                - master
+    jobs:
+      - build-format-compatible
@@ -32,7 +32,7 @@ jobs:
    - name: Download clang-format-diff.py
      uses: wei/wget@v1
      with:
-        args: https://raw.githubusercontent.com/llvm/llvm-project/master/clang/tools/clang-format/clang-format-diff.py
+        args: https://raw.githubusercontent.com/llvm/llvm-project/main/clang/tools/clang-format/clang-format-diff.py

    - name: Check format
      run: VERBOSE_CHECK=1 make check-format
@@ -93,3 +93,5 @@ clang-format-diff.py

 fuzz/proto/gen/
 fuzz/crash-*
+
+cmake-build-*
@@ -196,30 +196,30 @@ script:
  - if [ `command -v ccache` ]; then ccache -C; fi
  - case $TEST_GROUP in
    platform_dependent)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=only make -j4 all_but_some_tests check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=only make -j4 all_but_some_tests check_some
      ;;
    1)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_END=backupable_db_test make -j4 check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_END=backupable_db_test make -j4 check_some
      ;;
    2)
-      OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" V=1 make -j4 tools && OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=backupable_db_test ROCKSDBTESTS_END=db_universal_compaction_test make -j4 check_some
+      OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" LIB_MODE=shared V=1 make -j4 tools && OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=backupable_db_test ROCKSDBTESTS_END=db_universal_compaction_test make -j4 check_some
      ;;
    3)
      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=db_universal_compaction_test ROCKSDBTESTS_END=table_properties_collector_test make -j4 check_some
      ;;
    4)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=table_properties_collector_test make -j4 check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=table_properties_collector_test make -j4 check_some
      ;;
    esac
  - case $JOB_NAME in
    java_test)
-      OPT=-DTRAVIS V=1 make rocksdbjava jtest
+      OPT=-DTRAVIS LIB_MODE=shared V=1 make rocksdbjava jtest
      ;;
    lite_build)
-      OPT='-DTRAVIS -DROCKSDB_LITE' V=1 make -j4 all
+      OPT='-DTRAVIS -DROCKSDB_LITE' LIB_MODE=shared V=1 make -j4 all
      ;;
    examples)
-      OPT=-DTRAVIS V=1 make -j4 static_lib && cd examples && make -j4
+      OPT=-DTRAVIS LIB_MODE=shared 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;
@@ -235,10 +235,10 @@ script:
      mkdir build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DWITH_TESTS=0 -DWITH_GFLAGS=0 -DWITH_BENCHMARK_TOOLS=0 -DWITH_TOOLS=0 -DWITH_CORE_TOOLS=1 .. && make -j4 && cd  .. && rm -rf build && mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release $OPT && make -j4 rocksdb rocksdbjni
      ;;
    make-gcc4.8)
-      OPT=-DTRAVIS V=1 SKIP_LINK=1 make -j4 all && [ "Linking broken because libgflags compiled with newer ABI" ]
+      OPT=-DTRAVIS LIB_MODE=shared V=1 SKIP_LINK=1 make -j4 all && [ "Linking broken because libgflags compiled with newer ABI" ]
      ;;
    status_checked)
-      OPT=-DTRAVIS V=1 ASSERT_STATUS_CHECKED=1 make -j4 check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ASSERT_STATUS_CHECKED=1 make -j4 check_some
      ;;
    esac
 notifications:
@@ -88,10 +88,9 @@ if( NOT DEFINED CMAKE_CXX_STANDARD )
 endif()

 include(CMakeDependentOption)
-CMAKE_DEPENDENT_OPTION(WITH_GFLAGS "build with GFlags" ON
-  "NOT MSVC;NOT MINGW" OFF)

 if(MSVC)
+  option(WITH_GFLAGS "build with GFlags" OFF)
  option(WITH_XPRESS "build with windows built in compression" OFF)
  include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
 else()
@@ -107,6 +106,11 @@ else()
    endif()
  endif()

+  if(MINGW)
+    option(WITH_GFLAGS "build with GFlags" OFF)
+  else()
+    option(WITH_GFLAGS "build with GFlags" ON)
+  endif()
  set(GFLAGS_LIB)
  if(WITH_GFLAGS)
    # Config with namespace available since gflags 2.2.2
@@ -170,23 +174,25 @@ else()
  endif()
 endif()

-string(TIMESTAMP TS "%Y/%m/%d %H:%M:%S" UTC)
-set(GIT_DATE_TIME "${TS}" CACHE STRING "the time we first built rocksdb")
+string(TIMESTAMP TS "%Y-%m-%d %H:%M:%S" UTC)
+set(BUILD_DATE "${TS}" CACHE STRING "the time we first built rocksdb")

 find_package(Git)

 if(GIT_FOUND AND EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
-  if(WIN32)
-    execute_process(COMMAND $ENV{COMSPEC} /C ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse HEAD OUTPUT_VARIABLE GIT_SHA)
-  else()
-    execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse HEAD OUTPUT_VARIABLE GIT_SHA)
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_SHA COMMAND "${GIT_EXECUTABLE}" rev-parse HEAD )
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" RESULT_VARIABLE GIT_MOD COMMAND "${GIT_EXECUTABLE}" diff-index HEAD --quiet)
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_DATE COMMAND "${GIT_EXECUTABLE}" log -1 --date=format:"%Y-%m-%d %T" --format="%ad")
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG RESULT_VARIABLE rv COMMAND "${GIT_EXECUTABLE}" symbolic-ref -q --short HEAD OUTPUT_STRIP_TRAILING_WHITESPACE)
+  if (rv AND NOT rv EQUAL 0)
+    execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG COMMAND "${GIT_EXECUTABLE}" describe --tags --exact-match OUTPUT_STRIP_TRAILING_WHITESPACE)
  endif()
 else()
  set(GIT_SHA 0)
+  set(GIT_MOD 1)
 endif()
-
-string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA "${GIT_SHA}")
-
+string(REGEX REPLACE "[^0-9a-fA-F]+" "" GIT_SHA "${GIT_SHA}")
+string(REGEX REPLACE "[^0-9: /-]+" "" GIT_DATE "${GIT_DATE}")

 option(WITH_MD_LIBRARY "build with MD" ON)
 if(WIN32 AND MSVC)
@@ -199,15 +205,16 @@ endif()

 set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
 configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
-add_library(build_version OBJECT ${BUILD_VERSION_CC})
-target_include_directories(build_version PRIVATE
-  ${CMAKE_CURRENT_SOURCE_DIR}/util)
+
 if(MSVC)
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4800 /wd4996 /wd4351 /wd4100 /wd4204 /wd4324")
 else()
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
+  if(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64")
+    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wstrict-prototypes")
+  endif()
  if(MINGW)
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format -fno-asynchronous-unwind-tables")
    add_definitions(-D_POSIX_C_SOURCE=1)
@@ -243,14 +250,14 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
  endif(HAS_ALTIVEC)
 endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")

-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")
        CHECK_C_COMPILER_FLAG("-march=armv8-a+crc+crypto" HAS_ARMV8_CRC)
  if(HAS_ARMV8_CRC)
    message(STATUS " HAS_ARMV8_CRC yes")
    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
  endif(HAS_ARMV8_CRC)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
+endif(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")

 option(PORTABLE "build a portable binary" OFF)
 option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
@@ -466,11 +473,6 @@ if(CMAKE_SYSTEM_NAME MATCHES "Cygwin")
  add_definitions(-fno-builtin-memcmp -DCYGWIN)
 elseif(CMAKE_SYSTEM_NAME MATCHES "Darwin")
  add_definitions(-DOS_MACOSX)
-  if(CMAKE_SYSTEM_PROCESSOR MATCHES arm)
-    add_definitions(-DIOS_CROSS_COMPILE -DROCKSDB_LITE)
-    # no debug info for IOS, that will make our library big
-    add_definitions(-DNDEBUG)
-  endif()
 elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
  add_definitions(-DOS_LINUX)
 elseif(CMAKE_SYSTEM_NAME MATCHES "SunOS")
@@ -581,7 +583,6 @@ set(SOURCES
        db/builder.cc
        db/c.cc
        db/column_family.cc
-        db/compacted_db_impl.cc
        db/compaction/compaction.cc
        db/compaction/compaction_iterator.cc
        db/compaction/compaction_picker.cc
@@ -592,6 +593,7 @@ set(SOURCES
        db/compaction/sst_partitioner.cc
        db/convenience.cc
        db/db_filesnapshot.cc
+        db/db_impl/compacted_db_impl.cc
        db/db_impl/db_impl.cc
        db/db_impl/db_impl_write.cc
        db/db_impl/db_impl_compaction_flush.cc
@@ -642,17 +644,20 @@ set(SOURCES
        db/write_batch_base.cc
        db/write_controller.cc
        db/write_thread.cc
+        env/composite_env.cc
        env/env.cc
        env/env_chroot.cc
        env/env_encryption.cc
        env/env_hdfs.cc
        env/file_system.cc
        env/file_system_tracer.cc
+        env/fs_remap.cc
        env/mock_env.cc
        file/delete_scheduler.cc
        file/file_prefetch_buffer.cc
        file/file_util.cc
        file/filename.cc
+        file/line_file_reader.cc
        file/random_access_file_reader.cc
        file/read_write_util.cc
        file/readahead_raf.cc
@@ -766,6 +771,7 @@ set(SOURCES
        util/murmurhash.cc
        util/random.cc
        util/rate_limiter.cc
+        util/ribbon_config.cc
        util/slice.cc
        util/file_checksum_helper.cc
        util/status.cc
@@ -830,8 +836,7 @@ set(SOURCES
        utilities/transactions/write_unprepared_txn_db.cc
        utilities/ttl/db_ttl_impl.cc
        utilities/write_batch_with_index/write_batch_with_index.cc
-        utilities/write_batch_with_index/write_batch_with_index_internal.cc
-        $<TARGET_OBJECTS:build_version>)
+        utilities/write_batch_with_index/write_batch_with_index_internal.cc)

 list(APPEND SOURCES
  utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc
@@ -922,12 +927,12 @@ else()
  set(SYSTEM_LIBS ${CMAKE_THREAD_LIBS_INIT})
 endif()

-add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES})
+add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES} ${BUILD_VERSION_CC})
 target_link_libraries(${ROCKSDB_STATIC_LIB} PRIVATE
  ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})

 if(ROCKSDB_BUILD_SHARED)
-  add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES})
+  add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES} ${BUILD_VERSION_CC})
  target_link_libraries(${ROCKSDB_SHARED_LIB} PRIVATE
    ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})

@@ -945,7 +950,7 @@ if(ROCKSDB_BUILD_SHARED)
                          LINKER_LANGUAGE CXX
                          VERSION ${rocksdb_VERSION}
                          SOVERSION ${rocksdb_VERSION_MAJOR}
-                          OUTPUT_NAME "rocksdb")
+                          OUTPUT_NAME "rocksdb${ARTIFACT_SUFFIX}")
  endif()
 endif()

@@ -1066,6 +1071,8 @@ if(WITH_TESTS)
        db/blob/blob_file_garbage_test.cc
        db/blob/blob_file_reader_test.cc
        db/blob/db_blob_basic_test.cc
+        db/blob/db_blob_compaction_test.cc
+        db/blob/db_blob_corruption_test.cc
        db/blob/db_blob_index_test.cc
        db/column_family_test.cc
        db/compact_files_test.cc
@@ -1088,6 +1095,7 @@ if(WITH_TESTS)
        db/db_iter_test.cc
        db/db_iter_stress_test.cc
        db/db_iterator_test.cc
+        db/db_kv_checksum_test.cc
        db/db_log_iter_test.cc
        db/db_memtable_test.cc
        db/db_merge_operator_test.cc
@@ -1095,7 +1103,7 @@ 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_secondary_test.cc
        db/db_sst_test.cc
        db/db_statistics_test.cc
        db/db_table_properties_test.cc
@@ -1301,40 +1309,40 @@ if(WITH_TESTS)
 endif()

 if(WITH_BENCHMARK_TOOLS)
-  add_executable(db_bench
+  add_executable(db_bench${ARTIFACT_SUFFIX}
    tools/db_bench.cc
    tools/db_bench_tool.cc)
-  target_link_libraries(db_bench
+  target_link_libraries(db_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} ${THIRDPARTY_LIBS})

-  add_executable(cache_bench
+  add_executable(cache_bench${ARTIFACT_SUFFIX}
    cache/cache_bench.cc)
-  target_link_libraries(cache_bench
+  target_link_libraries(cache_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} ${GFLAGS_LIB})

-  add_executable(memtablerep_bench
+  add_executable(memtablerep_bench${ARTIFACT_SUFFIX}
    memtable/memtablerep_bench.cc)
-  target_link_libraries(memtablerep_bench
+  target_link_libraries(memtablerep_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} ${GFLAGS_LIB})

-  add_executable(range_del_aggregator_bench
+  add_executable(range_del_aggregator_bench${ARTIFACT_SUFFIX}
    db/range_del_aggregator_bench.cc)
-  target_link_libraries(range_del_aggregator_bench
+  target_link_libraries(range_del_aggregator_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} ${GFLAGS_LIB})

-  add_executable(table_reader_bench
+  add_executable(table_reader_bench${ARTIFACT_SUFFIX}
    table/table_reader_bench.cc)
-  target_link_libraries(table_reader_bench
+  target_link_libraries(table_reader_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} testharness ${GFLAGS_LIB})

-  add_executable(filter_bench
+  add_executable(filter_bench${ARTIFACT_SUFFIX}
    util/filter_bench.cc)
-  target_link_libraries(filter_bench
+  target_link_libraries(filter_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} ${GFLAGS_LIB})

-  add_executable(hash_table_bench
+  add_executable(hash_table_bench${ARTIFACT_SUFFIX}
    utilities/persistent_cache/hash_table_bench.cc)
-  target_link_libraries(hash_table_bench
+  target_link_libraries(hash_table_bench${ARTIFACT_SUFFIX}
    ${ROCKSDB_LIB} ${GFLAGS_LIB})
 endif()

@@ -1,20 +1,99 @@
 # Rocksdb Change Log
+## Unreleased
+### Behavior Changes
+* `ColumnFamilyOptions::sample_for_compression` now takes effect for creation of all block-based tables. Previously it only took effect for block-based tables created by flush.
+* `CompactFiles()` can no longer compact files from lower level to up level, which has the risk to corrupt DB (details: #8063). The validation is also added to all compactions.
+* Fixed some cases in which DB::OpenForReadOnly() could write to the filesystem. If you want a Logger with a read-only DB, you must now set DBOptions::info_log yourself, such as using CreateLoggerFromOptions().
+
+### Bug Fixes
+* Use thread-safe `strerror_r()` to get error messages.
+* Fixed a potential hang in shutdown for a DB whose `Env` has high-pri thread pool disabled (`Env::GetBackgroundThreads(Env::Priority::HIGH) == 0`)
+* Made BackupEngine thread-safe and added documentation comments to clarify what is safe for multiple BackupEngine objects accessing the same backup directory.
+* Fixed crash (divide by zero) when compression dictionary is applied to a file containing only range tombstones.
+* Fixed a backward iteration bug with partitioned filter enabled: not including the prefix of the last key of the previous filter partition in current filter partition can cause wrong iteration result.
+
+### Performance Improvements
+* On ARM platform, use `yield` instead of `wfe` to relax cpu to gain better performance.
+
+### Public API change
+* Added `TableProperties::slow_compression_estimated_data_size` and `TableProperties::fast_compression_estimated_data_size`. When `ColumnFamilyOptions::sample_for_compression > 0`, they estimate what `TableProperties::data_size` would have been if the "fast" or "slow" (see `ColumnFamilyOptions::sample_for_compression` API doc for definitions) compression had been used instead.
+* Update DB::StartIOTrace and remove Env object from the arguments as its redundant and DB already has Env object that is passed down to IOTracer::StartIOTrace
+* For new integrated BlobDB, add support for blob files for backup/restore like table files. Because of current limitations, blob files always use the kLegacyCrc32cAndFileSize naming scheme, and incremental backups must read and checksum all blob files in a DB, even for files that are already backed up.
+
+### New Features
+* Added the ability to open BackupEngine backups as read-only DBs, using BackupInfo::name_for_open and env_for_open provided by BackupEngine::GetBackupInfo() with include_file_details=true.
+
+## 6.19.0 (03/21/2021)
+### Bug Fixes
+* Fixed the truncation error found in APIs/tools when dumping block-based SST files in a human-readable format. After fix, the block-based table can be fully dumped as a readable file.
+* When hitting a write slowdown condition, no write delay (previously 1 millisecond) is imposed until `delayed_write_rate` is actually exceeded, with an initial burst allowance of 1 millisecond worth of bytes. Also, beyond the initial burst allowance, `delayed_write_rate` is now more strictly enforced, especially with multiple column families.
+
+### Public API change
+* Changed default `BackupableDBOptions::share_files_with_checksum` to `true` and deprecated `false` because of potential for data loss. Note that accepting this change in behavior can temporarily increase backup data usage because files are not shared between backups using the two different settings. Also removed obsolete option kFlagMatchInterimNaming.
+* Add a new option BlockBasedTableOptions::max_auto_readahead_size. RocksDB does auto-readahead for iterators on noticing more than two reads for a table file if user doesn't provide readahead_size. The readahead starts at 8KB and doubles on every additional read upto max_auto_readahead_size and now max_auto_readahead_size can be configured dynamically as well. Found that 256 KB readahead size provides the best performance, based on experiments, for auto readahead. Experiment data is in PR #3282. If value is set 0 then no automatic prefetching will be done by rocksdb. Also changing the value will only affect files opened after the change.
+* Add suppport to extend DB::VerifyFileChecksums API to also verify blob files checksum.
+* When using the new BlobDB, the amount of data written by flushes/compactions is now broken down into table files and blob files in the compaction statistics; namely, Write(GB) denotes the amount of data written to table files, while Wblob(GB) means the amount of data written to blob files.
+* New default BlockBasedTableOptions::format_version=5 to enable new Bloom filter implementation by default, compatible with RocksDB versions >= 6.6.0.
+* Add new SetBufferSize API to WriteBufferManager to allow dynamic management of memory allotted to all write buffers.  This allows user code to adjust memory monitoring provided by WriteBufferManager as process memory needs change datasets grow and shrink.
+* Clarified the required semantics of Read() functions in FileSystem and Env APIs. Please ensure any custom implementations are compliant.
+* For the new integrated BlobDB implementation, compaction statistics now include the amount of data read from blob files during compaction (due to garbage collection or compaction filters). Write amplification metrics have also been extended to account for data read from blob files.
+* Add EqualWithoutTimestamp() to Comparator.
+* Extend support to track blob files in SSTFileManager whenever a blob file is created/deleted. Blob files will be scheduled to delete via SSTFileManager and SStFileManager will now take blob files in account while calculating size and space limits along with SST files.
+* Add new Append and PositionedAppend API with checksum handoff to legacy Env.
+
+### New Features
+* Support compaction filters for the new implementation of BlobDB. Add `FilterBlobByKey()` to `CompactionFilter`. Subclasses can override this method so that compaction filters can determine whether the actual blob value has to be read during compaction. Use a new `kUndetermined` in `CompactionFilter::Decision` to indicated that further action is necessary for compaction filter to make a decision.
+* Add support to extend retrieval of checksums for blob files from the MANIFEST when checkpointing. During backup, rocksdb can detect corruption in blob files  during file copies.
+* Add new options for db_bench --benchmarks: flush, waitforcompaction, compact0, compact1.
+* Add an option to BackupEngine::GetBackupInfo to include the name and size of each backed-up file. Especially in the presence of file sharing among backups, this offers detailed insight into backup space usage.
+* Enable backward iteration on keys with user-defined timestamps.
+* Add statistics and info log for error handler: counters for bg error, bg io error, bg retryable io error, auto resume count, auto resume total retry number, and auto resume sucess; Histogram for auto resume retry count in each recovery call. Note that, each auto resume attempt will have one or multiple retries.
+
+### Behavior Changes
+* During flush, only WAL sync retryable IO error is mapped to hard error, which will stall the writes. When WAL is used but only SST file write has retryable IO error, it will be mapped to soft error and write will not be affected.
+
+## 6.18.0 (02/19/2021)
+### Behavior Changes
+* When retryable IO error occurs during compaction, it is mapped to soft error and set the BG error. However, auto resume is not called to clean the soft error since compaction will reschedule by itself. In this change, When retryable IO error occurs during compaction, BG error is not set. User will be informed the error via EventHelper.
+* Introduce a new trace file format for query tracing and replay and trace file version is bump up to 0.2. A payload map is added as the first portion of the payload. We will not have backward compatible issues when adding new entries to trace records. Added the iterator_upper_bound and iterator_lower_bound in Seek and SeekForPrev tracing function. Added them as the new payload member for iterator tracing.
+
+### New Features
+* Add support for key-value integrity protection in live updates from the user buffers provided to `WriteBatch` through the write to RocksDB's in-memory update buffer (memtable). This is intended to detect some cases of in-memory data corruption, due to either software or hardware errors. Users can enable protection by constructing their `WriteBatch` with `protection_bytes_per_key == 8`.
+* Add support for updating `full_history_ts_low` option in manual compaction, which is for old timestamp data GC.
+* Add a mechanism for using Makefile to build external plugin code into the RocksDB libraries/binaries. This intends to simplify compatibility and distribution for plugins (e.g., special-purpose `FileSystem`s) whose source code resides outside the RocksDB repo. See "plugin/README.md" for developer details, and "PLUGINS.md" for a listing of available plugins.
+* Added memory pre-fetching for experimental Ribbon filter, which especially optimizes performance with batched MultiGet.
+* A new, experimental version of BlobDB (key-value separation) is now available. The new implementation is integrated into the RocksDB core, i.e. it is accessible via the usual `rocksdb::DB` API, as opposed to the separate `rocksdb::blob_db::BlobDB` interface used by the earlier version, and can be configured on a per-column family basis using the configuration options `enable_blob_files`, `min_blob_size`, `blob_file_size`, `blob_compression_type`, `enable_blob_garbage_collection`, and `blob_garbage_collection_age_cutoff`. It extends RocksDB's consistency guarantees to blobs, and offers more features and better performance. Note that some features, most notably `Merge`, compaction filters, and backup/restore are not yet supported, and there is no support for migrating a database created by the old implementation.
+
+### Bug Fixes
+* Since 6.15.0, `TransactionDB` returns error `Status`es from calls to `DeleteRange()` and calls to `Write()` where the `WriteBatch` contains a range deletion. Previously such operations may have succeeded while not providing the expected transactional guarantees. There are certain cases where range deletion can still be used on such DBs; see the API doc on `TransactionDB::DeleteRange()` for details.
+* `OptimisticTransactionDB` now returns error `Status`es from calls to `DeleteRange()` and calls to `Write()` where the `WriteBatch` contains a range deletion. Previously such operations may have succeeded while not providing the expected transactional guarantees.
+* Fix `WRITE_PREPARED`, `WRITE_UNPREPARED` TransactionDB `MultiGet()` may return uncommitted data with snapshot.
+* In DB::OpenForReadOnly, if any error happens while checking Manifest file path, it was overridden by Status::NotFound. It has been fixed and now actual error is returned.
+
+### Public API Change
+* Added a "only_mutable_options" flag to the ConfigOptions.  When this flag is "true", the Configurable functions and convenience methods (such as GetDBOptionsFromString) will only deal with options that are marked as mutable.  When this flag is true, only options marked as mutable can be configured (a Status::InvalidArgument will be returned) and options not marked as mutable will not be returned or compared.  The default is "false", meaning to compare all options.
+* Add new Append and PositionedAppend APIs to FileSystem to bring the data verification information (data checksum information) from upper layer (e.g., WritableFileWriter) to the storage layer. In this way, the customized FileSystem is able to verify the correctness of data being written to the storage on time. Add checksum_handoff_file_types to DBOptions. User can use this option to control which file types (Currently supported file tyes: kWALFile, kTableFile, kDescriptorFile.) should use the new Append and PositionedAppend APIs to handoff the verification information. Currently, RocksDB only use crc32c to calculate the checksum for write handoff.
+* Add an option, `CompressionOptions::max_dict_buffer_bytes`, to limit the in-memory buffering for selecting samples for generating/training a dictionary. The limit is currently loosely adhered to.
+
+
 ## 6.17.0 (01/15/2021)
 ### Behavior Changes
 * When verifying full file checksum with `DB::VerifyFileChecksums()`, we now fail with `Status::InvalidArgument` if the name of the checksum generator used for verification does not match the name of the checksum generator used for protecting the file when it was created.
 * Since RocksDB does not continue write the same file if a file write fails for any reason, the file scope write IO error is treated the same as retryable IO error. More information about error handling of file scope IO error is included in `ErrorHandler::SetBGError`.

+### Bug Fixes
+* Version older than 6.15 cannot decode VersionEdits `WalAddition` and `WalDeletion`, fixed this by changing the encoded format of them to be ignorable by older versions.
+* Fix a race condition between DB startups and shutdowns in managing the periodic background worker threads. One effect of this race condition could be the process being terminated.
+
 ### Public API Change
 * Add a public API WriteBufferManager::dummy_entries_in_cache_usage() which reports the size of dummy entries stored in cache (passed to WriteBufferManager). Dummy entries are used to account for DataBlocks.
+* Add a SystemClock class that contains the time-related methods from Env.  The original methods in Env may be deprecated in a future release.  This class will allow easier testing, development, and expansion of time-related features.
+* Add a public API GetRocksBuildProperties and GetRocksBuildInfoAsString to get properties about the current build.  These properties may include settings related to the GIT settings (branch, timestamp).  This change also sets the "build date" based on the GIT properties, rather than the actual build time, thereby enabling more reproducible builds.

 ## 6.16.0 (12/18/2020)
 ### Behavior Changes
 * Attempting to write a merge operand without explicitly configuring `merge_operator` now fails immediately, causing the DB to enter read-only mode. Previously, failure was deferred until the `merge_operator` was needed by a user read or a background operation.

-### API Changes
-* `rocksdb_approximate_sizes` and `rocksdb_approximate_sizes_cf` in the C API now requires an error pointer (`char** errptr`) for receiving any error.
-* All overloads of DB::GetApproximateSizes now return Status, so that any failure to obtain the sizes is indicated to the caller.
-
 ### Bug Fixes
 * Truncated WALs ending in incomplete records can no longer produce gaps in the recovered data when `WALRecoveryMode::kPointInTimeRecovery` is used. Gaps are still possible when WALs are truncated exactly on record boundaries; for complete protection, users should enable `track_and_verify_wals_in_manifest`.
 * Fix a bug where compressed blocks read by MultiGet are not inserted into the compressed block cache when use_direct_reads = true.
@@ -33,6 +112,9 @@
 ### Public API Change
 * Deprecated public but rarely-used FilterBitsBuilder::CalculateNumEntry, which is replaced with ApproximateNumEntries taking a size_t parameter and returning size_t.
 * To improve portability the functions `Env::GetChildren` and `Env::GetChildrenFileAttributes` will no longer return entries for the special directories `.` or `..`.
+* Added a new option `track_and_verify_wals_in_manifest`. If `true`, the log numbers and sizes of the synced WALs are tracked in MANIFEST, then during DB recovery, if a synced WAL is missing from disk, or the WAL's size does not match the recorded size in MANIFEST, an error will be reported and the recovery will be aborted. Note that this option does not work with secondary instance.
+* `rocksdb_approximate_sizes` and `rocksdb_approximate_sizes_cf` in the C API now requires an error pointer (`char** errptr`) for receiving any error.
+* All overloads of DB::GetApproximateSizes now return Status, so that any failure to obtain the sizes is indicated to the caller.

 ## 6.15.0 (11/13/2020)
 ### Bug Fixes
@@ -54,7 +136,6 @@
 ### Public API Change
 * Deprecate `BlockBasedTableOptions::pin_l0_filter_and_index_blocks_in_cache` and `BlockBasedTableOptions::pin_top_level_index_and_filter`. These options still take effect until users migrate to the replacement APIs in `BlockBasedTableOptions::metadata_cache_options`. Migration guidance can be found in the API comments on the deprecated options.
 * Add new API `DB::VerifyFileChecksums` to verify SST file checksum with corresponding entries in the MANIFEST if present. Current implementation requires scanning and recomputing file checksums.
-* Added a new option `track_and_verify_wals_in_manifest`. If `true`, the log numbers and sizes of the synced WALs are tracked in MANIFEST, then during DB recovery, if a synced WAL is missing from disk, or the WAL's size does not match the recorded size in MANIFEST, an error will be reported and the recovery will be aborted. Note that this option does not work with secondary instance.

 ### Behavior Changes
 * The dictionary compression settings specified in `ColumnFamilyOptions::compression_opts` now additionally affect files generated by flush and compaction to non-bottommost level. Previously those settings at most affected files generated by compaction to bottommost level, depending on whether `ColumnFamilyOptions::bottommost_compression_opts` overrode them. Users who relied on dictionary compression settings in `ColumnFamilyOptions::compression_opts` affecting only the bottommost level can keep the behavior by moving their dictionary settings to `ColumnFamilyOptions::bottommost_compression_opts` and setting its `enabled` flag.
@@ -79,6 +160,7 @@
 * The settings of the DBOptions and ColumnFamilyOptions are now managed by Configurable objects (see New Features).  The same convenience methods to configure these options still exist but the backend implementation has been unified under a common implementation.

 ### New Features
+
 * Methods to configure serialize, and compare -- such as TableFactory -- are exposed directly through the Configurable base class (from which these objects inherit).  This change will allow for better and more thorough configuration management and retrieval in the future.  The options for a Configurable object can be set via the ConfigureFromMap, ConfigureFromString, or ConfigureOption method.  The serialized version of the options of an object can be retrieved via the GetOptionString, ToString, or GetOption methods.  The list of options supported by an object can be obtained via the GetOptionNames method.  The "raw" object (such as the BlockBasedTableOption) for an option may be retrieved via the GetOptions method.  Configurable options can be compared via the AreEquivalent method.  The settings within a Configurable object may be validated via the ValidateOptions method.  The object may be intialized (at which point only mutable options may be updated) via the PrepareOptions method.
 * Introduce options.check_flush_compaction_key_order with default value to be true. With this option, during flush and compaction, key order will be checked when writing to each SST file. If the order is violated, the flush or compaction will fail.
 * Added is_full_compaction to CompactionJobStats, so that the information is available through the EventListener interface.
@@ -43,6 +43,8 @@ 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.

+* `make check` will also check code formatting, which requires [clang-format](https://clang.llvm.org/docs/ClangFormat.html)
+
 * If you wish to build the RocksJava static target, then cmake is required for building Snappy.

 ## Supported platforms
@@ -94,12 +96,21 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
              sudo yum install libasan

    * Install zstandard:
+        * With [EPEL](https://fedoraproject.org/wiki/EPEL):

-             wget https://github.com/facebook/zstd/archive/v1.1.3.tar.gz
-             mv v1.1.3.tar.gz zstd-1.1.3.tar.gz
-             tar zxvf zstd-1.1.3.tar.gz
-             cd zstd-1.1.3
-             make && sudo make install
+              sudo yum install libzstd-devel
+
+        * With CentOS 8:
+
+              sudo dnf install libzstd-devel
+
+        * From source:
+
+              wget https://github.com/facebook/zstd/archive/v1.1.3.tar.gz
+              mv v1.1.3.tar.gz zstd-1.1.3.tar.gz
+              tar zxvf zstd-1.1.3.tar.gz
+              cd zstd-1.1.3
+              make && sudo make install

 * **OS X**:
    * Install latest C++ compiler that supports C++ 11:
@@ -259,6 +259,8 @@ AM_SHARE = $(AM_V_CCLD) $(CXX) $(PLATFORM_SHARED_LDFLAGS)$@ -L. $(patsubst lib%.
 # Export some common variables that might have been passed as Make variables
 # instead of environment variables.
 dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
+                  export CXXFLAGS="$(EXTRA_CXXFLAGS)"; \
+                  export LDFLAGS="$(EXTRA_LDFLAGS)"; \
                  export COMPILE_WITH_ASAN="$(COMPILE_WITH_ASAN)"; \
                  export COMPILE_WITH_TSAN="$(COMPILE_WITH_TSAN)"; \
                  export COMPILE_WITH_UBSAN="$(COMPILE_WITH_UBSAN)"; \
@@ -269,6 +271,12 @@ dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
 # this file is generated by the previous line to set build flags and sources
 include make_config.mk

+ROCKSDB_PLUGIN_MKS = $(foreach plugin, $(ROCKSDB_PLUGINS), plugin/$(plugin)/*.mk)
+include $(ROCKSDB_PLUGIN_MKS)
+ROCKSDB_PLUGIN_SOURCES = $(foreach plugin, $(ROCKSDB_PLUGINS), $(foreach source, $($(plugin)_SOURCES), plugin/$(plugin)/$(source)))
+ROCKSDB_PLUGIN_HEADERS = $(foreach plugin, $(ROCKSDB_PLUGINS), $(foreach header, $($(plugin)_HEADERS), plugin/$(plugin)/$(header)))
+PLATFORM_LDFLAGS += $(foreach plugin, $(ROCKSDB_PLUGINS), $($(plugin)_LDFLAGS))
+
 export JAVAC_ARGS
 CLEAN_FILES += make_config.mk rocksdb.pc

@@ -430,6 +438,10 @@ default: all
 WARNING_FLAGS = -W -Wextra -Wall -Wsign-compare -Wshadow \
  -Wunused-parameter

+ifeq (,$(filter amd64, $(MACHINE)))
+	C_WARNING_FLAGS = -Wstrict-prototypes
+endif
+
 ifdef USE_CLANG
 	# Used by some teams in Facebook
 	WARNING_FLAGS += -Wshift-sign-overflow
@@ -474,38 +486,14 @@ ifeq ($(NO_THREEWAY_CRC32C), 1)
 	CXXFLAGS += -DNO_THREEWAY_CRC32C
 endif

-CFLAGS += $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CCFLAGS) $(OPT)
+CFLAGS += $(C_WARNING_FLAGS) $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CCFLAGS) $(OPT)
 CXXFLAGS += $(WARNING_FLAGS) -I. -I./include $(PLATFORM_CXXFLAGS) $(OPT) -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers

 LDFLAGS += $(PLATFORM_LDFLAGS)

-# If NO_UPDATE_BUILD_VERSION is set we don't update util/build_version.cc, but
-# the file needs to already exist or else the build will fail
-ifndef NO_UPDATE_BUILD_VERSION
-date := $(shell date +%F)
-ifdef FORCE_GIT_SHA
-	git_sha := $(FORCE_GIT_SHA)
-else
-	git_sha := $(shell git rev-parse HEAD 2>/dev/null)
-endif
-gen_build_version = sed -e s/@@GIT_SHA@@/$(git_sha)/ -e s/@@GIT_DATE_TIME@@/$(date)/ util/build_version.cc.in
-
-# Record the version of the source that we are compiling.
-# We keep a record of the git revision in this file.  It is then built
-# as a regular source file as part of the compilation process.
-# One can run "strings executable_filename | grep _build_" to find
-# the version of the source that we used to build the executable file.
-FORCE:
-util/build_version.cc: FORCE
-	$(AM_V_GEN)rm -f $@-t
-	$(AM_V_at)$(gen_build_version) > $@-t
-	$(AM_V_at)if test -f $@; then					\
-	  cmp -s $@-t $@ && rm -f $@-t || mv -f $@-t $@;		\
-	else mv -f $@-t $@; fi
-endif
-
 OBJ_DIR?=.
 LIB_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(LIB_SOURCES))
+LIB_OBJECTS += $(patsubst %.cc, $(OBJ_DIR)/%.o, $(ROCKSDB_PLUGIN_SOURCES))
 ifeq ($(HAVE_POWER8),1)
 LIB_OBJECTS += $(patsubst %.c, $(OBJ_DIR)/%.o, $(LIB_SOURCES_C))
 LIB_OBJECTS += $(patsubst %.S, $(OBJ_DIR)/%.o, $(LIB_SOURCES_ASM))
@@ -515,6 +503,12 @@ ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
  LIB_OBJECTS += $(patsubst %.cpp, $(OBJ_DIR)/%.o, $(FOLLY_SOURCES))
 endif

+# range_tree is not compatible with non GNU libc on ppc64
+# see https://jira.percona.com/browse/PS-7559
+ifneq ($(PPC_LIBC_IS_GNU),0)
+  LIB_OBJECTS += $(patsubst %.cc, $(OBJ_DIR)/%.o, $(RANGE_TREE_SOURCES))
+endif
+
 GTEST = $(OBJ_DIR)/$(GTEST_DIR)/gtest/gtest-all.o
 TESTUTIL = $(OBJ_DIR)/test_util/testutil.o
 TESTHARNESS = $(OBJ_DIR)/test_util/testharness.o $(TESTUTIL) $(GTEST)
@@ -529,7 +523,8 @@ TOOL_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(TOOL_LIB_SOURCES))
 ANALYZE_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(ANALYZER_LIB_SOURCES))
 STRESS_OBJECTS =  $(patsubst %.cc, $(OBJ_DIR)/%.o, $(STRESS_LIB_SOURCES))

-ALL_SOURCES  = $(LIB_SOURCES) $(TEST_LIB_SOURCES) $(MOCK_LIB_SOURCES) $(GTEST_DIR)/gtest/gtest-all.cc
+# Exclude build_version.cc -- a generated source file -- from all sources.  Not needed for dependencies
+ALL_SOURCES  = $(filter-out util/build_version.cc, $(LIB_SOURCES)) $(TEST_LIB_SOURCES) $(MOCK_LIB_SOURCES) $(GTEST_DIR)/gtest/gtest-all.cc
 ALL_SOURCES += $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(ANALYZER_LIB_SOURCES) $(STRESS_LIB_SOURCES)
 ALL_SOURCES += $(TEST_MAIN_SOURCES) $(TOOL_MAIN_SOURCES) $(BENCH_MAIN_SOURCES)

@@ -541,238 +536,38 @@ ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
 	ALL_SOURCES += third-party/folly/folly/synchronization/test/DistributedMutexTest.cc
 endif

-PARALLEL_TEST = \
-	backupable_db_test \
-	db_bloom_filter_test \
-	db_compaction_filter_test \
-	db_compaction_test \
-	db_merge_operator_test \
-	db_sst_test \
-	db_test \
-	db_test2 \
-	db_universal_compaction_test \
-	db_wal_test \
-	column_family_test \
-	external_sst_file_test \
-	import_column_family_test \
-	fault_injection_test \
-	file_reader_writer_test \
-	inlineskiplist_test \
-	manual_compaction_test \
-	persistent_cache_test \
-	table_test \
-	transaction_test \
-	point_lock_manager_test \
-	range_locking_test \
-	write_prepared_transaction_test \
-	write_unprepared_transaction_test \
-
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-	TESTS += folly_synchronization_distributed_mutex_test
-	PARALLEL_TEST += folly_synchronization_distributed_mutex_test
-	TESTS_PASSING_ASC = folly_synchronization_distributed_mutex_test
-endif
-
 # options_settable_test doesn't pass with UBSAN as we use hack in the test
 ifdef COMPILE_WITH_UBSAN
        TESTS := $(shell echo $(TESTS) | sed 's/\boptions_settable_test\b//g')
 endif
 ifdef ASSERT_STATUS_CHECKED
-# This is a new check for which we will add support incrementally. This
-# list can be removed once support is fully added.
-	TESTS_PASSING_ASC = \
-		arena_test \
-		autovector_test \
-		cache_test \
-		lru_cache_test \
-		blob_file_addition_test \
-		blob_file_builder_test \
-		blob_file_cache_test \
-		blob_file_garbage_test \
-		blob_file_reader_test \
-		bloom_test \
-		cassandra_format_test \
-		cassandra_functional_test \
-		cassandra_row_merge_test \
-		cassandra_serialize_test \
-		cleanable_test \
-		checkpoint_test \
-		coding_test \
-		crc32c_test \
-		dbformat_test \
-		db_basic_test \
-		compact_files_test \
-		compaction_picker_test \
-		comparator_db_test \
-		db_encryption_test \
-		db_iter_test \
-		db_iter_stress_test \
-		db_log_iter_test \
-		db_bloom_filter_test \
-		db_blob_basic_test \
-		db_blob_index_test \
-		db_block_cache_test \
-		db_compaction_test \
-		db_compaction_filter_test \
-		db_dynamic_level_test \
-		db_flush_test \
-		db_inplace_update_test \
-		db_io_failure_test \
-		db_iterator_test \
-		db_logical_block_size_cache_test \
-		db_memtable_test \
-		db_merge_operand_test \
-		db_merge_operator_test \
-		db_wal_test \
-		db_with_timestamp_basic_test \
-		db_with_timestamp_compaction_test \
-		db_write_test \
-		db_options_test \
-		db_properties_test \
-		db_range_del_test \
-		db_secondary_test \
-		deletefile_test \
-		external_sst_file_test \
-		options_file_test \
-		db_sst_test \
-		db_statistics_test \
-		db_table_properties_test \
-		db_tailing_iter_test \
-		fault_injection_test \
-		listener_test \
-		log_test \
-		manual_compaction_test \
-		obsolete_files_test \
-		perf_context_test \
-		periodic_work_scheduler_test \
-		perf_context_test \
-		version_set_test \
-		wal_manager_test \
-		defer_test \
-		filename_test \
-		dynamic_bloom_test \
-		env_basic_test \
-		env_test \
-		env_logger_test \
-		event_logger_test \
-		error_handler_fs_test \
-		external_sst_file_basic_test \
-		auto_roll_logger_test \
-		file_indexer_test \
-		delete_scheduler_test \
-		flush_job_test \
-		hash_table_test \
-		hash_test \
-		heap_test \
-		histogram_test \
-		inlineskiplist_test \
-		io_posix_test \
-		iostats_context_test \
-		ldb_cmd_test \
-		memkind_kmem_allocator_test \
-		merge_test \
-		merger_test \
-		mock_env_test \
-		object_registry_test \
-		optimistic_transaction_test \
-		prefix_test \
-		plain_table_db_test \
-		repair_test \
-		configurable_test \
-		customizable_test \
-		options_settable_test \
-		options_test \
-		point_lock_manager_test \
-		random_access_file_reader_test \
-		random_test \
-		range_del_aggregator_test \
-		sst_file_reader_test \
-		range_tombstone_fragmenter_test \
-		repeatable_thread_test \
-		ribbon_test \
-		skiplist_test \
-		slice_test \
-		slice_transform_test \
-		sst_dump_test \
-		statistics_test \
-		stats_history_test \
-		stringappend_test \
-		thread_local_test \
-		trace_analyzer_test \
-		transaction_test \
-		env_timed_test \
-		filelock_test \
-		timer_queue_test \
-		timer_test \
-		options_util_test \
-		persistent_cache_test \
-		util_merge_operators_test \
-		block_cache_trace_analyzer_test \
-		block_cache_tracer_test \
-		cache_simulator_test \
-		sim_cache_test \
-		version_builder_test \
-		version_edit_test \
-		work_queue_test \
-		write_buffer_manager_test \
-		write_controller_test \
-		write_prepared_transaction_test \
-		write_unprepared_transaction_test \
-		compaction_iterator_test \
-		compaction_job_test \
-		compaction_job_stats_test \
-		io_tracer_test \
-		io_tracer_parser_test \
-		prefetch_test \
-		merge_helper_test \
-		memtable_list_test \
-		flush_job_test \
-		block_based_filter_block_test \
-		block_fetcher_test \
-		block_test \
-		data_block_hash_index_test \
-		full_filter_block_test \
-		partitioned_filter_block_test \
-		column_family_test \
-		file_reader_writer_test \
-		rate_limiter_test \
-		corruption_test \
-		reduce_levels_test \
-		thread_list_test \
-		compact_on_deletion_collector_test \
-		db_universal_compaction_test \
-		import_column_family_test \
-		option_change_migration_test \
-		cuckoo_table_builder_test \
-		cuckoo_table_db_test \
-		cuckoo_table_reader_test \
-		memory_test \
-		table_test \
-		backupable_db_test \
-		blob_db_test \
-		ttl_test \
-		write_batch_test \
-		write_batch_with_index_test \
+	# TODO: finish fixing all tests to pass this check
+	TESTS_FAILING_ASC = \
+		db_test \
+		db_test2 \
+		range_locking_test \
+		testutil_test \

-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-TESTS_PASSING_ASC += folly_synchronization_distributed_mutex_test
+	# Since we have very few ASC exclusions left, excluding them from
+	# the build is the most convenient way to exclude them from testing
+	TESTS := $(filter-out $(TESTS_FAILING_ASC),$(TESTS))
 endif

-	# Enable building all unit tests, but use check_some to run only tests
-	# known to pass ASC (ASSERT_STATUS_CHECKED)
-	ROCKSDBTESTS_SUBSET ?= $(TESTS_PASSING_ASC)
-	# Alternate: only build unit tests known to pass ASC, and run them
-	# with make check
-	#TESTS := $(filter $(TESTS_PASSING_ASC),$(TESTS))
-	#PARALLEL_TEST := $(filter $(TESTS_PASSING_ASC),$(PARALLEL_TEST))
-else
-	ROCKSDBTESTS_SUBSET ?= $(TESTS)
-endif
+ROCKSDBTESTS_SUBSET ?= $(TESTS)
+
+# env_test - suspicious use of test::TmpDir
+# deletefile_test - serial because it generates giant temporary files in
+#   its various tests. Parallel can fill up your /dev/shm
+NON_PARALLEL_TEST = \
+	env_test \
+	deletefile_test \
+
+PARALLEL_TEST = $(filter-out $(NON_PARALLEL_TEST), $(TESTS))
+
 # Not necessarily well thought out or up-to-date, but matches old list
 TESTS_PLATFORM_DEPENDENT := \
 	db_basic_test \
 	db_blob_basic_test \
-	db_with_timestamp_basic_test \
 	db_encryption_test \
 	db_test2 \
 	external_sst_file_basic_test \
@@ -863,6 +658,37 @@ ROCKSDB_MAJOR = $(shell egrep "ROCKSDB_MAJOR.[0-9]" include/rocksdb/version.h |
 ROCKSDB_MINOR = $(shell egrep "ROCKSDB_MINOR.[0-9]" include/rocksdb/version.h | cut -d ' ' -f 3)
 ROCKSDB_PATCH = $(shell egrep "ROCKSDB_PATCH.[0-9]" include/rocksdb/version.h | cut -d ' ' -f 3)

+# If NO_UPDATE_BUILD_VERSION is set we don't update util/build_version.cc, but
+# the file needs to already exist or else the build will fail
+ifndef NO_UPDATE_BUILD_VERSION
+
+# By default, use the current date-time as the date.  If there are no changes,
+# we will use the last commit date instead.
+build_date := $(shell date "+%Y-%m-%d %T")
+
+ifdef FORCE_GIT_SHA
+	git_sha := $(FORCE_GIT_SHA)
+	git_mod := 1
+	git_date := $(build_date)
+else
+	git_sha := $(shell git rev-parse HEAD 2>/dev/null)
+	git_tag  := $(shell git symbolic-ref -q --short HEAD 2> /dev/null || git describe --tags --exact-match 2>/dev/null)
+	git_mod  := $(shell git diff-index HEAD --quiet 2>/dev/null; echo $$?)
+	git_date := $(shell git log -1 --date=format:"%Y-%m-%d %T" --format="%ad" 2>/dev/null)
+endif
+gen_build_version = sed -e s/@GIT_SHA@/$(git_sha)/ -e s:@GIT_TAG@:"$(git_tag)": -e s/@GIT_MOD@/"$(git_mod)"/ -e s/@BUILD_DATE@/"$(build_date)"/ -e s/@GIT_DATE@/"$(git_date)"/ util/build_version.cc.in
+
+# Record the version of the source that we are compiling.
+# We keep a record of the git revision in this file.  It is then built
+# as a regular source file as part of the compilation process.
+# One can run "strings executable_filename | grep _build_" to find
+# the version of the source that we used to build the executable file.
+util/build_version.cc: $(filter-out $(OBJ_DIR)/util/build_version.o, $(LIB_OBJECTS)) util/build_version.cc.in
+	$(AM_V_GEN)rm -f $@-t
+	$(AM_V_at)$(gen_build_version) > $@
+endif
+CLEAN_FILES += util/build_version.cc
+
 default: all

 #-----------------------------------------------
@@ -910,7 +736,8 @@ endif  # PLATFORM_SHARED_EXT
 	analyze tools tools_lib \
 	blackbox_crash_test_with_atomic_flush whitebox_crash_test_with_atomic_flush  \
 	blackbox_crash_test_with_txn whitebox_crash_test_with_txn \
-	blackbox_crash_test_with_best_efforts_recovery
+	blackbox_crash_test_with_best_efforts_recovery \
+	blackbox_crash_test_with_ts whitebox_crash_test_with_ts


 all: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(TESTS)
@@ -1026,7 +853,7 @@ gen_parallel_tests:
 # 107.816 PASS t/DBTest.EncodeDecompressedBlockSizeTest
 #
 slow_test_regexp = \
-	^.*SnapshotConcurrentAccessTest.*$$|^t/run-table_test-HarnessTest.Randomized$$|^t/run-db_test-.*(?:FileCreationRandomFailure|EncodeDecompressedBlockSizeTest)$$|^.*RecoverFromCorruptedWALWithoutFlush$$
+	^.*SnapshotConcurrentAccessTest.*$$|^.*SeqAdvanceConcurrentTest.*$$|^t/run-table_test-HarnessTest.Randomized$$|^t/run-db_test-.*(?:FileCreationRandomFailure|EncodeDecompressedBlockSizeTest)$$|^.*RecoverFromCorruptedWALWithoutFlush$$
 prioritize_long_running_tests =						\
  perl -pe 's,($(slow_test_regexp)),100 $$1,'				\
    | sort -k1,1gr							\
@@ -1148,6 +975,8 @@ crash_test_with_txn: whitebox_crash_test_with_txn blackbox_crash_test_with_txn

 crash_test_with_best_efforts_recovery: blackbox_crash_test_with_best_efforts_recovery

+crash_test_with_ts: whitebox_crash_test_with_ts blackbox_crash_test_with_ts
+
 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)
@@ -1161,6 +990,9 @@ blackbox_crash_test_with_txn: db_stress
 blackbox_crash_test_with_best_efforts_recovery: db_stress
 	$(PYTHON) -u tools/db_crashtest.py --test_best_efforts_recovery blackbox $(CRASH_TEST_EXT_ARGS)

+blackbox_crash_test_with_ts: db_stress
+	$(PYTHON) -u tools/db_crashtest.py --enable_ts blackbox $(CRASH_TEST_EXT_ARGS)
+
 ifeq ($(CRASH_TEST_KILL_ODD),)
  CRASH_TEST_KILL_ODD=888887
 endif
@@ -1179,6 +1011,10 @@ whitebox_crash_test_with_txn: db_stress
 	$(PYTHON) -u tools/db_crashtest.py --txn whitebox --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

+whitebox_crash_test_with_ts: db_stress
+	$(PYTHON) -u tools/db_crashtest.py --enable_ts whitebox --random_kill_odd \
+      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+
 asan_check: clean
 	COMPILE_WITH_ASAN=1 $(MAKE) check -j32
 	$(MAKE) clean
@@ -1324,8 +1160,9 @@ analyze_incremental:
 		$(MAKE) dbg

 CLEAN_FILES += unity.cc
-unity.cc: Makefile
+unity.cc: Makefile util/build_version.cc.in
 	rm -f $@ $@-t
+	$(AM_V_at)$(gen_build_version) > util/build_version.cc
 	for source_file in $(LIB_SOURCES); do \
 		echo "#include \"$$source_file\"" >> $@-t; \
 	done
@@ -1405,7 +1242,7 @@ $(STATIC_TEST_LIBRARY): $(TEST_OBJECTS)
 	$(AM_V_AR)rm -f $@ $(SHARED_TEST_LIBRARY)
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^

-$(STATIC_TOOLS_LIBRARY): $(BENCH_OBJECTS) $(TOOL_OBJECTS)
+$(STATIC_TOOLS_LIBRARY): $(TOOL_OBJECTS)
 	$(AM_V_AR)rm -f $@ $(SHARED_TOOLS_LIBRARY)
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^

@@ -1455,7 +1292,7 @@ memtablerep_bench: $(OBJ_DIR)/memtable/memtablerep_bench.o $(LIBRARY)
 filter_bench: $(OBJ_DIR)/util/filter_bench.o $(LIBRARY)
 	$(AM_LINK)

-db_stress: $(OBJ_DIR)/db_stress_tool/db_stress.o $(STRESS_LIBRARY) $(TOOLS_LIBRARY) $(LIBRARY)
+db_stress: $(OBJ_DIR)/db_stress_tool/db_stress.o $(STRESS_LIBRARY) $(TOOLS_LIBRARY) $(TESTUTIL) $(LIBRARY)
 	$(AM_LINK)

 write_stress: $(OBJ_DIR)/tools/write_stress.o $(LIBRARY)
@@ -1554,6 +1391,9 @@ db_basic_test: $(OBJ_DIR)/db/db_basic_test.o $(TEST_LIBRARY) $(LIBRARY)
 db_blob_basic_test: $(OBJ_DIR)/db/blob/db_blob_basic_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

+db_blob_compaction_test: $(OBJ_DIR)/db/blob/db_blob_compaction_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 db_with_timestamp_basic_test: $(OBJ_DIR)/db/db_with_timestamp_basic_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

@@ -1602,6 +1442,9 @@ db_inplace_update_test: $(OBJ_DIR)/db/db_inplace_update_test.o $(TEST_LIBRARY) $
 db_iterator_test: $(OBJ_DIR)/db/db_iterator_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

+db_kv_checksum_test: $(OBJ_DIR)/db/db_kv_checksum_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 db_memtable_test: $(OBJ_DIR)/db/db_memtable_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

@@ -1994,7 +1837,7 @@ range_tombstone_fragmenter_test: $(OBJ_DIR)/db/range_tombstone_fragmenter_test.o
 sst_file_reader_test: $(OBJ_DIR)/table/sst_file_reader_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

-db_secondary_test: $(OBJ_DIR)/db/db_impl/db_secondary_test.o $(TEST_LIBRARY) $(LIBRARY)
+db_secondary_test: $(OBJ_DIR)/db/db_secondary_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

 block_cache_tracer_test: $(OBJ_DIR)/trace_replay/block_cache_tracer_test.o $(TEST_LIBRARY) $(LIBRARY)
@@ -2042,6 +1885,8 @@ io_tracer_parser_test: $(OBJ_DIR)/tools/io_tracer_parser_test.o $(OBJ_DIR)/tools
 io_tracer_parser: $(OBJ_DIR)/tools/io_tracer_parser.o $(TOOLS_LIBRARY) $(LIBRARY)
 	$(AM_LINK)

+db_blob_corruption_test: $(OBJ_DIR)/db/blob/db_blob_corruption_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
 #-------------------------------------------------
 # make install related stuff
 PREFIX ?= /usr/local
@@ -2066,6 +1911,10 @@ install-headers: gen-pc
 	for header in `$(FIND) "include/rocksdb" -type f -name *.h`; do \
 		install -C -m 644 $$header $(DESTDIR)/$(PREFIX)/$$header; \
 	done
+	for header in $(ROCKSDB_PLUGIN_HEADERS); do \
+		install -d $(DESTDIR)/$(PREFIX)/include/rocksdb/`dirname $$header`; \
+		install -C -m 644 $$header $(DESTDIR)/$(PREFIX)/include/rocksdb/$$header; \
+	done
 	install -C -m 644 rocksdb.pc $(INSTALL_LIBDIR)/pkgconfig/rocksdb.pc

 install-static: install-headers $(LIBRARY)
@@ -2152,8 +2001,8 @@ SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/archive
 LZ4_VER ?= 1.9.3
 LZ4_SHA256 ?= 030644df4611007ff7dc962d981f390361e6c97a34e5cbc393ddfbe019ffe2c1
 LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
-ZSTD_VER ?= 1.4.7
-ZSTD_SHA256 ?= 085500c8d0b9c83afbc1dc0d8b4889336ad019eba930c5d6a9c6c86c20c769c8
+ZSTD_VER ?= 1.4.9
+ZSTD_SHA256 ?= acf714d98e3db7b876e5b540cbf6dee298f60eb3c0723104f6d3f065cd60d6a8
 ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
 CURL_SSL_OPTS ?= --tlsv1

@@ -2453,12 +2302,14 @@ endif
 # ---------------------------------------------------------------------------
 #  	Source files dependencies detection
 # ---------------------------------------------------------------------------
-
+# If skip dependencies is ON, skip including the dep files
+ifneq ($(SKIP_DEPENDS), 1)
 DEPFILES = $(patsubst %.cc, $(OBJ_DIR)/%.cc.d, $(ALL_SOURCES))
 DEPFILES+ = $(patsubst %.c, $(OBJ_DIR)/%.c.d, $(LIB_SOURCES_C) $(TEST_MAIN_SOURCES_C))
 ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
  DEPFILES +=$(patsubst %.cpp, $(OBJ_DIR)/%.cpp.d, $(FOLLY_SOURCES))
 endif
+endif

 # Add proper dependency support so changing a .h file forces a .cc file to
 # rebuild.
@@ -2498,24 +2349,9 @@ endif
 build_subset_tests: $(ROCKSDBTESTS_SUBSET)
 	$(AM_V_GEN)if [ -n "$${ROCKSDBTESTS_SUBSET_TESTS_TO_FILE}" ]; then echo "$(ROCKSDBTESTS_SUBSET)" > "$${ROCKSDBTESTS_SUBSET_TESTS_TO_FILE}"; else echo "$(ROCKSDBTESTS_SUBSET)"; fi

-# if the make goal is either "clean" or "format", we shouldn't
-# try to import the *.d files.
-# TODO(kailiu) The unfamiliarity of Make's conditions leads to the ugly
-# working solution.
-ifneq ($(MAKECMDGOALS),clean)
-ifneq ($(MAKECMDGOALS),format)
-ifneq ($(MAKECMDGOALS),jclean)
-ifneq ($(MAKECMDGOALS),jtest)
-ifneq ($(MAKECMDGOALS),rocksdbjavastatic)
-ifneq ($(MAKECMDGOALS),rocksdbjavastatic_deps)
-ifneq ($(MAKECMDGOALS),package)
-ifneq ($(MAKECMDGOALS),analyze)
+# Remove the rules for which dependencies should not be generated and see if any are left.
+#If so, include the dependencies; if not, do not include the dependency files
+ROCKS_DEP_RULES=$(filter-out clean format check-format check-buck-targets jclean jtest package analyze tags rocksdbjavastatic% unity.% unity_test, $(MAKECMDGOALS))
+ifneq ("$(ROCKS_DEP_RULES)", "")
 -include $(DEPFILES)
 endif
-endif
-endif
-endif
-endif
-endif
-endif
-endif
@@ -0,0 +1,3 @@
+This is the list of all known third-party plugins for RocksDB. If something is missing, please open a pull request to add it.
+
+* [Dedupfs](https://github.com/ajkr/dedupfs): an example for plugin developers to reference
@@ -26,6 +26,9 @@ Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasu
 ## Yahoo
 Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa. Learn more about it here: http://yahooeng.tumblr.com/post/120730204806/sherpa-scales-new-heights

+## Baidu
+[Apache Doris](http://doris.apache.org/master/en/) is a MPP analytical database engine released by Baidu. It [uses RocksDB](http://doris.apache.org/master/en/administrator-guide/operation/tablet-meta-tool.html) to manage its tablet's metadata.
+
 ## 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

@@ -67,7 +70,7 @@ Pinterest's Object Retrieval System uses RocksDB for storage: https://www.youtub
 [VWO's](https://vwo.com/) Smart Code checker and URL helper uses RocksDB to store all the URLs where VWO's Smart Code is installed.

 ## quasardb
-[quasardb](https://www.quasardb.net) is a high-performance, distributed, transactional key-value database that integrates well with in-memory analytics engines such as Apache Spark. 
+[quasardb](https://www.quasardb.net) is a high-performance, distributed, transactional key-value database that integrates well with in-memory analytics engines such as Apache Spark.
 quasardb uses a heavily tuned RocksDB as its persistence layer.

 ## Netflix
@@ -96,10 +99,10 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed

 ## IOTA Foundation
 [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
- 
+
 ## Avrio Project
 [Avrio Project](http://avrio-project.github.io/avrio.network/) is using RocksDB in [Avrio ](https://github.com/avrio-project/avrio) to store blocks, account balances and data and other blockchain-releated data. Avrio is a multiblockchain decentralized cryptocurrency empowering monetary transactions.
- 
+
 ## Crux
 [Crux](https://github.com/juxt/crux) is a document database that uses RocksDB for local [EAV](https://en.wikipedia.org/wiki/Entity%E2%80%93attribute%E2%80%93value_model) index storage to enable point-in-time bitemporal Datalog queries. The "unbundled" architecture uses Kafka to provide horizontal scalability.

@@ -24,10 +24,10 @@ from util import ColorString
 # (This generates a TARGET file without user-specified dependency for unit
 # tests.)
 # $python3 buckifier/buckify_rocksdb.py \
-#        '{"fake": { \
-#                      "extra_deps": [":test_dep", "//fakes/module:mock1"],  \
-#                      "extra_compiler_flags": ["-DROCKSDB_LITE", "-Os"], \
-#                  } \
+#        '{"fake": {
+#                      "extra_deps": [":test_dep", "//fakes/module:mock1"],
+#                      "extra_compiler_flags": ["-DROCKSDB_LITE", "-Os"]
+#                  }
 #         }'
 # (Generated TARGETS file has test_dep and mock1 as dependencies for RocksDB
 # unit tests, and will use the extra_compiler_flags to compile the unit test
@@ -69,25 +69,25 @@ def get_cc_files(repo_path):
    return cc_files


-# Get parallel tests from Makefile
-def get_parallel_tests(repo_path):
+# Get non_parallel tests from Makefile
+def get_non_parallel_tests(repo_path):
    Makefile = repo_path + "/Makefile"

    s = set({})

-    found_parallel_tests = False
+    found_non_parallel_tests = False
    for line in open(Makefile):
        line = line.strip()
-        if line.startswith("PARALLEL_TEST ="):
-            found_parallel_tests = True
-        elif found_parallel_tests:
+        if line.startswith("NON_PARALLEL_TEST ="):
+            found_non_parallel_tests = True
+        elif found_non_parallel_tests:
            if line.endswith("\\"):
                # remove the trailing \
                line = line[:-1]
                line = line.strip()
                s.add(line)
            else:
-                # we consumed all the parallel tests
+                # we consumed all the non_parallel tests
                break

    return s
@@ -123,23 +123,33 @@ def generate_targets(repo_path, deps_map):
    src_mk = parse_src_mk(repo_path)
    # get all .cc files
    cc_files = get_cc_files(repo_path)
-    # get parallel tests from Makefile
-    parallel_tests = get_parallel_tests(repo_path)
+    # get non_parallel tests from Makefile
+    non_parallel_tests = get_non_parallel_tests(repo_path)

-    if src_mk is None or cc_files is None or parallel_tests is None:
+    if src_mk is None or cc_files is None or non_parallel_tests is None:
        return False

-    TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path)
+    extra_argv = ""
+    if len(sys.argv) >= 2:
+        # Heuristically quote and canonicalize whitespace for inclusion
+        # in how the file was generated.
+        extra_argv = " '{0}'".format(" ".join(sys.argv[1].split()))
+
+    TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path, extra_argv)

    # rocksdb_lib
    TARGETS.add_library(
        "rocksdb_lib",
        src_mk["LIB_SOURCES"] +
+        # always add range_tree, it's only excluded on ppc64, which we don't use internally
+        src_mk["RANGE_TREE_SOURCES"] +
        src_mk["TOOL_LIB_SOURCES"])
    # rocksdb_whole_archive_lib
    TARGETS.add_library(
        "rocksdb_whole_archive_lib",
        src_mk["LIB_SOURCES"] +
+        # always add range_tree, it's only excluded on ppc64, which we don't use internally
+        src_mk["RANGE_TREE_SOURCES"] +
        src_mk["TOOL_LIB_SOURCES"],
        deps=None,
        headers=None,
@@ -201,7 +211,7 @@ def generate_targets(repo_path, deps_map):
            TARGETS.register_test(
                test_target_name,
                test_src,
-                test in parallel_tests,
+                test not in non_parallel_tests,
                json.dumps(deps['extra_deps']),
                json.dumps(deps['extra_compiler_flags']))

@@ -25,10 +25,11 @@ def pretty_list(lst, indent=8):


 class TARGETSBuilder(object):
-    def __init__(self, path):
+    def __init__(self, path, extra_argv):
        self.path = path
        self.targets_file = open(path, 'wb')
-        header = targets_cfg.rocksdb_target_header_template
+        header = targets_cfg.rocksdb_target_header_template.format(
+            extra_argv=extra_argv)
        self.targets_file.write(header.encode("utf-8"))
        self.total_lib = 0
        self.total_bin = 0
@@ -86,6 +87,7 @@ cpp_binary(
    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
    compiler_flags = ROCKSDB_COMPILER_FLAGS,
    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
    deps = [":rocksdb_test_lib"],
 ) if not is_opt_mode else None

@@ -5,7 +5,8 @@ from __future__ import print_function
 from __future__ import unicode_literals

 rocksdb_target_header_template = \
-    """# This file \100generated by `python3 buckifier/buckify_rocksdb.py`
+    """# This file \100generated by:
+#$ python3 buckifier/buckify_rocksdb.py{extra_argv}
 # --> DO NOT EDIT MANUALLY <--
 # This file is a Facebook-specific integration for buck builds, so can
 # only be validated by Facebook employees.
@@ -31,7 +32,7 @@ ROCKSDB_EXTERNAL_DEPS = [
    ("zlib", None, "z"),
    ("gflags", None, "gflags"),
    ("lz4", None, "lz4"),
-    ("zstd", None),
+    ("zstd", None, "zstd"),
 ]

 ROCKSDB_OS_DEPS = [
@@ -93,17 +94,19 @@ ROCKSDB_PREPROCESSOR_FLAGS = [

    # Added missing flags from output of build_detect_platform
    "-DROCKSDB_BACKTRACE",
-
-    # Directories with files for #include
-    "-I" + REPO_PATH + "include/",
-    "-I" + REPO_PATH,
 ]

-ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {
+# Directories with files for #include
+ROCKSDB_INCLUDE_PATHS = [
+    "",
+    "include",
+]
+
+ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {{
    "x86_64": [
        "-DHAVE_PCLMUL",
    ],
-}
+}}

 build_mode = read_config("fbcode", "build_mode")

@@ -144,6 +147,7 @@ cpp_library(
    os_deps = ROCKSDB_OS_DEPS,
    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
    deps = [{deps}],
    external_deps = ROCKSDB_EXTERNAL_DEPS{extra_external_deps},
    link_whole = {link_whole},
@@ -160,6 +164,7 @@ cpp_library(
    os_deps = ROCKSDB_OS_DEPS,
    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
    deps = ROCKSDB_LIB_DEPS,
    external_deps = ROCKSDB_EXTERNAL_DEPS,
 )
@@ -172,6 +177,7 @@ cpp_binary(
    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
    compiler_flags = ROCKSDB_COMPILER_FLAGS,
    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
    deps = [{deps}],
    external_deps = ROCKSDB_EXTERNAL_DEPS,
 )
@@ -202,6 +208,7 @@ ROCKS_TESTS = [
        os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
        compiler_flags = ROCKSDB_COMPILER_FLAGS + extra_compiler_flags,
        preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+        include_paths = ROCKSDB_INCLUDE_PATHS,
        deps = [":rocksdb_test_lib"] + extra_deps,
        external_deps = ROCKSDB_EXTERNAL_DEPS + [
            ("googletest", None, "gtest"),
@@ -177,7 +177,7 @@ case "$TARGET_OS" in
        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt -ldl"
        if test $ROCKSDB_USE_IO_URING; then
            # check for liburing
-            $CXX $CFLAGS -x c++ - -luring -o /dev/null 2>/dev/null  <<EOF
+            $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o /dev/null 2>/dev/null  <<EOF
              #include <liburing.h>
              int main() {
                struct io_uring ring;
@@ -288,7 +288,7 @@ if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
 else
    if ! test $ROCKSDB_DISABLE_FALLOCATE; then
        # Test whether fallocate is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <fcntl.h>
          #include <linux/falloc.h>
          int main() {
@@ -304,7 +304,7 @@ EOF
    if ! test $ROCKSDB_DISABLE_SNAPPY; then
        # Test whether Snappy library is installed
        # http://code.google.com/p/snappy/
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <snappy.h>
          int main() {}
 EOF
@@ -319,7 +319,7 @@ EOF
        # Test whether gflags library is installed
        # http://gflags.github.io/gflags/
        # check if the namespace is gflags
-        if $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+        if $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
          #include <gflags/gflags.h>
          using namespace GFLAGS_NAMESPACE;
          int main() {}
@@ -328,7 +328,7 @@ EOF
          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1"
          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
        # check if namespace is gflags
-        elif $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+        elif $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
            #include <gflags/gflags.h>
            using namespace gflags;
            int main() {}
@@ -337,7 +337,7 @@ EOF
          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1 -DGFLAGS_NAMESPACE=gflags"
          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
        # check if namespace is google
-        elif $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+        elif $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
            #include <gflags/gflags.h>
            using namespace google;
            int main() {}
@@ -350,7 +350,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_ZLIB; then
        # Test whether zlib library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <zlib.h>
          int main() {}
 EOF
@@ -363,7 +363,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_BZIP; then
        # Test whether bzip library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <bzlib.h>
          int main() {}
 EOF
@@ -376,7 +376,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_LZ4; then
        # Test whether lz4 library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <lz4.h>
          #include <lz4hc.h>
          int main() {}
@@ -390,7 +390,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_ZSTD; then
        # Test whether zstd library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <zstd.h>
          int main() {}
 EOF
@@ -403,7 +403,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_NUMA; then
        # Test whether numa is available
-        $CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
          #include <numa.h>
          #include <numaif.h>
          int main() {}
@@ -417,7 +417,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_TBB; then
        # Test whether tbb is available
-        $CXX $CFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null  <<EOF
          #include <tbb/tbb.h>
          int main() {}
 EOF
@@ -430,7 +430,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_JEMALLOC; then
        # Test whether jemalloc is available
-        if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
+        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -ljemalloc \
          2>/dev/null; then
            # This will enable some preprocessor identifiers in the Makefile
            JEMALLOC=1
@@ -451,7 +451,7 @@ EOF
    fi
    if ! test $JEMALLOC && ! test $ROCKSDB_DISABLE_TCMALLOC; then
        # jemalloc is not available. Let's try tcmalloc
-        if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null \
+        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null \
          -ltcmalloc 2>/dev/null; then
            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltcmalloc"
            JAVA_LDFLAGS="$JAVA_LDFLAGS -ltcmalloc"
@@ -460,7 +460,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_MALLOC_USABLE_SIZE; then
        # Test whether malloc_usable_size is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <malloc.h>
          int main() {
            size_t res = malloc_usable_size(0);
@@ -475,7 +475,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_MEMKIND; then
        # Test whether memkind library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -lmemkind -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -lmemkind -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <memkind.h>
          int main() {
            memkind_malloc(MEMKIND_DAX_KMEM, 1024);
@@ -491,7 +491,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_PTHREAD_MUTEX_ADAPTIVE_NP; then
        # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <pthread.h>
          int main() {
            int x = PTHREAD_MUTEX_ADAPTIVE_NP;
@@ -506,7 +506,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_BACKTRACE; then
        # Test whether backtrace is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <execinfo.h>
          int main() {
            void* frames[1];
@@ -518,7 +518,7 @@ EOF
            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
        else
            # Test whether execinfo library is installed
-            $CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
+            $CXX $PLATFORM_CXXFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
              #include <execinfo.h>
              int main() {
                void* frames[1];
@@ -535,7 +535,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_PG; then
        # Test if -pg is supported
-        $CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
          int main() {
            return 0;
          }
@@ -547,7 +547,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_SYNC_FILE_RANGE; then
        # Test whether sync_file_range is supported for compatibility with an old glibc
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <fcntl.h>
          int main() {
            int fd = open("/dev/null", 0);
@@ -561,7 +561,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_SCHED_GETCPU; then
        # Test whether sched_getcpu is supported
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <sched.h>
          int main() {
            int cpuid = sched_getcpu();
@@ -575,7 +575,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_AUXV_GETAUXVAL; then
        # Test whether getauxval is supported
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <sys/auxv.h>
          int main() {
            uint64_t auxv = getauxval(AT_HWCAP);
@@ -603,7 +603,7 @@ fi
 # -Wshorten-64-to-32 breaks compilation on FreeBSD i386
 if ! [ "$TARGET_OS" = FreeBSD -a "$TARGET_ARCHITECTURE" = i386 ]; then
  # Test whether -Wshorten-64-to-32 is available
-  $CXX $CFLAGS -x c++ - -o /dev/null -Wshorten-64-to-32 2>/dev/null  <<EOF
+  $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -Wshorten-64-to-32 2>/dev/null  <<EOF
    int main() {}
 EOF
  if [ "$?" = 0 ]; then
@@ -668,6 +668,23 @@ else
  fi
 fi

+if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
+  # check for GNU libc on ppc64
+  $CXX -x c++ - -o /dev/null 2>/dev/null <<EOF
+    #include <stdio.h>
+    #include <stdlib.h>
+    #include <gnu/libc-version.h>
+
+    int main(int argc, char *argv[]) {
+      printf("GNU libc version: %s\n", gnu_get_libc_version());
+      return 0;
+    }
+EOF
+  if [ "$?" != 0 ]; then
+      PPC_LIBC_IS_GNU=0
+  fi
+fi
+
 if test "$TRY_SSE_ETC"; then
  # The USE_SSE flag now means "attempt to compile with widely-available
  # Intel architecture extensions utilized by specific optimizations in the
@@ -861,3 +878,6 @@ echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
 if test -n "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
  echo "USE_FOLLY_DISTRIBUTED_MUTEX=$USE_FOLLY_DISTRIBUTED_MUTEX" >> "$OUTPUT"
 fi
+if test -n "$PPC_LIBC_IS_GNU"; then
+  echo "PPC_LIBC_IS_GNU=$PPC_LIBC_IS_GNU" >> "$OUTPUT"
+fi
@@ -52,7 +52,8 @@ else
    else
      echo "You didn't have clang-format-diff.py and/or clang-format available in your computer!"
      echo "You can download clang-format-diff.py by running: "
-      echo "    curl --location https://tinyurl.com/y2kvokof -o ${REPO_ROOT}/clang-format-diff.py"
+      echo "    curl --location https://raw.githubusercontent.com/llvm/llvm-project/main/clang/tools/clang-format/clang-format-diff.py -o ${REPO_ROOT}/clang-format-diff.py"
+      echo "You should make sure the downloaded script is not compromised."
      echo "You can download clang-format by running:"
      echo "    brew install clang-format"
      echo "  Or"
@@ -82,7 +83,8 @@ else
      echo "You have clang-format-diff.py for Python 2 but are using a Python 3"
      echo "interpreter (${PYTHON:-python3})."
      echo "You can download clang-format-diff.py for Python 3 by running: "
-      echo "    curl --location https://tinyurl.com/y2kvokof -o ${REPO_ROOT}/clang-format-diff.py"
+      echo "    curl --location https://raw.githubusercontent.com/llvm/llvm-project/main/clang/tools/clang-format/clang-format-diff.py -o ${REPO_ROOT}/clang-format-diff.py"
+      echo "You should make sure the downloaded script is not compromised."
      exit 130
    fi
    CLANG_FORMAT_DIFF="${PYTHON:-python3} $CFD_PATH"
@@ -134,9 +136,11 @@ then
  FORMAT_UPSTREAM_MERGE_BASE="$(git merge-base "$FORMAT_UPSTREAM" HEAD)"
  # Get the differences
  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1)
+  echo "Checking format of changes not yet in $FORMAT_UPSTREAM..."
 else
  # Check the format of uncommitted lines,
  diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
+  echo "Checking format of uncommitted changes..."
 fi

 if [ -z "$diffs" ]
@@ -3,7 +3,7 @@
 # to determine next steps to run

 # Usage:
-# EMAIL=<email> ONCALL=<email> TRIGGER=<trigger> SUBSCRIBER=<email> rocks_ci.py <test-name>
+# EMAIL=<email> ONCALL=<email> TRIGGER=<trigger> SUBSCRIBER=<email> WORKINGDIR=<working_dir> rocksdb-lego-determinator <test-name>
 #
 # Input         Value
 # -------------------------------------------------------------------------
@@ -11,7 +11,7 @@
 # ONCALL        Email address to raise a task on failure
 # TRIGGER       Trigger conditions for email. Valid values are fail, warn, all
 # SUBSCRIBER    Email addresss to add as subscriber for task
-#
+# WORKINGDIR    Working directory

 #
 # Report configuration
@@ -53,13 +53,19 @@ if [[ ! -z $REPORT_EMAIL || ! -z $CREATE_TASK ]]; then
  ]"
 fi

+# Working directory for the following command, default to current directory
+WORKING_DIR=.
+if [ ! -z $WORKINGDIR ]; then
+  WORKING_DIR=$WORKINGDIR
+fi
+
 #
 # Helper variables
 #
 CLEANUP_ENV="
 {
    'name':'Cleanup environment',
-    'shell':'rm -rf /dev/shm/rocksdb && mkdir /dev/shm/rocksdb && (chmod +t /dev/shm || true)  && make clean',
+    'shell':'cd $WORKING_DIR; rm -rf /dev/shm/rocksdb && mkdir /dev/shm/rocksdb && (chmod +t /dev/shm || true) && make clean',
    'user':'root'
 }"

@@ -112,6 +118,7 @@ SETUP_JAVA_ENV="export $HTTP_PROXY; export JAVA_HOME=/usr/local/jdk-8u60-64/; ex
 PARSER="'parser':'python build_tools/error_filter.py $1'"

 CONTRUN_NAME="ROCKSDB_CONTRUN_NAME"
+SKIP_FORMAT_CHECKS="SKIP_FORMAT_BUCK_CHECKS=1"

 # This code is getting called under various scenarios. What we care about is to
 # understand when it's called from nightly contruns because in that case we'll
@@ -153,7 +160,7 @@ UNIT_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and test RocksDB debug version',
-                'shell':'$SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM check || $CONTRUN_NAME=check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -176,7 +183,7 @@ UNIT_TEST_NON_SHM_COMMANDS="[
            {
                'name':'Build and test RocksDB debug version',
                'timeout': 86400,
-                'shell':'$NON_SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $NON_SHM $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -197,7 +204,7 @@ RELEASE_BUILD_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build RocksDB release',
-                'shell':'make $PARALLEL_j release || $CONTRUN_NAME=release $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; make $PARALLEL_j release || $CONTRUN_NAME=release $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -218,7 +225,7 @@ UNIT_TEST_COMMANDS_481="[
            $CLEANUP_ENV,
            {
                'name':'Build and test RocksDB debug version',
-                'shell':'$SHM $GCC_481 $DEBUG make $PARALLELISM check || $CONTRUN_NAME=unit_gcc_481_check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $GCC_481 $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM check || $CONTRUN_NAME=unit_gcc_481_check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -239,7 +246,7 @@ RELEASE_BUILD_COMMANDS_481="[
            $CLEANUP_ENV,
            {
                'name':'Build RocksDB release on GCC 4.8.1',
-                'shell':'$GCC_481 make $PARALLEL_j release || $CONTRUN_NAME=release_gcc481 $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $GCC_481 make $PARALLEL_j release || $CONTRUN_NAME=release_gcc481 $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -260,7 +267,7 @@ CLANG_UNIT_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and test RocksDB debug',
-                'shell':'$CLANG $SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=clang_check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $CLANG $SHM $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM check || $CONTRUN_NAME=clang_check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -281,7 +288,7 @@ CLANG_RELEASE_BUILD_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build RocksDB release',
-                'shell':'$CLANG make $PARALLEL_j release|| $CONTRUN_NAME=clang_release $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $CLANG make $PARALLEL_j release|| $CONTRUN_NAME=clang_release $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -302,7 +309,7 @@ CLANG_ANALYZE_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'RocksDB build and analyze',
-                'shell':'$CLANG $SHM $DEBUG make $PARALLEL_j analyze || $CONTRUN_NAME=clang_analyze $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $CLANG $SHM $DEBUG make $PARALLEL_j analyze || $CONTRUN_NAME=clang_analyze $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -323,7 +330,7 @@ CODE_COV_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build, test and collect code coverage info',
-                'shell':'$SHM $DEBUG make $PARALLELISM coverage || $CONTRUN_NAME=coverage $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM coverage || $CONTRUN_NAME=coverage $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -344,7 +351,7 @@ UNITY_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build, test unity test',
-                'shell':'$SHM $DEBUG V=1 make J=1 unity_test || $CONTRUN_NAME=unity_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG V=1 make J=1 unity_test || $CONTRUN_NAME=unity_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -365,7 +372,7 @@ LITE_BUILD_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build RocksDB debug version',
-                'shell':'make J=1 LITE=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SKIP_FORMAT_CHECKS make J=1 LITE=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -385,7 +392,7 @@ REPORT_LITE_BINARY_SIZE_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Report RocksDB Lite binary size to scuba',
-                'shell':'tools/report_lite_binary_size.sh',
+                'shell':'cd $WORKING_DIR; tools/report_lite_binary_size.sh',
                'user':'root',
            },
        ],
@@ -404,14 +411,14 @@ STRESS_CRASH_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
            {
                'name':'Build and run RocksDB debug crash tests',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -434,14 +441,14 @@ BLACKBOX_STRESS_CRASH_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
            {
                'name':'Build and run RocksDB debug blackbox crash tests',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 blackbox_crash_test || $CONTRUN_NAME=blackbox_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 blackbox_crash_test || $CONTRUN_NAME=blackbox_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -464,14 +471,14 @@ WHITEBOX_STRESS_CRASH_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
            {
                'name':'Build and run RocksDB debug whitebox crash tests',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 whitebox_crash_test || $CONTRUN_NAME=whitebox_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 whitebox_crash_test || $CONTRUN_NAME=whitebox_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -494,14 +501,14 @@ STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $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',
+                'shell':'cd $WORKING_DIR; $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
            },
@@ -524,14 +531,44 @@ STRESS_CRASH_TEST_WITH_TXN_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
            {
                'name':'Build and run RocksDB debug crash tests with txn',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_txn || $CONTRUN_NAME=crash_test_with_txn $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_txn || $CONTRUN_NAME=crash_test_with_txn $TASK_CREATION_TOOL',
+                'user':'root',
+                $PARSER
+            },
+            $UPLOAD_DB_DIR,
+        ],
+        $REPORT
+    }
+]"
+
+#
+# RocksDB stress/crash test with timestamp
+#
+STRESS_CRASH_TEST_WITH_TS_COMMANDS="[
+    {
+        'name':'Rocksdb Stress and Crash Test with ts',
+        'oncall':'$ONCALL',
+        'executeLocal': 'true',
+        'timeout': 86400,
+        'steps': [
+            $CLEANUP_ENV,
+            {
+                'name':'Build and run RocksDB debug stress tests',
+                'shell':'cd $WORKING_DIR; $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 ts',
+                'timeout': 86400,
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_ts || $CONTRUN_NAME=crash_test_with_ts $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -553,7 +590,7 @@ WRITE_STRESS_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build and run RocksDB write stress tests',
-                'shell':'make write_stress && python tools/write_stress_runner.py --runtime_sec=3600 --db=/tmp/rocksdb_write_stress || $CONTRUN_NAME=write_stress $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; make write_stress && python tools/write_stress_runner.py --runtime_sec=3600 --db=/tmp/rocksdb_write_stress || $CONTRUN_NAME=write_stress $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            }
@@ -576,7 +613,7 @@ ASAN_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Test RocksDB debug under ASAN',
-'shell':'set -o pipefail && ($SHM $ASAN $DEBUG make $PARALLELISM asan_check || $CONTRUN_NAME=asan_check $TASK_CREATION_TOOL) |& /usr/facebook/ops/scripts/asan_symbolize.py -d',
+'shell':'cd $WORKING_DIR; set -o pipefail && ($SHM $ASAN $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM asan_check || $CONTRUN_NAME=asan_check $TASK_CREATION_TOOL) |& /usr/facebook/ops/scripts/asan_symbolize.py -d',
                'user':'root',
                $PARSER
            }
@@ -599,7 +636,7 @@ ASAN_CRASH_TEST_COMMANDS="[
            {
                'name':'Build and run RocksDB debug asan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $SKIP_FORMAT_CHECKS make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -623,7 +660,7 @@ ASAN_BLACKBOX_CRASH_TEST_COMMANDS="[
            {
                'name':'Build and run RocksDB debug blackbox asan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 blackbox_asan_crash_test || $CONTRUN_NAME=blackbox_asan_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $SKIP_FORMAT_CHECKS make J=1 blackbox_asan_crash_test || $CONTRUN_NAME=blackbox_asan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -647,7 +684,7 @@ ASAN_WHITEBOX_CRASH_TEST_COMMANDS="[
            {
                'name':'Build and run RocksDB debug whitebox asan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 whitebox_asan_crash_test || $CONTRUN_NAME=whitebox_asan_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $SKIP_FORMAT_CHECKS make J=1 whitebox_asan_crash_test || $CONTRUN_NAME=whitebox_asan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -671,7 +708,7 @@ ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
            {
                'name':'Build and run RocksDB debug asan_crash_test_with_atomic_flush',
                'timeout': 86400,
-                'shell':'$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',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $SKIP_FORMAT_CHECKS make J=1 asan_crash_test_with_atomic_flush || $CONTRUN_NAME=asan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -695,7 +732,7 @@ ASAN_CRASH_TEST_WITH_TXN_COMMANDS="[
            {
                'name':'Build and run RocksDB debug asan_crash_test_with_txn',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_txn || $CONTRUN_NAME=asan_crash_test_with_txn $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $SKIP_FORMAT_CHECKS make J=1 asan_crash_test_with_txn || $CONTRUN_NAME=asan_crash_test_with_txn $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -717,7 +754,7 @@ UBSAN_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Test RocksDB debug under UBSAN',
-                'shell':'set -o pipefail && $SHM $UBSAN $CLANG $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; set -o pipefail && $SHM $UBSAN $CLANG $DEBUG $SKIP_FORMAT_CHECKS make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            }
@@ -740,7 +777,7 @@ UBSAN_CRASH_TEST_COMMANDS="[
            {
                'name':'Build and run RocksDB debug ubsan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $CLANG $SKIP_FORMAT_CHECKS make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -764,7 +801,7 @@ UBSAN_BLACKBOX_CRASH_TEST_COMMANDS="[
            {
                'name':'Build and run RocksDB debug blackbox ubsan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 blackbox_ubsan_crash_test || $CONTRUN_NAME=blackbox_ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $CLANG $SKIP_FORMAT_CHECKS make J=1 blackbox_ubsan_crash_test || $CONTRUN_NAME=blackbox_ubsan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -788,7 +825,7 @@ UBSAN_WHITEBOX_CRASH_TEST_COMMANDS="[
            {
                'name':'Build and run RocksDB debug whitebox ubsan_crash_test',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 whitebox_ubsan_crash_test || $CONTRUN_NAME=whitebox_ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $CLANG $SKIP_FORMAT_CHECKS make J=1 whitebox_ubsan_crash_test || $CONTRUN_NAME=whitebox_ubsan_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -812,7 +849,7 @@ UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
            {
                'name':'Build and run RocksDB debug ubsan_crash_test_with_atomic_flush',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $CLANG $SKIP_FORMAT_CHECKS make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -836,7 +873,7 @@ UBSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
            {
                'name':'Build and run RocksDB debug ubsan_crash_test_with_txn',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_txn || $CONTRUN_NAME=ubsan_crash_test_with_txn $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG $NON_TSAN_CRASH $CLANG $SKIP_FORMAT_CHECKS make J=1 ubsan_crash_test_with_txn || $CONTRUN_NAME=ubsan_crash_test_with_txn $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -860,7 +897,7 @@ VALGRIND_TEST_COMMANDS="[
            {
                'name':'Run RocksDB debug unit tests',
                'timeout': 86400,
-                'shell':'$SHM $DEBUG make $PARALLELISM valgrind_test || $CONTRUN_NAME=valgrind_check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SHM $DEBUG make $PARALLELISM valgrind_test || $CONTRUN_NAME=valgrind_check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -883,7 +920,7 @@ TSAN_UNIT_TEST_COMMANDS="[
            {
                'name':'Run RocksDB debug unit test',
                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN make $PARALLELISM check || $CONTRUN_NAME=tsan_check $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; set -o pipefail && $SHM $DEBUG $TSAN $SKIP_FORMAT_CHECKS make $PARALLELISM check || $CONTRUN_NAME=tsan_check $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -906,7 +943,7 @@ TSAN_CRASH_TEST_COMMANDS="[
            {
                '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':'cd $WORKING_DIR; 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',
                'user':'root',
                $PARSER
            },
@@ -930,7 +967,7 @@ TSAN_BLACKBOX_CRASH_TEST_COMMANDS="[
            {
                'name':'Compile and run',
                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 blackbox_crash_test || $CONTRUN_NAME=tsan_blackbox_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 blackbox_crash_test || $CONTRUN_NAME=tsan_blackbox_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -954,7 +991,7 @@ TSAN_WHITEBOX_CRASH_TEST_COMMANDS="[
            {
                'name':'Compile and run',
                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 whitebox_crash_test || $CONTRUN_NAME=tsan_whitebox_crash_test $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 whitebox_crash_test || $CONTRUN_NAME=tsan_whitebox_crash_test $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -978,7 +1015,7 @@ TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
            {
                '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',
+                'shell':'cd $WORKING_DIR; 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
            },
@@ -1002,7 +1039,7 @@ TSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
            {
                'name':'Compile and run',
                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_txn || $CONTRUN_NAME=tsan_crash_test_with_txn $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_txn || $CONTRUN_NAME=tsan_crash_test_with_txn $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -1036,7 +1073,7 @@ FORMAT_COMPATIBLE_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Run RocksDB debug unit test',
-                'shell':'build_tools/rocksdb-lego-determinator run_format_compatible || $CONTRUN_NAME=run_format_compatible $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; build_tools/rocksdb-lego-determinator run_format_compatible || $CONTRUN_NAME=run_format_compatible $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -1058,6 +1095,7 @@ run_no_compression()
  mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
  cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
  mv .tmp.Makefile Makefile
+  export $SKIP_FORMAT_CHECKS
  make $DEBUG J=1 check
 }

@@ -1070,7 +1108,7 @@ NO_COMPRESSION_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Run RocksDB debug unit test',
-                'shell':'build_tools/rocksdb-lego-determinator run_no_compression || $CONTRUN_NAME=run_no_compression $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; build_tools/rocksdb-lego-determinator run_no_compression || $CONTRUN_NAME=run_no_compression $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -1129,7 +1167,7 @@ REGRESSION_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Make and run script',
-                'shell':'build_tools/rocksdb-lego-determinator run_regression || $CONTRUN_NAME=run_regression $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; build_tools/rocksdb-lego-determinator run_regression || $CONTRUN_NAME=run_regression $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -1150,7 +1188,7 @@ JAVA_BUILD_TEST_COMMANDS="[
            $CLEANUP_ENV,
            {
                'name':'Build RocksDB for Java',
-                'shell':'$SETUP_JAVA_ENV; $SHM make rocksdbjava || $CONTRUN_NAME=rocksdbjava $TASK_CREATION_TOOL',
+                'shell':'cd $WORKING_DIR; $SETUP_JAVA_ENV; $SHM make rocksdbjava || $CONTRUN_NAME=rocksdbjava $TASK_CREATION_TOOL',
                'user':'root',
                $PARSER
            },
@@ -1212,6 +1250,9 @@ case $1 in
  stress_crash_with_txn)
    echo $STRESS_CRASH_TEST_WITH_TXN_COMMANDS
    ;;
+  stress_crash_with_ts)
+    echo $STRESS_CRASH_TEST_WITH_TS_COMMANDS
+    ;;
  write_stress)
    echo $WRITE_STRESS_COMMANDS
    ;;
@@ -68,7 +68,7 @@ $BinariesFolder = -Join($RootFolder, "\build\Debug\")

 if($WorkFolder -eq "") {

-    # If TEST_TMPDIR is set use it    
+    # If TEST_TMPDIR is set use it
    [string]$var = $Env:TEST_TMPDIR
    if($var -eq "") {
        $WorkFolder = -Join($RootFolder, "\db_tests\")
@@ -93,7 +93,7 @@ $ExcludeCasesSet = New-Object System.Collections.Generic.HashSet[string]
 if($ExcludeCases -ne "") {
    Write-Host "ExcludeCases: $ExcludeCases"
    $l = $ExcludeCases -split ' '
-    ForEach($t in $l) { 
+    ForEach($t in $l) {
      $ExcludeCasesSet.Add($t) | Out-Null
    }
 }
@@ -102,7 +102,7 @@ $ExcludeExesSet = New-Object System.Collections.Generic.HashSet[string]
 if($ExcludeExes -ne "") {
    Write-Host "ExcludeExe: $ExcludeExes"
    $l = $ExcludeExes -split ' '
-    ForEach($t in $l) { 
+    ForEach($t in $l) {
      $ExcludeExesSet.Add($t) | Out-Null
    }
 }
@@ -118,6 +118,10 @@ if($ExcludeExes -ne "") {
 #   MultiThreaded/MultiThreadedDBTest.
 #     MultiThreaded/0  # GetParam() = 0
 #     MultiThreaded/1  # GetParam() = 1
+#   RibbonTypeParamTest/0.  # TypeParam = struct DefaultTypesAndSettings
+#     CompactnessAndBacktrackAndFpRate
+#     Extremes
+#     FindOccupancyForSuccessRate
 #
 # into this:
 #
@@ -125,6 +129,9 @@ if($ExcludeExes -ne "") {
 #   DBTest.WriteEmptyBatch
 #   MultiThreaded/MultiThreadedDBTest.MultiThreaded/0
 #   MultiThreaded/MultiThreadedDBTest.MultiThreaded/1
+#   RibbonTypeParamTest/0.CompactnessAndBacktrackAndFpRate
+#   RibbonTypeParamTest/0.Extremes
+#   RibbonTypeParamTest/0.FindOccupancyForSuccessRate
 #
 # Output into the parameter in a form TestName -> Log File Name
 function ExtractTestCases([string]$GTestExe, $HashTable) {
@@ -138,6 +145,8 @@ function ExtractTestCases([string]$GTestExe, $HashTable) {

    ForEach( $l in $Tests) {

+      # remove trailing comment if any
+      $l = $l -replace '\s+\#.*',''
      # Leading whitespace is fine
      $l = $l -replace '^\s+',''
      # Trailing dot is a test group but no whitespace
@@ -146,8 +155,7 @@ function ExtractTestCases([string]$GTestExe, $HashTable) {
      }  else {
        # Otherwise it is a test name, remove leading space
        $test = $l
-        # remove trailing comment if any and create a log name
-        $test = $test -replace '\s+\#.*',''
+        # create a log name
        $test = "$Group$test"

        if($ExcludeCasesSet.Contains($test)) {
@@ -253,7 +261,7 @@ if($Run -ne "") {

  $DiscoveredExe = @()
  dir -Path $search_path | ForEach-Object {
-     $DiscoveredExe += ($_.Name)     
+     $DiscoveredExe += ($_.Name)
  }

  # Remove exclusions
@@ -293,7 +301,7 @@ if($SuiteRun -ne "") {

  $ListOfExe = @()
  dir -Path $search_path | ForEach-Object {
-     $ListOfExe += ($_.Name)     
+     $ListOfExe += ($_.Name)
  }

  # Exclude those in RunOnly from running as suites
@@ -348,7 +356,7 @@ function RunJobs($Suites, $TestCmds, [int]$ConcurrencyVal)

    # Wait for all to finish and get the results
    while(($JobToLog.Count -gt 0) -or
-          ($TestCmds.Count -gt 0) -or 
+          ($TestCmds.Count -gt 0) -or
           ($Suites.Count -gt 0)) {

        # Make sure we have maximum concurrent jobs running if anything
@@ -468,8 +476,8 @@ RunJobs -Suites $CasesToRun -TestCmds $TestExes -ConcurrencyVal $Concurrency

 $EndDate = (Get-Date)

-New-TimeSpan -Start $StartDate -End $EndDate | 
-  ForEach-Object { 
+New-TimeSpan -Start $StartDate -End $EndDate |
+  ForEach-Object {
    "Elapsed time: {0:g}" -f $_
  }

@@ -484,4 +492,4 @@ if(!$script:success) {

 exit 0

- 
+
@@ -11,15 +11,17 @@ int main() {
 }
 #else

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

 #include "port/port.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
+#include "rocksdb/system_clock.h"
 #include "util/coding.h"
 #include "util/gflags_compat.h"
 #include "util/hash.h"
@@ -210,6 +212,7 @@ class CacheBench {

  bool Run() {
    ROCKSDB_NAMESPACE::Env* env = ROCKSDB_NAMESPACE::Env::Default();
+    const auto& clock = env->GetSystemClock();

    PrintEnv();
    SharedState shared(this);
@@ -224,7 +227,7 @@ class CacheBench {
        shared.GetCondVar()->Wait();
      }
      // Record start time
-      uint64_t start_time = env->NowMicros();
+      uint64_t start_time = clock->NowMicros();

      // Start all threads
      shared.SetStart();
@@ -236,7 +239,7 @@ class CacheBench {
      }

      // Record end time
-      uint64_t end_time = env->NowMicros();
+      uint64_t end_time = clock->NowMicros();
      double elapsed = static_cast<double>(end_time - start_time) * 1e-6;
      uint32_t qps = static_cast<uint32_t>(
          static_cast<double>(FLAGS_threads * FLAGS_ops_per_thread) / elapsed);
@@ -9,8 +9,8 @@

 #include "cache/lru_cache.h"

-#include <assert.h>
-#include <stdio.h>
+#include <cassert>
+#include <cstdio>
 #include <string>

 #include "util/mutexlock.h"
@@ -239,7 +239,7 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  //  not threadsafe
  size_t TEST_GetLRUSize();

-  //  Retrives high pri pool ratio
+  //  Retrieves high pri pool ratio
  double GetHighPriPoolRatio();

 private:
@@ -328,7 +328,7 @@ class LRUCache

  //  Retrieves number of elements in LRU, for unit test purpose only
  size_t TEST_GetLRUSize();
-  //  Retrives high pri pool ratio
+  //  Retrieves high pri pool ratio
  double GetHighPriPoolRatio();

 private:
@@ -30,7 +30,7 @@ class LRUCacheTest : public testing::Test {
    DeleteCache();
    cache_ = reinterpret_cast<LRUCacheShard*>(
        port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
-    new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
+    new (cache_) LRUCacheShard(capacity, false /*strict_capacity_limit*/,
                               high_pri_pool_ratio, use_adaptive_mutex,
                               kDontChargeCacheMetadata);
  }
@@ -8,6 +8,7 @@
 #include <cassert>

 #include "db/blob/blob_file_addition.h"
+#include "db/blob/blob_file_completion_callback.h"
 #include "db/blob/blob_index.h"
 #include "db/blob/blob_log_format.h"
 #include "db/blob/blob_log_writer.h"
@@ -17,39 +18,44 @@
 #include "file/writable_file_writer.h"
 #include "logging/logging.h"
 #include "options/cf_options.h"
+#include "options/options_helper.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/status.h"
 #include "test_util/sync_point.h"
+#include "trace_replay/io_tracer.h"
 #include "util/compression.h"

 namespace ROCKSDB_NAMESPACE {

 BlobFileBuilder::BlobFileBuilder(
-    VersionSet* versions, Env* env, FileSystem* fs,
+    VersionSet* versions, FileSystem* fs,
    const ImmutableCFOptions* immutable_cf_options,
    const MutableCFOptions* mutable_cf_options, const FileOptions* file_options,
    int job_id, uint32_t column_family_id,
    const std::string& column_family_name, Env::IOPriority io_priority,
    Env::WriteLifeTimeHint write_hint,
+    const std::shared_ptr<IOTracer>& io_tracer,
+    BlobFileCompletionCallback* blob_callback,
    std::vector<std::string>* blob_file_paths,
    std::vector<BlobFileAddition>* blob_file_additions)
-    : BlobFileBuilder([versions]() { return versions->NewFileNumber(); }, env,
-                      fs, immutable_cf_options, mutable_cf_options,
-                      file_options, job_id, column_family_id,
-                      column_family_name, io_priority, write_hint,
-                      blob_file_paths, blob_file_additions) {}
+    : BlobFileBuilder([versions]() { return versions->NewFileNumber(); }, fs,
+                      immutable_cf_options, mutable_cf_options, file_options,
+                      job_id, column_family_id, column_family_name, io_priority,
+                      write_hint, io_tracer, blob_callback, blob_file_paths,
+                      blob_file_additions) {}

 BlobFileBuilder::BlobFileBuilder(
-    std::function<uint64_t()> file_number_generator, Env* env, FileSystem* fs,
+    std::function<uint64_t()> file_number_generator, FileSystem* fs,
    const ImmutableCFOptions* immutable_cf_options,
    const MutableCFOptions* mutable_cf_options, const FileOptions* file_options,
    int job_id, uint32_t column_family_id,
    const std::string& column_family_name, Env::IOPriority io_priority,
    Env::WriteLifeTimeHint write_hint,
+    const std::shared_ptr<IOTracer>& io_tracer,
+    BlobFileCompletionCallback* blob_callback,
    std::vector<std::string>* blob_file_paths,
    std::vector<BlobFileAddition>* blob_file_additions)
    : file_number_generator_(std::move(file_number_generator)),
-      env_(env),
      fs_(fs),
      immutable_cf_options_(immutable_cf_options),
      min_blob_size_(mutable_cf_options->min_blob_size),
@@ -61,12 +67,13 @@ BlobFileBuilder::BlobFileBuilder(
      column_family_name_(column_family_name),
      io_priority_(io_priority),
      write_hint_(write_hint),
+      io_tracer_(io_tracer),
+      blob_callback_(blob_callback),
      blob_file_paths_(blob_file_paths),
      blob_file_additions_(blob_file_additions),
      blob_count_(0),
      blob_bytes_(0) {
  assert(file_number_generator_);
-  assert(env_);
  assert(fs_);
  assert(immutable_cf_options_);
  assert(file_options_);
@@ -157,11 +164,12 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
  std::unique_ptr<FSWritableFile> file;

  {
-    TEST_SYNC_POINT("BlobFileBuilder::OpenBlobFileIfNeeded:NewWritableFile");
-
    assert(file_options_);
-    const Status s =
-        NewWritableFile(fs_, blob_file_path, &file, *file_options_);
+    Status s = NewWritableFile(fs_, blob_file_path, &file, *file_options_);
+
+    TEST_SYNC_POINT_CALLBACK(
+        "BlobFileBuilder::OpenBlobFileIfNeeded:NewWritableFile", &s);
+
    if (!s.ok()) {
      return s;
    }
@@ -176,17 +184,20 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
  assert(file);
  file->SetIOPriority(io_priority_);
  file->SetWriteLifeTimeHint(write_hint_);
-
+  FileTypeSet tmp_set = immutable_cf_options_->checksum_handoff_file_types;
  Statistics* const statistics = immutable_cf_options_->statistics;
-
  std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-      std::move(file), blob_file_paths_->back(), *file_options_, env_,
-      nullptr /*IOTracer*/, statistics, immutable_cf_options_->listeners,
-      immutable_cf_options_->file_checksum_gen_factory));
+      std::move(file), blob_file_paths_->back(), *file_options_,
+      immutable_cf_options_->clock, io_tracer_, statistics,
+      immutable_cf_options_->listeners,
+      immutable_cf_options_->file_checksum_gen_factory,
+      tmp_set.Contains(FileType::kBlobFile)));

-  std::unique_ptr<BlobLogWriter> blob_log_writer(
-      new BlobLogWriter(std::move(file_writer), env_, statistics,
-                        blob_file_number, immutable_cf_options_->use_fsync));
+  constexpr bool do_flush = false;
+
+  std::unique_ptr<BlobLogWriter> blob_log_writer(new BlobLogWriter(
+      std::move(file_writer), immutable_cf_options_->clock, statistics,
+      blob_file_number, immutable_cf_options_->use_fsync, do_flush));

  constexpr bool has_ttl = false;
  constexpr ExpirationRange expiration_range;
@@ -195,9 +206,11 @@ Status BlobFileBuilder::OpenBlobFileIfNeeded() {
                       expiration_range);

  {
-    TEST_SYNC_POINT("BlobFileBuilder::OpenBlobFileIfNeeded:WriteHeader");
+    Status s = blob_log_writer->WriteHeader(header);
+
+    TEST_SYNC_POINT_CALLBACK(
+        "BlobFileBuilder::OpenBlobFileIfNeeded:WriteHeader", &s);

-    const Status s = blob_log_writer->WriteHeader(header);
    if (!s.ok()) {
      return s;
    }
@@ -247,9 +260,10 @@ Status BlobFileBuilder::WriteBlobToFile(const Slice& key, const Slice& blob,

  uint64_t key_offset = 0;

-  TEST_SYNC_POINT("BlobFileBuilder::WriteBlobToFile:AddRecord");
+  Status s = writer_->AddRecord(key, blob, &key_offset, blob_offset);
+
+  TEST_SYNC_POINT_CALLBACK("BlobFileBuilder::WriteBlobToFile:AddRecord", &s);

-  const Status s = writer_->AddRecord(key, blob, &key_offset, blob_offset);
  if (!s.ok()) {
    return s;
  }
@@ -271,10 +285,10 @@ Status BlobFileBuilder::CloseBlobFile() {
  std::string checksum_method;
  std::string checksum_value;

-  TEST_SYNC_POINT("BlobFileBuilder::WriteBlobToFile:AppendFooter");
+  Status s = writer_->AppendFooter(footer, &checksum_method, &checksum_value);
+
+  TEST_SYNC_POINT_CALLBACK("BlobFileBuilder::WriteBlobToFile:AppendFooter", &s);

-  const Status s =
-      writer_->AppendFooter(footer, &checksum_method, &checksum_value);
  if (!s.ok()) {
    return s;
  }
@@ -293,11 +307,15 @@ Status BlobFileBuilder::CloseBlobFile() {
                 column_family_name_.c_str(), job_id_, blob_file_number,
                 blob_count_, blob_bytes_);

+  if (blob_callback_) {
+    s = blob_callback_->OnBlobFileCompleted(blob_file_paths_->back());
+  }
+
  writer_.reset();
  blob_count_ = 0;
  blob_bytes_ = 0;

-  return Status::OK();
+  return s;
 }

 Status BlobFileBuilder::CloseBlobFileIfNeeded() {
@@ -313,4 +331,20 @@ Status BlobFileBuilder::CloseBlobFileIfNeeded() {
  return CloseBlobFile();
 }

+void BlobFileBuilder::Abandon() {
+  if (!IsBlobFileOpen()) {
+    return;
+  }
+
+  if (blob_callback_) {
+    // BlobFileBuilder::Abandon() is called because of error while writing to
+    // Blob files. So we can ignore the below error.
+    blob_callback_->OnBlobFileCompleted(blob_file_paths_->back())
+        .PermitUncheckedError();
+  }
+
+  writer_.reset();
+  blob_count_ = 0;
+  blob_bytes_ = 0;
+}
 }  // namespace ROCKSDB_NAMESPACE
@@ -18,6 +18,7 @@ namespace ROCKSDB_NAMESPACE {

 class VersionSet;
 class FileSystem;
+class SystemClock;
 struct ImmutableCFOptions;
 struct MutableCFOptions;
 struct FileOptions;
@@ -25,10 +26,12 @@ class BlobFileAddition;
 class Status;
 class Slice;
 class BlobLogWriter;
+class IOTracer;
+class BlobFileCompletionCallback;

 class BlobFileBuilder {
 public:
-  BlobFileBuilder(VersionSet* versions, Env* env, FileSystem* fs,
+  BlobFileBuilder(VersionSet* versions, FileSystem* fs,
                  const ImmutableCFOptions* immutable_cf_options,
                  const MutableCFOptions* mutable_cf_options,
                  const FileOptions* file_options, int job_id,
@@ -36,10 +39,12 @@ class BlobFileBuilder {
                  const std::string& column_family_name,
                  Env::IOPriority io_priority,
                  Env::WriteLifeTimeHint write_hint,
+                  const std::shared_ptr<IOTracer>& io_tracer,
+                  BlobFileCompletionCallback* blob_callback,
                  std::vector<std::string>* blob_file_paths,
                  std::vector<BlobFileAddition>* blob_file_additions);

-  BlobFileBuilder(std::function<uint64_t()> file_number_generator, Env* env,
+  BlobFileBuilder(std::function<uint64_t()> file_number_generator,
                  FileSystem* fs,
                  const ImmutableCFOptions* immutable_cf_options,
                  const MutableCFOptions* mutable_cf_options,
@@ -48,6 +53,8 @@ class BlobFileBuilder {
                  const std::string& column_family_name,
                  Env::IOPriority io_priority,
                  Env::WriteLifeTimeHint write_hint,
+                  const std::shared_ptr<IOTracer>& io_tracer,
+                  BlobFileCompletionCallback* blob_callback,
                  std::vector<std::string>* blob_file_paths,
                  std::vector<BlobFileAddition>* blob_file_additions);

@@ -58,6 +65,7 @@ class BlobFileBuilder {

  Status Add(const Slice& key, const Slice& value, std::string* blob_index);
  Status Finish();
+  void Abandon();

 private:
  bool IsBlobFileOpen() const;
@@ -69,7 +77,6 @@ class BlobFileBuilder {
  Status CloseBlobFileIfNeeded();

  std::function<uint64_t()> file_number_generator_;
-  Env* env_;
  FileSystem* fs_;
  const ImmutableCFOptions* immutable_cf_options_;
  uint64_t min_blob_size_;
@@ -81,6 +88,8 @@ class BlobFileBuilder {
  std::string column_family_name_;
  Env::IOPriority io_priority_;
  Env::WriteLifeTimeHint write_hint_;
+  std::shared_ptr<IOTracer> io_tracer_;
+  BlobFileCompletionCallback* blob_callback_;
  std::vector<std::string>* blob_file_paths_;
  std::vector<BlobFileAddition>* blob_file_additions_;
  std::unique_ptr<BlobLogWriter> writer_;
@@ -40,7 +40,8 @@ class TestFileNumberGenerator {
 class BlobFileBuilderTest : public testing::Test {
 protected:
  BlobFileBuilderTest() : mock_env_(Env::Default()) {
-    fs_ = mock_env_.GetFileSystem();
+    fs_ = mock_env_.GetFileSystem().get();
+    clock_ = mock_env_.GetSystemClock().get();
  }

  void VerifyBlobFile(uint64_t blob_file_number,
@@ -58,11 +59,10 @@ class BlobFileBuilderTest : public testing::Test {
        fs_->NewRandomAccessFile(blob_file_path, file_options_, &file, dbg));

    std::unique_ptr<RandomAccessFileReader> file_reader(
-        new RandomAccessFileReader(std::move(file), blob_file_path,
-                                   &mock_env_));
+        new RandomAccessFileReader(std::move(file), blob_file_path, clock_));

    constexpr Statistics* statistics = nullptr;
-    BlobLogSequentialReader blob_log_reader(std::move(file_reader), &mock_env_,
+    BlobLogSequentialReader blob_log_reader(std::move(file_reader), clock_,
                                            statistics);

    BlobLogHeader header;
@@ -109,7 +109,8 @@ class BlobFileBuilderTest : public testing::Test {
  }

  MockEnv mock_env_;
-  std::shared_ptr<FileSystem> fs_;
+  FileSystem* fs_;
+  SystemClock* clock_;
  FileOptions file_options_;
 };

@@ -126,6 +127,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
                            "BlobFileBuilderTest_BuildAndCheckOneFile"),
      0);
  options.enable_blob_files = true;
+  options.env = &mock_env_;

  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);
@@ -139,10 +141,11 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckOneFile) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &mock_env_, fs_.get(),
-                          &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

  std::vector<std::pair<std::string, std::string>> expected_key_value_pairs(
@@ -209,6 +212,7 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
      0);
  options.enable_blob_files = true;
  options.blob_file_size = value_size;
+  options.env = &mock_env_;

  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);
@@ -222,10 +226,11 @@ TEST_F(BlobFileBuilderTest, BuildAndCheckMultipleFiles) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &mock_env_, fs_.get(),
-                          &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

  std::vector<std::pair<std::string, std::string>> expected_key_value_pairs(
@@ -294,6 +299,7 @@ TEST_F(BlobFileBuilderTest, InlinedValues) {
      0);
  options.enable_blob_files = true;
  options.min_blob_size = 1024;
+  options.env = &mock_env_;

  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);
@@ -307,10 +313,11 @@ TEST_F(BlobFileBuilderTest, InlinedValues) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &mock_env_, fs_.get(),
-                          &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

  for (size_t i = 0; i < number_of_blobs; ++i) {
@@ -346,6 +353,7 @@ TEST_F(BlobFileBuilderTest, Compression) {
      test::PerThreadDBPath(&mock_env_, "BlobFileBuilderTest_Compression"), 0);
  options.enable_blob_files = true;
  options.blob_compression_type = kSnappyCompression;
+  options.env = &mock_env_;

  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);
@@ -359,10 +367,11 @@ TEST_F(BlobFileBuilderTest, Compression) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &mock_env_, fs_.get(),
-                          &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

  const std::string key("1");
@@ -428,7 +437,7 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
      0);
  options.enable_blob_files = true;
  options.blob_compression_type = kSnappyCompression;
-
+  options.env = &mock_env_;
  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);

@@ -441,10 +450,11 @@ TEST_F(BlobFileBuilderTest, CompressionError) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &mock_env_, fs_.get(),
-                          &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

  SyncPoint::GetInstance()->SetCallBack("CompressData:TamperWithReturnValue",
@@ -505,6 +515,7 @@ TEST_F(BlobFileBuilderTest, Checksum) {
  options.enable_blob_files = true;
  options.file_checksum_gen_factory =
      std::make_shared<DummyFileChecksumGenFactory>();
+  options.env = &mock_env_;

  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);
@@ -518,10 +529,11 @@ TEST_F(BlobFileBuilderTest, Checksum) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &mock_env_, fs_.get(),
-                          &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

  const std::string key("1");
@@ -571,13 +583,11 @@ class BlobFileBuilderIOErrorTest
 protected:
  BlobFileBuilderIOErrorTest()
      : mock_env_(Env::Default()),
-        fault_injection_env_(&mock_env_),
-        fs_(fault_injection_env_.GetFileSystem()),
+        fs_(mock_env_.GetFileSystem().get()),
        sync_point_(GetParam()) {}

  MockEnv mock_env_;
-  FaultInjectionTestEnv fault_injection_env_;
-  std::shared_ptr<FileSystem> fs_;
+  FileSystem* fs_;
  FileOptions file_options_;
  std::string sync_point_;
 };
@@ -598,11 +608,11 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {

  Options options;
  options.cf_paths.emplace_back(
-      test::PerThreadDBPath(&fault_injection_env_,
-                            "BlobFileBuilderIOErrorTest_IOError"),
+      test::PerThreadDBPath(&mock_env_, "BlobFileBuilderIOErrorTest_IOError"),
      0);
  options.enable_blob_files = true;
  options.blob_file_size = value_size;
+  options.env = &mock_env_;

  ImmutableCFOptions immutable_cf_options(options);
  MutableCFOptions mutable_cf_options(options);
@@ -616,15 +626,18 @@ TEST_P(BlobFileBuilderIOErrorTest, IOError) {
  std::vector<std::string> blob_file_paths;
  std::vector<BlobFileAddition> blob_file_additions;

-  BlobFileBuilder builder(TestFileNumberGenerator(), &fault_injection_env_,
-                          fs_.get(), &immutable_cf_options, &mutable_cf_options,
-                          &file_options_, job_id, column_family_id,
-                          column_family_name, io_priority, write_hint,
+  BlobFileBuilder builder(TestFileNumberGenerator(), fs_, &immutable_cf_options,
+                          &mutable_cf_options, &file_options_, job_id,
+                          column_family_id, column_family_name, io_priority,
+                          write_hint, nullptr /*IOTracer*/,
+                          nullptr /*BlobFileCompletionCallback*/,
                          &blob_file_paths, &blob_file_additions);

-  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
-    fault_injection_env_.SetFilesystemActive(false,
-                                             Status::IOError(sync_point_));
+  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* arg) {
+    Status* const s = static_cast<Status*>(arg);
+    assert(s);
+
+    (*s) = Status::IOError(sync_point_);
  });
  SyncPoint::GetInstance()->EnableProcessing();

@@ -13,6 +13,7 @@
 #include "rocksdb/cache.h"
 #include "rocksdb/slice.h"
 #include "test_util/sync_point.h"
+#include "trace_replay/io_tracer.h"
 #include "util/hash.h"

 namespace ROCKSDB_NAMESPACE {
@@ -21,13 +22,15 @@ BlobFileCache::BlobFileCache(Cache* cache,
                             const ImmutableCFOptions* immutable_cf_options,
                             const FileOptions* file_options,
                             uint32_t column_family_id,
-                             HistogramImpl* blob_file_read_hist)
+                             HistogramImpl* blob_file_read_hist,
+                             const std::shared_ptr<IOTracer>& io_tracer)
    : cache_(cache),
-      mutex_(kNumberOfMutexStripes, GetSliceNPHash64),
+      mutex_(kNumberOfMutexStripes, kGetSliceNPHash64UnseededFnPtr),
      immutable_cf_options_(immutable_cf_options),
      file_options_(file_options),
      column_family_id_(column_family_id),
-      blob_file_read_hist_(blob_file_read_hist) {
+      blob_file_read_hist_(blob_file_read_hist),
+      io_tracer_(io_tracer) {
  assert(cache_);
  assert(immutable_cf_options_);
  assert(file_options_);
@@ -71,7 +74,7 @@ Status BlobFileCache::GetBlobFileReader(
    assert(file_options_);
    const Status s = BlobFileReader::Create(
        *immutable_cf_options_, *file_options_, column_family_id_,
-        blob_file_read_hist_, blob_file_number, &reader);
+        blob_file_read_hist_, blob_file_number, io_tracer_, &reader);
    if (!s.ok()) {
      RecordTick(statistics, NO_FILE_ERRORS);
      return s;
@@ -20,12 +20,14 @@ class HistogramImpl;
 class Status;
 class BlobFileReader;
 class Slice;
+class IOTracer;

 class BlobFileCache {
 public:
  BlobFileCache(Cache* cache, const ImmutableCFOptions* immutable_cf_options,
                const FileOptions* file_options, uint32_t column_family_id,
-                HistogramImpl* blob_file_read_hist);
+                HistogramImpl* blob_file_read_hist,
+                const std::shared_ptr<IOTracer>& io_tracer);

  BlobFileCache(const BlobFileCache&) = delete;
  BlobFileCache& operator=(const BlobFileCache&) = delete;
@@ -42,6 +44,7 @@ class BlobFileCache {
  const FileOptions* file_options_;
  uint32_t column_family_id_;
  HistogramImpl* blob_file_read_hist_;
+  std::shared_ptr<IOTracer> io_tracer_;

  static constexpr size_t kNumberOfMutexStripes = 1 << 7;
 };
@@ -42,14 +42,15 @@ void WriteBlobFile(uint32_t column_family_id,

  std::unique_ptr<WritableFileWriter> file_writer(
      new WritableFileWriter(std::move(file), blob_file_path, FileOptions(),
-                             immutable_cf_options.env));
+                             immutable_cf_options.clock));

  constexpr Statistics* statistics = nullptr;
  constexpr bool use_fsync = false;
+  constexpr bool do_flush = false;

  BlobLogWriter blob_log_writer(std::move(file_writer),
-                                immutable_cf_options.env, statistics,
-                                blob_file_number, use_fsync);
+                                immutable_cf_options.clock, statistics,
+                                blob_file_number, use_fsync, do_flush);

  constexpr bool has_ttl = false;
  constexpr ExpirationRange expiration_range;
@@ -63,7 +64,6 @@ void WriteBlobFile(uint32_t column_family_id,
  constexpr char blob[] = "blob";

  std::string compressed_blob;
-  Slice blob_to_write;

  uint64_t key_offset = 0;
  uint64_t blob_offset = 0;
@@ -113,7 +113,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader) {

  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
                                &file_options, column_family_id,
-                                blob_file_read_hist);
+                                blob_file_read_hist, nullptr /*IOTracer*/);

  // First try: reader should be opened and put in cache
  CacheHandleGuard<BlobFileReader> first;
@@ -158,7 +158,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_Race) {

  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
                                &file_options, column_family_id,
-                                blob_file_read_hist);
+                                blob_file_read_hist, nullptr /*IOTracer*/);

  CacheHandleGuard<BlobFileReader> first;
  CacheHandleGuard<BlobFileReader> second;
@@ -206,7 +206,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_IOError) {

  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
                                &file_options, column_family_id,
-                                blob_file_read_hist);
+                                blob_file_read_hist, nullptr /*IOTracer*/);

  // Note: there is no blob file with the below number
  constexpr uint64_t blob_file_number = 123;
@@ -247,7 +247,7 @@ TEST_F(BlobFileCacheTest, GetBlobFileReader_CacheFull) {

  BlobFileCache blob_file_cache(backing_cache.get(), &immutable_cf_options,
                                &file_options, column_family_id,
-                                blob_file_read_hist);
+                                blob_file_read_hist, nullptr /*IOTracer*/);

  // Insert into cache should fail since it has zero capacity and
  // strict_capacity_limit is set
@@ -0,0 +1,53 @@
+//  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/error_handler.h"
+#include "file/sst_file_manager_impl.h"
+#include "rocksdb/status.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class BlobFileCompletionCallback {
+ public:
+  BlobFileCompletionCallback(SstFileManager* sst_file_manager,
+                             InstrumentedMutex* mutex,
+                             ErrorHandler* error_handler)
+      : sst_file_manager_(sst_file_manager),
+        mutex_(mutex),
+        error_handler_(error_handler) {}
+
+  Status OnBlobFileCompleted(const std::string& file_name) {
+    Status s;
+
+#ifndef ROCKSDB_LITE
+    auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager_);
+    if (sfm) {
+      // Report new blob files to SstFileManagerImpl
+      s = sfm->OnAddFile(file_name);
+      if (sfm->IsMaxAllowedSpaceReached()) {
+        s = Status::SpaceLimit("Max allowed space was reached");
+        TEST_SYNC_POINT(
+            "BlobFileCompletionCallback::CallBack::MaxAllowedSpaceReached");
+        InstrumentedMutexLock l(mutex_);
+        error_handler_->SetBGError(s, BackgroundErrorReason::kFlush);
+      }
+    }
+#else
+    (void)file_name;
+#endif  // ROCKSDB_LITE
+    return s;
+  }
+
+ private:
+  SstFileManager* sst_file_manager_;
+  InstrumentedMutex* mutex_;
+  ErrorHandler* error_handler_;
+};
+}  // namespace ROCKSDB_NAMESPACE
@@ -24,6 +24,7 @@ Status BlobFileReader::Create(
    const ImmutableCFOptions& immutable_cf_options,
    const FileOptions& file_options, uint32_t column_family_id,
    HistogramImpl* blob_file_read_hist, uint64_t blob_file_number,
+    const std::shared_ptr<IOTracer>& io_tracer,
    std::unique_ptr<BlobFileReader>* blob_file_reader) {
  assert(blob_file_reader);
  assert(!*blob_file_reader);
@@ -34,7 +35,7 @@ Status BlobFileReader::Create(
  {
    const Status s =
        OpenFile(immutable_cf_options, file_options, blob_file_read_hist,
-                 blob_file_number, &file_size, &file_reader);
+                 blob_file_number, io_tracer, &file_size, &file_reader);
    if (!s.ok()) {
      return s;
    }
@@ -68,8 +69,8 @@ Status BlobFileReader::Create(
 Status BlobFileReader::OpenFile(
    const ImmutableCFOptions& immutable_cf_options,
    const FileOptions& file_opts, HistogramImpl* blob_file_read_hist,
-    uint64_t blob_file_number, uint64_t* file_size,
-    std::unique_ptr<RandomAccessFileReader>* file_reader) {
+    uint64_t blob_file_number, const std::shared_ptr<IOTracer>& io_tracer,
+    uint64_t* file_size, std::unique_ptr<RandomAccessFileReader>* file_reader) {
  assert(file_size);
  assert(file_reader);

@@ -117,10 +118,10 @@ Status BlobFileReader::OpenFile(
  }

  file_reader->reset(new RandomAccessFileReader(
-      std::move(file), blob_file_path, immutable_cf_options.env,
-      std::shared_ptr<IOTracer>(), immutable_cf_options.statistics,
-      BLOB_DB_BLOB_FILE_READ_MICROS, blob_file_read_hist,
-      immutable_cf_options.rate_limiter, immutable_cf_options.listeners));
+      std::move(file), blob_file_path, immutable_cf_options.clock, io_tracer,
+      immutable_cf_options.statistics, BLOB_DB_BLOB_FILE_READ_MICROS,
+      blob_file_read_hist, immutable_cf_options.rate_limiter,
+      immutable_cf_options.listeners));

  return Status::OK();
 }
@@ -269,7 +270,8 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,
                               const Slice& user_key, uint64_t offset,
                               uint64_t value_size,
                               CompressionType compression_type,
-                               PinnableSlice* value) const {
+                               PinnableSlice* value,
+                               uint64_t* bytes_read) const {
  assert(value);

  const uint64_t key_size = user_key.size();
@@ -292,6 +294,9 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,
          : 0;
  assert(offset >= adjustment);

+  const uint64_t record_offset = offset - adjustment;
+  const uint64_t record_size = value_size + adjustment;
+
  Slice record_slice;
  Buffer buf;
  AlignedBuf aligned_buf;
@@ -299,9 +304,6 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,
  {
    TEST_SYNC_POINT("BlobFileReader::GetBlob:ReadFromFile");

-    const uint64_t record_offset = offset - adjustment;
-    const uint64_t record_size = value_size + adjustment;
-
    const Status s = ReadFromFile(file_reader_.get(), record_offset,
                                  static_cast<size_t>(record_size),
                                  &record_slice, &buf, &aligned_buf);
@@ -330,6 +332,10 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,
    }
  }

+  if (bytes_read) {
+    *bytes_read = record_size;
+  }
+
  return Status::OK();
 }

@@ -29,6 +29,7 @@ class BlobFileReader {
                       uint32_t column_family_id,
                       HistogramImpl* blob_file_read_hist,
                       uint64_t blob_file_number,
+                       const std::shared_ptr<IOTracer>& io_tracer,
                       std::unique_ptr<BlobFileReader>* reader);

  BlobFileReader(const BlobFileReader&) = delete;
@@ -38,7 +39,8 @@ class BlobFileReader {

  Status GetBlob(const ReadOptions& read_options, const Slice& user_key,
                 uint64_t offset, uint64_t value_size,
-                 CompressionType compression_type, PinnableSlice* value) const;
+                 CompressionType compression_type, PinnableSlice* value,
+                 uint64_t* bytes_read) const;

 private:
  BlobFileReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
@@ -47,7 +49,9 @@ class BlobFileReader {
  static Status OpenFile(const ImmutableCFOptions& immutable_cf_options,
                         const FileOptions& file_opts,
                         HistogramImpl* blob_file_read_hist,
-                         uint64_t blob_file_number, uint64_t* file_size,
+                         uint64_t blob_file_number,
+                         const std::shared_ptr<IOTracer>& io_tracer,
+                         uint64_t* file_size,
                         std::unique_ptr<RandomAccessFileReader>* file_reader);

  static Status ReadHeader(const RandomAccessFileReader* file_reader,
@@ -50,14 +50,15 @@ void WriteBlobFile(const ImmutableCFOptions& immutable_cf_options,

  std::unique_ptr<WritableFileWriter> file_writer(
      new WritableFileWriter(std::move(file), blob_file_path, FileOptions(),
-                             immutable_cf_options.env));
+                             immutable_cf_options.clock));

  constexpr Statistics* statistics = nullptr;
  constexpr bool use_fsync = false;
+  constexpr bool do_flush = false;

  BlobLogWriter blob_log_writer(std::move(file_writer),
-                                immutable_cf_options.env, statistics,
-                                blob_file_number, use_fsync);
+                                immutable_cf_options.clock, statistics,
+                                blob_file_number, use_fsync, do_flush);

  BlobLogHeader header(column_family_id, compression_type, has_ttl,
                       expiration_range_header);
@@ -141,9 +142,9 @@ TEST_F(BlobFileReaderTest, CreateReaderAndGetBlob) {

  std::unique_ptr<BlobFileReader> reader;

-  ASSERT_OK(BlobFileReader::Create(immutable_cf_options, FileOptions(),
-                                   column_family_id, blob_file_read_hist,
-                                   blob_file_number, &reader));
+  ASSERT_OK(BlobFileReader::Create(
+      immutable_cf_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));

  // Make sure the blob can be retrieved with and without checksum verification
  ReadOptions read_options;
@@ -151,83 +152,103 @@ TEST_F(BlobFileReaderTest, CreateReaderAndGetBlob) {

  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_OK(reader->GetBlob(read_options, key, blob_offset, blob_size,
-                              kNoCompression, &value));
+                              kNoCompression, &value, &bytes_read));
    ASSERT_EQ(value, blob);
+    ASSERT_EQ(bytes_read, blob_size);
  }

  read_options.verify_checksums = true;

  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_OK(reader->GetBlob(read_options, key, blob_offset, blob_size,
-                              kNoCompression, &value));
+                              kNoCompression, &value, &bytes_read));
    ASSERT_EQ(value, blob);
+
+    constexpr uint64_t key_size = sizeof(key) - 1;
+    ASSERT_EQ(bytes_read,
+              BlobLogRecord::CalculateAdjustmentForRecordHeader(key_size) +
+                  blob_size);
  }

  // Invalid offset (too close to start of file)
  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(read_options, key, blob_offset - 1, blob_size,
-                              kNoCompression, &value)
+                              kNoCompression, &value, &bytes_read)
                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }

  // Invalid offset (too close to end of file)
  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(read_options, key, blob_offset + 1, blob_size,
-                              kNoCompression, &value)
+                              kNoCompression, &value, &bytes_read)
                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }

  // Incorrect compression type
  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

-    ASSERT_TRUE(
-        reader
-            ->GetBlob(read_options, key, blob_offset, blob_size, kZSTD, &value)
-            .IsCorruption());
+    ASSERT_TRUE(reader
+                    ->GetBlob(read_options, key, blob_offset, blob_size, kZSTD,
+                              &value, &bytes_read)
+                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }

  // Incorrect key size
  {
    constexpr char shorter_key[] = "k";
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(read_options, shorter_key,
                              blob_offset - (sizeof(key) - sizeof(shorter_key)),
-                              blob_size, kNoCompression, &value)
+                              blob_size, kNoCompression, &value, &bytes_read)
                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }

  // Incorrect key
  {
    constexpr char incorrect_key[] = "foo";
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(read_options, incorrect_key, blob_offset,
-                              blob_size, kNoCompression, &value)
+                              blob_size, kNoCompression, &value, &bytes_read)
                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }

  // Incorrect value size
  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(read_options, key, blob_offset, blob_size + 1,
-                              kNoCompression, &value)
+                              kNoCompression, &value, &bytes_read)
                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }
 }

@@ -259,14 +280,15 @@ TEST_F(BlobFileReaderTest, Malformed) {

    std::unique_ptr<WritableFileWriter> file_writer(
        new WritableFileWriter(std::move(file), blob_file_path, FileOptions(),
-                               immutable_cf_options.env));
+                               immutable_cf_options.clock));

    constexpr Statistics* statistics = nullptr;
    constexpr bool use_fsync = false;
+    constexpr bool do_flush = false;

    BlobLogWriter blob_log_writer(std::move(file_writer),
-                                  immutable_cf_options.env, statistics,
-                                  blob_file_number, use_fsync);
+                                  immutable_cf_options.clock, statistics,
+                                  blob_file_number, use_fsync, do_flush);

    BlobLogHeader header(column_family_id, kNoCompression, has_ttl,
                         expiration_range);
@@ -280,7 +302,8 @@ TEST_F(BlobFileReaderTest, Malformed) {

  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, &reader)
+                                     blob_file_number, nullptr /*IOTracer*/,
+                                     &reader)
                  .IsCorruption());
 }

@@ -313,7 +336,8 @@ TEST_F(BlobFileReaderTest, TTL) {

  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, &reader)
+                                     blob_file_number, nullptr /*IOTracer*/,
+                                     &reader)
                  .IsCorruption());
 }

@@ -351,7 +375,8 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInHeader) {

  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, &reader)
+                                     blob_file_number, nullptr /*IOTracer*/,
+                                     &reader)
                  .IsCorruption());
 }

@@ -389,7 +414,8 @@ TEST_F(BlobFileReaderTest, ExpirationRangeInFooter) {

  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
                                     column_family_id, blob_file_read_hist,
-                                     blob_file_number, &reader)
+                                     blob_file_number, nullptr /*IOTracer*/,
+                                     &reader)
                  .IsCorruption());
 }

@@ -427,7 +453,7 @@ TEST_F(BlobFileReaderTest, IncorrectColumnFamily) {
  ASSERT_TRUE(BlobFileReader::Create(immutable_cf_options, FileOptions(),
                                     incorrect_column_family_id,
                                     blob_file_read_hist, blob_file_number,
-                                     &reader)
+                                     nullptr /*IOTracer*/, &reader)
                  .IsCorruption());
 }

@@ -458,9 +484,9 @@ TEST_F(BlobFileReaderTest, BlobCRCError) {

  std::unique_ptr<BlobFileReader> reader;

-  ASSERT_OK(BlobFileReader::Create(immutable_cf_options, FileOptions(),
-                                   column_family_id, blob_file_read_hist,
-                                   blob_file_number, &reader));
+  ASSERT_OK(BlobFileReader::Create(
+      immutable_cf_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));

  SyncPoint::GetInstance()->SetCallBack(
      "BlobFileReader::VerifyBlob:CheckBlobCRC", [](void* arg) {
@@ -473,11 +499,13 @@ TEST_F(BlobFileReaderTest, BlobCRCError) {
  SyncPoint::GetInstance()->EnableProcessing();

  PinnableSlice value;
+  uint64_t bytes_read = 0;

  ASSERT_TRUE(reader
                  ->GetBlob(ReadOptions(), key, blob_offset, blob_size,
-                            kNoCompression, &value)
+                            kNoCompression, &value, &bytes_read)
                  .IsCorruption());
+  ASSERT_EQ(bytes_read, 0);

  SyncPoint::GetInstance()->DisableProcessing();
  SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -514,9 +542,9 @@ TEST_F(BlobFileReaderTest, Compression) {

  std::unique_ptr<BlobFileReader> reader;

-  ASSERT_OK(BlobFileReader::Create(immutable_cf_options, FileOptions(),
-                                   column_family_id, blob_file_read_hist,
-                                   blob_file_number, &reader));
+  ASSERT_OK(BlobFileReader::Create(
+      immutable_cf_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));

  // Make sure the blob can be retrieved with and without checksum verification
  ReadOptions read_options;
@@ -524,20 +552,28 @@ TEST_F(BlobFileReaderTest, Compression) {

  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_OK(reader->GetBlob(read_options, key, blob_offset, blob_size,
-                              kSnappyCompression, &value));
+                              kSnappyCompression, &value, &bytes_read));
    ASSERT_EQ(value, blob);
+    ASSERT_EQ(bytes_read, blob_size);
  }

  read_options.verify_checksums = true;

  {
    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_OK(reader->GetBlob(read_options, key, blob_offset, blob_size,
-                              kSnappyCompression, &value));
+                              kSnappyCompression, &value, &bytes_read));
    ASSERT_EQ(value, blob);
+
+    constexpr uint64_t key_size = sizeof(key) - 1;
+    ASSERT_EQ(bytes_read,
+              BlobLogRecord::CalculateAdjustmentForRecordHeader(key_size) +
+                  blob_size);
  }
 }

@@ -574,9 +610,9 @@ TEST_F(BlobFileReaderTest, UncompressionError) {

  std::unique_ptr<BlobFileReader> reader;

-  ASSERT_OK(BlobFileReader::Create(immutable_cf_options, FileOptions(),
-                                   column_family_id, blob_file_read_hist,
-                                   blob_file_number, &reader));
+  ASSERT_OK(BlobFileReader::Create(
+      immutable_cf_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader));

  SyncPoint::GetInstance()->SetCallBack(
      "BlobFileReader::UncompressBlobIfNeeded:TamperWithResult", [](void* arg) {
@@ -590,11 +626,13 @@ TEST_F(BlobFileReaderTest, UncompressionError) {
  SyncPoint::GetInstance()->EnableProcessing();

  PinnableSlice value;
+  uint64_t bytes_read = 0;

  ASSERT_TRUE(reader
                  ->GetBlob(ReadOptions(), key, blob_offset, blob_size,
-                            kSnappyCompression, &value)
+                            kSnappyCompression, &value, &bytes_read)
                  .IsCorruption());
+  ASSERT_EQ(bytes_read, 0);

  SyncPoint::GetInstance()->DisableProcessing();
  SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -659,9 +697,9 @@ TEST_P(BlobFileReaderIOErrorTest, IOError) {

  std::unique_ptr<BlobFileReader> reader;

-  const Status s = BlobFileReader::Create(immutable_cf_options, FileOptions(),
-                                          column_family_id, blob_file_read_hist,
-                                          blob_file_number, &reader);
+  const Status s = BlobFileReader::Create(
+      immutable_cf_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader);

  const bool fail_during_create =
      (sync_point_ != "BlobFileReader::GetBlob:ReadFromFile");
@@ -672,11 +710,13 @@ TEST_P(BlobFileReaderIOErrorTest, IOError) {
    ASSERT_OK(s);

    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(ReadOptions(), key, blob_offset, blob_size,
-                              kNoCompression, &value)
+                              kNoCompression, &value, &bytes_read)
                    .IsIOError());
+    ASSERT_EQ(bytes_read, 0);
  }

  SyncPoint::GetInstance()->DisableProcessing();
@@ -739,9 +779,9 @@ TEST_P(BlobFileReaderDecodingErrorTest, DecodingError) {

  std::unique_ptr<BlobFileReader> reader;

-  const Status s = BlobFileReader::Create(immutable_cf_options, FileOptions(),
-                                          column_family_id, blob_file_read_hist,
-                                          blob_file_number, &reader);
+  const Status s = BlobFileReader::Create(
+      immutable_cf_options, FileOptions(), column_family_id,
+      blob_file_read_hist, blob_file_number, nullptr /*IOTracer*/, &reader);

  const bool fail_during_create =
      sync_point_ != "BlobFileReader::GetBlob:TamperWithResult";
@@ -752,11 +792,13 @@ TEST_P(BlobFileReaderDecodingErrorTest, DecodingError) {
    ASSERT_OK(s);

    PinnableSlice value;
+    uint64_t bytes_read = 0;

    ASSERT_TRUE(reader
                    ->GetBlob(ReadOptions(), key, blob_offset, blob_size,
-                              kNoCompression, &value)
+                              kNoCompression, &value, &bytes_read)
                    .IsCorruption());
+    ASSERT_EQ(bytes_read, 0);
  }

  SyncPoint::GetInstance()->DisableProcessing();
@@ -13,10 +13,10 @@
 namespace ROCKSDB_NAMESPACE {

 BlobLogSequentialReader::BlobLogSequentialReader(
-    std::unique_ptr<RandomAccessFileReader>&& file_reader, Env* env,
+    std::unique_ptr<RandomAccessFileReader>&& file_reader, SystemClock* clock,
    Statistics* statistics)
    : file_(std::move(file_reader)),
-      env_(env),
+      clock_(clock),
      statistics_(statistics),
      next_byte_(0) {}

@@ -27,7 +27,7 @@ Status BlobLogSequentialReader::ReadSlice(uint64_t size, Slice* slice,
  assert(slice);
  assert(file_);

-  StopWatch read_sw(env_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
+  StopWatch read_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
  Status s = file_->Read(IOOptions(), next_byte_, static_cast<size_t>(size),
                         slice, buf, nullptr);
  next_byte_ += size;
@@ -16,6 +16,7 @@ class RandomAccessFileReader;
 class Env;
 class Statistics;
 class Status;
+class SystemClock;

 /**
 * BlobLogSequentialReader is a general purpose log stream reader
@@ -35,7 +36,7 @@ class BlobLogSequentialReader {

  // Create a reader that will return log records from "*file_reader".
  BlobLogSequentialReader(std::unique_ptr<RandomAccessFileReader>&& file_reader,
-                          Env* env, Statistics* statistics);
+                          SystemClock* clock, Statistics* statistics);

  // No copying allowed
  BlobLogSequentialReader(const BlobLogSequentialReader&) = delete;
@@ -63,7 +64,8 @@ class BlobLogSequentialReader {
  Status ReadSlice(uint64_t size, Slice* slice, char* buf);

  const std::unique_ptr<RandomAccessFileReader> file_;
-  Env* env_;
+  SystemClock* clock_;
+
  Statistics* statistics_;

  Slice buffer_;
@@ -11,7 +11,7 @@
 #include "db/blob/blob_log_format.h"
 #include "file/writable_file_writer.h"
 #include "monitoring/statistics.h"
-#include "rocksdb/env.h"
+#include "rocksdb/system_clock.h"
 #include "test_util/sync_point.h"
 #include "util/coding.h"
 #include "util/stop_watch.h"
@@ -19,14 +19,16 @@
 namespace ROCKSDB_NAMESPACE {

 BlobLogWriter::BlobLogWriter(std::unique_ptr<WritableFileWriter>&& dest,
-                             Env* env, Statistics* statistics,
-                             uint64_t log_number, bool use_fs, uint64_t boffset)
+                             SystemClock* clock, Statistics* statistics,
+                             uint64_t log_number, bool use_fs, bool do_flush,
+                             uint64_t boffset)
    : dest_(std::move(dest)),
-      env_(env),
+      clock_(clock),
      statistics_(statistics),
      log_number_(log_number),
      block_offset_(boffset),
      use_fsync_(use_fs),
+      do_flush_(do_flush),
      last_elem_type_(kEtNone) {}

 BlobLogWriter::~BlobLogWriter() = default;
@@ -34,7 +36,7 @@ BlobLogWriter::~BlobLogWriter() = default;
 Status BlobLogWriter::Sync() {
  TEST_SYNC_POINT("BlobLogWriter::Sync");

-  StopWatch sync_sw(env_, statistics_, BLOB_DB_BLOB_FILE_SYNC_MICROS);
+  StopWatch sync_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_SYNC_MICROS);
  Status s = dest_->Sync(use_fsync_);
  RecordTick(statistics_, BLOB_DB_BLOB_FILE_SYNCED);
  return s;
@@ -49,7 +51,9 @@ Status BlobLogWriter::WriteHeader(BlobLogHeader& header) {
  Status s = dest_->Append(Slice(str));
  if (s.ok()) {
    block_offset_ += str.size();
-    s = dest_->Flush();
+    if (do_flush_) {
+      s = dest_->Flush();
+    }
  }
  last_elem_type_ = kEtFileHdr;
  RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_WRITTEN,
@@ -144,7 +148,7 @@ Status BlobLogWriter::EmitPhysicalRecord(const std::string& headerbuf,
                                         const Slice& key, const Slice& val,
                                         uint64_t* key_offset,
                                         uint64_t* blob_offset) {
-  StopWatch write_sw(env_, statistics_, BLOB_DB_BLOB_FILE_WRITE_MICROS);
+  StopWatch write_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_WRITE_MICROS);
  Status s = dest_->Append(Slice(headerbuf));
  if (s.ok()) {
    s = dest_->Append(key);
@@ -152,7 +156,7 @@ Status BlobLogWriter::EmitPhysicalRecord(const std::string& headerbuf,
  if (s.ok()) {
    s = dest_->Append(val);
  }
-  if (s.ok()) {
+  if (do_flush_ && s.ok()) {
    s = dest_->Flush();
  }

@@ -9,7 +9,6 @@
 #include <string>

 #include "db/blob/blob_log_format.h"
-#include "rocksdb/env.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/statistics.h"
 #include "rocksdb/status.h"
@@ -18,7 +17,7 @@
 namespace ROCKSDB_NAMESPACE {

 class WritableFileWriter;
-
+class SystemClock;
 /**
 * BlobLogWriter is the blob log stream writer. It provides an append-only
 * abstraction for writing blob data.
@@ -32,9 +31,9 @@ class BlobLogWriter {
  // Create a writer that will append data to "*dest".
  // "*dest" must be initially empty.
  // "*dest" must remain live while this BlobLogWriter is in use.
-  BlobLogWriter(std::unique_ptr<WritableFileWriter>&& dest, Env* env,
+  BlobLogWriter(std::unique_ptr<WritableFileWriter>&& dest, SystemClock* clock,
                Statistics* statistics, uint64_t log_number, bool use_fsync,
-                uint64_t boffset = 0);
+                bool do_flush, uint64_t boffset = 0);
  // No copying allowed
  BlobLogWriter(const BlobLogWriter&) = delete;
  BlobLogWriter& operator=(const BlobLogWriter&) = delete;
@@ -69,11 +68,12 @@ class BlobLogWriter {

 private:
  std::unique_ptr<WritableFileWriter> dest_;
-  Env* env_;
+  SystemClock* clock_;
  Statistics* statistics_;
  uint64_t log_number_;
  uint64_t block_offset_;  // Current offset in block
  bool use_fsync_;
+  bool do_flush_;

 public:
  enum ElemType { kEtNone, kEtFileHdr, kEtRecord, kEtFileFooter };
@@ -210,6 +210,63 @@ TEST_F(DBBlobBasicTest, GetBlob_IndexWithInvalidFileNumber) {
                  .IsCorruption());
 }

+#ifndef ROCKSDB_LITE
+TEST_F(DBBlobBasicTest, GenerateIOTracing) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  std::string trace_file = dbname_ + "/io_trace_file";
+
+  Reopen(options);
+  {
+    // Create IO trace file
+    std::unique_ptr<TraceWriter> trace_writer;
+    ASSERT_OK(
+        NewFileTraceWriter(env_, EnvOptions(), trace_file, &trace_writer));
+    ASSERT_OK(db_->StartIOTrace(TraceOptions(), std::move(trace_writer)));
+
+    constexpr char key[] = "key";
+    constexpr char blob_value[] = "blob_value";
+
+    ASSERT_OK(Put(key, blob_value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(Get(key), blob_value);
+
+    ASSERT_OK(db_->EndIOTrace());
+    ASSERT_OK(env_->FileExists(trace_file));
+  }
+  {
+    // Parse trace file to check file operations related to blob files are
+    // recorded.
+    std::unique_ptr<TraceReader> trace_reader;
+    ASSERT_OK(
+        NewFileTraceReader(env_, EnvOptions(), trace_file, &trace_reader));
+    IOTraceReader reader(std::move(trace_reader));
+
+    IOTraceHeader header;
+    ASSERT_OK(reader.ReadHeader(&header));
+    ASSERT_EQ(kMajorVersion, static_cast<int>(header.rocksdb_major_version));
+    ASSERT_EQ(kMinorVersion, static_cast<int>(header.rocksdb_minor_version));
+
+    // Read records.
+    int blob_files_op_count = 0;
+    Status status;
+    while (true) {
+      IOTraceRecord record;
+      status = reader.ReadIOOp(&record);
+      if (!status.ok()) {
+        break;
+      }
+      if (record.file_name.find("blob") != std::string::npos) {
+        blob_files_op_count++;
+      }
+    }
+    // Assuming blob files will have Append, Close and then Read operations.
+    ASSERT_GT(blob_files_op_count, 2);
+  }
+}
+#endif  // !ROCKSDB_LITE
+
 class DBBlobBasicIOErrorTest : public DBBlobBasicTest,
                               public testing::WithParamInterface<std::string> {
 protected:
@@ -298,6 +355,59 @@ TEST_P(DBBlobBasicIOErrorTest, MultiGetBlobs_IOError) {
  ASSERT_TRUE(statuses[1].IsIOError());
 }

+namespace {
+
+class ReadBlobCompactionFilter : public CompactionFilter {
+ public:
+  ReadBlobCompactionFilter() = default;
+  const char* Name() const override {
+    return "rocksdb.compaction.filter.read.blob";
+  }
+  CompactionFilter::Decision FilterV2(
+      int /*level*/, const Slice& /*key*/, ValueType value_type,
+      const Slice& existing_value, std::string* new_value,
+      std::string* /*skip_until*/) const override {
+    if (value_type != CompactionFilter::ValueType::kValue) {
+      return CompactionFilter::Decision::kKeep;
+    }
+    assert(new_value);
+    new_value->assign(existing_value.data(), existing_value.size());
+    return CompactionFilter::Decision::kChangeValue;
+  }
+};
+
+}  // anonymous namespace
+
+TEST_P(DBBlobBasicIOErrorTest, CompactionFilterReadBlob_IOError) {
+  Options options = GetDefaultOptions();
+  options.env = fault_injection_env_.get();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  options.create_if_missing = true;
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new ReadBlobCompactionFilter);
+  options.compaction_filter = compaction_filter_guard.get();
+
+  DestroyAndReopen(options);
+  constexpr char key[] = "foo";
+  constexpr char blob_value[] = "foo_blob_value";
+  ASSERT_OK(Put(key, blob_value));
+  ASSERT_OK(Flush());
+
+  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
+    fault_injection_env_->SetFilesystemActive(false,
+                                              Status::IOError(sync_point_));
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_TRUE(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                                /*end=*/nullptr)
+                  .IsIOError());
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
 }  // namespace ROCKSDB_NAMESPACE

 int main(int argc, char** argv) {
@@ -0,0 +1,399 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/blob/blob_index.h"
+#include "db/db_test_util.h"
+#include "port/stack_trace.h"
+#include "test_util/sync_point.h"
+#include "utilities/fault_injection_env.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class DBBlobCompactionTest : public DBTestBase {
+ public:
+  explicit DBBlobCompactionTest()
+      : DBTestBase("/db_blob_compaction_test", /*env_do_fsync=*/false) {}
+
+#ifndef ROCKSDB_LITE
+  const std::vector<InternalStats::CompactionStats>& GetCompactionStats() {
+    VersionSet* const versions = dbfull()->TEST_GetVersionSet();
+    assert(versions);
+    assert(versions->GetColumnFamilySet());
+
+    ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
+    assert(cfd);
+
+    const InternalStats* const internal_stats = cfd->internal_stats();
+    assert(internal_stats);
+
+    return internal_stats->TEST_GetCompactionStats();
+  }
+#endif  // ROCKSDB_LITE
+};
+
+namespace {
+
+class FilterByKeyLength : public CompactionFilter {
+ public:
+  explicit FilterByKeyLength(size_t len) : length_threshold_(len) {}
+  const char* Name() const override {
+    return "rocksdb.compaction.filter.by.key.length";
+  }
+  CompactionFilter::Decision FilterBlobByKey(
+      int /*level*/, const Slice& key, std::string* /*new_value*/,
+      std::string* /*skip_until*/) const override {
+    if (key.size() < length_threshold_) {
+      return CompactionFilter::Decision::kRemove;
+    }
+    return CompactionFilter::Decision::kKeep;
+  }
+
+ private:
+  size_t length_threshold_;
+};
+
+class BadBlobCompactionFilter : public CompactionFilter {
+ public:
+  explicit BadBlobCompactionFilter(std::string prefix,
+                                   CompactionFilter::Decision filter_by_key,
+                                   CompactionFilter::Decision filter_v2)
+      : prefix_(std::move(prefix)),
+        filter_blob_by_key_(filter_by_key),
+        filter_v2_(filter_v2) {}
+  const char* Name() const override { return "rocksdb.compaction.filter.bad"; }
+  CompactionFilter::Decision FilterBlobByKey(
+      int /*level*/, const Slice& key, std::string* /*new_value*/,
+      std::string* /*skip_until*/) const override {
+    if (key.size() >= prefix_.size() &&
+        0 == strncmp(prefix_.data(), key.data(), prefix_.size())) {
+      return CompactionFilter::Decision::kUndetermined;
+    }
+    return filter_blob_by_key_;
+  }
+  CompactionFilter::Decision FilterV2(
+      int /*level*/, const Slice& /*key*/, ValueType /*value_type*/,
+      const Slice& /*existing_value*/, std::string* /*new_value*/,
+      std::string* /*skip_until*/) const override {
+    return filter_v2_;
+  }
+
+ private:
+  const std::string prefix_;
+  const CompactionFilter::Decision filter_blob_by_key_;
+  const CompactionFilter::Decision filter_v2_;
+};
+
+class ValueBlindWriteFilter : public CompactionFilter {
+ public:
+  explicit ValueBlindWriteFilter(std::string new_val)
+      : new_value_(std::move(new_val)) {}
+  const char* Name() const override {
+    return "rocksdb.compaction.filter.blind.write";
+  }
+  CompactionFilter::Decision FilterBlobByKey(
+      int level, const Slice& key, std::string* new_value,
+      std::string* skip_until) const override;
+
+ private:
+  const std::string new_value_;
+};
+
+CompactionFilter::Decision ValueBlindWriteFilter::FilterBlobByKey(
+    int /*level*/, const Slice& /*key*/, std::string* new_value,
+    std::string* /*skip_until*/) const {
+  assert(new_value);
+  new_value->assign(new_value_);
+  return CompactionFilter::Decision::kChangeValue;
+}
+
+class ValueMutationFilter : public CompactionFilter {
+ public:
+  explicit ValueMutationFilter(std::string padding)
+      : padding_(std::move(padding)) {}
+  const char* Name() const override {
+    return "rocksdb.compaction.filter.value.mutation";
+  }
+  CompactionFilter::Decision FilterV2(int level, const Slice& key,
+                                      ValueType value_type,
+                                      const Slice& existing_value,
+                                      std::string* new_value,
+                                      std::string* skip_until) const override;
+
+ private:
+  const std::string padding_;
+};
+
+CompactionFilter::Decision ValueMutationFilter::FilterV2(
+    int /*level*/, const Slice& /*key*/, ValueType value_type,
+    const Slice& existing_value, std::string* new_value,
+    std::string* /*skip_until*/) const {
+  assert(CompactionFilter::ValueType::kBlobIndex != value_type);
+  if (CompactionFilter::ValueType::kValue != value_type) {
+    return CompactionFilter::Decision::kKeep;
+  }
+  assert(new_value);
+  new_value->assign(existing_value.data(), existing_value.size());
+  new_value->append(padding_);
+  return CompactionFilter::Decision::kChangeValue;
+}
+
+class AlwaysKeepFilter : public CompactionFilter {
+ public:
+  explicit AlwaysKeepFilter() = default;
+  const char* Name() const override {
+    return "rocksdb.compaction.filter.always.keep";
+  }
+  CompactionFilter::Decision FilterV2(
+      int /*level*/, const Slice& /*key*/, ValueType /*value_type*/,
+      const Slice& /*existing_value*/, std::string* /*new_value*/,
+      std::string* /*skip_until*/) const override {
+    return CompactionFilter::Decision::kKeep;
+  }
+};
+}  // anonymous namespace
+
+class DBBlobBadCompactionFilterTest
+    : public DBBlobCompactionTest,
+      public testing::WithParamInterface<
+          std::tuple<std::string, CompactionFilter::Decision,
+                     CompactionFilter::Decision>> {
+ public:
+  explicit DBBlobBadCompactionFilterTest()
+      : compaction_filter_guard_(new BadBlobCompactionFilter(
+            std::get<0>(GetParam()), std::get<1>(GetParam()),
+            std::get<2>(GetParam()))) {}
+
+ protected:
+  std::unique_ptr<CompactionFilter> compaction_filter_guard_;
+};
+
+INSTANTIATE_TEST_CASE_P(
+    BadCompactionFilter, DBBlobBadCompactionFilterTest,
+    testing::Combine(
+        testing::Values("a"),
+        testing::Values(CompactionFilter::Decision::kChangeBlobIndex,
+                        CompactionFilter::Decision::kIOError),
+        testing::Values(CompactionFilter::Decision::kUndetermined,
+                        CompactionFilter::Decision::kChangeBlobIndex,
+                        CompactionFilter::Decision::kIOError)));
+
+TEST_F(DBBlobCompactionTest, FilterByKeyLength) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  options.create_if_missing = true;
+  constexpr size_t kKeyLength = 2;
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new FilterByKeyLength(kKeyLength));
+  options.compaction_filter = compaction_filter_guard.get();
+
+  constexpr char short_key[] = "a";
+  constexpr char long_key[] = "abc";
+  constexpr char blob_value[] = "value";
+
+  DestroyAndReopen(options);
+  ASSERT_OK(Put(short_key, blob_value));
+  ASSERT_OK(Put(long_key, blob_value));
+  ASSERT_OK(Flush());
+  CompactRangeOptions cro;
+  ASSERT_OK(db_->CompactRange(cro, /*begin=*/nullptr, /*end=*/nullptr));
+  std::string value;
+  ASSERT_TRUE(db_->Get(ReadOptions(), short_key, &value).IsNotFound());
+  value.clear();
+  ASSERT_OK(db_->Get(ReadOptions(), long_key, &value));
+  ASSERT_EQ("value", value);
+
+#ifndef ROCKSDB_LITE
+  const auto& compaction_stats = GetCompactionStats();
+  ASSERT_GE(compaction_stats.size(), 2);
+
+  // Filter decides between kKeep and kRemove solely based on key;
+  // this involves neither reading nor writing blobs
+  ASSERT_EQ(compaction_stats[1].bytes_read_blob, 0);
+  ASSERT_EQ(compaction_stats[1].bytes_written_blob, 0);
+#endif  // ROCKSDB_LITE
+
+  Close();
+}
+
+TEST_F(DBBlobCompactionTest, BlindWriteFilter) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  options.create_if_missing = true;
+  constexpr char new_blob_value[] = "new_blob_value";
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new ValueBlindWriteFilter(new_blob_value));
+  options.compaction_filter = compaction_filter_guard.get();
+  DestroyAndReopen(options);
+  const std::vector<std::string> keys = {"a", "b", "c"};
+  const std::vector<std::string> values = {"a_value", "b_value", "c_value"};
+  assert(keys.size() == values.size());
+  for (size_t i = 0; i < keys.size(); ++i) {
+    ASSERT_OK(Put(keys[i], values[i]));
+  }
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                              /*end=*/nullptr));
+  for (const auto& key : keys) {
+    ASSERT_EQ(new_blob_value, Get(key));
+  }
+
+#ifndef ROCKSDB_LITE
+  const auto& compaction_stats = GetCompactionStats();
+  ASSERT_GE(compaction_stats.size(), 2);
+
+  // Filter unconditionally changes value in FilterBlobByKey;
+  // this involves writing but not reading blobs
+  ASSERT_EQ(compaction_stats[1].bytes_read_blob, 0);
+  ASSERT_GT(compaction_stats[1].bytes_written_blob, 0);
+#endif  // ROCKSDB_LITE
+
+  Close();
+}
+
+TEST_P(DBBlobBadCompactionFilterTest, BadDecisionFromCompactionFilter) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  options.create_if_missing = true;
+  options.compaction_filter = compaction_filter_guard_.get();
+  DestroyAndReopen(options);
+  ASSERT_OK(Put("b", "value"));
+  ASSERT_OK(Flush());
+  ASSERT_TRUE(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                                /*end=*/nullptr)
+                  .IsNotSupported());
+  Close();
+
+  DestroyAndReopen(options);
+  std::string key(std::get<0>(GetParam()));
+  ASSERT_OK(Put(key, "value"));
+  ASSERT_OK(Flush());
+  ASSERT_TRUE(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                                /*end=*/nullptr)
+                  .IsNotSupported());
+  Close();
+}
+
+TEST_F(DBBlobCompactionTest, CompactionFilter_InlinedTTLIndex) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new ValueMutationFilter(""));
+  options.compaction_filter = compaction_filter_guard.get();
+  DestroyAndReopen(options);
+  constexpr char key[] = "key";
+  constexpr char blob[] = "blob";
+  // Fake an inlined TTL blob index.
+  std::string blob_index;
+  constexpr uint64_t expiration = 1234567890;
+  BlobIndex::EncodeInlinedTTL(&blob_index, expiration, blob);
+  WriteBatch batch;
+  ASSERT_OK(WriteBatchInternal::PutBlobIndex(&batch, 0, key, blob_index));
+  ASSERT_OK(db_->Write(WriteOptions(), &batch));
+  ASSERT_OK(Flush());
+  ASSERT_TRUE(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                                /*end=*/nullptr)
+                  .IsCorruption());
+  Close();
+}
+
+TEST_F(DBBlobCompactionTest, CompactionFilter) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  constexpr char padding[] = "_delta";
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new ValueMutationFilter(padding));
+  options.compaction_filter = compaction_filter_guard.get();
+  DestroyAndReopen(options);
+  const std::vector<std::pair<std::string, std::string>> kvs = {
+      {"a", "a_value"}, {"b", "b_value"}, {"c", "c_value"}};
+  for (const auto& kv : kvs) {
+    ASSERT_OK(Put(kv.first, kv.second));
+  }
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                              /*end=*/nullptr));
+  for (const auto& kv : kvs) {
+    ASSERT_EQ(kv.second + std::string(padding), Get(kv.first));
+  }
+
+#ifndef ROCKSDB_LITE
+  const auto& compaction_stats = GetCompactionStats();
+  ASSERT_GE(compaction_stats.size(), 2);
+
+  // Filter changes the value using the previous value in FilterV2;
+  // this involves reading and writing blobs
+  ASSERT_GT(compaction_stats[1].bytes_read_blob, 0);
+  ASSERT_GT(compaction_stats[1].bytes_written_blob, 0);
+#endif  // ROCKSDB_LITE
+
+  Close();
+}
+
+TEST_F(DBBlobCompactionTest, CorruptedBlobIndex) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new ValueMutationFilter(""));
+  options.compaction_filter = compaction_filter_guard.get();
+  DestroyAndReopen(options);
+  // Mock a corrupted blob index
+  constexpr char key[] = "key";
+  std::string blob_idx("blob_idx");
+  WriteBatch write_batch;
+  ASSERT_OK(WriteBatchInternal::PutBlobIndex(&write_batch, 0, key, blob_idx));
+  ASSERT_OK(db_->Write(WriteOptions(), &write_batch));
+  ASSERT_OK(Flush());
+  ASSERT_TRUE(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                                /*end=*/nullptr)
+                  .IsCorruption());
+  Close();
+}
+
+TEST_F(DBBlobCompactionTest, CompactionFilterReadBlobAndKeep) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  std::unique_ptr<CompactionFilter> compaction_filter_guard(
+      new AlwaysKeepFilter());
+  options.compaction_filter = compaction_filter_guard.get();
+  DestroyAndReopen(options);
+  ASSERT_OK(Put("foo", "foo_value"));
+  ASSERT_OK(Flush());
+  std::vector<uint64_t> blob_files = GetBlobFileNumbers();
+  ASSERT_EQ(1, blob_files.size());
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
+                              /*end=*/nullptr));
+  ASSERT_EQ(blob_files, GetBlobFileNumbers());
+
+#ifndef ROCKSDB_LITE
+  const auto& compaction_stats = GetCompactionStats();
+  ASSERT_GE(compaction_stats.size(), 2);
+
+  // Filter decides to keep the existing value in FilterV2;
+  // this involves reading but not writing blobs
+  ASSERT_GT(compaction_stats[1].bytes_read_blob, 0);
+  ASSERT_EQ(compaction_stats[1].bytes_written_blob, 0);
+#endif  // ROCKSDB_LITE
+
+  Close();
+}
+
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
@@ -0,0 +1,81 @@
+//  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_test_util.h"
+#include "port/stack_trace.h"
+#include "test_util/sync_point.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class DBBlobCorruptionTest : public DBTestBase {
+ protected:
+  DBBlobCorruptionTest()
+      : DBTestBase("/db_blob_corruption_test", /* env_do_fsync */ false) {}
+
+  void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
+    // Pick file to corrupt
+    std::vector<std::string> filenames;
+    ASSERT_OK(env_->GetChildren(dbname_, &filenames));
+    uint64_t number;
+    FileType type;
+    std::string fname;
+    uint64_t picked_number = kInvalidBlobFileNumber;
+    for (size_t i = 0; i < filenames.size(); i++) {
+      if (ParseFileName(filenames[i], &number, &type) && type == filetype &&
+          number > picked_number) {  // Pick latest file
+        fname = dbname_ + "/" + filenames[i];
+        picked_number = number;
+      }
+    }
+    ASSERT_TRUE(!fname.empty()) << filetype;
+    ASSERT_OK(test::CorruptFile(env_, fname, offset, bytes_to_corrupt));
+  }
+};
+
+#ifndef ROCKSDB_LITE
+TEST_F(DBBlobCorruptionTest, VerifyWholeBlobFileChecksum) {
+  Options options = GetDefaultOptions();
+  options.enable_blob_files = true;
+  options.min_blob_size = 0;
+  options.create_if_missing = true;
+  options.file_checksum_gen_factory =
+      ROCKSDB_NAMESPACE::GetFileChecksumGenCrc32cFactory();
+  Reopen(options);
+
+  ASSERT_OK(Put(Slice("key_1"), Slice("blob_value_1")));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put(Slice("key_2"), Slice("blob_value_2")));
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->VerifyFileChecksums(ReadOptions()));
+  Close();
+
+  Corrupt(kBlobFile, 0, 2);
+
+  ASSERT_OK(TryReopen(options));
+
+  int count{0};
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::VerifyFullFileChecksum:mismatch", [&](void* arg) {
+        const Status* s = static_cast<Status*>(arg);
+        ASSERT_NE(s, nullptr);
+        ++count;
+        ASSERT_NOK(*s);
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_TRUE(db_->VerifyFileChecksums(ReadOptions()).IsCorruption());
+  ASSERT_EQ(1, count);
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+#endif  // !ROCKSDB_LITE
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
@@ -23,11 +23,13 @@
 #include "db/range_del_aggregator.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
+#include "file/file_util.h"
 #include "file/filename.h"
 #include "file/read_write_util.h"
 #include "file/writable_file_writer.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
+#include "options/options_helper.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
@@ -50,8 +52,8 @@ 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 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 std::string& db_id,
    const std::string& db_session_id) {
@@ -61,10 +63,10 @@ TableBuilder* NewTableBuilder(
  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, db_id, db_session_id),
+                          compression_opts, skip_filters, column_family_name,
+                          level, creation_time, oldest_key_time,
+                          target_file_size, file_creation_time, db_id,
+                          db_session_id),
      column_family_id, file);
 }

@@ -83,15 +85,15 @@ Status BuildTable(
    std::vector<SequenceNumber> snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
    SnapshotChecker* snapshot_checker, const CompressionType compression,
-    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
-    bool paranoid_file_checks, InternalStats* internal_stats,
-    TableFileCreationReason reason, IOStatus* io_status,
-    const std::shared_ptr<IOTracer>& io_tracer, EventLogger* event_logger,
-    int job_id, const Env::IOPriority io_priority,
+    const CompressionOptions& compression_opts, bool paranoid_file_checks,
+    InternalStats* internal_stats, TableFileCreationReason reason,
+    IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
+    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 std::string& db_id,
-    const std::string& db_session_id, const std::string* full_history_ts_low) {
+    const std::string& db_session_id, const std::string* full_history_ts_low,
+    BlobFileCompletionCallback* blob_callback) {
  assert((column_family_id ==
          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
         column_family_name.empty());
@@ -124,6 +126,7 @@ Status BuildTable(
  assert(env);
  FileSystem* fs = db_options.fs.get();
  assert(fs);
+
  TableProperties tp;
  if (iter->Valid() || !range_del_agg->IsEmpty()) {
    TableBuilder* builder;
@@ -147,20 +150,20 @@ Status BuildTable(
            file_checksum, file_checksum_func_name);
        return s;
      }
+      FileTypeSet tmp_set = ioptions.checksum_handoff_file_types;
      file->SetIOPriority(io_priority);
      file->SetWriteLifeTimeHint(write_hint);
-
      file_writer.reset(new WritableFileWriter(
-          std::move(file), fname, file_options, env, io_tracer,
+          std::move(file), fname, file_options, ioptions.clock, io_tracer,
          ioptions.statistics, ioptions.listeners,
-          ioptions.file_checksum_gen_factory));
+          ioptions.file_checksum_gen_factory,
+          tmp_set.Contains(FileType::kTableFile)));

      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, level,
-          false /* skip_filters */, creation_time, oldest_key_time,
+          column_family_name, file_writer.get(), compression, compression_opts,
+          level, false /* skip_filters */, creation_time, oldest_key_time,
          0 /*target_file_size*/, file_creation_time, db_id, db_session_id);
    }

@@ -172,10 +175,10 @@ Status BuildTable(

    std::unique_ptr<BlobFileBuilder> blob_file_builder(
        (mutable_cf_options.enable_blob_files && blob_file_additions)
-            ? new BlobFileBuilder(versions, env, fs, &ioptions,
-                                  &mutable_cf_options, &file_options, job_id,
-                                  column_family_id, column_family_name,
-                                  io_priority, write_hint, &blob_file_paths,
+            ? new BlobFileBuilder(versions, fs, &ioptions, &mutable_cf_options,
+                                  &file_options, job_id, column_family_id,
+                                  column_family_name, io_priority, write_hint,
+                                  io_tracer, blob_callback, &blob_file_paths,
                                  blob_file_additions)
            : nullptr);

@@ -254,7 +257,7 @@ Status BuildTable(
    // Finish and check for file errors
    TEST_SYNC_POINT("BuildTable:BeforeSyncTable");
    if (s.ok() && !empty) {
-      StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
+      StopWatch sw(ioptions.clock, ioptions.statistics, TABLE_SYNC_MICROS);
      *io_status = file_writer->Sync(ioptions.use_fsync);
    }
    TEST_SYNC_POINT("BuildTable:BeforeCloseTableFile");
@@ -276,8 +279,9 @@ Status BuildTable(
    if (blob_file_builder) {
      if (s.ok()) {
        s = blob_file_builder->Finish();
+      } else {
+        blob_file_builder->Abandon();
      }
-
      blob_file_builder.reset();
    }

@@ -337,8 +341,10 @@ Status BuildTable(

    if (blob_file_additions) {
      for (const std::string& blob_file_path : blob_file_paths) {
-        ignored = fs->DeleteFile(blob_file_path, IOOptions(), dbg);
+        ignored = DeleteDBFile(&db_options, blob_file_path, dbname,
+                               /*force_bg=*/false, /*force_fg=*/false);
        ignored.PermitUncheckedError();
+        TEST_SYNC_POINT("BuildTable::AfterDeleteFile");
      }
    }
  }
@@ -38,6 +38,7 @@ class VersionEdit;
 class TableBuilder;
 class WritableFileWriter;
 class InternalStats;
+class BlobFileCompletionCallback;

 // @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
@@ -49,7 +50,6 @@ 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 bool skip_filters = false, const uint64_t creation_time = 0,
    const uint64_t oldest_key_time = 0, const uint64_t target_file_size = 0,
@@ -79,7 +79,6 @@ extern Status BuildTable(
    std::vector<SequenceNumber> snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
    SnapshotChecker* snapshot_checker, const CompressionType compression,
-    const uint64_t sample_for_compression,
    const CompressionOptions& compression_opts, bool paranoid_file_checks,
    InternalStats* internal_stats, TableFileCreationReason reason,
    IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
@@ -90,6 +89,7 @@ extern Status BuildTable(
    Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
    const uint64_t file_creation_time = 0, const std::string& db_id = "",
    const std::string& db_session_id = "",
-    const std::string* full_history_ts_low = nullptr);
+    const std::string* full_history_ts_low = nullptr,
+    BlobFileCompletionCallback* blob_callback = nullptr);

 }  // namespace ROCKSDB_NAMESPACE
@@ -11,7 +11,11 @@

 #include "rocksdb/c.h"

-#include <stdlib.h>
+#include <cstdlib>
+#include <map>
+#include <unordered_set>
+#include <vector>
+
 #include "port/port.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/compaction_filter.h"
@@ -24,6 +28,7 @@
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/merge_operator.h"
 #include "rocksdb/options.h"
+#include "rocksdb/perf_context.h"
 #include "rocksdb/rate_limiter.h"
 #include "rocksdb/slice_transform.h"
 #include "rocksdb/statistics.h"
@@ -39,13 +44,8 @@
 #include "rocksdb/utilities/transaction_db.h"
 #include "rocksdb/utilities/write_batch_with_index.h"
 #include "rocksdb/write_batch.h"
-#include "rocksdb/perf_context.h"
 #include "utilities/merge_operators.h"

-#include <vector>
-#include <unordered_set>
-#include <map>
-
 using ROCKSDB_NAMESPACE::BackupableDBOptions;
 using ROCKSDB_NAMESPACE::BackupEngine;
 using ROCKSDB_NAMESPACE::BackupID;
@@ -2774,6 +2774,14 @@ void rocksdb_options_set_bottommost_compression_options_zstd_max_train_bytes(
  opt->rep.bottommost_compression_opts.enabled = enabled;
 }

+void rocksdb_options_set_bottommost_compression_options_max_dict_buffer_bytes(
+    rocksdb_options_t* opt, uint64_t max_dict_buffer_bytes,
+    unsigned char enabled) {
+  opt->rep.bottommost_compression_opts.max_dict_buffer_bytes =
+      max_dict_buffer_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) {
@@ -2788,6 +2796,11 @@ void rocksdb_options_set_compression_options_zstd_max_train_bytes(
  opt->rep.compression_opts.zstd_max_train_bytes = zstd_max_train_bytes;
 }

+void rocksdb_options_set_compression_options_max_dict_buffer_bytes(
+    rocksdb_options_t* opt, uint64_t max_dict_buffer_bytes) {
+  opt->rep.compression_opts.max_dict_buffer_bytes = max_dict_buffer_bytes;
+}
+
 void rocksdb_options_set_prefix_extractor(
    rocksdb_options_t* opt, rocksdb_slicetransform_t* prefix_extractor) {
  opt->rep.prefix_extractor.reset(prefix_extractor);
@@ -2946,6 +2959,8 @@ void rocksdb_options_set_access_hint_on_compaction_start(
      opt->rep.access_hint_on_compaction_start =
          ROCKSDB_NAMESPACE::Options::WILLNEED;
      break;
+    default:
+      assert(0);
  }
 }

@@ -3936,6 +3951,25 @@ unsigned char rocksdb_readoptions_get_ignore_range_deletions(
  return opt->rep.ignore_range_deletions;
 }

+void rocksdb_readoptions_set_deadline(rocksdb_readoptions_t* opt,
+                                      uint64_t microseconds) {
+  opt->rep.deadline = std::chrono::microseconds(microseconds);
+}
+
+uint64_t rocksdb_readoptions_get_deadline(rocksdb_readoptions_t* opt) {
+  return opt->rep.deadline.count();
+}
+
+void rocksdb_readoptions_set_io_timeout(rocksdb_readoptions_t* opt,
+                                        uint64_t microseconds) {
+  opt->rep.io_timeout = std::chrono::microseconds(microseconds);
+}
+
+extern ROCKSDB_LIBRARY_API uint64_t
+rocksdb_readoptions_get_io_timeout(rocksdb_readoptions_t* opt) {
+  return opt->rep.io_timeout.count();
+}
+
 rocksdb_writeoptions_t* rocksdb_writeoptions_create() {
  return new rocksdb_writeoptions_t;
 }
@@ -4756,7 +4790,10 @@ void rocksdb_transaction_destroy(rocksdb_transaction_t* txn) {

 const rocksdb_snapshot_t* rocksdb_transaction_get_snapshot(
    rocksdb_transaction_t* txn) {
-  rocksdb_snapshot_t* result = new rocksdb_snapshot_t;
+  // This will be freed later on using free, so use malloc here to avoid a
+  // mismatch
+  rocksdb_snapshot_t* result =
+      (rocksdb_snapshot_t*)malloc(sizeof(rocksdb_snapshot_t));
  result->rep = txn->rep->GetSnapshot();
  return result;
 }
@@ -1119,9 +1119,8 @@ int main(int argc, char** argv) {
        // Essentially a fingerprint of the block-based Bloom schema
        CheckCondition(hits == 241);
      } else {
-        // Essentially a fingerprint of the full Bloom schema(s),
-        // format_version < 5, which vary for three different CACHE_LINE_SIZEs
-        CheckCondition(hits == 224 || hits == 180 || hits == 125);
+        // Essentially a fingerprint of full Bloom schema, format_version=5
+        CheckCondition(hits == 188);
      }
      CheckCondition(
          (keys_to_query - hits) ==
@@ -2281,6 +2280,12 @@ int main(int argc, char** argv) {
    rocksdb_readoptions_set_ignore_range_deletions(ro, 1);
    CheckCondition(1 == rocksdb_readoptions_get_ignore_range_deletions(ro));

+    rocksdb_readoptions_set_deadline(ro, 300);
+    CheckCondition(300 == rocksdb_readoptions_get_deadline(ro));
+
+    rocksdb_readoptions_set_io_timeout(ro, 400);
+    CheckCondition(400 == rocksdb_readoptions_get_io_timeout(ro));
+
    rocksdb_readoptions_destroy(ro);
  }

@@ -2875,7 +2880,7 @@ int main(int argc, char** argv) {

 #else

-int main() {
+int main(void) {
  fprintf(stderr, "SKIPPED\n");
  return 0;
 }
@@ -33,6 +33,7 @@
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
 #include "port/port.h"
+#include "rocksdb/convenience.h"
 #include "rocksdb/table.h"
 #include "table/merging_iterator.h"
 #include "util/autovector.h"
@@ -557,12 +558,12 @@ ColumnFamilyData::ColumnFamilyData(
  // if _dummy_versions is nullptr, then this is a dummy column family.
  if (_dummy_versions != nullptr) {
    internal_stats_.reset(
-        new InternalStats(ioptions_.num_levels, db_options.env, this));
+        new InternalStats(ioptions_.num_levels, ioptions_.clock, this));
    table_cache_.reset(new TableCache(ioptions_, file_options, _table_cache,
                                      block_cache_tracer, io_tracer));
    blob_file_cache_.reset(
        new BlobFileCache(_table_cache, ioptions(), soptions(), id_,
-                          internal_stats_->GetBlobFileReadHist()));
+                          internal_stats_->GetBlobFileReadHist(), io_tracer));

    if (ioptions_.compaction_style == kCompactionStyleLevel) {
      compaction_picker_.reset(
@@ -632,7 +633,7 @@ ColumnFamilyData::~ColumnFamilyData() {

  if (dummy_versions_ != nullptr) {
    // List must be empty
-    assert(dummy_versions_->TEST_Next() == dummy_versions_);
+    assert(dummy_versions_->Next() == dummy_versions_);
    bool deleted __attribute__((__unused__));
    deleted = dummy_versions_->Unref();
    assert(deleted);
@@ -834,7 +835,8 @@ std::pair<WriteStallCondition, ColumnFamilyData::WriteStallCause>
 ColumnFamilyData::GetWriteStallConditionAndCause(
    int num_unflushed_memtables, int num_l0_files,
    uint64_t num_compaction_needed_bytes,
-    const MutableCFOptions& mutable_cf_options) {
+    const MutableCFOptions& mutable_cf_options,
+    const ImmutableCFOptions& immutable_cf_options) {
  if (num_unflushed_memtables >= mutable_cf_options.max_write_buffer_number) {
    return {WriteStallCondition::kStopped, WriteStallCause::kMemtableLimit};
  } else if (!mutable_cf_options.disable_auto_compactions &&
@@ -848,7 +850,9 @@ ColumnFamilyData::GetWriteStallConditionAndCause(
            WriteStallCause::kPendingCompactionBytes};
  } else if (mutable_cf_options.max_write_buffer_number > 3 &&
             num_unflushed_memtables >=
-                 mutable_cf_options.max_write_buffer_number - 1) {
+                 mutable_cf_options.max_write_buffer_number - 1 &&
+             num_unflushed_memtables - 1 >=
+                 immutable_cf_options.min_write_buffer_number_to_merge) {
    return {WriteStallCondition::kDelayed, WriteStallCause::kMemtableLimit};
  } else if (!mutable_cf_options.disable_auto_compactions &&
             mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
@@ -876,7 +880,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(

    auto write_stall_condition_and_cause = GetWriteStallConditionAndCause(
        imm()->NumNotFlushed(), vstorage->l0_delay_trigger_count(),
-        vstorage->estimated_compaction_needed_bytes(), mutable_cf_options);
+        vstorage->estimated_compaction_needed_bytes(), mutable_cf_options,
+        *ioptions());
    write_stall_condition = write_stall_condition_and_cause.first;
    auto write_stall_cause = write_stall_condition_and_cause.second;

@@ -1355,19 +1360,19 @@ Status ColumnFamilyData::ValidateOptions(

 #ifndef ROCKSDB_LITE
 Status ColumnFamilyData::SetOptions(
-    const DBOptions& db_options,
+    const DBOptions& db_opts,
    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);
+  ColumnFamilyOptions cf_opts =
+      BuildColumnFamilyOptions(initial_cf_options_, mutable_cf_options_);
+  ConfigOptions config_opts;
+  config_opts.mutable_options_only = true;
+  Status s = GetColumnFamilyOptionsFromMap(config_opts, cf_opts, options_map,
+                                           &cf_opts);
  if (s.ok()) {
-    ColumnFamilyOptions cf_options =
-        BuildColumnFamilyOptions(initial_cf_options_, new_mutable_cf_options);
-    s = ValidateOptions(db_options, cf_options);
+    s = ValidateOptions(db_opts, cf_opts);
  }
  if (s.ok()) {
-    mutable_cf_options_ = new_mutable_cf_options;
+    mutable_cf_options_ = MutableCFOptions(cf_opts);
    mutable_cf_options_.RefreshDerivedOptions(ioptions_);
  }
  return s;
@@ -253,7 +253,7 @@ extern Status CheckCFPathsSupported(const DBOptions& db_options,

 extern ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                           const ColumnFamilyOptions& src);
-// Wrap user defined table proproties collector factories `from cf_options`
+// Wrap user defined table properties collector factories `from cf_options`
 // into internal ones in int_tbl_prop_collector_factories. Add a system internal
 // one too.
 extern void GetIntTblPropCollectorFactory(
@@ -441,7 +441,7 @@ class ColumnFamilyData {
  // Get SuperVersion stored in thread local storage. If it does not exist,
  // get a reference from a current SuperVersion.
  SuperVersion* GetThreadLocalSuperVersion(DBImpl* db);
-  // Try to return SuperVersion back to thread local storage. Retrun true on
+  // Try to return SuperVersion back to thread local storage. Return true on
  // success and false on failure. It fails when the thread local storage
  // contains anything other than SuperVersion::kSVInUse flag.
  bool ReturnThreadLocalSuperVersion(SuperVersion* sv);
@@ -475,9 +475,11 @@ class ColumnFamilyData {
    kPendingCompactionBytes,
  };
  static std::pair<WriteStallCondition, WriteStallCause>
-  GetWriteStallConditionAndCause(int num_unflushed_memtables, int num_l0_files,
-                                 uint64_t num_compaction_needed_bytes,
-                                 const MutableCFOptions& mutable_cf_options);
+  GetWriteStallConditionAndCause(
+      int num_unflushed_memtables, int num_l0_files,
+      uint64_t num_compaction_needed_bytes,
+      const MutableCFOptions& mutable_cf_options,
+      const ImmutableCFOptions& immutable_cf_options);

  // Recalculate some small conditions, which are changed only during
  // compaction, adding new memtable and/or
@@ -118,6 +118,78 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
  delete db;
 }

+TEST_F(CompactFilesTest, MultipleLevel) {
+  Options options;
+  options.create_if_missing = true;
+  options.level_compaction_dynamic_level_bytes = true;
+  options.num_levels = 6;
+  // 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_OK(s);
+  ASSERT_NE(db, nullptr);
+
+  // create couple files in L0, L3, L4 and L5
+  for (int i = 5; i > 2; --i) {
+    collector->ClearFlushedFiles();
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i), ""));
+    ASSERT_OK(db->Flush(FlushOptions()));
+    auto l0_files = collector->GetFlushedFiles();
+    ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files, i));
+
+    std::string prop;
+    ASSERT_TRUE(
+        db->GetProperty("rocksdb.num-files-at-level" + ToString(i), &prop));
+    ASSERT_EQ("1", prop);
+  }
+  ASSERT_OK(db->Put(WriteOptions(), ToString(0), ""));
+  ASSERT_OK(db->Flush(FlushOptions()));
+
+  ColumnFamilyMetaData meta;
+  db->GetColumnFamilyMetaData(&meta);
+  // Compact files except the file in L3
+  std::vector<std::string> files;
+  for (int i = 0; i < 6; ++i) {
+    if (i == 3) continue;
+    for (auto& file : meta.levels[i].files) {
+      files.push_back(file.db_path + "/" + file.name);
+    }
+  }
+
+  SyncPoint::GetInstance()->LoadDependency({
+      {"CompactionJob::Run():Start", "CompactFilesTest.MultipleLevel:0"},
+      {"CompactFilesTest.MultipleLevel:1", "CompactFilesImpl:3"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  std::thread thread([&] {
+    TEST_SYNC_POINT("CompactFilesTest.MultipleLevel:0");
+    ASSERT_OK(db->Put(WriteOptions(), "bar", "v2"));
+    ASSERT_OK(db->Put(WriteOptions(), "foo", "v2"));
+    ASSERT_OK(db->Flush(FlushOptions()));
+    TEST_SYNC_POINT("CompactFilesTest.MultipleLevel:1");
+  });
+
+  // Compaction cannot move up the data to higher level
+  // here we have input file from level 5, so the output level has to be >= 5
+  for (int invalid_output_level = 0; invalid_output_level < 5;
+       invalid_output_level++) {
+    s = db->CompactFiles(CompactionOptions(), files, invalid_output_level);
+    std::cout << s.ToString() << std::endl;
+    ASSERT_TRUE(s.IsInvalidArgument());
+  }
+
+  ASSERT_OK(db->CompactFiles(CompactionOptions(), files, 5));
+  SyncPoint::GetInstance()->DisableProcessing();
+  thread.join();
+
+  delete db;
+}
+
 TEST_F(CompactFilesTest, ObsoleteFiles) {
  Options options;
  // to trigger compaction more easily
@@ -519,7 +519,7 @@ uint64_t Compaction::OutputFilePreallocationSize() const {

  // Over-estimate slightly so we don't end up just barely crossing
  // the threshold
-  // No point to prellocate more than 1GB.
+  // No point to preallocate more than 1GB.
  return std::min(uint64_t{1073741824},
                  preallocation_size + (preallocation_size / 10));
 }
@@ -341,7 +341,7 @@ 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.
+  // If true, then the compaction can be done by simply deleting input files.
  const bool deletion_compaction_;

  // Compaction input files organized by level. Constant after construction
@@ -34,4 +34,8 @@ struct CompactionIterationStats {
  // Single-Delete diagnostics for exceptional situations
  uint64_t num_single_del_fallthru = 0;
  uint64_t num_single_del_mismatch = 0;
+
+  // Blob related statistics
+  uint64_t num_blobs_read = 0;
+  uint64_t total_blob_bytes_read = 0;
 };
@@ -80,6 +80,7 @@ CompactionIterator::CompactionIterator(
      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
      snapshot_checker_(snapshot_checker),
      env_(env),
+      clock_(env_->GetSystemClock().get()),
      report_detailed_time_(report_detailed_time),
      expect_valid_internal_key_(expect_valid_internal_key),
      range_del_agg_(range_del_agg),
@@ -134,7 +135,7 @@ CompactionIterator::CompactionIterator(
 }

 CompactionIterator::~CompactionIterator() {
-  // input_ Iteartor lifetime is longer than pinned_iters_mgr_ lifetime
+  // input_ Iterator lifetime is longer than pinned_iters_mgr_ lifetime
  input_->SetPinnedItersMgr(nullptr);
 }

@@ -203,72 +204,146 @@ void CompactionIterator::Next() {

 bool CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
                                              Slice* skip_until) {
-  if (compaction_filter_ != nullptr &&
-      (ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex)) {
-    // 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,
-    // replace the entry with a deletion marker.
-    CompactionFilter::Decision filter;
-    compaction_filter_value_.clear();
-    compaction_filter_skip_until_.Clear();
-    CompactionFilter::ValueType value_type =
-        ikey_.type == kTypeValue ? CompactionFilter::ValueType::kValue
-                                 : CompactionFilter::ValueType::kBlobIndex;
-    // Hack: pass internal key to BlobIndexCompactionFilter since it needs
-    // to get sequence number.
-    Slice& filter_key = ikey_.type == kTypeValue ? ikey_.user_key : key_;
-    {
-      StopWatchNano timer(env_, report_detailed_time_);
+  if (!compaction_filter_ ||
+      (ikey_.type != kTypeValue && ikey_.type != kTypeBlobIndex)) {
+    return true;
+  }
+  bool error = false;
+  // 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,
+  // replace the entry with a deletion marker.
+  CompactionFilter::Decision filter = CompactionFilter::Decision::kUndetermined;
+  compaction_filter_value_.clear();
+  compaction_filter_skip_until_.Clear();
+  CompactionFilter::ValueType value_type =
+      ikey_.type == kTypeValue ? CompactionFilter::ValueType::kValue
+                               : CompactionFilter::ValueType::kBlobIndex;
+  // Hack: pass internal key to BlobIndexCompactionFilter since it needs
+  // to get sequence number.
+  assert(compaction_filter_);
+  Slice& filter_key =
+      (ikey_.type == kTypeValue ||
+       !compaction_filter_->IsStackedBlobDbInternalCompactionFilter())
+          ? ikey_.user_key
+          : key_;
+  {
+    StopWatchNano timer(clock_, report_detailed_time_);
+    if (kTypeBlobIndex == ikey_.type) {
+      blob_value_.Reset();
+      filter = compaction_filter_->FilterBlobByKey(
+          compaction_->level(), filter_key, &compaction_filter_value_,
+          compaction_filter_skip_until_.rep());
+      if (CompactionFilter::Decision::kUndetermined == filter &&
+          !compaction_filter_->IsStackedBlobDbInternalCompactionFilter()) {
+        // For integrated BlobDB impl, CompactionIterator reads blob value.
+        // For Stacked BlobDB impl, the corresponding CompactionFilter's
+        // FilterV2 method should read the blob value.
+        BlobIndex blob_index;
+        Status s = blob_index.DecodeFrom(value_);
+        if (!s.ok()) {
+          status_ = s;
+          valid_ = false;
+          return false;
+        }
+        if (blob_index.HasTTL() || blob_index.IsInlined()) {
+          status_ = Status::Corruption("Unexpected TTL/inlined blob index");
+          valid_ = false;
+          return false;
+        }
+        const Version* const version = compaction_->input_version();
+        assert(version);
+
+        uint64_t bytes_read = 0;
+        s = version->GetBlob(ReadOptions(), ikey_.user_key, blob_index,
+                             &blob_value_, &bytes_read);
+        if (!s.ok()) {
+          status_ = s;
+          valid_ = false;
+          return false;
+        }
+
+        ++iter_stats_.num_blobs_read;
+        iter_stats_.total_blob_bytes_read += bytes_read;
+
+        value_type = CompactionFilter::ValueType::kValue;
+      }
+    }
+    if (CompactionFilter::Decision::kUndetermined == filter) {
      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;
+          compaction_->level(), filter_key, value_type,
+          blob_value_.empty() ? value_ : blob_value_, &compaction_filter_value_,
+          compaction_filter_skip_until_.rep());
    }
+    iter_stats_.total_filter_time +=
+        env_ != nullptr && report_detailed_time_ ? timer.ElapsedNanos() : 0;
+  }

-    if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
-        cmp_->Compare(*compaction_filter_skip_until_.rep(), ikey_.user_key) <=
-            0) {
-      // Can't skip to a key smaller than the current one.
-      // Keep the key as per FilterV2 documentation.
-      filter = CompactionFilter::Decision::kKeep;
+  if (CompactionFilter::Decision::kUndetermined == filter) {
+    // Should not reach here, since FilterV2 should never return kUndetermined.
+    status_ =
+        Status::NotSupported("FilterV2() should never return kUndetermined");
+    valid_ = false;
+    return false;
+  }
+
+  if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
+      cmp_->Compare(*compaction_filter_skip_until_.rep(), ikey_.user_key) <=
+          0) {
+    // Can't skip to a key smaller than the current one.
+    // Keep the key as per FilterV2 documentation.
+    filter = CompactionFilter::Decision::kKeep;
+  }
+
+  if (filter == CompactionFilter::Decision::kRemove) {
+    // convert the current key to a delete; key_ is pointing into
+    // current_key_ at this point, so updating current_key_ updates key()
+    ikey_.type = kTypeDeletion;
+    current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
+    // no value associated with delete
+    value_.clear();
+    iter_stats_.num_record_drop_user++;
+  } else if (filter == CompactionFilter::Decision::kChangeValue) {
+    if (ikey_.type == kTypeBlobIndex) {
+      // value transfer from blob file to inlined data
+      ikey_.type = kTypeValue;
+      current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
    }
-
-    if (filter == CompactionFilter::Decision::kRemove) {
-      // convert the current key to a delete; key_ is pointing into
-      // current_key_ at this point, so updating current_key_ updates key()
-      ikey_.type = kTypeDeletion;
-      current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
-      // no value associated with delete
-      value_.clear();
-      iter_stats_.num_record_drop_user++;
-    } else if (filter == CompactionFilter::Decision::kChangeValue) {
-      if (ikey_.type == kTypeBlobIndex) {
-        // value transfer from blob file to inlined data
-        ikey_.type = kTypeValue;
-        current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      }
-      value_ = compaction_filter_value_;
-    } else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
-      *need_skip = true;
-      compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
-                                                       kValueTypeForSeek);
-      *skip_until = compaction_filter_skip_until_.Encode();
-    } else if (filter == CompactionFilter::Decision::kChangeBlobIndex) {
-      if (ikey_.type == kTypeValue) {
-        // value transfer from inlined data to blob file
-        ikey_.type = kTypeBlobIndex;
-        current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      }
-      value_ = compaction_filter_value_;
-    } else if (filter == CompactionFilter::Decision::kIOError) {
-      status_ =
-          Status::IOError("Failed to access blob during compaction filter");
+    value_ = compaction_filter_value_;
+  } else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
+    *need_skip = true;
+    compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
+                                                     kValueTypeForSeek);
+    *skip_until = compaction_filter_skip_until_.Encode();
+  } else if (filter == CompactionFilter::Decision::kChangeBlobIndex) {
+    // Only the StackableDB-based BlobDB impl's compaction filter should return
+    // kChangeBlobIndex. Decision about rewriting blob and changing blob index
+    // in the integrated BlobDB impl is made in subsequent call to
+    // PrepareOutput() and its callees.
+    if (!compaction_filter_->IsStackedBlobDbInternalCompactionFilter()) {
+      status_ = Status::NotSupported(
+          "Only stacked BlobDB's internal compaction filter can return "
+          "kChangeBlobIndex.");
+      valid_ = false;
      return false;
    }
+    if (ikey_.type == kTypeValue) {
+      // value transfer from inlined data to blob file
+      ikey_.type = kTypeBlobIndex;
+      current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
+    }
+    value_ = compaction_filter_value_;
+  } else if (filter == CompactionFilter::Decision::kIOError) {
+    if (!compaction_filter_->IsStackedBlobDbInternalCompactionFilter()) {
+      status_ = Status::NotSupported(
+          "CompactionFilter for integrated BlobDB should not return kIOError");
+      valid_ = false;
+      return false;
+    }
+    status_ = Status::IOError("Failed to access blob during compaction filter");
+    error = true;
  }
-  return true;
+  return !error;
 }

 void CompactionIterator::NextFromInput() {
@@ -315,13 +390,11 @@ void CompactionIterator::NextFromInput() {
    // merge_helper_->compaction_filter_skip_until_.
    Slice skip_until;

-    int cmp_user_key_without_ts = 0;
+    bool user_key_equal_without_ts = false;
    int cmp_ts = 0;
    if (has_current_user_key_) {
-      cmp_user_key_without_ts =
-          timestamp_size_
-              ? cmp_->CompareWithoutTimestamp(ikey_.user_key, current_user_key_)
-              : cmp_->Compare(ikey_.user_key, current_user_key_);
+      user_key_equal_without_ts =
+          cmp_->EqualWithoutTimestamp(ikey_.user_key, current_user_key_);
      // if timestamp_size_ > 0, then curr_ts_ has been initialized by a
      // previous key.
      cmp_ts = timestamp_size_ ? cmp_->CompareTimestamp(
@@ -334,7 +407,7 @@ void CompactionIterator::NextFromInput() {
    // Check whether the user key changed. After this if statement current_key_
    // is a copy of the current input key (maybe converted to a delete by the
    // compaction filter). ikey_.user_key is pointing to the copy.
-    if (!has_current_user_key_ || cmp_user_key_without_ts != 0 || cmp_ts != 0) {
+    if (!has_current_user_key_ || !user_key_equal_without_ts || cmp_ts != 0) {
      // First occurrence of this user key
      // Copy key for output
      key_ = current_key_.SetInternalKey(key_, &ikey_);
@@ -355,7 +428,7 @@ void CompactionIterator::NextFromInput() {
      // consider this key for GC, e.g. it may be dropped if certain conditions
      // match.
      if (!has_current_user_key_ || !timestamp_size_ || !full_history_ts_low_ ||
-          0 != cmp_user_key_without_ts || cmp_with_history_ts_low_ >= 0) {
+          !user_key_equal_without_ts || cmp_with_history_ts_low_ >= 0) {
        // Initialize for future comparison for rule (A) and etc.
        current_user_key_sequence_ = kMaxSequenceNumber;
        current_user_key_snapshot_ = 0;
@@ -422,8 +495,8 @@ void CompactionIterator::NextFromInput() {
      // In the previous iteration we encountered a single delete that we could
      // not compact out.  We will keep this Put, but can drop it's data.
      // (See Optimization 3, below.)
-      assert(ikey_.type == kTypeValue);
-      if (ikey_.type != kTypeValue) {
+      assert(ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex);
+      if (ikey_.type != kTypeValue && ikey_.type != kTypeBlobIndex) {
        ROCKS_LOG_FATAL(info_log_,
                        "Unexpected key type %d for compaction output",
                        ikey_.type);
@@ -436,6 +509,11 @@ void CompactionIterator::NextFromInput() {
                        current_user_key_snapshot_, last_snapshot);
      }

+      if (ikey_.type == kTypeBlobIndex) {
+        ikey_.type = kTypeValue;
+        current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
+      }
+
      value_.clear();
      valid_ = true;
      clear_and_output_next_key_ = false;
@@ -644,8 +722,7 @@ void CompactionIterator::NextFromInput() {
             input_->Valid() &&
             (ParseInternalKey(input_->key(), &next_ikey, allow_data_in_errors_)
                  .ok()) &&
-             0 == cmp_->CompareWithoutTimestamp(ikey_.user_key,
-                                                next_ikey.user_key) &&
+             cmp_->EqualWithoutTimestamp(ikey_.user_key, next_ikey.user_key) &&
             (prev_snapshot == 0 ||
              DEFINITELY_NOT_IN_SNAPSHOT(next_ikey.sequence, prev_snapshot))) {
        input_->Next();
@@ -655,8 +732,7 @@ void CompactionIterator::NextFromInput() {
      if (input_->Valid() &&
          (ParseInternalKey(input_->key(), &next_ikey, allow_data_in_errors_)
               .ok()) &&
-          0 == cmp_->CompareWithoutTimestamp(ikey_.user_key,
-                                             next_ikey.user_key)) {
+          cmp_->EqualWithoutTimestamp(ikey_.user_key, next_ikey.user_key)) {
        valid_ = true;
        at_next_ = true;
      }
@@ -809,9 +885,11 @@ void CompactionIterator::GarbageCollectBlobIfNeeded() {
    const Version* const version = compaction_->input_version();
    assert(version);

+    uint64_t bytes_read = 0;
+
    {
-      const Status s =
-          version->GetBlob(ReadOptions(), user_key(), blob_index, &blob_value_);
+      const Status s = version->GetBlob(ReadOptions(), user_key(), blob_index,
+                                        &blob_value_, &bytes_read);

      if (!s.ok()) {
        status_ = s;
@@ -821,6 +899,9 @@ void CompactionIterator::GarbageCollectBlobIfNeeded() {
      }
    }

+    ++iter_stats_.num_blobs_read;
+    iter_stats_.total_blob_bytes_read += bytes_read;
+
    value_ = blob_value_;

    if (ExtractLargeValueIfNeededImpl()) {
@@ -834,7 +915,8 @@ void CompactionIterator::GarbageCollectBlobIfNeeded() {
  }

  // GC for stacked BlobDB
-  if (compaction_filter_) {
+  if (compaction_filter_ &&
+      compaction_filter_->IsStackedBlobDbInternalCompactionFilter()) {
    const auto blob_decision = compaction_filter_->PrepareBlobOutput(
        user_key(), value_, &compaction_filter_value_);

@@ -248,6 +248,7 @@ class CompactionIterator {
  const SequenceNumber earliest_write_conflict_snapshot_;
  const SnapshotChecker* const snapshot_checker_;
  Env* env_;
+  SystemClock* clock_;
  bool report_detailed_time_;
  bool expect_valid_internal_key_;
  CompactionRangeDelAggregator* range_del_agg_;
@@ -38,7 +38,7 @@ class NoMergingMergeOp : public MergeOperator {

 // Compaction filter that gets stuck when it sees a particular key,
 // then gets unstuck when told to.
-// Always returns Decition::kRemove.
+// Always returns Decision::kRemove.
 class StallingFilter : public CompactionFilter {
 public:
  Decision FilterV2(int /*level*/, const Slice& key, ValueType /*type*/,
@@ -189,7 +189,7 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {
  bool is_allow_ingest_behind = false;
 };

-// A simplifed snapshot checker which assumes each snapshot has a global
+// A simplified snapshot checker which assumes each snapshot has a global
 // last visible sequence.
 class TestSnapshotChecker : public SnapshotChecker {
 public:
@@ -711,7 +711,7 @@ TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
  RunTest({test::KeyStr("a", 1, kTypeValue), test::KeyStr("b", 2, kTypeValue)},
          {"v1", "v2"},
          {test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 2, kTypeValue)},
-          {"v1", "v2"}, kMaxSequenceNumber /*last_commited_seq*/,
+          {"v1", "v2"}, kMaxSequenceNumber /*last_committed_seq*/,
          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
          true /*bottommost_level*/);
 }
@@ -720,15 +720,14 @@ TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
 // permanently.
 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)},
-          {"", ""},
-          kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
-          nullptr /*compaction_filter*/, true /*bottommost_level*/);
+  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)},
+      {"", ""}, kMaxSequenceNumber /*last_committed_seq*/,
+      nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
+      true /*bottommost_level*/);
 }

 // In bottommost level, single deletions earlier than earliest snapshot can be
@@ -738,7 +737,7 @@ TEST_P(CompactionIteratorTest, RemoveSingleDeletionAtBottomLevel) {
  RunTest({test::KeyStr("a", 1, kTypeSingleDeletion),
           test::KeyStr("b", 2, kTypeSingleDeletion)},
          {"", ""}, {test::KeyStr("b", 2, kTypeSingleDeletion)}, {""},
-          kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
+          kMaxSequenceNumber /*last_committed_seq*/, nullptr /*merge_operator*/,
          nullptr /*compaction_filter*/, true /*bottommost_level*/);
 }

@@ -895,7 +894,7 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
          {"v1", "v2", "v3"},
          {test::KeyStr("a", 0, kTypeValue), test::KeyStr("b", 2, kTypeValue),
           test::KeyStr("c", 3, kTypeValue)},
-          {"v1", "v2", "v3"}, kMaxSequenceNumber /*last_commited_seq*/,
+          {"v1", "v2", "v3"}, kMaxSequenceNumber /*last_committed_seq*/,
          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
          true /*bottommost_level*/);
 }
@@ -906,9 +905,7 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
  RunTest(
      {test::KeyStr("a", 1, kTypeDeletion), test::KeyStr("b", 2, kTypeDeletion),
       test::KeyStr("c", 3, kTypeDeletion)},
-      {"", "", ""},
-      {},
-      {"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
+      {"", "", ""}, {}, {"", ""}, kMaxSequenceNumber /*last_committed_seq*/,
      nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
      true /*bottommost_level*/);
 }
@@ -916,15 +913,14 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
 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*/);
+  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_committed_seq*/,
+          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
+          true /*bottommost_level*/);
 }

 TEST_F(CompactionIteratorWithSnapshotCheckerTest,
@@ -936,7 +932,7 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
          {"", "", ""},
          {test::KeyStr("b", 2, kTypeSingleDeletion),
           test::KeyStr("c", 3, kTypeSingleDeletion)},
-          {"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
+          {"", ""}, kMaxSequenceNumber /*last_committed_seq*/,
          nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
          true /*bottommost_level*/);
 }
@@ -970,9 +966,24 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
          2 /*earliest_write_conflict_snapshot*/);
 }

+// Same as above but with a blob index. In addition to the value getting
+// trimmed, the type of the KV is changed to kTypeValue.
+TEST_F(CompactionIteratorWithSnapshotCheckerTest,
+       KeepSingleDeletionForWriteConflictChecking_BlobIndex) {
+  AddSnapshot(2, 0);
+  RunTest({test::KeyStr("a", 2, kTypeSingleDeletion),
+           test::KeyStr("a", 1, kTypeBlobIndex)},
+          {"", "fake_blob_index"},
+          {test::KeyStr("a", 2, kTypeSingleDeletion),
+           test::KeyStr("a", 1, kTypeValue)},
+          {"", ""}, 2 /*last_committed_seq*/, nullptr /*merge_operator*/,
+          nullptr /*compaction_filter*/, false /*bottommost_level*/,
+          2 /*earliest_write_conflict_snapshot*/);
+}
+
 // Compaction filter should keep uncommitted key as-is, and
-//   * Convert the latest velue to deletion, and/or
-//   * if latest value is a merge, apply filter to all suequent merges.
+//   * Convert the latest value to deletion, and/or
+//   * if latest value is a merge, apply filter to all subsequent merges.

 TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_Value) {
  std::unique_ptr<CompactionFilter> compaction_filter(
@@ -46,6 +46,7 @@
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/thread_status_util.h"
+#include "options/options_helper.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
@@ -149,7 +150,7 @@ struct CompactionJob::SubcompactionState {
      // This subcompaction's output could be empty if compaction was aborted
      // before this subcompaction had a chance to generate any output files.
      // When subcompactions are executed sequentially this is more likely and
-      // will be particulalry likely for the later subcompactions to be empty.
+      // will be particularly likely for the later subcompactions to be empty.
      // Once they are run in parallel however it should be much rarer.
      return nullptr;
    } else {
@@ -309,7 +310,8 @@ CompactionJob::CompactionJob(
    const std::string& dbname, CompactionJobStats* compaction_job_stats,
    Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
    const std::atomic<int>* manual_compaction_paused, const std::string& db_id,
-    const std::string& db_session_id, std::string full_history_ts_low)
+    const std::string& db_session_id, std::string full_history_ts_low,
+    BlobFileCompletionCallback* blob_callback)
    : job_id_(job_id),
      compact_(new CompactionState(compaction)),
      compaction_job_stats_(compaction_job_stats),
@@ -345,7 +347,8 @@ CompactionJob::CompactionJob(
      measure_io_stats_(measure_io_stats),
      write_hint_(Env::WLTH_NOT_SET),
      thread_pri_(thread_pri),
-      full_history_ts_low_(std::move(full_history_ts_low)) {
+      full_history_ts_low_(std::move(full_history_ts_low)),
+      blob_callback_(blob_callback) {
  assert(compaction_job_stats_ != nullptr);
  assert(log_buffer_ != nullptr);
  const auto* cfd = compact_->compaction->column_family_data();
@@ -407,7 +410,7 @@ void CompactionJob::Prepare() {
  AutoThreadOperationStageUpdater stage_updater(
      ThreadStatus::STAGE_COMPACTION_PREPARE);

-  // Generate file_levels_ for compaction berfore making Iterator
+  // Generate file_levels_ for compaction before making Iterator
  auto* c = compact_->compaction;
  assert(c->column_family_data() != nullptr);
  assert(c->column_family_data()->current()->storage_info()->NumLevelFiles(
@@ -419,7 +422,7 @@ void CompactionJob::Prepare() {

  if (c->ShouldFormSubcompactions()) {
    {
-      StopWatch sw(env_, stats_, SUBCOMPACTION_SETUP_TIME);
+      StopWatch sw(db_options_.clock, stats_, SUBCOMPACTION_SETUP_TIME);
      GenSubcompactionBoundaries();
    }
    assert(sizes_.size() == boundaries_.size() + 1);
@@ -585,7 +588,7 @@ Status CompactionJob::Run() {

  const size_t num_threads = compact_->sub_compact_states.size();
  assert(num_threads > 0);
-  const uint64_t start_micros = env_->NowMicros();
+  const uint64_t start_micros = db_options_.clock->NowMicros();

  // Launch a thread for each of subcompactions 1...num_threads-1
  std::vector<port::Thread> thread_pool;
@@ -604,7 +607,7 @@ Status CompactionJob::Run() {
    thread.join();
  }

-  compaction_stats_.micros = env_->NowMicros() - start_micros;
+  compaction_stats_.micros = db_options_.clock->NowMicros() - start_micros;
  compaction_stats_.cpu_micros = 0;
  for (size_t i = 0; i < compact_->sub_compact_states.size(); i++) {
    compaction_stats_.cpu_micros +=
@@ -792,39 +795,45 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
  double bytes_read_per_sec = 0;
  double bytes_written_per_sec = 0;

-  if (stats.bytes_read_non_output_levels > 0) {
-    read_write_amp = (stats.bytes_written + stats.bytes_read_output_level +
-                      stats.bytes_read_non_output_levels) /
-                     static_cast<double>(stats.bytes_read_non_output_levels);
-    write_amp = stats.bytes_written /
-                static_cast<double>(stats.bytes_read_non_output_levels);
+  const uint64_t bytes_read_non_output_and_blob =
+      stats.bytes_read_non_output_levels + stats.bytes_read_blob;
+  const uint64_t bytes_read_all =
+      stats.bytes_read_output_level + bytes_read_non_output_and_blob;
+  const uint64_t bytes_written_all =
+      stats.bytes_written + stats.bytes_written_blob;
+
+  if (bytes_read_non_output_and_blob > 0) {
+    read_write_amp = (bytes_written_all + bytes_read_all) /
+                     static_cast<double>(bytes_read_non_output_and_blob);
+    write_amp =
+        bytes_written_all / static_cast<double>(bytes_read_non_output_and_blob);
  }
  if (stats.micros > 0) {
-    bytes_read_per_sec =
-        (stats.bytes_read_non_output_levels + stats.bytes_read_output_level) /
-        static_cast<double>(stats.micros);
+    bytes_read_per_sec = bytes_read_all / static_cast<double>(stats.micros);
    bytes_written_per_sec =
-        stats.bytes_written / static_cast<double>(stats.micros);
+        bytes_written_all / static_cast<double>(stats.micros);
  }

  const std::string& column_family_name = cfd->GetName();

+  constexpr double kMB = 1048576.0;
+
  ROCKS_LOG_BUFFER(
      log_buffer_,
      "[%s] compacted to: %s, MB/sec: %.1f rd, %.1f wr, level %d, "
-      "files in(%d, %d) out(%d) "
-      "MB in(%.1f, %.1f) out(%.1f), read-write-amplify(%.1f) "
-      "write-amplify(%.1f) %s, records in: %" PRIu64
+      "files in(%d, %d) out(%d +%d blob) "
+      "MB in(%.1f, %.1f +%.1f blob) out(%.1f +%.1f blob), "
+      "read-write-amplify(%.1f) write-amplify(%.1f) %s, records in: %" PRIu64
      ", records dropped: %" PRIu64 " output_compression: %s\n",
      column_family_name.c_str(), vstorage->LevelSummary(&tmp),
      bytes_read_per_sec, bytes_written_per_sec,
      compact_->compaction->output_level(),
      stats.num_input_files_in_non_output_levels,
      stats.num_input_files_in_output_level, stats.num_output_files,
-      stats.bytes_read_non_output_levels / 1048576.0,
-      stats.bytes_read_output_level / 1048576.0,
-      stats.bytes_written / 1048576.0, read_write_amp, write_amp,
-      status.ToString().c_str(), stats.num_input_records,
+      stats.num_output_files_blob, stats.bytes_read_non_output_levels / kMB,
+      stats.bytes_read_output_level / kMB, stats.bytes_read_blob / kMB,
+      stats.bytes_written / kMB, stats.bytes_written_blob / kMB, read_write_amp,
+      write_amp, status.ToString().c_str(), stats.num_input_records,
      stats.num_dropped_records,
      CompressionTypeToString(compact_->compaction->output_compression())
          .c_str());
@@ -894,7 +903,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  assert(sub_compact);
  assert(sub_compact->compaction);

-  uint64_t prev_cpu_micros = env_->NowCPUNanos() / 1000;
+  uint64_t prev_cpu_micros = db_options_.clock->CPUNanos() / 1000;

  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();

@@ -971,12 +980,13 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {

  std::unique_ptr<BlobFileBuilder> blob_file_builder(
      mutable_cf_options->enable_blob_files
-          ? new BlobFileBuilder(
-                versions_, env_, fs_.get(),
-                sub_compact->compaction->immutable_cf_options(),
-                mutable_cf_options, &file_options_, job_id_, cfd->GetID(),
-                cfd->GetName(), Env::IOPriority::IO_LOW, write_hint_,
-                &blob_file_paths, &sub_compact->blob_file_additions)
+          ? new BlobFileBuilder(versions_, fs_.get(),
+                                sub_compact->compaction->immutable_cf_options(),
+                                mutable_cf_options, &file_options_, job_id_,
+                                cfd->GetID(), cfd->GetName(),
+                                Env::IOPriority::IO_LOW, write_hint_,
+                                io_tracer_, blob_callback_, &blob_file_paths,
+                                &sub_compact->blob_file_additions)
          : nullptr);

  TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
@@ -1119,6 +1129,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
    }
  }

+  sub_compact->compaction_job_stats.num_blobs_read =
+      c_iter_stats.num_blobs_read;
+  sub_compact->compaction_job_stats.total_blob_bytes_read =
+      c_iter_stats.total_blob_bytes_read;
  sub_compact->compaction_job_stats.num_input_deletion_records =
      c_iter_stats.num_input_deletion_records;
  sub_compact->compaction_job_stats.num_corrupt_keys =
@@ -1178,13 +1192,14 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  if (blob_file_builder) {
    if (status.ok()) {
      status = blob_file_builder->Finish();
+    } else {
+      blob_file_builder->Abandon();
    }
-
    blob_file_builder.reset();
  }

  sub_compact->compaction_job_stats.cpu_micros =
-      env_->NowCPUNanos() / 1000 - prev_cpu_micros;
+      db_options_.clock->CPUNanos() / 1000 - prev_cpu_micros;

  if (measure_io_stats_) {
    sub_compact->compaction_job_stats.file_write_nanos +=
@@ -1463,7 +1478,7 @@ Status CompactionJob::FinishCompactionOutputFile(

  // Finish and check for file errors
  if (s.ok()) {
-    StopWatch sw(env_, stats_, COMPACTION_OUTFILE_SYNC_MICROS);
+    StopWatch sw(db_options_.clock, stats_, COMPACTION_OUTFILE_SYNC_MICROS);
    io_s = sub_compact->outfile->Sync(db_options_.use_fsync);
  }
  if (s.ok() && io_s.ok()) {
@@ -1702,7 +1717,7 @@ Status CompactionJob::OpenCompactionOutputFile(

  // Try to figure out the output file's oldest ancester time.
  int64_t temp_current_time = 0;
-  auto get_time_status = env_->GetCurrentTime(&temp_current_time);
+  auto get_time_status = db_options_.clock->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,
@@ -1733,14 +1748,16 @@ Status CompactionJob::OpenCompactionOutputFile(

  writable_file->SetIOPriority(Env::IOPriority::IO_LOW);
  writable_file->SetWriteLifeTimeHint(write_hint_);
+  FileTypeSet tmp_set = db_options_.checksum_handoff_file_types;
  writable_file->SetPreallocationBlockSize(static_cast<size_t>(
      sub_compact->compaction->OutputFilePreallocationSize()));
  const auto& listeners =
      sub_compact->compaction->immutable_cf_options()->listeners;
  sub_compact->outfile.reset(new WritableFileWriter(
-      std::move(writable_file), fname, file_options_, env_, io_tracer_,
-      db_options_.statistics.get(), listeners,
-      db_options_.file_checksum_gen_factory.get()));
+      std::move(writable_file), fname, file_options_, db_options_.clock,
+      io_tracer_, db_options_.statistics.get(), listeners,
+      db_options_.file_checksum_gen_factory.get(),
+      tmp_set.Contains(FileType::kTableFile)));

  // If the Column family flag is to only optimize filters for hits,
  // we can skip creating filters if this is the bottommost_level where
@@ -1753,7 +1770,6 @@ 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,
      oldest_ancester_time, 0 /* oldest_key_time */,
@@ -1820,11 +1836,16 @@ void CompactionJob::UpdateCompactionStats() {
    }
  }

+  assert(compaction_job_stats_);
+  compaction_stats_.bytes_read_blob =
+      compaction_job_stats_->total_blob_bytes_read;
+
  compaction_stats_.num_output_files =
-      static_cast<int>(compact_->num_output_files) +
+      static_cast<int>(compact_->num_output_files);
+  compaction_stats_.num_output_files_blob =
      static_cast<int>(compact_->num_blob_output_files);
-  compaction_stats_.bytes_written =
-      compact_->total_bytes + compact_->total_blob_bytes;
+  compaction_stats_.bytes_written = compact_->total_bytes;
+  compaction_stats_.bytes_written_blob = compact_->total_blob_bytes;

  if (compaction_stats_.num_input_records > compact_->num_output_records) {
    compaction_stats_.num_dropped_records =
@@ -1864,8 +1885,10 @@ void CompactionJob::UpdateCompactionJobStats(

  // output information
  compaction_job_stats_->total_output_bytes = stats.bytes_written;
+  compaction_job_stats_->total_output_bytes_blob = stats.bytes_written_blob;
  compaction_job_stats_->num_output_records = compact_->num_output_records;
  compaction_job_stats_->num_output_files = stats.num_output_files;
+  compaction_job_stats_->num_output_files_blob = stats.num_output_files_blob;

  if (stats.num_output_files > 0) {
    CopyPrefix(compact_->SmallestUserKey(),
@@ -17,6 +17,7 @@
 #include <utility>
 #include <vector>

+#include "db/blob/blob_file_completion_callback.h"
 #include "db/column_family.h"
 #include "db/compaction/compaction_iterator.h"
 #include "db/dbformat.h"
@@ -50,6 +51,7 @@ class Arena;
 class ErrorHandler;
 class MemTable;
 class SnapshotChecker;
+class SystemClock;
 class TableCache;
 class Version;
 class VersionEdit;
@@ -79,7 +81,8 @@ class CompactionJob {
      Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
      const std::atomic<int>* manual_compaction_paused = nullptr,
      const std::string& db_id = "", const std::string& db_session_id = "",
-      std::string full_history_ts_low = "");
+      std::string full_history_ts_low = "",
+      BlobFileCompletionCallback* blob_callback = nullptr);

  ~CompactionJob();

@@ -203,6 +206,7 @@ class CompactionJob {
  Env::Priority thread_pri_;
  IOStatus io_status_;
  std::string full_history_ts_low_;
+  BlobFileCompletionCallback* blob_callback_;
 };

 }  // namespace ROCKSDB_NAMESPACE
@@ -5,6 +5,8 @@

 #ifndef ROCKSDB_LITE

+#include "db/compaction/compaction_job.h"
+
 #include <algorithm>
 #include <array>
 #include <cinttypes>
@@ -14,13 +16,13 @@

 #include "db/blob/blob_index.h"
 #include "db/column_family.h"
-#include "db/compaction/compaction_job.h"
 #include "db/db_impl/db_impl.h"
 #include "db/error_handler.h"
 #include "db/version_set.h"
 #include "file/writable_file_writer.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
+#include "rocksdb/file_system.h"
 #include "rocksdb/options.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/mock_table.h"
@@ -277,12 +279,13 @@ class CompactionJobTestBase : public testing::Test {
    new_db.SetLastSequence(0);

    const std::string manifest = DescriptorFileName(dbname_, 1);
-    std::unique_ptr<WritableFile> file;
-    Status s = env_->NewWritableFile(
-        manifest, &file, env_->OptimizeForManifestWrite(env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer;
+    const auto& fs = env_->GetFileSystem();
+    Status s = WritableFileWriter::Create(
+        fs, manifest, fs->OptimizeForManifestWrite(env_options_), &file_writer,
+        nullptr);
+
    ASSERT_OK(s);
-    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-        NewLegacyWritableFileWrapper(std::move(file)), manifest, env_options_));
    {
      log::Writer log(std::move(file_writer), 0, false);
      std::string record;
@@ -1004,6 +1004,7 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
  // any currently-existing files.
  for (auto file_num : *input_files) {
    bool found = false;
+    int input_file_level = -1;
    for (const auto& level_meta : cf_meta.levels) {
      for (const auto& file_meta : level_meta.files) {
        if (file_num == TableFileNameToNumber(file_meta.name)) {
@@ -1013,6 +1014,7 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
                                   " is already being compacted.");
          }
          found = true;
+          input_file_level = level_meta.level;
          break;
        }
      }
@@ -1025,6 +1027,13 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
          "Specified compaction input file " + MakeTableFileName("", file_num) +
          " does not exist in column family " + cf_meta.name + ".");
    }
+    if (input_file_level > output_level) {
+      return Status::InvalidArgument(
+          "Cannot compact file to up level, input file: " +
+          MakeTableFileName("", file_num) + " level " +
+          ToString(input_file_level) + " > output level " +
+          ToString(output_level));
+    }
  }

  return Status::OK();
@@ -45,7 +45,7 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
  uint64_t total_size = GetTotalFilesSize(level_files);

  int64_t _current_time;
-  auto status = ioptions_.env->GetCurrentTime(&_current_time);
+  auto status = ioptions_.clock->GetCurrentTime(&_current_time);
  if (!status.ok()) {
    ROCKS_LOG_BUFFER(log_buffer,
                     "[%s] FIFO compaction: Couldn't get current time: %s. "
@@ -650,7 +650,7 @@ TEST_F(CompactionPickerTest, UniversalPeriodicCompaction3) {

 TEST_F(CompactionPickerTest, UniversalPeriodicCompaction4) {
  // The case where universal periodic compaction couldn't form
-  // a compaction that inlcudes any file marked for periodic compaction.
+  // a compaction that includes any file marked for periodic compaction.
  // Right now we form the compaction anyway if it is more than one
  // sorted run. Just put the case here to validate that it doesn't
  // crash.
@@ -800,7 +800,7 @@ TEST_F(CompactionPickerTest, CompactionPriMinOverlapping2) {
  Add(2, 6U, "150", "175",
      60000000U);  // Overlaps with file 26, 27, total size 521M
  Add(2, 7U, "176", "200", 60000000U);  // Overlaps with file 27, 28, total size
-                                        // 520M, the smalelst overlapping
+                                        // 520M, the smallest overlapping
  Add(2, 8U, "201", "300",
      60000000U);  // Overlaps with file 28, 29, total size 521M

@@ -1228,7 +1228,7 @@ TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri1) {
  Add(0, 32U, "001", "400", 1000000000U, 0, 0);
  Add(0, 33U, "001", "400", 1000000000U, 0, 0);

-  // L1 total size 2GB, score 2.2. If one file being comapcted, score 1.1.
+  // L1 total size 2GB, score 2.2. If one file being compacted, score 1.1.
  Add(1, 4U, "050", "300", 1000000000U, 0, 0);
  file_map_[4u].first->being_compacted = true;
  Add(1, 5U, "301", "350", 1000000000U, 0, 0);
@@ -1261,7 +1261,7 @@ TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri2) {
  Add(0, 32U, "001", "400", 1000000000U, 0, 0);
  Add(0, 33U, "001", "400", 1000000000U, 0, 0);

-  // L1 total size 2GB, score 2.2. If one file being comapcted, score 1.1.
+  // L1 total size 2GB, score 2.2. If one file being compacted, score 1.1.
  Add(1, 4U, "050", "300", 1000000000U, 0, 0);
  Add(1, 5U, "301", "350", 1000000000U, 0, 0);

@@ -733,7 +733,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
 }

 // Look at overall size amplification. If size amplification
-// exceeeds the configured value, then do a compaction
+// exceeds the configured value, then do a compaction
 // of the candidate files all the way upto the earliest
 // base file (overrides configured values of file-size ratios,
 // min_merge_width and max_merge_width).
@@ -19,7 +19,6 @@
 #include "db/db_test_util.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "env/composite_env_wrapper.h"
 #include "file/filename.h"
 #include "port/stack_trace.h"
 #include "rocksdb/cache.h"
@@ -539,14 +538,15 @@ TEST_F(CorruptionTest, RangeDeletionCorrupted) {
  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(NewLegacyRandomAccessFileWrapper(file),
-                                 filename));
+  FileOptions file_opts;
+  const auto& fs = options_.env->GetFileSystem();
+  std::unique_ptr<RandomAccessFileReader> file_reader;
+  ASSERT_OK(RandomAccessFileReader::Create(fs, filename, file_opts,
+                                           &file_reader, nullptr));

  uint64_t file_size;
-  ASSERT_OK(options_.env->GetFileSize(filename, &file_size));
+  ASSERT_OK(
+      fs->GetFileSize(filename, file_opts.io_options, &file_size, nullptr));

  BlockHandle range_del_handle;
  ASSERT_OK(FindMetaBlock(
@@ -882,7 +882,7 @@ TEST_F(CorruptionTest, VerifyWholeTableChecksum) {
  SyncPoint::GetInstance()->ClearAllCallBacks();
  int count{0};
  SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::VerifySstFileChecksum:mismatch", [&](void* arg) {
+      "DBImpl::VerifyFullFileChecksum:mismatch", [&](void* arg) {
        auto* s = reinterpret_cast<Status*>(arg);
        ASSERT_NE(s, nullptr);
        ++count;
@@ -7,6 +7,9 @@
 // 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 <iomanip>
+#include <sstream>
+
 #include "db/db_test_util.h"
 #include "options/options_helper.h"
 #include "port/stack_trace.h"
@@ -2117,6 +2120,54 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
  }
 }

+TEST_F(DBBloomFilterTest, SeekForPrevWithPartitionedFilters) {
+  Options options = CurrentOptions();
+  constexpr size_t kNumKeys = 10000;
+  static_assert(kNumKeys <= 10000, "kNumKeys have to be <= 10000");
+  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeys + 10));
+  options.create_if_missing = true;
+  constexpr size_t kPrefixLength = 4;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(kPrefixLength));
+  options.compression = kNoCompression;
+  BlockBasedTableOptions bbto;
+  bbto.filter_policy.reset(NewBloomFilterPolicy(50));
+  bbto.index_shortening =
+      BlockBasedTableOptions::IndexShorteningMode::kNoShortening;
+  bbto.block_size = 128;
+  bbto.metadata_block_size = 128;
+  bbto.partition_filters = true;
+  bbto.index_type = BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  DestroyAndReopen(options);
+
+  const std::string value(64, '\0');
+
+  WriteOptions write_opts;
+  write_opts.disableWAL = true;
+  for (size_t i = 0; i < kNumKeys; ++i) {
+    std::ostringstream oss;
+    oss << std::setfill('0') << std::setw(4) << std::fixed << i;
+    ASSERT_OK(db_->Put(write_opts, oss.str(), value));
+  }
+  ASSERT_OK(Flush());
+
+  ReadOptions read_opts;
+  // Use legacy, implicit prefix seek
+  read_opts.total_order_seek = false;
+  read_opts.auto_prefix_mode = false;
+  std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
+  for (size_t i = 0; i < kNumKeys; ++i) {
+    // Seek with a key after each one added but with same prefix. One will
+    // surely cross a partition boundary.
+    std::ostringstream oss;
+    oss << std::setfill('0') << std::setw(4) << std::fixed << i << "a";
+    it->SeekForPrev(oss.str());
+    ASSERT_OK(it->status());
+    ASSERT_TRUE(it->Valid());
+  }
+  it.reset();
+}
+
 #endif  // ROCKSDB_LITE

 }  // namespace ROCKSDB_NAMESPACE
@@ -11,6 +11,7 @@

 #include "db/blob/blob_index.h"
 #include "db/db_test_util.h"
+#include "env/mock_env.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
 #include "rocksdb/concurrent_task_limiter.h"
@@ -21,6 +22,7 @@
 #include "util/concurrent_task_limiter_impl.h"
 #include "util/random.h"
 #include "utilities/fault_injection_env.h"
+#include "utilities/fault_injection_fs.h"

 namespace ROCKSDB_NAMESPACE {

@@ -31,31 +33,6 @@ class DBCompactionTest : public DBTestBase {
 public:
  DBCompactionTest()
      : DBTestBase("/db_compaction_test", /*env_do_fsync=*/true) {}
-
-  std::vector<uint64_t> GetBlobFileNumbers() {
-    VersionSet* const versions = dbfull()->TEST_GetVersionSet();
-    assert(versions);
-
-    ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
-    assert(cfd);
-
-    Version* const current = cfd->current();
-    assert(current);
-
-    const VersionStorageInfo* const storage_info = current->storage_info();
-    assert(storage_info);
-
-    const auto& blob_files = storage_info->GetBlobFiles();
-
-    std::vector<uint64_t> result;
-    result.reserve(blob_files.size());
-
-    for (const auto& blob_file : blob_files) {
-      result.emplace_back(blob_file.first);
-    }
-
-    return result;
-  }
 };

 class DBCompactionTestWithParam
@@ -204,6 +181,7 @@ Options DeletionTriggerOptions(Options options) {
      options.target_file_size_base * options.target_file_size_multiplier;
  options.max_bytes_for_level_multiplier = 2;
  options.disable_auto_compactions = false;
+  options.compaction_options_universal.max_size_amplification_percent = 100;
  return options;
 }

@@ -358,12 +336,34 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
    for (int k = 0; k < kTestSize; ++k) {
      ASSERT_OK(Delete(Key(k)));
    }
-    ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+    ASSERT_OK(Flush());
    ASSERT_OK(dbfull()->TEST_WaitForCompact());
    ASSERT_OK(Size(Key(0), Key(kTestSize - 1), &db_size[1]));

-    // must have much smaller db size.
-    ASSERT_GT(db_size[0] / 3, db_size[1]);
+    if (options.compaction_style == kCompactionStyleUniversal) {
+      // Claim: in universal compaction none of the original data will remain
+      // once compactions settle.
+      //
+      // Proof: The compensated size of the file containing the most tombstones
+      // is enough on its own to trigger size amp compaction. Size amp
+      // compaction is a full compaction, so all tombstones meet the obsolete
+      // keys they cover.
+      ASSERT_EQ(0, db_size[1]);
+    } else {
+      // Claim: in level compaction at most `db_size[0] / 2` of the original
+      // data will remain once compactions settle.
+      //
+      // Proof: Assume the original data is all in the bottom level. If it were
+      // not, it would meet its tombstone sooner. The original data size is
+      // large enough to require fanout to bottom level to be greater than
+      // `max_bytes_for_level_multiplier == 2`. In the level just above,
+      // tombstones must cover less than `db_size[0] / 4` bytes since fanout >=
+      // 2 and file size is compensated by doubling the size of values we expect
+      // are covered (`kDeletionWeightOnCompaction == 2`). The tombstones in
+      // levels above must cover less than `db_size[0] / 8` bytes of original
+      // data, `db_size[0] / 16`, and so on.
+      ASSERT_GT(db_size[0] / 2, db_size[1]);
+    }
  }
 }
 #endif  // ROCKSDB_VALGRIND_RUN
@@ -630,9 +630,8 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTriggerReopen) {
    }
    ASSERT_OK(Size(Key(0), Key(kTestSize - 1), &db_size[1]));
    Close();
-    // as auto_compaction is off, we shouldn't see too much reduce
-    // in db size.
-    ASSERT_LT(db_size[0] / 3, db_size[1]);
+    // as auto_compaction is off, we shouldn't see any reduction in db size.
+    ASSERT_LE(db_size[0], db_size[1]);

    // round 3 --- reopen db with auto_compaction on and see if
    // deletion compensation still work.
@@ -646,7 +645,13 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTriggerReopen) {
    ASSERT_OK(dbfull()->TEST_WaitForCompact());
    ASSERT_OK(Size(Key(0), Key(kTestSize - 1), &db_size[2]));
    // this time we're expecting significant drop in size.
-    ASSERT_GT(db_size[0] / 3, db_size[2]);
+    //
+    // See "CompactionDeletionTrigger" test for proof that at most
+    // `db_size[0] / 2` of the original data remains. In addition to that, this
+    // test inserts `db_size[0] / 10` to push the tombstones into SST files and
+    // then through automatic compactions. So in total `3 * db_size[0] / 5` of
+    // the original data may remain.
+    ASSERT_GT(3 * db_size[0] / 5, db_size[2]);
  }
 }

@@ -733,8 +738,15 @@ TEST_F(DBCompactionTest, DisableStatsUpdateReopen) {
      values.push_back(rnd.RandomString(kCDTValueSize));
      ASSERT_OK(Put(Key(k), values[k]));
    }
-    ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+    ASSERT_OK(Flush());
    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    // L1 and L2 can fit deletions iff size compensation does not take effect,
+    // i.e., when `skip_stats_update_on_db_open == true`. Move any remaining
+    // files at or above L2 down to L3 to ensure obsolete data does not
+    // accidentally meet its tombstone above L3. This makes the final size more
+    // deterministic and easy to see whether size compensation for deletions
+    // took effect.
+    MoveFilesToLevel(3 /* level */);
    ASSERT_OK(Size(Key(0), Key(kTestSize - 1), &db_size[0]));
    Close();

@@ -750,9 +762,8 @@ TEST_F(DBCompactionTest, DisableStatsUpdateReopen) {
    }
    ASSERT_OK(Size(Key(0), Key(kTestSize - 1), &db_size[1]));
    Close();
-    // as auto_compaction is off, we shouldn't see too much reduce
-    // in db size.
-    ASSERT_LT(db_size[0] / 3, db_size[1]);
+    // as auto_compaction is off, we shouldn't see any reduction in db size.
+    ASSERT_LE(db_size[0], db_size[1]);

    // round 3 --- reopen db with auto_compaction on and see if
    // deletion compensation still work.
@@ -765,10 +776,17 @@ TEST_F(DBCompactionTest, DisableStatsUpdateReopen) {
    if (options.skip_stats_update_on_db_open) {
      // If update stats on DB::Open is disable, we don't expect
      // deletion entries taking effect.
-      ASSERT_LT(db_size[0] / 3, db_size[2]);
+      //
+      // The deletions are small enough to fit in L1 and L2, and obsolete keys
+      // were moved to L3+, so none of the original data should have been
+      // dropped.
+      ASSERT_LE(db_size[0], db_size[2]);
    } else {
      // Otherwise, we should see a significant drop in db size.
-      ASSERT_GT(db_size[0] / 3, db_size[2]);
+      //
+      // See "CompactionDeletionTrigger" test for proof that at most
+      // `db_size[0] / 2` of the original data remains.
+      ASSERT_GT(db_size[0] / 2, db_size[2]);
    }
  }
 }
@@ -5944,24 +5962,22 @@ TEST_F(DBCompactionTest, CompactionWithBlob) {
  const InternalStats* const internal_stats = cfd->internal_stats();
  ASSERT_NE(internal_stats, nullptr);

-  const uint64_t expected_bytes =
-      table_file->fd.GetFileSize() + blob_file->GetTotalBlobBytes();
-
  const auto& compaction_stats = internal_stats->TEST_GetCompactionStats();
  ASSERT_GE(compaction_stats.size(), 2);
-  ASSERT_EQ(compaction_stats[1].bytes_written, expected_bytes);
-  ASSERT_EQ(compaction_stats[1].num_output_files, 2);
+  ASSERT_EQ(compaction_stats[1].bytes_read_blob, 0);
+  ASSERT_EQ(compaction_stats[1].bytes_written, table_file->fd.GetFileSize());
+  ASSERT_EQ(compaction_stats[1].bytes_written_blob,
+            blob_file->GetTotalBlobBytes());
+  ASSERT_EQ(compaction_stats[1].num_output_files, 1);
+  ASSERT_EQ(compaction_stats[1].num_output_files_blob, 1);
 }

 class DBCompactionTestBlobError
    : public DBCompactionTest,
      public testing::WithParamInterface<std::string> {
 public:
-  DBCompactionTestBlobError()
-      : fault_injection_env_(env_), sync_point_(GetParam()) {}
-  ~DBCompactionTestBlobError() { Close(); }
+  DBCompactionTestBlobError() : sync_point_(GetParam()) {}

-  FaultInjectionTestEnv fault_injection_env_;
  std::string sync_point_;
 };

@@ -5996,13 +6012,14 @@ TEST_P(DBCompactionTestBlobError, CompactionError) {
  ASSERT_OK(Flush());

  options.enable_blob_files = true;
-  options.env = &fault_injection_env_;

  Reopen(options);

-  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
-    fault_injection_env_.SetFilesystemActive(false,
-                                             Status::IOError(sync_point_));
+  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* arg) {
+    Status* const s = static_cast<Status*>(arg);
+    assert(s);
+
+    (*s) = Status::IOError(sync_point_);
  });
  SyncPoint::GetInstance()->EnableProcessing();

@@ -6039,12 +6056,18 @@ TEST_P(DBCompactionTestBlobError, CompactionError) {
  ASSERT_GE(compaction_stats.size(), 2);

  if (sync_point_ == "BlobFileBuilder::WriteBlobToFile:AddRecord") {
+    ASSERT_EQ(compaction_stats[1].bytes_read_blob, 0);
    ASSERT_EQ(compaction_stats[1].bytes_written, 0);
+    ASSERT_EQ(compaction_stats[1].bytes_written_blob, 0);
    ASSERT_EQ(compaction_stats[1].num_output_files, 0);
+    ASSERT_EQ(compaction_stats[1].num_output_files_blob, 0);
  } else {
    // SST file writing succeeded; blob file writing failed (during Finish)
+    ASSERT_EQ(compaction_stats[1].bytes_read_blob, 0);
    ASSERT_GT(compaction_stats[1].bytes_written, 0);
+    ASSERT_EQ(compaction_stats[1].bytes_written_blob, 0);
    ASSERT_EQ(compaction_stats[1].num_output_files, 1);
+    ASSERT_EQ(compaction_stats[1].num_output_files_blob, 0);
  }
 }

@@ -6129,6 +6152,36 @@ TEST_P(DBCompactionTestBlobGC, CompactionWithBlobGC) {
  for (size_t i = cutoff_index; i < original_blob_files.size(); ++i) {
    ASSERT_EQ(new_blob_files[i - cutoff_index], original_blob_files[i]);
  }
+
+  VersionSet* const versions = dbfull()->TEST_GetVersionSet();
+  assert(versions);
+  assert(versions->GetColumnFamilySet());
+
+  ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
+  assert(cfd);
+
+  const InternalStats* const internal_stats = cfd->internal_stats();
+  assert(internal_stats);
+
+  const auto& compaction_stats = internal_stats->TEST_GetCompactionStats();
+  ASSERT_GE(compaction_stats.size(), 2);
+
+  if (blob_gc_age_cutoff_ > 0.0) {
+    ASSERT_GT(compaction_stats[1].bytes_read_blob, 0);
+
+    if (updated_enable_blob_files_) {
+      // GC relocated some blobs to new blob files
+      ASSERT_GT(compaction_stats[1].bytes_written_blob, 0);
+      ASSERT_EQ(compaction_stats[1].bytes_read_blob,
+                compaction_stats[1].bytes_written_blob);
+    } else {
+      // GC moved some blobs back to the LSM, no new blob files
+      ASSERT_EQ(compaction_stats[1].bytes_written_blob, 0);
+    }
+  } else {
+    ASSERT_EQ(compaction_stats[1].bytes_read_blob, 0);
+    ASSERT_EQ(compaction_stats[1].bytes_written_blob, 0);
+  }
 }

 TEST_F(DBCompactionTest, CompactionWithBlobGCError_CorruptIndex) {
@@ -6275,6 +6328,297 @@ TEST_F(DBCompactionTest, CompactionWithBlobGCError_IndexWithInvalidFileNumber) {
      db_->CompactRange(CompactRangeOptions(), begin, end).IsCorruption());
 }

+TEST_F(DBCompactionTest, CompactionWithChecksumHandoff1) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.level0_file_num_compaction_trigger = 2;
+  options.num_levels = 3;
+  options.env = fault_fs_env.get();
+  options.create_if_missing = true;
+  options.checksum_handoff_file_types.Add(FileType::kTableFile);
+  Status s;
+  Reopen(options);
+
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+  Destroy(options);
+  Reopen(options);
+
+  // The hash does not match, compaction write fails
+  // fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+  // Since the file system returns IOStatus::Corruption, it is an
+  // unrecoverable error.
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
+        "BackgroundCallCompaction:0"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0", [&](void*) {
+        fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s.severity(),
+            ROCKSDB_NAMESPACE::Status::Severity::kUnrecoverableError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  Destroy(options);
+  Reopen(options);
+
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+
+  // Each write will be similated as corrupted.
+  // Since the file system returns IOStatus::Corruption, it is an
+  // unrecoverable error.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
+        "BackgroundCallCompaction:0"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0",
+      [&](void*) { fault_fs->IngestDataCorruptionBeforeWrite(); });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s.severity(),
+            ROCKSDB_NAMESPACE::Status::Severity::kUnrecoverableError);
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  Destroy(options);
+}
+
+TEST_F(DBCompactionTest, CompactionWithChecksumHandoff2) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.level0_file_num_compaction_trigger = 2;
+  options.num_levels = 3;
+  options.env = fault_fs_env.get();
+  options.create_if_missing = true;
+  Status s;
+  Reopen(options);
+
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+  Destroy(options);
+  Reopen(options);
+
+  // options is not set, the checksum handoff will not be triggered
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
+        "BackgroundCallCompaction:0"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0", [&](void*) {
+        fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+  SyncPoint::GetInstance()->DisableProcessing();
+  Destroy(options);
+  Reopen(options);
+
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+
+  // options is not set, the checksum handoff will not be triggered
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
+        "BackgroundCallCompaction:0"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0",
+      [&](void*) { fault_fs->IngestDataCorruptionBeforeWrite(); });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+
+  Destroy(options);
+}
+
+TEST_F(DBCompactionTest, CompactionWithChecksumHandoffManifest1) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.level0_file_num_compaction_trigger = 2;
+  options.num_levels = 3;
+  options.env = fault_fs_env.get();
+  options.create_if_missing = true;
+  options.checksum_handoff_file_types.Add(FileType::kDescriptorFile);
+  Status s;
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  Reopen(options);
+
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+  Destroy(options);
+  Reopen(options);
+
+  // The hash does not match, compaction write fails
+  // fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+  // Since the file system returns IOStatus::Corruption, it is mapped to
+  // kFatalError error.
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
+        "BackgroundCallCompaction:0"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0", [&](void*) {
+        fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kFatalError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  Destroy(options);
+}
+
+TEST_F(DBCompactionTest, CompactionWithChecksumHandoffManifest2) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.level0_file_num_compaction_trigger = 2;
+  options.num_levels = 3;
+  options.env = fault_fs_env.get();
+  options.create_if_missing = true;
+  options.checksum_handoff_file_types.Add(FileType::kDescriptorFile);
+  Status s;
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+  Reopen(options);
+
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s, Status::OK());
+
+  // Each write will be similated as corrupted.
+  // Since the file system returns IOStatus::Corruption, it is mapped to
+  // kFatalError error.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put(Key(0), "value1"));
+  ASSERT_OK(Put(Key(2), "value2"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
+        "BackgroundCallCompaction:0"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0",
+      [&](void*) { fault_fs->IngestDataCorruptionBeforeWrite(); });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "value3"));
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kFatalError);
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  Destroy(options);
+}
+
 #endif  // !defined(ROCKSDB_LITE)

 }  // namespace ROCKSDB_NAMESPACE
@@ -13,6 +13,7 @@
 #if !defined(ROCKSDB_LITE)

 #include "db/db_test_util.h"
+#include "env/mock_env.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
 #include "util/random.h"
@@ -11,6 +11,7 @@

 #include "db/db_impl/db_impl.h"
 #include "db/db_test_util.h"
+#include "env/mock_env.h"
 #include "file/filename.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
@@ -19,6 +20,7 @@
 #include "util/cast_util.h"
 #include "util/mutexlock.h"
 #include "utilities/fault_injection_env.h"
+#include "utilities/fault_injection_fs.h"

 namespace ROCKSDB_NAMESPACE {

@@ -80,29 +82,16 @@ 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);
  ASSERT_OK(Put("key", "value"));
-  auto* cfd =
-      static_cast_with_check<ColumnFamilyHandleImpl>(db_->DefaultColumnFamily())
-          ->cfd();
  FlushOptions flush_options;
  flush_options.wait = false;
  ASSERT_OK(dbfull()->Flush(flush_options));
  // 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");
@@ -113,9 +102,6 @@ TEST_F(DBFlushTest, SyncFail) {
 #ifndef ROCKSDB_LITE
  ASSERT_EQ("", FilesPerLevel());  // flush failed.
 #endif                             // ROCKSDB_LITE
-  // Backgroun flush job should release ref count to current version.
-  ASSERT_EQ(current_before, cfd->current());
-  ASSERT_EQ(refs_before, cfd->current()->TEST_refs());
  Destroy(options);
 }

@@ -180,6 +166,66 @@ TEST_F(DBFlushTest, FlushInLowPriThreadPool) {
  ASSERT_EQ(1, num_compactions);
 }

+// Test when flush job is submitted to low priority thread pool and when DB is
+// closed in the meanwhile, CloseHelper doesn't hang.
+TEST_F(DBFlushTest, CloseDBWhenFlushInLowPri) {
+  Options options = CurrentOptions();
+  options.max_background_flushes = 1;
+  options.max_total_wal_size = 8192;
+
+  DestroyAndReopen(options);
+  CreateColumnFamilies({"cf1", "cf2"}, options);
+
+  env_->SetBackgroundThreads(0, Env::HIGH);
+  env_->SetBackgroundThreads(1, Env::LOW);
+  test::SleepingBackgroundTask sleeping_task_low;
+  int num_flushes = 0;
+
+  SyncPoint::GetInstance()->SetCallBack("DBImpl::BGWorkFlush",
+                                        [&](void* /*arg*/) { ++num_flushes; });
+
+  int num_low_flush_unscheduled = 0;
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::UnscheduleLowFlushCallback", [&](void* /*arg*/) {
+        num_low_flush_unscheduled++;
+        // There should be one flush job in low pool that needs to be
+        // unscheduled
+        ASSERT_EQ(num_low_flush_unscheduled, 1);
+      });
+
+  int num_high_flush_unscheduled = 0;
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::UnscheduleHighFlushCallback", [&](void* /*arg*/) {
+        num_high_flush_unscheduled++;
+        // There should be no flush job in high pool
+        ASSERT_EQ(num_high_flush_unscheduled, 0);
+      });
+
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_OK(Put(0, "key1", DummyString(8192)));
+  // Block thread so that flush cannot be run and can be removed from the queue
+  // when called Unschedule.
+  env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask, &sleeping_task_low,
+                 Env::Priority::LOW);
+  sleeping_task_low.WaitUntilSleeping();
+
+  // Trigger flush and flush job will be scheduled to LOW priority thread.
+  ASSERT_OK(Put(0, "key2", DummyString(8192)));
+
+  // Close DB and flush job in low priority queue will be removed without
+  // running.
+  Close();
+  sleeping_task_low.WakeUp();
+  sleeping_task_low.WaitUntilDone();
+  ASSERT_EQ(0, num_flushes);
+
+  TryReopenWithColumnFamilies({"default", "cf1", "cf2"}, options);
+  ASSERT_OK(Put(0, "key3", DummyString(8192)));
+  ASSERT_OK(Flush(0));
+  ASSERT_EQ(1, num_flushes);
+}
+
 TEST_F(DBFlushTest, ManualFlushWithMinWriteBufferNumberToMerge) {
  Options options = CurrentOptions();
  options.write_buffer_size = 100;
@@ -451,7 +497,6 @@ TEST_F(DBFlushTest, FlushWithBlob) {
  constexpr uint64_t min_blob_size = 10;

  Options options;
-  options.env = CurrentOptions().env;
  options.enable_blob_files = true;
  options.min_blob_size = min_blob_size;
  options.disable_auto_compactions = true;
@@ -512,27 +557,224 @@ TEST_F(DBFlushTest, FlushWithBlob) {
  const InternalStats* const internal_stats = cfd->internal_stats();
  assert(internal_stats);

-  const uint64_t expected_bytes =
-      table_file->fd.GetFileSize() + blob_file->GetTotalBlobBytes();
-
  const auto& compaction_stats = internal_stats->TEST_GetCompactionStats();
  ASSERT_FALSE(compaction_stats.empty());
-  ASSERT_EQ(compaction_stats[0].bytes_written, expected_bytes);
-  ASSERT_EQ(compaction_stats[0].num_output_files, 2);
+  ASSERT_EQ(compaction_stats[0].bytes_written, table_file->fd.GetFileSize());
+  ASSERT_EQ(compaction_stats[0].bytes_written_blob,
+            blob_file->GetTotalBlobBytes());
+  ASSERT_EQ(compaction_stats[0].num_output_files, 1);
+  ASSERT_EQ(compaction_stats[0].num_output_files_blob, 1);

  const uint64_t* const cf_stats_value = internal_stats->TEST_GetCFStatsValue();
-  ASSERT_EQ(cf_stats_value[InternalStats::BYTES_FLUSHED], expected_bytes);
+  ASSERT_EQ(cf_stats_value[InternalStats::BYTES_FLUSHED],
+            compaction_stats[0].bytes_written +
+                compaction_stats[0].bytes_written_blob);
 #endif  // ROCKSDB_LITE
 }

+TEST_F(DBFlushTest, FlushWithChecksumHandoff1) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.write_buffer_size = 100;
+  options.max_write_buffer_number = 4;
+  options.min_write_buffer_number_to_merge = 3;
+  options.disable_auto_compactions = true;
+  options.env = fault_fs_env.get();
+  options.checksum_handoff_file_types.Add(FileType::kTableFile);
+  Reopen(options);
+
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put("key1", "value1"));
+  ASSERT_OK(Put("key2", "value2"));
+  ASSERT_OK(dbfull()->TEST_SwitchMemtable());
+
+  // The hash does not match, write fails
+  // fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+  // Since the file system returns IOStatus::Corruption, it is an
+  // unrecoverable error.
+  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
+    fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+  });
+  ASSERT_OK(Put("key3", "value3"));
+  ASSERT_OK(Put("key4", "value4"));
+  SyncPoint::GetInstance()->EnableProcessing();
+  Status s = Flush();
+  ASSERT_EQ(s.severity(),
+            ROCKSDB_NAMESPACE::Status::Severity::kUnrecoverableError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  Destroy(options);
+  Reopen(options);
+
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+  ASSERT_OK(Put("key5", "value5"));
+  ASSERT_OK(Put("key6", "value6"));
+  ASSERT_OK(dbfull()->TEST_SwitchMemtable());
+
+  // Each write will be similated as corrupted.
+  // Since the file system returns IOStatus::Corruption, it is an
+  // unrecoverable error.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
+    fault_fs->IngestDataCorruptionBeforeWrite();
+  });
+  ASSERT_OK(Put("key7", "value7"));
+  ASSERT_OK(Put("key8", "value8"));
+  SyncPoint::GetInstance()->EnableProcessing();
+  s = Flush();
+  ASSERT_EQ(s.severity(),
+            ROCKSDB_NAMESPACE::Status::Severity::kUnrecoverableError);
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  Destroy(options);
+}
+
+TEST_F(DBFlushTest, FlushWithChecksumHandoff2) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.write_buffer_size = 100;
+  options.max_write_buffer_number = 4;
+  options.min_write_buffer_number_to_merge = 3;
+  options.disable_auto_compactions = true;
+  options.env = fault_fs_env.get();
+  Reopen(options);
+
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  ASSERT_OK(Put("key1", "value1"));
+  ASSERT_OK(Put("key2", "value2"));
+  ASSERT_OK(Flush());
+
+  // options is not set, the checksum handoff will not be triggered
+  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
+    fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+  });
+  ASSERT_OK(Put("key3", "value3"));
+  ASSERT_OK(Put("key4", "value4"));
+  SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Flush());
+  SyncPoint::GetInstance()->DisableProcessing();
+  Destroy(options);
+  Reopen(options);
+
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+  ASSERT_OK(Put("key5", "value5"));
+  ASSERT_OK(Put("key6", "value6"));
+  ASSERT_OK(Flush());
+
+  // options is not set, the checksum handoff will not be triggered
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
+    fault_fs->IngestDataCorruptionBeforeWrite();
+  });
+  ASSERT_OK(Put("key7", "value7"));
+  ASSERT_OK(Put("key8", "value8"));
+  SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Flush());
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  Destroy(options);
+}
+
+TEST_F(DBFlushTest, FlushWithChecksumHandoffManifest1) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.write_buffer_size = 100;
+  options.max_write_buffer_number = 4;
+  options.min_write_buffer_number_to_merge = 3;
+  options.disable_auto_compactions = true;
+  options.env = fault_fs_env.get();
+  options.checksum_handoff_file_types.Add(FileType::kDescriptorFile);
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  Reopen(options);
+
+  ASSERT_OK(Put("key1", "value1"));
+  ASSERT_OK(Put("key2", "value2"));
+  ASSERT_OK(Flush());
+
+  // The hash does not match, write fails
+  // fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+  // Since the file system returns IOStatus::Corruption, it is mapped to
+  // kFatalError error.
+  ASSERT_OK(Put("key3", "value3"));
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::LogAndApply:WriteManifest", [&](void*) {
+        fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+      });
+  ASSERT_OK(Put("key3", "value3"));
+  ASSERT_OK(Put("key4", "value4"));
+  SyncPoint::GetInstance()->EnableProcessing();
+  Status s = Flush();
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kFatalError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  Destroy(options);
+}
+
+TEST_F(DBFlushTest, FlushWithChecksumHandoffManifest2) {
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  Options options = CurrentOptions();
+  options.write_buffer_size = 100;
+  options.max_write_buffer_number = 4;
+  options.min_write_buffer_number_to_merge = 3;
+  options.disable_auto_compactions = true;
+  options.env = fault_fs_env.get();
+  options.checksum_handoff_file_types.Add(FileType::kDescriptorFile);
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+  Reopen(options);
+  // The file system does not support checksum handoff. The check
+  // will be ignored.
+  ASSERT_OK(Put("key5", "value5"));
+  ASSERT_OK(Put("key6", "value6"));
+  ASSERT_OK(Flush());
+
+  // Each write will be similated as corrupted.
+  // Since the file system returns IOStatus::Corruption, it is mapped to
+  // kFatalError error.
+  fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::LogAndApply:WriteManifest",
+      [&](void*) { fault_fs->IngestDataCorruptionBeforeWrite(); });
+  ASSERT_OK(Put("key7", "value7"));
+  ASSERT_OK(Put("key8", "value8"));
+  SyncPoint::GetInstance()->EnableProcessing();
+  Status s = Flush();
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kFatalError);
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  Destroy(options);
+}
+
 class DBFlushTestBlobError : public DBFlushTest,
                             public testing::WithParamInterface<std::string> {
 public:
-  DBFlushTestBlobError()
-      : fault_injection_env_(env_), sync_point_(GetParam()) {}
-  ~DBFlushTestBlobError() { Close(); }
+  DBFlushTestBlobError() : sync_point_(GetParam()) {}

-  FaultInjectionTestEnv fault_injection_env_;
  std::string sync_point_;
 };

@@ -545,20 +787,18 @@ TEST_P(DBFlushTestBlobError, FlushError) {
  Options options;
  options.enable_blob_files = true;
  options.disable_auto_compactions = true;
-  options.env = &fault_injection_env_;
+  options.env = env_;

  Reopen(options);

  ASSERT_OK(Put("key", "blob"));

-  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
-    fault_injection_env_.SetFilesystemActive(false,
-                                             Status::IOError(sync_point_));
+  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* arg) {
+    Status* const s = static_cast<Status*>(arg);
+    assert(s);
+
+    (*s) = Status::IOError(sync_point_);
  });
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeDeleteFile", [this](void* /* arg */) {
-        fault_injection_env_.SetFilesystemActive(true);
-      });
  SyncPoint::GetInstance()->EnableProcessing();

  ASSERT_NOK(Flush());
@@ -608,16 +848,21 @@ TEST_P(DBFlushTestBlobError, FlushError) {

  if (sync_point_ == "BlobFileBuilder::WriteBlobToFile:AddRecord") {
    ASSERT_EQ(compaction_stats[0].bytes_written, 0);
+    ASSERT_EQ(compaction_stats[0].bytes_written_blob, 0);
    ASSERT_EQ(compaction_stats[0].num_output_files, 0);
+    ASSERT_EQ(compaction_stats[0].num_output_files_blob, 0);
  } else {
    // SST file writing succeeded; blob file writing failed (during Finish)
    ASSERT_GT(compaction_stats[0].bytes_written, 0);
+    ASSERT_EQ(compaction_stats[0].bytes_written_blob, 0);
    ASSERT_EQ(compaction_stats[0].num_output_files, 1);
+    ASSERT_EQ(compaction_stats[0].num_output_files_blob, 0);
  }

  const uint64_t* const cf_stats_value = internal_stats->TEST_GetCFStatsValue();
  ASSERT_EQ(cf_stats_value[InternalStats::BYTES_FLUSHED],
-            compaction_stats[0].bytes_written);
+            compaction_stats[0].bytes_written +
+                compaction_stats[0].bytes_written_blob);
 #endif  // ROCKSDB_LITE
 }

@@ -4,7 +4,7 @@
 //  (found in the LICENSE.Apache file in the root directory).

 #ifndef ROCKSDB_LITE
-#include "db/compacted_db_impl.h"
+#include "db/db_impl/compacted_db_impl.h"

 #include "db/db_impl/db_impl.h"
 #include "db/version_set.h"
@@ -17,11 +17,13 @@ extern void MarkKeyMayExist(void* arg);
 extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
                      const Slice& v, bool hit_and_return);

-CompactedDBImpl::CompactedDBImpl(
-  const DBOptions& options, const std::string& dbname)
-  : DBImpl(options, dbname), cfd_(nullptr), version_(nullptr),
-    user_comparator_(nullptr) {
-}
+CompactedDBImpl::CompactedDBImpl(const DBOptions& options,
+                                 const std::string& dbname)
+    : DBImpl(options, dbname, /*seq_per_batch*/ false, +/*batch_per_txn*/ true,
+             /*read_only*/ true),
+      cfd_(nullptr),
+      version_(nullptr),
+      user_comparator_(nullptr) {}

 CompactedDBImpl::~CompactedDBImpl() {
 }
@@ -78,6 +80,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
                             nullptr, nullptr, nullptr, true, nullptr, nullptr);
      LookupKey lkey(keys[idx], kMaxSequenceNumber);
      Status s = r->Get(options, lkey.internal_key(), &get_context, nullptr);
+      assert(static_cast<size_t>(idx) < statuses.size());
      if (!s.ok() && !s.IsNotFound()) {
        statuses[idx] = s;
      } else {
@@ -18,7 +18,7 @@ class CompactedDBImpl : public DBImpl {
  CompactedDBImpl(const CompactedDBImpl&) = delete;
  void operator=(const CompactedDBImpl&) = delete;

-  virtual ~CompactedDBImpl();
+  ~CompactedDBImpl() override;

  static Status Open(const Options& options, const std::string& dbname,
                     DB** dbptr);
@@ -82,6 +82,7 @@
 #include "rocksdb/stats_history.h"
 #include "rocksdb/status.h"
 #include "rocksdb/table.h"
+#include "rocksdb/version.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/block_based/block.h"
 #include "table/block_based/block_based_table_factory.h"
@@ -93,7 +94,6 @@
 #include "table/two_level_iterator.h"
 #include "test_util/sync_point.h"
 #include "util/autovector.h"
-#include "util/build_version.h"
 #include "util/cast_util.h"
 #include "util/coding.h"
 #include "util/compression.h"
@@ -146,17 +146,18 @@ void DumpSupportInfo(Logger* logger) {
 }  // namespace

 DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
-               const bool seq_per_batch, const bool batch_per_txn)
+               const bool seq_per_batch, const bool batch_per_txn,
+               bool read_only)
    : dbname_(dbname),
      own_info_log_(options.info_log == nullptr),
-      initial_db_options_(SanitizeOptions(dbname, options)),
+      initial_db_options_(SanitizeOptions(dbname, options, read_only)),
      env_(initial_db_options_.env),
      io_tracer_(std::make_shared<IOTracer>()),
      immutable_db_options_(initial_db_options_),
      fs_(immutable_db_options_.fs, io_tracer_),
      mutable_db_options_(initial_db_options_),
      stats_(immutable_db_options_.statistics.get()),
-      mutex_(stats_, env_, DB_MUTEX_WAIT_MICROS,
+      mutex_(stats_, immutable_db_options_.clock, DB_MUTEX_WAIT_MICROS,
             immutable_db_options_.use_adaptive_mutex),
      default_cf_handle_(nullptr),
      max_total_in_memory_state_(0),
@@ -191,7 +192,7 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
      bg_purge_scheduled_(0),
      disable_delete_obsolete_files_(0),
      pending_purge_obsolete_files_(0),
-      delete_obsolete_files_last_run_(env_->NowMicros()),
+      delete_obsolete_files_last_run_(immutable_db_options_.clock->NowMicros()),
      last_stats_dump_time_microsec_(0),
      next_job_id_(1),
      has_unpersisted_data_(false),
@@ -231,7 +232,9 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
      preserve_deletes_(options.preserve_deletes),
      closed_(false),
      error_handler_(this, immutable_db_options_, &mutex_),
-      atomic_flush_install_cv_(&mutex_) {
+      atomic_flush_install_cv_(&mutex_),
+      blob_callback_(immutable_db_options_.sst_file_manager.get(), &mutex_,
+                     &error_handler_) {
  // !batch_per_trx_ implies seq_per_batch_ because it is only unset for
  // WriteUnprepared, which should use seq_per_batch_.
  assert(batch_per_txn_ || seq_per_batch_);
@@ -511,19 +514,20 @@ Status DBImpl::CloseHelper() {
  }
  mutex_.Unlock();

+  // Below check is added as recovery_error_ is not checked and it causes crash
+  // in DBSSTTest.DBWithMaxSpaceAllowedWithBlobFiles when space limit is
+  // reached.
+  error_handler_.GetRecoveryError().PermitUncheckedError();
+
  // CancelAllBackgroundWork called with false means we just set the shutdown
  // marker. After this we do a variant of the waiting and unschedule work
  // (to consider: moving all the waiting into CancelAllBackgroundWork(true))
  CancelAllBackgroundWork(false);
-  int bottom_compactions_unscheduled =
-      env_->UnSchedule(this, Env::Priority::BOTTOM);
-  int compactions_unscheduled = env_->UnSchedule(this, Env::Priority::LOW);
-  int flushes_unscheduled = env_->UnSchedule(this, Env::Priority::HIGH);
-  Status ret = Status::OK();
  mutex_.Lock();
-  bg_bottom_compaction_scheduled_ -= bottom_compactions_unscheduled;
-  bg_compaction_scheduled_ -= compactions_unscheduled;
-  bg_flush_scheduled_ -= flushes_unscheduled;
+  env_->UnSchedule(this, Env::Priority::BOTTOM);
+  env_->UnSchedule(this, Env::Priority::LOW);
+  env_->UnSchedule(this, Env::Priority::HIGH);
+  Status ret = Status::OK();

  // Wait for background work to finish
  while (bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
@@ -752,7 +756,8 @@ void DBImpl::PersistStats() {
    return;
  }
  TEST_SYNC_POINT("DBImpl::PersistStats:StartRunning");
-  uint64_t now_seconds = env_->NowMicros() / kMicrosInSecond;
+  uint64_t now_seconds =
+      immutable_db_options_.clock->NowMicros() / kMicrosInSecond;

  Statistics* statistics = immutable_db_options_.statistics.get();
  if (!statistics) {
@@ -1653,8 +1658,8 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
  }
 #endif  // NDEBUG

-  PERF_CPU_TIMER_GUARD(get_cpu_nanos, env_);
-  StopWatch sw(env_, stats_, DB_GET);
+  PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
+  StopWatch sw(immutable_db_options_.clock, stats_, DB_GET);
  PERF_TIMER_GUARD(get_snapshot_time);

  auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(
@@ -1718,7 +1723,9 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
  }
  // If timestamp is used, we use read callback to ensure <key,t,s> is returned
  // only if t <= read_opts.timestamp and s <= snapshot.
-  if (ts_sz > 0 && !get_impl_options.callback) {
+  if (ts_sz > 0) {
+    assert(!get_impl_options
+                .callback);  // timestamp with callback is not supported
    read_cb.Refresh(snapshot);
    get_impl_options.callback = &read_cb;
  }
@@ -1842,8 +1849,8 @@ std::vector<Status> DBImpl::MultiGet(
    const std::vector<ColumnFamilyHandle*>& column_family,
    const std::vector<Slice>& keys, std::vector<std::string>* values,
    std::vector<std::string>* timestamps) {
-  PERF_CPU_TIMER_GUARD(get_cpu_nanos, env_);
-  StopWatch sw(env_, stats_, DB_MULTIGET);
+  PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
+  StopWatch sw(immutable_db_options_.clock, stats_, DB_MULTIGET);
  PERF_TIMER_GUARD(get_snapshot_time);

 #ifndef NDEBUG
@@ -1972,9 +1979,8 @@ std::vector<Status> DBImpl::MultiGet(
        break;
      }
    }
-
    if (read_options.deadline.count() &&
-        env_->NowMicros() >
+        immutable_db_options_.clock->NowMicros() >
            static_cast<uint64_t>(read_options.deadline.count())) {
      break;
    }
@@ -1983,8 +1989,8 @@ std::vector<Status> DBImpl::MultiGet(
  if (keys_read < num_keys) {
    // The only reason to break out of the loop is when the deadline is
    // exceeded
-    assert(env_->NowMicros() >
-        static_cast<uint64_t>(read_options.deadline.count()));
+    assert(immutable_db_options_.clock->NowMicros() >
+           static_cast<uint64_t>(read_options.deadline.count()));
    for (++keys_read; keys_read < num_keys; ++keys_read) {
      stat_list[keys_read] = Status::TimedOut();
    }
@@ -2394,8 +2400,9 @@ void DBImpl::MultiGetWithCallback(
  }

  GetWithTimestampReadCallback timestamp_read_callback(0);
-  ReadCallback* read_callback = nullptr;
+  ReadCallback* read_callback = callback;
  if (read_options.timestamp && read_options.timestamp->size() > 0) {
+    assert(!read_callback);  // timestamp with callback is not supported
    timestamp_read_callback.Refresh(consistent_seqnum);
    read_callback = &timestamp_read_callback;
  }
@@ -2422,8 +2429,8 @@ Status DBImpl::MultiGetImpl(
    autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys,
    SuperVersion* super_version, SequenceNumber snapshot,
    ReadCallback* callback) {
-  PERF_CPU_TIMER_GUARD(get_cpu_nanos, env_);
-  StopWatch sw(env_, stats_, DB_MULTIGET);
+  PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
+  StopWatch sw(immutable_db_options_.clock, stats_, DB_MULTIGET);

  // For each of the given keys, apply the entire "get" process as follows:
  // First look in the memtable, then in the immutable memtable (if any).
@@ -2434,7 +2441,7 @@ Status DBImpl::MultiGetImpl(
  uint64_t curr_value_size = 0;
  while (keys_left) {
    if (read_options.deadline.count() &&
-        env_->NowMicros() >
+        immutable_db_options_.clock->NowMicros() >
            static_cast<uint64_t>(read_options.deadline.count())) {
      s = Status::TimedOut();
      break;
@@ -2987,7 +2994,8 @@ const Snapshot* DBImpl::GetSnapshotForWriteConflictBoundary() {
 SnapshotImpl* DBImpl::GetSnapshotImpl(bool is_write_conflict_boundary,
                                      bool lock) {
  int64_t unix_time = 0;
-  env_->GetCurrentTime(&unix_time).PermitUncheckedError();  // Ignore error
+  immutable_db_options_.clock->GetCurrentTime(&unix_time)
+      .PermitUncheckedError();  // Ignore error
  SnapshotImpl* s = new SnapshotImpl;

  if (lock) {
@@ -3132,12 +3140,17 @@ FileSystem* DBImpl::GetFileSystem() const {
  return immutable_db_options_.fs.get();
 }

+SystemClock* DBImpl::GetSystemClock() const {
+  return immutable_db_options_.clock;
+}
+
 #ifndef ROCKSDB_LITE

-Status DBImpl::StartIOTrace(Env* env, const TraceOptions& trace_options,
+Status DBImpl::StartIOTrace(const TraceOptions& trace_options,
                            std::unique_ptr<TraceWriter>&& trace_writer) {
  assert(trace_writer != nullptr);
-  return io_tracer_->StartIOTrace(env, trace_options, std::move(trace_writer));
+  return io_tracer_->StartIOTrace(GetSystemClock(), trace_options,
+                                  std::move(trace_writer));
 }

 Status DBImpl::EndIOTrace() {
@@ -3934,7 +3947,8 @@ Status DestroyDB(const std::string& dbname, const Options& options,
        std::string path_to_delete = dbname + "/" + fname;
        if (type == kMetaDatabase) {
          del = DestroyDB(path_to_delete, options);
-        } else if (type == kTableFile || type == kWalFile) {
+        } else if (type == kTableFile || type == kWalFile ||
+                   type == kBlobFile) {
          del = DeleteDBFile(&soptions, path_to_delete, dbname,
                             /*force_bg=*/false, /*force_fg=*/!wal_in_db_path);
        } else {
@@ -3959,9 +3973,10 @@ Status DestroyDB(const std::string& dbname, const Options& options,
      if (env->GetChildren(path, &filenames).ok()) {
        for (const auto& fname : filenames) {
          if (ParseFileName(fname, &number, &type) &&
-              type == kTableFile) {  // Lock file will be deleted at end
-            std::string table_path = path + "/" + fname;
-            Status del = DeleteDBFile(&soptions, table_path, dbname,
+              (type == kTableFile ||
+               type == kBlobFile)) {  // Lock file will be deleted at end
+            std::string file_path = path + "/" + fname;
+            Status del = DeleteDBFile(&soptions, file_path, dbname,
                                      /*force_bg=*/false, /*force_fg=*/false);
            if (!del.ok() && result.ok()) {
              result = del;
@@ -4205,16 +4220,17 @@ void DBImpl::EraseThreadStatusDbInfo() const {}
 //
 // A global method that can dump out the build version
 void DumpRocksDBBuildVersion(Logger* log) {
-#if !defined(IOS_CROSS_COMPILE)
-  // if we compile with Xcode, we don't run build_detect_version, so we don't
-  // generate util/build_version.cc
-  ROCKS_LOG_HEADER(log, "RocksDB version: %d.%d.%d\n", ROCKSDB_MAJOR,
-                   ROCKSDB_MINOR, ROCKSDB_PATCH);
-  ROCKS_LOG_HEADER(log, "Git sha %s", rocksdb_build_git_sha);
-  ROCKS_LOG_HEADER(log, "Compile date %s", rocksdb_build_compile_date);
-#else
-  (void)log;  // ignore "-Wunused-parameter"
-#endif
+  ROCKS_LOG_HEADER(log, "RocksDB version: %s\n",
+                   GetRocksVersionAsString().c_str());
+  const auto& props = GetRocksBuildProperties();
+  const auto& sha = props.find("rocksdb_build_git_sha");
+  if (sha != props.end()) {
+    ROCKS_LOG_HEADER(log, "Git sha %s", sha->second.c_str());
+  }
+  const auto date = props.find("rocksdb_build_date");
+  if (date != props.end()) {
+    ROCKS_LOG_HEADER(log, "Compile date %s", date->second.c_str());
+  }
 }

 #ifndef ROCKSDB_LITE
@@ -4416,9 +4432,9 @@ Status DBImpl::IngestExternalFiles(
  std::vector<ExternalSstFileIngestionJob> ingestion_jobs;
  for (const auto& arg : args) {
    auto* cfd = static_cast<ColumnFamilyHandleImpl*>(arg.column_family)->cfd();
-    ingestion_jobs.emplace_back(
-        env_, versions_.get(), cfd, immutable_db_options_, file_options_,
-        &snapshots_, arg.options, &directories_, &event_logger_, io_tracer_);
+    ingestion_jobs.emplace_back(versions_.get(), cfd, immutable_db_options_,
+                                file_options_, &snapshots_, arg.options,
+                                &directories_, &event_logger_, io_tracer_);
  }

  // TODO(yanqin) maybe make jobs run in parallel
@@ -4685,9 +4701,9 @@ Status DBImpl::CreateColumnFamilyWithImport(
  // Import sst files from metadata.
  auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(*handle);
  auto cfd = cfh->cfd();
-  ImportColumnFamilyJob import_job(env_, versions_.get(), cfd,
-                                   immutable_db_options_, file_options_,
-                                   import_options, metadata.files, io_tracer_);
+  ImportColumnFamilyJob import_job(versions_.get(), cfd, immutable_db_options_,
+                                   file_options_, import_options,
+                                   metadata.files, io_tracer_);

  SuperVersionContext dummy_sv_ctx(/* create_superversion */ true);
  VersionEdit dummy_edit;
@@ -4849,17 +4865,37 @@ Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
        std::string fname = TableFileName(cfd->ioptions()->cf_paths,
                                          fd.GetNumber(), fd.GetPathId());
        if (use_file_checksum) {
-          s = VerifySstFileChecksum(*fmeta, fname, read_options);
+          s = VerifyFullFileChecksum(fmeta->file_checksum,
+                                     fmeta->file_checksum_func_name, fname,
+                                     read_options);
        } else {
          s = ROCKSDB_NAMESPACE::VerifySstFileChecksum(opts, file_options_,
                                                       read_options, fname);
        }
      }
    }
+
+    if (s.ok() && use_file_checksum) {
+      const auto& blob_files = vstorage->GetBlobFiles();
+      for (const auto& pair : blob_files) {
+        const uint64_t blob_file_number = pair.first;
+        const auto& meta = pair.second;
+        assert(meta);
+        const std::string blob_file_name = BlobFileName(
+            cfd->ioptions()->cf_paths.front().path, blob_file_number);
+        s = VerifyFullFileChecksum(meta->GetChecksumValue(),
+                                   meta->GetChecksumMethod(), blob_file_name,
+                                   read_options);
+        if (!s.ok()) {
+          break;
+        }
+      }
+    }
    if (!s.ok()) {
      break;
    }
  }
+
  bool defer_purge =
          immutable_db_options().avoid_unnecessary_blocking_io;
  {
@@ -4884,29 +4920,31 @@ Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
  return s;
 }

-Status DBImpl::VerifySstFileChecksum(const FileMetaData& fmeta,
-                                     const std::string& fname,
-                                     const ReadOptions& read_options) {
+Status DBImpl::VerifyFullFileChecksum(const std::string& file_checksum_expected,
+                                      const std::string& func_name_expected,
+                                      const std::string& fname,
+                                      const ReadOptions& read_options) {
  Status s;
-  if (fmeta.file_checksum == kUnknownFileChecksum) {
+  if (file_checksum_expected == kUnknownFileChecksum) {
    return s;
  }
  std::string file_checksum;
  std::string func_name;
  s = ROCKSDB_NAMESPACE::GenerateOneFileChecksum(
      fs_.get(), fname, immutable_db_options_.file_checksum_gen_factory.get(),
-      fmeta.file_checksum_func_name, &file_checksum, &func_name,
+      func_name_expected, &file_checksum, &func_name,
      read_options.readahead_size, immutable_db_options_.allow_mmap_reads,
      io_tracer_, immutable_db_options_.rate_limiter.get());
  if (s.ok()) {
-    assert(fmeta.file_checksum_func_name == func_name);
-    if (file_checksum != fmeta.file_checksum) {
+    assert(func_name_expected == func_name);
+    if (file_checksum != file_checksum_expected) {
      std::ostringstream oss;
      oss << fname << " file checksum mismatch, ";
-      oss << "expecting " << Slice(fmeta.file_checksum).ToString(/*hex=*/true);
+      oss << "expecting "
+          << Slice(file_checksum_expected).ToString(/*hex=*/true);
      oss << ", but actual " << Slice(file_checksum).ToString(/*hex=*/true);
      s = Status::Corruption(oss.str());
-      TEST_SYNC_POINT_CALLBACK("DBImpl::VerifySstFileChecksum:mismatch", &s);
+      TEST_SYNC_POINT_CALLBACK("DBImpl::VerifyFullFileChecksum:mismatch", &s);
    }
  }
  return s;
@@ -4941,7 +4979,8 @@ void DBImpl::WaitForIngestFile() {
 Status DBImpl::StartTrace(const TraceOptions& trace_options,
                          std::unique_ptr<TraceWriter>&& trace_writer) {
  InstrumentedMutexLock lock(&trace_mutex_);
-  tracer_.reset(new Tracer(env_, trace_options, std::move(trace_writer)));
+  tracer_.reset(new Tracer(immutable_db_options_.clock, trace_options,
+                           std::move(trace_writer)));
  return Status::OK();
 }

@@ -4960,8 +4999,8 @@ Status DBImpl::EndTrace() {
 Status DBImpl::StartBlockCacheTrace(
    const TraceOptions& trace_options,
    std::unique_ptr<TraceWriter>&& trace_writer) {
-  return block_cache_tracer_.StartTrace(env_, trace_options,
-                                        std::move(trace_writer));
+  return block_cache_tracer_.StartTrace(immutable_db_options_.clock,
+                                        trace_options, std::move(trace_writer));
 }

 Status DBImpl::EndBlockCacheTrace() {
@@ -4969,24 +5008,27 @@ Status DBImpl::EndBlockCacheTrace() {
  return Status::OK();
 }

-Status DBImpl::TraceIteratorSeek(const uint32_t& cf_id, const Slice& key) {
+Status DBImpl::TraceIteratorSeek(const uint32_t& cf_id, const Slice& key,
+                                 const Slice& lower_bound,
+                                 const Slice upper_bound) {
  Status s;
  if (tracer_) {
    InstrumentedMutexLock lock(&trace_mutex_);
    if (tracer_) {
-      s = tracer_->IteratorSeek(cf_id, key);
+      s = tracer_->IteratorSeek(cf_id, key, lower_bound, upper_bound);
    }
  }
  return s;
 }

-Status DBImpl::TraceIteratorSeekForPrev(const uint32_t& cf_id,
-                                        const Slice& key) {
+Status DBImpl::TraceIteratorSeekForPrev(const uint32_t& cf_id, const Slice& key,
+                                        const Slice& lower_bound,
+                                        const Slice upper_bound) {
  Status s;
  if (tracer_) {
    InstrumentedMutexLock lock(&trace_mutex_);
    if (tracer_) {
-      s = tracer_->IteratorSeekForPrev(cf_id, key);
+      s = tracer_->IteratorSeekForPrev(cf_id, key, lower_bound, upper_bound);
    }
  }
  return s;
@@ -54,9 +54,6 @@
 #include "rocksdb/transaction_log.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/scoped_arena_iterator.h"
-#include "trace_replay/block_cache_tracer.h"
-#include "trace_replay/io_tracer.h"
-#include "trace_replay/trace_replay.h"
 #include "util/autovector.h"
 #include "util/hash.h"
 #include "util/repeatable_thread.h"
@@ -132,7 +129,8 @@ class Directories {
 class DBImpl : public DB {
 public:
  DBImpl(const DBOptions& options, const std::string& dbname,
-         const bool seq_per_batch = false, const bool batch_per_txn = true);
+         const bool seq_per_batch = false, const bool batch_per_txn = true,
+         bool read_only = false);
  // No copying allowed
  DBImpl(const DBImpl&) = delete;
  void operator=(const DBImpl&) = delete;
@@ -450,9 +448,10 @@ class DBImpl : public DB {
  Status VerifyChecksumInternal(const ReadOptions& read_options,
                                bool use_file_checksum);

-  Status VerifySstFileChecksum(const FileMetaData& fmeta,
-                               const std::string& fpath,
-                               const ReadOptions& read_options);
+  Status VerifyFullFileChecksum(const std::string& file_checksum_expected,
+                                const std::string& func_name_expected,
+                                const std::string& fpath,
+                                const ReadOptions& read_options);

  using DB::StartTrace;
  virtual Status StartTrace(
@@ -471,7 +470,7 @@ class DBImpl : public DB {
  Status EndBlockCacheTrace() override;

  using DB::StartIOTrace;
-  Status StartIOTrace(Env* env, const TraceOptions& options,
+  Status StartIOTrace(const TraceOptions& options,
                      std::unique_ptr<TraceWriter>&& trace_writer) override;

  using DB::EndIOTrace;
@@ -488,6 +487,7 @@ class DBImpl : public DB {
 #endif  // ROCKSDB_LITE

  // ---- End of implementations of the DB interface ----
+  SystemClock* GetSystemClock() const;

  struct GetImplOptions {
    ColumnFamilyHandle* column_family = nullptr;
@@ -595,8 +595,11 @@ class DBImpl : public DB {
                                 bool* found_record_for_key,
                                 bool* is_blob_index = nullptr);

-  Status TraceIteratorSeek(const uint32_t& cf_id, const Slice& key);
-  Status TraceIteratorSeekForPrev(const uint32_t& cf_id, const Slice& key);
+  Status TraceIteratorSeek(const uint32_t& cf_id, const Slice& key,
+                           const Slice& lower_bound, const Slice upper_bound);
+  Status TraceIteratorSeekForPrev(const uint32_t& cf_id, const Slice& key,
+                                  const Slice& lower_bound,
+                                  const Slice upper_bound);
 #endif  // ROCKSDB_LITE

  // Similar to GetSnapshot(), but also lets the db know that this snapshot
@@ -954,6 +957,9 @@ class DBImpl : public DB {
  // is only for the special test of CancelledCompactions
  Status TEST_WaitForCompact(bool waitUnscheduled = false);

+  // Get the background error status
+  Status TEST_GetBGError();
+
  // Return the maximum overlapping data (in bytes) at next level for any
  // file at a level >= 1.
  int64_t TEST_MaxNextLevelOverlappingBytes(
@@ -1231,7 +1237,7 @@ class DBImpl : public DB {
  virtual bool OwnTablesAndLogs() const { return true; }

  // Set DB identity file, and write DB ID to manifest if necessary.
-  Status SetDBId();
+  Status SetDBId(bool read_only);

  // REQUIRES: db mutex held when calling this function, but the db mutex can
  // be released and re-acquired. Db mutex will be held when the function
@@ -1303,6 +1309,7 @@ class DBImpl : public DB {

  struct LogFileNumberSize {
    explicit LogFileNumberSize(uint64_t _number) : number(_number) {}
+    LogFileNumberSize() {}
    void AddSize(uint64_t new_size) { size += new_size; }
    uint64_t number;
    uint64_t size = 0;
@@ -1408,6 +1415,7 @@ class DBImpl : public DB {
    DBImpl* db;
    // background compaction takes ownership of `prepicked_compaction`.
    PrepickedCompaction* prepicked_compaction;
+    Env::Priority compaction_pri_;
  };

  // Initialize the built-in column family for persistent stats. Depending on
@@ -1502,6 +1510,12 @@ class DBImpl : public DB {
  Status WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                                     MemTable* mem, VersionEdit* edit);

+  // Get the size of a log file and, if truncate is true, truncate the
+  // log file to its actual size, thereby freeing preallocated space.
+  // Return success even if truncate fails
+  Status GetLogSizeAndMaybeTruncate(uint64_t wal_number, bool truncate,
+                                    LogFileNumberSize* log);
+
  // Restore alive_log_files_ and total_log_size_ after recovery.
  // It needs to run only when there's no flush during recovery
  // (e.g. avoid_flush_during_recovery=true). May also trigger flush
@@ -1870,6 +1884,8 @@ class DBImpl : public DB {

  Status DisableFileDeletionsWithLock();

+  Status IncreaseFullHistoryTsLow(ColumnFamilyData* cfd, std::string ts_low);
+
  // table_cache_ provides its own synchronization
  std::shared_ptr<Cache> table_cache_;

@@ -2212,11 +2228,15 @@ class DBImpl : public DB {
  InstrumentedCondVar atomic_flush_install_cv_;

  bool wal_in_db_path_;
+
+  BlobFileCompletionCallback blob_callback_;
 };

-extern Options SanitizeOptions(const std::string& db, const Options& src);
+extern Options SanitizeOptions(const std::string& db, const Options& src,
+                               bool read_only = false);

-extern DBOptions SanitizeOptions(const std::string& db, const DBOptions& src);
+extern DBOptions SanitizeOptions(const std::string& db, const DBOptions& src,
+                                 bool read_only = false);

 extern CompressionType GetCompressionFlush(
    const ImmutableCFOptions& ioptions,
@@ -131,16 +131,11 @@ IOStatus DBImpl::SyncClosedLogs(JobContext* job_context) {
      MarkLogsNotSynced(current_log_number - 1);
    }
    if (!io_s.ok()) {
-      if (total_log_size_ > 0) {
-        error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
-      } else {
-        // If the WAL is empty, we use different error reason
-        error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlushNoWAL);
-      }
      TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Failed");
      return io_s;
    }
  }
+  TEST_SYNC_POINT("DBImpl::SyncClosedLogs:end");
  return io_s;
 }

@@ -166,20 +161,18 @@ Status DBImpl::FlushMemTableToOutputFile(
      GetCompressionFlush(*cfd->ioptions(), mutable_cf_options), stats_,
      &event_logger_, mutable_cf_options.report_bg_io_stats,
      true /* sync_output_directory */, true /* write_manifest */, thread_pri,
-      io_tracer_, db_id_, db_session_id_, cfd->GetFullHistoryTsLow());
+      io_tracer_, db_id_, db_session_id_, cfd->GetFullHistoryTsLow(),
+      &blob_callback_);
  FileMetaData file_meta;

-  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:BeforePickMemtables");
-  flush_job.PickMemTable();
-  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:AfterPickMemtables");
-
 #ifndef ROCKSDB_LITE
  // may temporarily unlock and lock the mutex.
  NotifyOnFlushBegin(cfd, &file_meta, mutable_cf_options, job_context->job_id);
 #endif  // ROCKSDB_LITE

  Status s;
-  IOStatus io_s = IOStatus::OK();
+  bool need_cancel = false;
+  IOStatus log_io_s = IOStatus::OK();
  if (logfile_number_ > 0 &&
      versions_->GetColumnFamilySet()->NumberOfColumnFamilies() > 1) {
    // If there are more than one column families, we need to make sure that
@@ -188,15 +181,24 @@ Status DBImpl::FlushMemTableToOutputFile(
    // flushed SST may contain data from write batches whose updates to
    // other column families are missing.
    // SyncClosedLogs() may unlock and re-lock the db_mutex.
-    io_s = SyncClosedLogs(job_context);
-    s = io_s;
-    if (!io_s.ok() && !io_s.IsShutdownInProgress() &&
-        !io_s.IsColumnFamilyDropped()) {
-      error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
+    log_io_s = SyncClosedLogs(job_context);
+    if (!log_io_s.ok() && !log_io_s.IsShutdownInProgress() &&
+        !log_io_s.IsColumnFamilyDropped()) {
+      error_handler_.SetBGError(log_io_s, BackgroundErrorReason::kFlush);
    }
  } else {
    TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Skip");
  }
+  s = log_io_s;
+
+  // If the log sync failed, we do not need to pick memtable. Otherwise,
+  // num_flush_not_started_ needs to be rollback.
+  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:BeforePickMemtables");
+  if (s.ok()) {
+    flush_job.PickMemTable();
+    need_cancel = true;
+  }
+  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:AfterPickMemtables");

  // Within flush_job.Run, rocksdb may call event listener to notify
  // file creation and deletion.
@@ -206,11 +208,16 @@ Status DBImpl::FlushMemTableToOutputFile(
  // is unlocked by the current thread.
  if (s.ok()) {
    s = flush_job.Run(&logs_with_prep_tracker_, &file_meta);
-  } else {
+    need_cancel = false;
+  }
+
+  if (!s.ok() && need_cancel) {
    flush_job.Cancel();
  }
-  if (io_s.ok()) {
-    io_s = flush_job.io_status();
+  IOStatus io_s = IOStatus::OK();
+  io_s = flush_job.io_status();
+  if (s.ok()) {
+    s = io_s;
  }

  if (s.ok()) {
@@ -246,29 +253,30 @@ Status DBImpl::FlushMemTableToOutputFile(
  if (!s.ok() && !s.IsShutdownInProgress() && !s.IsColumnFamilyDropped()) {
    if (!io_s.ok() && !io_s.IsShutdownInProgress() &&
        !io_s.IsColumnFamilyDropped()) {
+      assert(log_io_s.ok());
      // Error while writing to MANIFEST.
      // In fact, versions_->io_status() can also be the result of renaming
      // CURRENT file. With current code, it's just difficult to tell. So just
      // be pessimistic and try write to a new MANIFEST.
      // TODO: distinguish between MANIFEST write and CURRENT renaming
      if (!versions_->io_status().ok()) {
-        if (total_log_size_ > 0) {
-          // If the WAL is empty, we use different error reason
-          error_handler_.SetBGError(io_s,
-                                    BackgroundErrorReason::kManifestWrite);
-        } else {
-          error_handler_.SetBGError(io_s,
-                                    BackgroundErrorReason::kManifestWriteNoWAL);
-        }
-      } else if (total_log_size_ > 0) {
-        error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
+        // If WAL sync is successful (either WAL size is 0 or there is no IO
+        // error), all the Manifest write will be map to soft error.
+        // TODO: kManifestWriteNoWAL and kFlushNoWAL are misleading. Refactor is
+        // needed.
+        error_handler_.SetBGError(io_s,
+                                  BackgroundErrorReason::kManifestWriteNoWAL);
      } else {
-        // If the WAL is empty, we use different error reason
+        // If WAL sync is successful (either WAL size is 0 or there is no IO
+        // error), all the other SST file write errors will be set as
+        // kFlushNoWAL.
        error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlushNoWAL);
      }
    } else {
-      Status new_bg_error = s;
-      error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
+      if (log_io_s.ok()) {
+        Status new_bg_error = s;
+        error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
+      }
    }
  } else {
    // If we got here, then we decided not to care about the i_os status (either
@@ -401,12 +409,11 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
        false /* sync_output_directory */, false /* write_manifest */,
        thread_pri, io_tracer_, db_id_, db_session_id_,
        cfd->GetFullHistoryTsLow()));
-    jobs.back()->PickMemTable();
  }

  std::vector<FileMetaData> file_meta(num_cfs);
  Status s;
-  IOStatus io_s;
+  IOStatus log_io_s = IOStatus::OK();
  assert(num_cfs == static_cast<int>(jobs.size()));

 #ifndef ROCKSDB_LITE
@@ -421,18 +428,36 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
  if (logfile_number_ > 0) {
    // TODO (yanqin) investigate whether we should sync the closed logs for
    // single column family case.
-    io_s = SyncClosedLogs(job_context);
-    s = io_s;
+    log_io_s = SyncClosedLogs(job_context);
+    if (!log_io_s.ok() && !log_io_s.IsShutdownInProgress() &&
+        !log_io_s.IsColumnFamilyDropped()) {
+      if (total_log_size_ > 0) {
+        error_handler_.SetBGError(log_io_s, BackgroundErrorReason::kFlush);
+      } else {
+        // If the WAL is empty, we use different error reason
+        error_handler_.SetBGError(log_io_s, BackgroundErrorReason::kFlushNoWAL);
+      }
+    }
  }
+  s = log_io_s;

  // exec_status stores the execution status of flush_jobs as
  // <bool /* executed */, Status /* status code */>
  autovector<std::pair<bool, Status>> exec_status;
  autovector<IOStatus> io_status;
+  std::vector<bool> pick_status;
  for (int i = 0; i != num_cfs; ++i) {
    // Initially all jobs are not executed, with status OK.
    exec_status.emplace_back(false, Status::OK());
    io_status.emplace_back(IOStatus::OK());
+    pick_status.push_back(false);
+  }
+
+  if (s.ok()) {
+    for (int i = 0; i != num_cfs; ++i) {
+      jobs[i]->PickMemTable();
+      pick_status[i] = true;
+    }
  }

  if (s.ok()) {
@@ -473,6 +498,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
    s = error_status.ok() ? s : error_status;
  }

+  IOStatus io_s = IOStatus::OK();
  if (io_s.ok()) {
    IOStatus io_error = IOStatus::OK();
    for (int i = 0; i != static_cast<int>(io_status.size()); i++) {
@@ -508,12 +534,12 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
    // Have to cancel the flush jobs that have NOT executed because we need to
    // unref the versions.
    for (int i = 0; i != num_cfs; ++i) {
-      if (!exec_status[i].first) {
+      if (pick_status[i] && !exec_status[i].first) {
        jobs[i]->Cancel();
      }
    }
    for (int i = 0; i != num_cfs; ++i) {
-      if (exec_status[i].first && exec_status[i].second.ok()) {
+      if (exec_status[i].second.ok() && exec_status[i].first) {
        auto& mems = jobs[i]->GetMemTables();
        cfds[i]->imm()->RollbackMemtableFlush(mems,
                                              file_meta[i].fd.GetNumber());
@@ -652,29 +678,30 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
  // it is not because of CF drop.
  if (!s.ok() && !s.IsColumnFamilyDropped()) {
    if (!io_s.ok() && !io_s.IsColumnFamilyDropped()) {
+      assert(log_io_s.ok());
      // Error while writing to MANIFEST.
      // In fact, versions_->io_status() can also be the result of renaming
      // CURRENT file. With current code, it's just difficult to tell. So just
      // be pessimistic and try write to a new MANIFEST.
      // TODO: distinguish between MANIFEST write and CURRENT renaming
      if (!versions_->io_status().ok()) {
-        if (total_log_size_ > 0) {
-          // If the WAL is empty, we use different error reason
-          error_handler_.SetBGError(io_s,
-                                    BackgroundErrorReason::kManifestWrite);
-        } else {
-          error_handler_.SetBGError(io_s,
-                                    BackgroundErrorReason::kManifestWriteNoWAL);
-        }
-      } else if (total_log_size_ > 0) {
-        error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
+        // If WAL sync is successful (either WAL size is 0 or there is no IO
+        // error), all the Manifest write will be map to soft error.
+        // TODO: kManifestWriteNoWAL and kFlushNoWAL are misleading. Refactor
+        // is needed.
+        error_handler_.SetBGError(io_s,
+                                  BackgroundErrorReason::kManifestWriteNoWAL);
      } else {
-        // If the WAL is empty, we use different error reason
+        // If WAL sync is successful (either WAL size is 0 or there is no IO
+        // error), all the other SST file write errors will be set as
+        // kFlushNoWAL.
        error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlushNoWAL);
      }
    } else {
-      Status new_bg_error = s;
-      error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
+      if (log_io_s.ok()) {
+        Status new_bg_error = s;
+        error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
+      }
    }
  }

@@ -806,6 +833,25 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
                              end_with_ts);
 }

+Status DBImpl::IncreaseFullHistoryTsLow(ColumnFamilyData* cfd,
+                                        std::string ts_low) {
+  VersionEdit edit;
+  edit.SetColumnFamily(cfd->GetID());
+  edit.SetFullHistoryTsLow(ts_low);
+
+  InstrumentedMutexLock l(&mutex_);
+  std::string current_ts_low = cfd->GetFullHistoryTsLow();
+  const Comparator* ucmp = cfd->user_comparator();
+  if (!current_ts_low.empty() &&
+      ucmp->CompareTimestamp(ts_low, current_ts_low) < 0) {
+    return Status::InvalidArgument(
+        "Cannot decrease full_history_timestamp_low");
+  }
+
+  return versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(), &edit,
+                                &mutex_);
+}
+
 Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
                                    ColumnFamilyHandle* column_family,
                                    const Slice* begin, const Slice* end) {
@@ -817,6 +863,22 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
  }

  bool flush_needed = true;
+
+  // Update full_history_ts_low if it's set
+  if (options.full_history_ts_low != nullptr &&
+      !options.full_history_ts_low->empty()) {
+    std::string ts_low = options.full_history_ts_low->ToString();
+    if (begin != nullptr || end != nullptr) {
+      return Status::InvalidArgument(
+          "Cannot specify compaction range with full_history_ts_low");
+    }
+    Status s = IncreaseFullHistoryTsLow(cfd, ts_low);
+    if (!s.ok()) {
+      LogFlush(immutable_db_options_.info_log);
+      return s;
+    }
+  }
+
  Status s;
  if (begin != nullptr && end != nullptr) {
    // TODO(ajkr): We could also optimize away the flush in certain cases where
@@ -1679,6 +1741,7 @@ Status DBImpl::RunManualCompaction(
      }
      ca = new CompactionArg;
      ca->db = this;
+      ca->compaction_pri_ = Env::Priority::LOW;
      ca->prepicked_compaction = new PrepickedCompaction;
      ca->prepicked_compaction->manual_compaction_state = &manual;
      ca->prepicked_compaction->compaction = compaction;
@@ -2026,12 +2089,12 @@ Status DBImpl::WaitUntilFlushWouldNotStallWrites(ColumnFamilyData* cfd,
      // check whether one extra immutable memtable or an extra L0 file would
      // cause write stalling mode to be entered. It could still enter stall
      // mode due to pending compaction bytes, but that's less common
-      write_stall_condition =
-          ColumnFamilyData::GetWriteStallConditionAndCause(
-              cfd->imm()->NumNotFlushed() + 1,
-              vstorage->l0_delay_trigger_count() + 1,
-              vstorage->estimated_compaction_needed_bytes(), mutable_cf_options)
-              .first;
+      write_stall_condition = ColumnFamilyData::GetWriteStallConditionAndCause(
+                                  cfd->imm()->NumNotFlushed() + 1,
+                                  vstorage->l0_delay_trigger_count() + 1,
+                                  vstorage->estimated_compaction_needed_bytes(),
+                                  mutable_cf_options, *cfd->ioptions())
+                                  .first;
    } while (write_stall_condition != WriteStallCondition::kNormal);
  }
  return Status::OK();
@@ -2210,6 +2273,7 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
         unscheduled_compactions_ > 0) {
    CompactionArg* ca = new CompactionArg;
    ca->db = this;
+    ca->compaction_pri_ = Env::Priority::LOW;
    ca->prepicked_compaction = nullptr;
    bg_compaction_scheduled_++;
    unscheduled_compactions_--;
@@ -2397,7 +2461,16 @@ void DBImpl::BGWorkPurge(void* db) {
 }

 void DBImpl::UnscheduleCompactionCallback(void* arg) {
-  CompactionArg ca = *(reinterpret_cast<CompactionArg*>(arg));
+  CompactionArg* ca_ptr = reinterpret_cast<CompactionArg*>(arg);
+  Env::Priority compaction_pri = ca_ptr->compaction_pri_;
+  if (Env::Priority::BOTTOM == compaction_pri) {
+    // Decrement bg_bottom_compaction_scheduled_ if priority is BOTTOM
+    ca_ptr->db->bg_bottom_compaction_scheduled_--;
+  } else if (Env::Priority::LOW == compaction_pri) {
+    // Decrement bg_compaction_scheduled_ if priority is LOW
+    ca_ptr->db->bg_compaction_scheduled_--;
+  }
+  CompactionArg ca = *(ca_ptr);
  delete reinterpret_cast<CompactionArg*>(arg);
  if (ca.prepicked_compaction != nullptr) {
    if (ca.prepicked_compaction->compaction != nullptr) {
@@ -2409,6 +2482,14 @@ void DBImpl::UnscheduleCompactionCallback(void* arg) {
 }

 void DBImpl::UnscheduleFlushCallback(void* arg) {
+  // Decrement bg_flush_scheduled_ in flush callback
+  reinterpret_cast<FlushThreadArg*>(arg)->db_->bg_flush_scheduled_--;
+  Env::Priority flush_pri = reinterpret_cast<FlushThreadArg*>(arg)->thread_pri_;
+  if (Env::Priority::LOW == flush_pri) {
+    TEST_SYNC_POINT("DBImpl::UnscheduleLowFlushCallback");
+  } else if (Env::Priority::HIGH == flush_pri) {
+    TEST_SYNC_POINT("DBImpl::UnscheduleHighFlushCallback");
+  }
  delete reinterpret_cast<FlushThreadArg*>(arg);
  TEST_SYNC_POINT("DBImpl::UnscheduleFlushCallback");
 }
@@ -2529,7 +2610,7 @@ void DBImpl::BackgroundCallFlush(Env::Priority thread_pri) {
                      s.ToString().c_str(), error_cnt);
      log_buffer.FlushBufferToLog();
      LogFlush(immutable_db_options_.info_log);
-      env_->SleepForMicroseconds(1000000);
+      immutable_db_options_.clock->SleepForMicroseconds(1000000);
      mutex_.Lock();
    }

@@ -2602,7 +2683,8 @@ void DBImpl::BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
    if (s.IsBusy()) {
      bg_cv_.SignalAll();  // In case a waiter can proceed despite the error
      mutex_.Unlock();
-      env_->SleepForMicroseconds(10000);  // prevent hot loop
+      immutable_db_options_.clock->SleepForMicroseconds(
+          10000);  // prevent hot loop
      mutex_.Lock();
    } else if (!s.ok() && !s.IsShutdownInProgress() &&
               !s.IsManualCompactionPaused() && !s.IsColumnFamilyDropped()) {
@@ -2620,7 +2702,7 @@ void DBImpl::BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
                      "Accumulated background error counts: %" PRIu64,
                      s.ToString().c_str(), error_cnt);
      LogFlush(immutable_db_options_.info_log);
-      env_->SleepForMicroseconds(1000000);
+      immutable_db_options_.clock->SleepForMicroseconds(1000000);
      mutex_.Lock();
    } else if (s.IsManualCompactionPaused()) {
      ManualCompactionState* m = prepicked_compaction->manual_compaction_state;
@@ -3010,6 +3092,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    TEST_SYNC_POINT("DBImpl::BackgroundCompaction:ForwardToBottomPriPool");
    CompactionArg* ca = new CompactionArg;
    ca->db = this;
+    ca->compaction_pri_ = Env::Priority::BOTTOM;
    ca->prepicked_compaction = new PrepickedCompaction;
    ca->prepicked_compaction->compaction = c.release();
    ca->prepicked_compaction->manual_compaction_state = nullptr;
@@ -177,6 +177,11 @@ Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
  return error_handler_.GetBGError();
 }

+Status DBImpl::TEST_GetBGError() {
+  InstrumentedMutexLock l(&mutex_);
+  return error_handler_.GetBGError();
+}
+
 void DBImpl::TEST_LockMutex() { mutex_.Lock(); }

 void DBImpl::TEST_UnlockMutex() { mutex_.Unlock(); }
@@ -120,7 +120,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
             mutable_db_options_.delete_obsolete_files_period_micros == 0) {
    doing_the_full_scan = true;
  } else {
-    const uint64_t now_micros = env_->NowMicros();
+    const uint64_t now_micros = immutable_db_options_.clock->NowMicros();
    if ((delete_obsolete_files_last_run_ +
         mutable_db_options_.delete_obsolete_files_period_micros) <
        now_micros) {
@@ -854,7 +854,7 @@ uint64_t PrecomputeMinLogNumberToKeep2PC(
  return min_log_number_to_keep;
 }

-Status DBImpl::SetDBId() {
+Status DBImpl::SetDBId(bool read_only) {
  Status s;
  // Happens when immutable_db_options_.write_dbid_to_manifest is set to true
  // the very first time.
@@ -865,9 +865,15 @@ Status DBImpl::SetDBId() {
    // it is no longer available then at this point DB ID is not in Identity
    // file or Manifest.
    if (s.IsNotFound()) {
-      s = SetIdentityFile(env_, dbname_);
-      if (!s.ok()) {
-        return s;
+      // Create a new DB ID, saving to file only if allowed
+      if (read_only) {
+        db_id_ = env_->GenerateUniqueId();
+        return Status::OK();
+      } else {
+        s = SetIdentityFile(env_, dbname_);
+        if (!s.ok()) {
+          return s;
+        }
      }
    } else if (!s.ok()) {
      assert(s.IsIOError());
@@ -884,7 +890,7 @@ Status DBImpl::SetDBId() {
                                 mutable_cf_options, &edit, &mutex_, nullptr,
                                 /* new_descriptor_log */ false);
    }
-  } else {
+  } else if (!read_only) {
    s = SetIdentityFile(env_, dbname_, db_id_);
  }
  return s;
@@ -24,15 +24,17 @@
 #include "util/rate_limiter.h"

 namespace ROCKSDB_NAMESPACE {
-Options SanitizeOptions(const std::string& dbname, const Options& src) {
-  auto db_options = SanitizeOptions(dbname, DBOptions(src));
+Options SanitizeOptions(const std::string& dbname, const Options& src,
+                        bool read_only) {
+  auto db_options = SanitizeOptions(dbname, DBOptions(src), read_only);
  ImmutableDBOptions immutable_db_options(db_options);
  auto cf_options =
      SanitizeOptions(immutable_db_options, ColumnFamilyOptions(src));
  return Options(db_options, cf_options);
 }

-DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
+DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src,
+                          bool read_only) {
  DBOptions result(src);

  if (result.env == nullptr) {
@@ -50,7 +52,7 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
                             &result.max_open_files);
  }

-  if (result.info_log == nullptr) {
+  if (result.info_log == nullptr && !read_only) {
    Status s = CreateLoggerFromOptions(dbname, result, &result.info_log);
    if (!s.ok()) {
      // No place suitable for logging
@@ -175,7 +177,7 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
        NewSstFileManager(result.env, result.info_log));
    result.sst_file_manager = sst_file_manager;
  }
-#endif
+#endif  // !ROCKSDB_LITE

  if (!result.paranoid_checks) {
    result.skip_checking_sst_file_sizes_on_db_open = true;
@@ -289,17 +291,19 @@ Status DBImpl::NewDB(std::vector<std::string>* new_filenames) {
    if (!s.ok()) {
      return s;
    }
+    FileTypeSet tmp_set = immutable_db_options_.checksum_handoff_file_types;
    file->SetPreallocationBlockSize(
        immutable_db_options_.manifest_preallocation_size);
    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-        std::move(file), manifest, file_options, env_, io_tracer_,
-        nullptr /* stats */, immutable_db_options_.listeners));
+        std::move(file), manifest, file_options, immutable_db_options_.clock,
+        io_tracer_, nullptr /* stats */, immutable_db_options_.listeners,
+        nullptr, tmp_set.Contains(FileType::kDescriptorFile)));
    log::Writer log(std::move(file_writer), 0, false);
    std::string record;
    new_db.EncodeTo(&record);
    s = log.AddRecord(record);
    if (s.ok()) {
-      s = SyncManifest(env_, &immutable_db_options_, log.file());
+      s = SyncManifest(&immutable_db_options_, log.file());
    }
  }
  if (s.ok()) {
@@ -486,7 +490,7 @@ Status DBImpl::Recover(
  if (!s.ok()) {
    return s;
  }
-  s = SetDBId();
+  s = SetDBId(read_only);
  if (s.ok() && !read_only) {
    s = DeleteUnreferencedSstFiles();
  }
@@ -1227,8 +1231,16 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
    }
  }

-  if (status.ok() && data_seen && !flushed) {
-    status = RestoreAliveLogFiles(wal_numbers);
+  if (status.ok()) {
+    if (data_seen && !flushed) {
+      status = RestoreAliveLogFiles(wal_numbers);
+    } else {
+      // If there's no data in the WAL, or we flushed all the data, still
+      // truncate the log file. If the process goes into a crash loop before
+      // the file is deleted, the preallocated space will never get freed.
+      GetLogSizeAndMaybeTruncate(wal_numbers.back(), true, nullptr)
+          .PermitUncheckedError();
+    }
  }

  event_logger_.Log() << "job" << job_id << "event"
@@ -1237,6 +1249,40 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
  return status;
 }

+Status DBImpl::GetLogSizeAndMaybeTruncate(uint64_t wal_number, bool truncate,
+                                          LogFileNumberSize* log_ptr) {
+  LogFileNumberSize log(wal_number);
+  std::string fname = LogFileName(immutable_db_options_.wal_dir, wal_number);
+  Status s;
+  // This gets the appear size of the wals, not including preallocated space.
+  s = env_->GetFileSize(fname, &log.size);
+  if (s.ok() && truncate) {
+    std::unique_ptr<FSWritableFile> last_log;
+    Status truncate_status = fs_->ReopenWritableFile(
+        fname,
+        fs_->OptimizeForLogWrite(
+            file_options_,
+            BuildDBOptions(immutable_db_options_, mutable_db_options_)),
+        &last_log, nullptr);
+    if (truncate_status.ok()) {
+      truncate_status = last_log->Truncate(log.size, IOOptions(), nullptr);
+    }
+    if (truncate_status.ok()) {
+      truncate_status = last_log->Close(IOOptions(), nullptr);
+    }
+    // Not a critical error if fail to truncate.
+    if (!truncate_status.ok()) {
+      ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                     "Failed to truncate log #%" PRIu64 ": %s", wal_number,
+                     truncate_status.ToString().c_str());
+    }
+  }
+  if (log_ptr) {
+    *log_ptr = log;
+  }
+  return s;
+}
+
 Status DBImpl::RestoreAliveLogFiles(const std::vector<uint64_t>& wal_numbers) {
  if (wal_numbers.empty()) {
    return Status::OK();
@@ -1252,39 +1298,17 @@ Status DBImpl::RestoreAliveLogFiles(const std::vector<uint64_t>& wal_numbers) {
  total_log_size_ = 0;
  log_empty_ = false;
  for (auto wal_number : wal_numbers) {
-    LogFileNumberSize log(wal_number);
-    std::string fname = LogFileName(immutable_db_options_.wal_dir, wal_number);
-    // This gets the appear size of the wals, not including preallocated space.
-    s = env_->GetFileSize(fname, &log.size);
+    // We preallocate space for wals, but then after a crash and restart, those
+    // preallocated space are not needed anymore. It is likely only the last
+    // log has such preallocated space, so we only truncate for the last log.
+    LogFileNumberSize log;
+    s = GetLogSizeAndMaybeTruncate(
+        wal_number, /*truncate=*/(wal_number == wal_numbers.back()), &log);
    if (!s.ok()) {
      break;
    }
    total_log_size_ += log.size;
    alive_log_files_.push_back(log);
-    // We preallocate space for wals, but then after a crash and restart, those
-    // preallocated space are not needed anymore. It is likely only the last
-    // log has such preallocated space, so we only truncate for the last log.
-    if (wal_number == wal_numbers.back()) {
-      std::unique_ptr<FSWritableFile> last_log;
-      Status truncate_status = fs_->ReopenWritableFile(
-          fname,
-          fs_->OptimizeForLogWrite(
-              file_options_,
-              BuildDBOptions(immutable_db_options_, mutable_db_options_)),
-          &last_log, nullptr);
-      if (truncate_status.ok()) {
-        truncate_status = last_log->Truncate(log.size, IOOptions(), nullptr);
-      }
-      if (truncate_status.ok()) {
-        truncate_status = last_log->Close(IOOptions(), nullptr);
-      }
-      // Not a critical error if fail to truncate.
-      if (!truncate_status.ok()) {
-        ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                       "Failed to truncate log #%" PRIu64 ": %s", wal_number,
-                       truncate_status.ToString().c_str());
-      }
-    }
  }
  if (two_write_queues_) {
    log_write_mutex_.Unlock();
@@ -1295,7 +1319,7 @@ Status DBImpl::RestoreAliveLogFiles(const std::vector<uint64_t>& wal_numbers) {
 Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                                           MemTable* mem, VersionEdit* edit) {
  mutex_.AssertHeld();
-  const uint64_t start_micros = env_->NowMicros();
+  const uint64_t start_micros = immutable_db_options_.clock->NowMicros();

  FileMetaData meta;
  std::vector<BlobFileAddition> blob_file_additions;
@@ -1323,7 +1347,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
        cfd->GetLatestMutableCFOptions()->paranoid_file_checks;

    int64_t _current_time = 0;
-    env_->GetCurrentTime(&_current_time)
+    immutable_db_options_.clock->GetCurrentTime(&_current_time)
        .PermitUncheckedError();  // ignore error
    const uint64_t current_time = static_cast<uint64_t>(_current_time);
    meta.oldest_ancester_time = current_time;
@@ -1356,13 +1380,13 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
          cfd->GetID(), cfd->GetName(), snapshot_seqs,
          earliest_write_conflict_snapshot, snapshot_checker,
          GetCompressionFlush(*cfd->ioptions(), mutable_cf_options),
-          mutable_cf_options.sample_for_compression,
          mutable_cf_options.compression_opts, paranoid_file_checks,
          cfd->internal_stats(), TableFileCreationReason::kRecovery, &io_s,
          io_tracer_, &event_logger_, job_id, Env::IO_HIGH,
          nullptr /* table_properties */, -1 /* level */, current_time,
          0 /* oldest_key_time */, write_hint, 0 /* file_creation_time */,
-          db_id_, db_session_id_);
+          db_id_, db_session_id_, nullptr /*full_history_ts_low*/,
+          &blob_callback_);
      LogFlush(immutable_db_options_.info_log);
      ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
                      "[%s] [WriteLevel0TableForRecovery]"
@@ -1391,11 +1415,13 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                  meta.oldest_ancester_time, meta.file_creation_time,
                  meta.file_checksum, meta.file_checksum_func_name);

-    edit->SetBlobFileAdditions(std::move(blob_file_additions));
+    for (const auto& blob : blob_file_additions) {
+      edit->AddBlobFile(blob);
+    }
  }

  InternalStats::CompactionStats stats(CompactionReason::kFlush, 1);
-  stats.micros = env_->NowMicros() - start_micros;
+  stats.micros = immutable_db_options_.clock->NowMicros() - start_micros;

  if (has_output) {
    stats.bytes_written = meta.fd.GetFileSize();
@@ -1404,14 +1430,15 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,

  const auto& blobs = edit->GetBlobFileAdditions();
  for (const auto& blob : blobs) {
-    stats.bytes_written += blob.GetTotalBlobBytes();
+    stats.bytes_written_blob += blob.GetTotalBlobBytes();
  }

-  stats.num_output_files += static_cast<int>(blobs.size());
+  stats.num_output_files_blob = static_cast<int>(blobs.size());

  cfd->internal_stats()->AddCompactionStats(level, Env::Priority::USER, stats);
-  cfd->internal_stats()->AddCFStats(InternalStats::BYTES_FLUSHED,
-                                    stats.bytes_written);
+  cfd->internal_stats()->AddCFStats(
+      InternalStats::BYTES_FLUSHED,
+      stats.bytes_written + stats.bytes_written_blob);
  RecordTick(stats_, COMPACT_WRITE_BYTES, meta.fd.GetFileSize());
  return s;
 }
@@ -1485,9 +1512,11 @@ IOStatus DBImpl::CreateWAL(uint64_t log_file_num, uint64_t recycle_log_number,
    lfile->SetPreallocationBlockSize(preallocate_block_size);

    const auto& listeners = immutable_db_options_.listeners;
+    FileTypeSet tmp_set = immutable_db_options_.checksum_handoff_file_types;
    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-        std::move(lfile), log_fname, opt_file_options, env_, io_tracer_,
-        nullptr /* stats */, listeners));
+        std::move(lfile), log_fname, opt_file_options,
+        immutable_db_options_.clock, io_tracer_, nullptr /* stats */, listeners,
+        nullptr, tmp_set.Contains(FileType::kWalFile)));
    *new_log = new log::Writer(std::move(file_writer), log_file_num,
                               immutable_db_options_.recycle_log_file_num > 0,
                               immutable_db_options_.manual_wal_flush);
@@ -1716,6 +1745,8 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,

    std::vector<LiveFileMetaData> metadata;

+    // TODO: Once GetLiveFilesMetaData supports blob files, update the logic
+    // below to get known_file_sizes for blob files.
    impl->mutex_.Lock();
    impl->versions_->GetLiveFilesMetaData(&metadata);
    impl->mutex_.Unlock();
@@ -1748,13 +1779,12 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
        FileType file_type;
        std::string file_path = path + "/" + file_name;
        if (ParseFileName(file_name, &file_number, &file_type) &&
-            file_type == kTableFile) {
+            (file_type == kTableFile || file_type == kBlobFile)) {
          // TODO: Check for errors from OnAddFile?
          if (known_file_sizes.count(file_name)) {
            // We're assuming that each sst file name exists in at most one of
            // the paths.
-            sfm->OnAddFile(file_path, known_file_sizes.at(file_name),
-                           /* compaction */ false)
+            sfm->OnAddFile(file_path, known_file_sizes.at(file_name))
                .PermitUncheckedError();
          } else {
            sfm->OnAddFile(file_path).PermitUncheckedError();
@@ -6,7 +6,7 @@
 #include "db/db_impl/db_impl_readonly.h"

 #include "db/arena_wrapped_db_iter.h"
-#include "db/compacted_db_impl.h"
+#include "db/db_impl/compacted_db_impl.h"
 #include "db/db_impl/db_impl.h"
 #include "db/db_iter.h"
 #include "db/merge_context.h"
@@ -19,7 +19,8 @@ namespace ROCKSDB_NAMESPACE {

 DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
                               const std::string& dbname)
-    : DBImpl(db_options, dbname) {
+    : DBImpl(db_options, dbname, /*seq_per_batch*/ false,
+             /*batch_per_txn*/ true, /*read_only*/ true) {
  ROCKS_LOG_INFO(immutable_db_options_.info_log,
                 "Opening the db in read only mode");
  LogFlush(immutable_db_options_.info_log);
@@ -131,8 +132,8 @@ Status DBImplReadOnly::NewIterators(
 }

 namespace {
-// Return OK if dbname exists in the file system
-// or create_if_missing is false
+// Return OK if dbname exists in the file system or create it if
+// create_if_missing
 Status OpenForReadOnlyCheckExistence(const DBOptions& db_options,
                                     const std::string& dbname) {
  Status s;
@@ -143,9 +144,9 @@ Status OpenForReadOnlyCheckExistence(const DBOptions& db_options,
    uint64_t manifest_file_number;
    s = VersionSet::GetCurrentManifestPath(dbname, fs.get(), &manifest_path,
                                           &manifest_file_number);
-    if (!s.ok()) {
-      return Status::NotFound(CurrentFileName(dbname), "does not exist");
-    }
+  } else {
+    // Historic behavior that doesn't necessarily make sense
+    s = db_options.env->CreateDirIfMissing(dbname);
  }
  return s;
 }
@@ -153,7 +154,6 @@ Status OpenForReadOnlyCheckExistence(const DBOptions& db_options,

 Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
                           DB** dbptr, bool /*error_if_wal_file_exists*/) {
-  // If dbname does not exist in the file system, should not do anything
  Status s = OpenForReadOnlyCheckExistence(options, dbname);
  if (!s.ok()) {
    return s;
@@ -327,8 +327,8 @@ 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_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
+  StopWatch sw(immutable_db_options_.clock, stats_, DB_GET);
  PERF_TIMER_GUARD(get_snapshot_time);

  auto cfh = static_cast<ColumnFamilyHandleImpl*>(column_family);
@@ -519,7 +519,8 @@ Status DBImplSecondary::TryCatchUpWithPrimary() {
  {
    InstrumentedMutexLock lock_guard(&mutex_);
    s = static_cast_with_check<ReactiveVersionSet>(versions_.get())
-            ->ReadAndApply(&mutex_, &manifest_reader_, &cfds_changed);
+            ->ReadAndApply(&mutex_, &manifest_reader_,
+                           manifest_reader_status_.get(), &cfds_changed);

    ROCKS_LOG_INFO(immutable_db_options_.info_log, "Last sequence is %" PRIu64,
                   static_cast<uint64_t>(versions_->LastSequence()));
@@ -160,7 +160,8 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
    RecordTick(stats_, WRITE_WITH_WAL);
  }

-  StopWatch write_sw(env_, immutable_db_options_.statistics.get(), DB_WRITE);
+  StopWatch write_sw(immutable_db_options_.clock,
+                     immutable_db_options_.statistics.get(), DB_WRITE);

  write_thread_.JoinBatchGroup(&w);
  if (w.state == WriteThread::STATE_PARALLEL_MEMTABLE_WRITER) {
@@ -465,7 +466,8 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
                                  uint64_t* log_used, uint64_t log_ref,
                                  bool disable_memtable, uint64_t* seq_used) {
  PERF_TIMER_GUARD(write_pre_and_post_process_time);
-  StopWatch write_sw(env_, immutable_db_options_.statistics.get(), DB_WRITE);
+  StopWatch write_sw(immutable_db_options_.clock,
+                     immutable_db_options_.statistics.get(), DB_WRITE);

  WriteContext write_context;

@@ -621,7 +623,8 @@ Status DBImpl::UnorderedWriteMemtable(const WriteOptions& write_options,
                                      SequenceNumber seq,
                                      const size_t sub_batch_cnt) {
  PERF_TIMER_GUARD(write_pre_and_post_process_time);
-  StopWatch write_sw(env_, immutable_db_options_.statistics.get(), DB_WRITE);
+  StopWatch write_sw(immutable_db_options_.clock,
+                     immutable_db_options_.statistics.get(), DB_WRITE);

  WriteThread::Writer w(write_options, my_batch, callback, log_ref,
                        false /*disable_memtable*/);
@@ -676,7 +679,8 @@ Status DBImpl::WriteImplWALOnly(
  WriteThread::Writer w(write_options, my_batch, callback, log_ref,
                        disable_memtable, sub_batch_cnt, pre_release_callback);
  RecordTick(stats_, WRITE_WITH_WAL);
-  StopWatch write_sw(env_, immutable_db_options_.statistics.get(), DB_WRITE);
+  StopWatch write_sw(immutable_db_options_.clock,
+                     immutable_db_options_.statistics.get(), DB_WRITE);

  write_thread->JoinBatchGroup(&w);
  assert(w.state != WriteThread::STATE_PARALLEL_MEMTABLE_WRITER);
@@ -1093,7 +1097,7 @@ IOStatus DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
  }

  if (io_s.ok() && need_log_sync) {
-    StopWatch sw(env_, stats_, WAL_FILE_SYNC_MICROS);
+    StopWatch sw(immutable_db_options_.clock, stats_, WAL_FILE_SYNC_MICROS);
    // It's safe to access logs_ with unlocked mutex_ here because:
    //  - we've set getting_synced=true for all logs,
    //    so other threads won't pop from logs_ while we're here,
@@ -1457,8 +1461,10 @@ Status DBImpl::DelayWrite(uint64_t num_bytes,
  uint64_t time_delayed = 0;
  bool delayed = false;
  {
-    StopWatch sw(env_, stats_, WRITE_STALL, &time_delayed);
-    uint64_t delay = write_controller_.GetDelay(env_, num_bytes);
+    StopWatch sw(immutable_db_options_.clock, stats_, WRITE_STALL,
+                 &time_delayed);
+    uint64_t delay =
+        write_controller_.GetDelay(immutable_db_options_.clock, num_bytes);
    if (delay > 0) {
      if (write_options.no_slowdown) {
        return Status::Incomplete("Write stall");
@@ -1470,19 +1476,21 @@ Status DBImpl::DelayWrite(uint64_t num_bytes,
      write_thread_.BeginWriteStall();
      TEST_SYNC_POINT("DBImpl::DelayWrite:BeginWriteStallDone");
      mutex_.Unlock();
-      // We will delay the write until we have slept for delay ms or
-      // we don't need a delay anymore
-      const uint64_t kDelayInterval = 1000;
+      // We will delay the write until we have slept for `delay` microseconds
+      // or we don't need a delay anymore. We check for cancellation every 1ms
+      // (slightly longer because WriteController minimum delay is 1ms, in
+      // case of sleep imprecision, rounding, etc.)
+      const uint64_t kDelayInterval = 1001;
      uint64_t stall_end = sw.start_time() + delay;
      while (write_controller_.NeedsDelay()) {
-        if (env_->NowMicros() >= stall_end) {
+        if (immutable_db_options_.clock->NowMicros() >= stall_end) {
          // We already delayed this write `delay` microseconds
          break;
        }

        delayed = true;
        // Sleep for 0.001 seconds
-        env_->SleepForMicroseconds(kDelayInterval);
+        immutable_db_options_.clock->SleepForMicroseconds(kDelayInterval);
      }
      mutex_.Lock();
      write_thread_.EndWriteStall();
@@ -64,9 +64,10 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
        break;
      case kWalFile:
        if (env->GetFileSize(dbname + "/" + file, &file_size).ok()) {
-          char str[16];
-          snprintf(str, sizeof(str), "%" PRIu64, file_size);
-          wal_info.append(file).append(" size: ").append(str).append(" ; ");
+          wal_info.append(file)
+              .append(" size: ")
+              .append(std::to_string(file_size))
+              .append(" ; ");
        } else {
          Error(options.info_log, "Error when reading LOG file: %s/%s\n",
                dbname.c_str(), file.c_str());
@@ -120,9 +121,10 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
      if (ParseFileName(file, &number, &type)) {
        if (type == kWalFile) {
          if (env->GetFileSize(options.wal_dir + "/" + file, &file_size).ok()) {
-            char str[16];
-            snprintf(str, sizeof(str), "%" PRIu64, file_size);
-            wal_info.append(file).append(" size: ").append(str).append(" ; ");
+            wal_info.append(file)
+                .append(" size: ")
+                .append(std::to_string(file_size))
+                .append(" ; ");
          } else {
            Error(options.info_log, "Error when reading LOG file %s/%s\n",
                  options.wal_dir.c_str(), file.c_str());
@@ -8,9 +8,10 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

 #include "db/db_iter.h"
-#include <string>
+
 #include <iostream>
 #include <limits>
+#include <string>

 #include "db/dbformat.h"
 #include "db/merge_context.h"
@@ -24,6 +25,7 @@
 #include "rocksdb/iterator.h"
 #include "rocksdb/merge_operator.h"
 #include "rocksdb/options.h"
+#include "rocksdb/system_clock.h"
 #include "table/internal_iterator.h"
 #include "table/iterator_wrapper.h"
 #include "trace_replay/trace_replay.h"
@@ -43,6 +45,7 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
               ColumnFamilyData* cfd, bool expose_blob_index)
    : prefix_extractor_(mutable_cf_options.prefix_extractor.get()),
      env_(_env),
+      clock_(_env->GetSystemClock().get()),
      logger_(cf_options.info_log),
      user_comparator_(cmp),
      merge_operator_(cf_options.merge_operator),
@@ -111,8 +114,7 @@ Status DBIter::GetProperty(std::string prop_name, std::string* prop) {
 }

 bool DBIter::ParseKey(ParsedInternalKey* ikey) {
-  Status s =
-      ParseInternalKey(iter_.key(), ikey, false /* log_err_key */);  // TODO
+  Status s = ParseInternalKey(iter_.key(), ikey, false /* log_err_key */);
  if (!s.ok()) {
    status_ = Status::Corruption("In DBIter: ", s.getState());
    valid_ = false;
@@ -127,7 +129,7 @@ void DBIter::Next() {
  assert(valid_);
  assert(status_.ok());

-  PERF_CPU_TIMER_GUARD(iter_next_cpu_nanos, env_);
+  PERF_CPU_TIMER_GUARD(iter_next_cpu_nanos, clock_);
  // Release temporarily pinned blocks from last operation
  ReleaseTempPinnedData();
  local_stats_.skip_count_ += num_internal_keys_skipped_;
@@ -190,8 +192,10 @@ bool DBIter::SetBlobValueIfNeeded(const Slice& user_key,
  read_options.read_tier = read_tier_;
  read_options.verify_checksums = verify_checksums_;

-  const Status s =
-      version_->GetBlob(read_options, user_key, blob_index, &blob_value_);
+  constexpr uint64_t* bytes_read = nullptr;
+
+  const Status s = version_->GetBlob(read_options, user_key, blob_index,
+                                     &blob_value_, bytes_read);

  if (!s.ok()) {
    status_ = s;
@@ -484,7 +488,7 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
              &last_key,
              ParsedInternalKey(saved_key_.GetUserKey(), 0, kTypeDeletion));
        } else {
-          const std::string kTsMin(timestamp_size_, static_cast<char>(0));
+          const std::string kTsMin(timestamp_size_, '\0');
          AppendInternalKeyWithDifferentTimestamp(
              &last_key,
              ParsedInternalKey(saved_key_.GetUserKey(), 0, kTypeDeletion),
@@ -574,7 +578,7 @@ bool DBIter::MergeValuesNewToOld() {
      const Slice val = iter_.value();
      Status s = MergeHelper::TimedFullMerge(
          merge_operator_, ikey.user_key, &val, merge_context_.GetOperands(),
-          &saved_value_, logger_, statistics_, env_, &pinned_value_, true);
+          &saved_value_, logger_, statistics_, clock_, &pinned_value_, true);
      if (!s.ok()) {
        valid_ = false;
        status_ = s;
@@ -617,7 +621,7 @@ bool DBIter::MergeValuesNewToOld() {
  // client can differentiate this scenario and do things accordingly.
  Status s = MergeHelper::TimedFullMerge(
      merge_operator_, saved_key_.GetUserKey(), nullptr,
-      merge_context_.GetOperands(), &saved_value_, logger_, statistics_, env_,
+      merge_context_.GetOperands(), &saved_value_, logger_, statistics_, clock_,
      &pinned_value_, true);
  if (!s.ok()) {
    valid_ = false;
@@ -630,17 +634,10 @@ bool DBIter::MergeValuesNewToOld() {
 }

 void DBIter::Prev() {
-  if (timestamp_size_ > 0) {
-    valid_ = false;
-    status_ = Status::NotSupported(
-        "SeekToLast/SeekForPrev/Prev currently not supported with timestamp.");
-    return;
-  }
-
  assert(valid_);
  assert(status_.ok());

-  PERF_CPU_TIMER_GUARD(iter_prev_cpu_nanos, env_);
+  PERF_CPU_TIMER_GUARD(iter_prev_cpu_nanos, clock_);
  ReleaseTempPinnedData();
  ResetInternalKeysSkippedCounter();
  bool ok = true;
@@ -675,9 +672,16 @@ bool DBIter::ReverseToForward() {
  // If that's the case, seek iter_ to current key.
  if (!expect_total_order_inner_iter() || !iter_.Valid()) {
    IterKey last_key;
-    last_key.SetInternalKey(ParsedInternalKey(
-        saved_key_.GetUserKey(), kMaxSequenceNumber, kValueTypeForSeek));
+    ParsedInternalKey pikey(saved_key_.GetUserKey(), kMaxSequenceNumber,
+                            kValueTypeForSeek);
+    if (timestamp_size_ > 0) {
+      // TODO: pre-create kTsMax.
+      const std::string kTsMax(timestamp_size_, '\xff');
+      pikey.SetTimestamp(kTsMax);
+    }
+    last_key.SetInternalKey(pikey);
    iter_.Seek(last_key.GetInternalKey());
+    RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
  }

  direction_ = kForward;
@@ -728,6 +732,7 @@ bool DBIter::ReverseToBackward() {
        iter_.SeekToLast();
      }
    }
+    RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
  }

  direction_ = kReverse;
@@ -753,11 +758,13 @@ void DBIter::PrevInternal(const Slice* prefix) {
    }

    assert(iterate_lower_bound_ == nullptr || iter_.MayBeOutOfLowerBound() ||
-           user_comparator_.Compare(saved_key_.GetUserKey(),
-                                    *iterate_lower_bound_) >= 0);
+           user_comparator_.CompareWithoutTimestamp(
+               saved_key_.GetUserKey(), /*a_has_ts=*/true,
+               *iterate_lower_bound_, /*b_has_ts=*/false) >= 0);
    if (iterate_lower_bound_ != nullptr && iter_.MayBeOutOfLowerBound() &&
-        user_comparator_.Compare(saved_key_.GetUserKey(),
-                                 *iterate_lower_bound_) < 0) {
+        user_comparator_.CompareWithoutTimestamp(
+            saved_key_.GetUserKey(), /*a_has_ts=*/true, *iterate_lower_bound_,
+            /*b_has_ts=*/false) < 0) {
      // We've iterated earlier than the user-specified lower bound.
      valid_ = false;
      return;
@@ -802,8 +809,8 @@ bool DBIter::FindValueForCurrentKey() {
  assert(iter_.Valid());
  merge_context_.Clear();
  current_entry_is_merged_ = false;
-  // last entry before merge (could be kTypeDeletion, kTypeSingleDeletion or
-  // kTypeValue)
+  // last entry before merge (could be kTypeDeletion,
+  // kTypeDeletionWithTimestamp, kTypeSingleDeletion or kTypeValue)
  ValueType last_not_merge_type = kTypeDeletion;
  ValueType last_key_entry_type = kTypeDeletion;

@@ -824,9 +831,13 @@ bool DBIter::FindValueForCurrentKey() {
                 timestamp_size_);
    }
    if (!IsVisible(ikey.sequence, ts) ||
-        !user_comparator_.Equal(ikey.user_key, saved_key_.GetUserKey())) {
+        !user_comparator_.EqualWithoutTimestamp(ikey.user_key,
+                                                saved_key_.GetUserKey())) {
      break;
    }
+    if (!ts.empty()) {
+      saved_timestamp_.assign(ts.data(), ts.size());
+    }
    if (TooManyInternalKeysSkipped()) {
      return false;
    }
@@ -866,6 +877,7 @@ bool DBIter::FindValueForCurrentKey() {
        }
        break;
      case kTypeDeletion:
+      case kTypeDeletionWithTimestamp:
      case kTypeSingleDeletion:
        merge_context_.Clear();
        last_not_merge_type = last_key_entry_type;
@@ -909,6 +921,7 @@ bool DBIter::FindValueForCurrentKey() {
  is_blob_ = false;
  switch (last_key_entry_type) {
    case kTypeDeletion:
+    case kTypeDeletionWithTimestamp:
    case kTypeSingleDeletion:
    case kTypeRangeDeletion:
      valid_ = false;
@@ -921,7 +934,7 @@ bool DBIter::FindValueForCurrentKey() {
        s = MergeHelper::TimedFullMerge(
            merge_operator_, saved_key_.GetUserKey(), nullptr,
            merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
-            env_, &pinned_value_, true);
+            clock_, &pinned_value_, true);
      } else if (last_not_merge_type == kTypeBlobIndex) {
        status_ =
            Status::NotSupported("BlobDB does not support merge operator.");
@@ -932,7 +945,7 @@ bool DBIter::FindValueForCurrentKey() {
        s = MergeHelper::TimedFullMerge(
            merge_operator_, saved_key_.GetUserKey(), &pinned_value_,
            merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
-            env_, &pinned_value_, true);
+            clock_, &pinned_value_, true);
      }
      break;
    case kTypeValue:
@@ -969,8 +982,17 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
  // FindValueForCurrentKeyUsingSeek()
  assert(pinned_iters_mgr_.PinningEnabled());
  std::string last_key;
-  AppendInternalKey(&last_key, ParsedInternalKey(saved_key_.GetUserKey(),
-                                                 sequence_, kValueTypeForSeek));
+  if (0 == timestamp_size_) {
+    AppendInternalKey(&last_key,
+                      ParsedInternalKey(saved_key_.GetUserKey(), sequence_,
+                                        kValueTypeForSeek));
+  } else {
+    AppendInternalKeyWithDifferentTimestamp(
+        &last_key,
+        ParsedInternalKey(saved_key_.GetUserKey(), sequence_,
+                          kValueTypeForSeek),
+        *timestamp_ub_);
+  }
  iter_.Seek(last_key);
  RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);

@@ -994,7 +1016,8 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
                 timestamp_size_);
    }

-    if (!user_comparator_.Equal(ikey.user_key, saved_key_.GetUserKey())) {
+    if (!user_comparator_.EqualWithoutTimestamp(ikey.user_key,
+                                                saved_key_.GetUserKey())) {
      // No visible values for this key, even though FindValueForCurrentKey()
      // has seen some. This is possible if we're using a tailing iterator, and
      // the entries were discarded in a compaction.
@@ -1011,7 +1034,8 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {

  if (ikey.type == kTypeDeletion || ikey.type == kTypeSingleDeletion ||
      range_del_agg_.ShouldDelete(
-          ikey, RangeDelPositioningMode::kBackwardTraversal)) {
+          ikey, RangeDelPositioningMode::kBackwardTraversal) ||
+      kTypeDeletionWithTimestamp == ikey.type) {
    valid_ = false;
    return true;
  }
@@ -1019,6 +1043,10 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
    valid_ = false;
    return false;
  }
+  if (timestamp_size_ > 0) {
+    Slice ts = ExtractTimestampFromUserKey(ikey.user_key, timestamp_size_);
+    saved_timestamp_.assign(ts.data(), ts.size());
+  }
  if (ikey.type == kTypeValue || ikey.type == kTypeBlobIndex) {
    assert(iter_.iter()->IsValuePinned());
    pinned_value_ = iter_.value();
@@ -1070,7 +1098,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
      Status s = MergeHelper::TimedFullMerge(
          merge_operator_, saved_key_.GetUserKey(), &val,
          merge_context_.GetOperands(), &saved_value_, logger_, statistics_,
-          env_, &pinned_value_, true);
+          clock_, &pinned_value_, true);
      if (!s.ok()) {
        valid_ = false;
        status_ = s;
@@ -1097,7 +1125,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {

  Status s = MergeHelper::TimedFullMerge(
      merge_operator_, saved_key_.GetUserKey(), nullptr,
-      merge_context_.GetOperands(), &saved_value_, logger_, statistics_, env_,
+      merge_context_.GetOperands(), &saved_value_, logger_, statistics_, clock_,
      &pinned_value_, true);
  if (!s.ok()) {
    valid_ = false;
@@ -1135,7 +1163,8 @@ bool DBIter::FindUserKeyBeforeSavedKey() {
      return false;
    }

-    if (user_comparator_.Compare(ikey.user_key, saved_key_.GetUserKey()) < 0) {
+    if (user_comparator_.CompareWithoutTimestamp(ikey.user_key,
+                                                 saved_key_.GetUserKey()) < 0) {
      return true;
    }

@@ -1159,8 +1188,14 @@ bool DBIter::FindUserKeyBeforeSavedKey() {
    if (num_skipped >= max_skip_) {
      num_skipped = 0;
      IterKey last_key;
-      last_key.SetInternalKey(ParsedInternalKey(
-          saved_key_.GetUserKey(), kMaxSequenceNumber, kValueTypeForSeek));
+      ParsedInternalKey pikey(saved_key_.GetUserKey(), kMaxSequenceNumber,
+                              kValueTypeForSeek);
+      if (timestamp_size_ > 0) {
+        // TODO: pre-create kTsMax.
+        const std::string kTsMax(timestamp_size_, '\xff');
+        pikey.SetTimestamp(kTsMax);
+      }
+      last_key.SetInternalKey(pikey);
      // It would be more efficient to use SeekForPrev() here, but some
      // iterators may not support it.
      iter_.Seek(last_key.GetInternalKey());
@@ -1237,24 +1272,50 @@ void DBIter::SetSavedKeyToSeekForPrevTarget(const Slice& target) {
  saved_key_.Clear();
  // now saved_key is used to store internal key.
  saved_key_.SetInternalKey(target, 0 /* sequence_number */,
-                            kValueTypeForSeekForPrev);
+                            kValueTypeForSeekForPrev, timestamp_ub_);
+
+  if (timestamp_size_ > 0) {
+    const std::string kTsMin(timestamp_size_, '\0');
+    Slice ts = kTsMin;
+    saved_key_.UpdateInternalKey(/*seq=*/0, kValueTypeForSeekForPrev, &ts);
+  }

  if (iterate_upper_bound_ != nullptr &&
-      user_comparator_.Compare(saved_key_.GetUserKey(),
-                               *iterate_upper_bound_) >= 0) {
+      user_comparator_.CompareWithoutTimestamp(
+          saved_key_.GetUserKey(), /*a_has_ts=*/true, *iterate_upper_bound_,
+          /*b_has_ts=*/false) >= 0) {
    saved_key_.Clear();
-    saved_key_.SetInternalKey(*iterate_upper_bound_, kMaxSequenceNumber);
+    saved_key_.SetInternalKey(*iterate_upper_bound_, kMaxSequenceNumber,
+                              kValueTypeForSeekForPrev, timestamp_ub_);
+    if (timestamp_size_ > 0) {
+      const std::string kTsMax(timestamp_size_, '\xff');
+      Slice ts = kTsMax;
+      saved_key_.UpdateInternalKey(kMaxSequenceNumber, kValueTypeForSeekForPrev,
+                                   &ts);
+    }
  }
 }

 void DBIter::Seek(const Slice& target) {
-  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, env_);
-  StopWatch sw(env_, statistics_, DB_SEEK);
+  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
+  StopWatch sw(clock_, statistics_, DB_SEEK);

 #ifndef ROCKSDB_LITE
  if (db_impl_ != nullptr && cfd_ != nullptr) {
    // TODO: What do we do if this returns an error?
-    db_impl_->TraceIteratorSeek(cfd_->GetID(), target).PermitUncheckedError();
+    Slice lower_bound, upper_bound;
+    if (iterate_lower_bound_ != nullptr) {
+      lower_bound = *iterate_lower_bound_;
+    } else {
+      lower_bound = Slice("");
+    }
+    if (iterate_upper_bound_ != nullptr) {
+      upper_bound = *iterate_upper_bound_;
+    } else {
+      upper_bound = Slice("");
+    }
+    db_impl_->TraceIteratorSeek(cfd_->GetID(), target, lower_bound, upper_bound)
+        .PermitUncheckedError();
  }
 #endif  // ROCKSDB_LITE

@@ -1282,7 +1343,7 @@ void DBIter::Seek(const Slice& target) {
  // we need to find out the next key that is visible to the user.
  ClearSavedValue();
  if (prefix_same_as_start_) {
-    // The case where the iterator needs to be invalidated if it has exausted
+    // The case where the iterator needs to be invalidated if it has exhausted
    // keys within the same prefix of the seek key.
    assert(prefix_extractor_ != nullptr);
    Slice target_prefix = prefix_extractor_->Transform(target);
@@ -1310,24 +1371,30 @@ void DBIter::Seek(const Slice& target) {
 }

 void DBIter::SeekForPrev(const Slice& target) {
-  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, env_);
-  StopWatch sw(env_, statistics_, DB_SEEK);
+  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
+  StopWatch sw(clock_, statistics_, DB_SEEK);

 #ifndef ROCKSDB_LITE
  if (db_impl_ != nullptr && cfd_ != nullptr) {
    // TODO: What do we do if this returns an error?
-    db_impl_->TraceIteratorSeekForPrev(cfd_->GetID(), target)
+    Slice lower_bound, upper_bound;
+    if (iterate_lower_bound_ != nullptr) {
+      lower_bound = *iterate_lower_bound_;
+    } else {
+      lower_bound = Slice("");
+    }
+    if (iterate_upper_bound_ != nullptr) {
+      upper_bound = *iterate_upper_bound_;
+    } else {
+      upper_bound = Slice("");
+    }
+    db_impl_
+        ->TraceIteratorSeekForPrev(cfd_->GetID(), target, lower_bound,
+                                   upper_bound)
        .PermitUncheckedError();
  }
 #endif  // ROCKSDB_LITE

-  if (timestamp_size_ > 0) {
-    valid_ = false;
-    status_ = Status::NotSupported(
-        "SeekToLast/SeekForPrev/Prev currently not supported with timestamp.");
-    return;
-  }
-
  status_ = Status::OK();
  ReleaseTempPinnedData();
  ResetInternalKeysSkippedCounter();
@@ -1351,7 +1418,7 @@ void DBIter::SeekForPrev(const Slice& target) {
  // backward direction.
  ClearSavedValue();
  if (prefix_same_as_start_) {
-    // The case where the iterator needs to be invalidated if it has exausted
+    // The case where the iterator needs to be invalidated if it has exhausted
    // keys within the same prefix of the seek key.
    assert(prefix_extractor_ != nullptr);
    Slice target_prefix = prefix_extractor_->Transform(target);
@@ -1378,7 +1445,7 @@ void DBIter::SeekToFirst() {
    Seek(*iterate_lower_bound_);
    return;
  }
-  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, env_);
+  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
  // Don't use iter_::Seek() if we set a prefix extractor
  // because prefix seek will be used.
  if (!expect_total_order_inner_iter()) {
@@ -1422,24 +1489,19 @@ void DBIter::SeekToFirst() {
 }

 void DBIter::SeekToLast() {
-  if (timestamp_size_ > 0) {
-    valid_ = false;
-    status_ = Status::NotSupported(
-        "SeekToLast/SeekForPrev/Prev currently not supported with timestamp.");
-    return;
-  }
-
  if (iterate_upper_bound_ != nullptr) {
    // Seek to last key strictly less than ReadOptions.iterate_upper_bound.
    SeekForPrev(*iterate_upper_bound_);
-    if (Valid() && user_comparator_.Equal(*iterate_upper_bound_, key())) {
+    if (Valid() && 0 == user_comparator_.CompareWithoutTimestamp(
+                            *iterate_upper_bound_, /*a_has_ts=*/false, key(),
+                            /*b_has_ts=*/false)) {
      ReleaseTempPinnedData();
      PrevInternal(nullptr);
    }
    return;
  }

-  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, env_);
+  PERF_CPU_TIMER_GUARD(iter_seek_cpu_nanos, clock_);
  // Don't use iter_::Seek() if we set a prefix extractor
  // because prefix seek will be used.
  if (!expect_total_order_inner_iter()) {
@@ -8,8 +8,9 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

 #pragma once
-#include <stdint.h>
+#include <cstdint>
 #include <string>
+
 #include "db/db_impl/db_impl.h"
 #include "db/dbformat.h"
 #include "db/range_del_aggregator.h"
@@ -21,7 +22,6 @@
 #include "util/autovector.h"

 namespace ROCKSDB_NAMESPACE {
-
 class Version;

 // This file declares the factory functions of DBIter, in its original form
@@ -68,7 +68,7 @@ class DBIter final : public Iterator {
  //        this->key().
  // (2) When moving backwards, the internal iterator is positioned
  //     just before all entries whose user key == this->key().
-  enum Direction { kForward, kReverse };
+  enum Direction : uint8_t { kForward, kReverse };

  // LocalStatistics contain Statistics counters that will be aggregated per
  // each iterator instance and then will be sent to the global statistics when
@@ -185,6 +185,9 @@ class DBIter final : public Iterator {
  Slice timestamp() const override {
    assert(valid_);
    assert(timestamp_size_ > 0);
+    if (direction_ == kReverse) {
+      return saved_timestamp_;
+    }
    const Slice ukey_and_ts = saved_key_.GetUserKey();
    assert(timestamp_size_ < ukey_and_ts.size());
    return ExtractTimestampFromUserKey(ukey_and_ts, timestamp_size_);
@@ -232,7 +235,7 @@ class DBIter final : public Iterator {
  // If `skipping_saved_key` is true, the function will keep iterating until it
  // finds a user key that is larger than `saved_key_`.
  // If `prefix` is not null, the iterator needs to stop when all keys for the
-  // prefix are exhausted and the interator is set to invalid.
+  // prefix are exhausted and the iterator is set to invalid.
  bool FindNextUserEntry(bool skipping_saved_key, const Slice* prefix);
  // Internal implementation of FindNextUserEntry().
  bool FindNextUserEntryInternal(bool skipping_saved_key, const Slice* prefix);
@@ -298,6 +301,7 @@ class DBIter final : public Iterator {

  const SliceTransform* prefix_extractor_;
  Env* const env_;
+  SystemClock* clock_;
  Logger* logger_;
  UserComparatorWrapper user_comparator_;
  const MergeOperator* const merge_operator_;
@@ -372,6 +376,7 @@ class DBIter final : public Iterator {
  const Slice* const timestamp_ub_;
  const Slice* const timestamp_lb_;
  const size_t timestamp_size_;
+  std::string saved_timestamp_;
 };

 // Return a new iterator that converts internal keys (yielded by
@@ -18,6 +18,7 @@
 #include "rocksdb/perf_context.h"
 #include "table/block_based/flush_block_policy.h"
 #include "util/random.h"
+#include "utilities/merge_operators/string_append/stringappend2.h"

 namespace ROCKSDB_NAMESPACE {

@@ -619,6 +620,40 @@ TEST_P(DBIteratorTest, IterReseek) {
  delete iter;
 }

+TEST_F(DBIteratorTest, ReseekUponDirectionChange) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.merge_operator.reset(
+      new StringAppendTESTOperator(/*delim_char=*/' '));
+  DestroyAndReopen(options);
+  ASSERT_OK(Put("foo", "value"));
+  ASSERT_OK(Put("bar", "value"));
+  {
+    std::unique_ptr<Iterator> it(db_->NewIterator(ReadOptions()));
+    it->SeekToLast();
+    it->Prev();
+    it->Next();
+  }
+  ASSERT_EQ(1,
+            options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
+
+  const std::string merge_key("good");
+  ASSERT_OK(Put(merge_key, "orig"));
+  ASSERT_OK(Merge(merge_key, "suffix"));
+  {
+    std::unique_ptr<Iterator> it(db_->NewIterator(ReadOptions()));
+    it->Seek(merge_key);
+    ASSERT_TRUE(it->Valid());
+    const uint64_t prev_reseek_count =
+        options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION);
+    it->Prev();
+    ASSERT_EQ(prev_reseek_count + 1, options.statistics->getTickerCount(
+                                         NUMBER_OF_RESEEKS_IN_ITERATION));
+  }
+}
+
 TEST_P(DBIteratorTest, IterSmallAndLargeMix) {
  do {
    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
@@ -1518,6 +1553,10 @@ TEST_P(DBIteratorTestForPinnedData, PinnedDataIteratorRandomizedFlush) {
  PinnedDataIteratorRandomized(TestConfig::FLUSH_EVERY_1000);
 }

+INSTANTIATE_TEST_CASE_P(DBIteratorTestForPinnedDataInstance,
+                        DBIteratorTestForPinnedData,
+                        testing::Values(true, false));
+
 #ifndef ROCKSDB_LITE
 TEST_P(DBIteratorTest, PinnedDataIteratorMultipleFiles) {
  Options options = CurrentOptions();
@@ -2997,18 +3036,18 @@ TEST_P(DBIteratorTest, Blob) {
  iter->Prev();
  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 5);
  iter->Next();
-  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 5);
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 6);
  ASSERT_EQ(IterStatus(iter), "b->vb3");

  // Switch from forward to reverse
  iter->SeekToFirst();
-  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 5);
-  iter->Next();
-  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 5);
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 6);
  iter->Next();
  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 6);
-  iter->Prev();
+  iter->Next();
  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 7);
+  iter->Prev();
+  ASSERT_EQ(TestGetTickerCount(options, NUMBER_OF_RESEEKS_IN_ITERATION), 8);
  ASSERT_EQ(IterStatus(iter), "b->vb3");
 }

@@ -0,0 +1,199 @@
+//  Copyright (c) 2020-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_test_util.h"
+#include "rocksdb/rocksdb_namespace.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+enum class WriteBatchOpType {
+  kPut = 0,
+  kDelete,
+  kSingleDelete,
+  kDeleteRange,
+  kMerge,
+  kBlobIndex,
+  kNum,
+};
+
+// Integer addition is needed for `::testing::Range()` to take the enum type.
+WriteBatchOpType operator+(WriteBatchOpType lhs, const int rhs) {
+  using T = std::underlying_type<WriteBatchOpType>::type;
+  return static_cast<WriteBatchOpType>(static_cast<T>(lhs) + rhs);
+}
+
+class DbKvChecksumTest
+    : public DBTestBase,
+      public ::testing::WithParamInterface<std::tuple<WriteBatchOpType, char>> {
+ public:
+  DbKvChecksumTest()
+      : DBTestBase("/db_kv_checksum_test", /*env_do_fsync=*/false) {
+    op_type_ = std::get<0>(GetParam());
+    corrupt_byte_addend_ = std::get<1>(GetParam());
+  }
+
+  std::pair<WriteBatch, Status> GetWriteBatch(size_t ts_sz,
+                                              ColumnFamilyHandle* cf_handle) {
+    Status s;
+    WriteBatch wb(0 /* reserved_bytes */, 0 /* max_bytes */, ts_sz,
+                  8 /* protection_bytes_per_entry */);
+    switch (op_type_) {
+      case WriteBatchOpType::kPut:
+        s = wb.Put(cf_handle, "key", "val");
+        break;
+      case WriteBatchOpType::kDelete:
+        s = wb.Delete(cf_handle, "key");
+        break;
+      case WriteBatchOpType::kSingleDelete:
+        s = wb.SingleDelete(cf_handle, "key");
+        break;
+      case WriteBatchOpType::kDeleteRange:
+        s = wb.DeleteRange(cf_handle, "begin", "end");
+        break;
+      case WriteBatchOpType::kMerge:
+        s = wb.Merge(cf_handle, "key", "val");
+        break;
+      case WriteBatchOpType::kBlobIndex:
+        // TODO(ajkr): use public API once available.
+        uint32_t cf_id;
+        if (cf_handle == nullptr) {
+          cf_id = 0;
+        } else {
+          cf_id = cf_handle->GetID();
+        }
+        s = WriteBatchInternal::PutBlobIndex(&wb, cf_id, "key", "val");
+        break;
+      case WriteBatchOpType::kNum:
+        assert(false);
+    }
+    return {std::move(wb), std::move(s)};
+  }
+
+  void CorruptNextByteCallBack(void* arg) {
+    Slice encoded = *static_cast<Slice*>(arg);
+    if (entry_len_ == port::kMaxSizet) {
+      // We learn the entry size on the first attempt
+      entry_len_ = encoded.size();
+    }
+    // All entries should be the same size
+    assert(entry_len_ == encoded.size());
+    char* buf = const_cast<char*>(encoded.data());
+    buf[corrupt_byte_offset_] += corrupt_byte_addend_;
+    ++corrupt_byte_offset_;
+  }
+
+  bool MoreBytesToCorrupt() { return corrupt_byte_offset_ < entry_len_; }
+
+ protected:
+  WriteBatchOpType op_type_;
+  char corrupt_byte_addend_;
+  size_t corrupt_byte_offset_ = 0;
+  size_t entry_len_ = port::kMaxSizet;
+};
+
+std::string GetTestNameSuffix(
+    ::testing::TestParamInfo<std::tuple<WriteBatchOpType, char>> info) {
+  std::ostringstream oss;
+  switch (std::get<0>(info.param)) {
+    case WriteBatchOpType::kPut:
+      oss << "Put";
+      break;
+    case WriteBatchOpType::kDelete:
+      oss << "Delete";
+      break;
+    case WriteBatchOpType::kSingleDelete:
+      oss << "SingleDelete";
+      break;
+    case WriteBatchOpType::kDeleteRange:
+      oss << "DeleteRange";
+      break;
+    case WriteBatchOpType::kMerge:
+      oss << "Merge";
+      break;
+    case WriteBatchOpType::kBlobIndex:
+      oss << "BlobIndex";
+      break;
+    case WriteBatchOpType::kNum:
+      assert(false);
+  }
+  oss << "Add"
+      << static_cast<int>(static_cast<unsigned char>(std::get<1>(info.param)));
+  return oss.str();
+}
+
+INSTANTIATE_TEST_CASE_P(
+    DbKvChecksumTest, DbKvChecksumTest,
+    ::testing::Combine(::testing::Range(static_cast<WriteBatchOpType>(0),
+                                        WriteBatchOpType::kNum),
+                       ::testing::Values(2, 103, 251)),
+    GetTestNameSuffix);
+
+TEST_P(DbKvChecksumTest, MemTableAddCorrupted) {
+  // This test repeatedly attempts to write `WriteBatch`es containing a single
+  // entry of type `op_type_`. Each attempt has one byte corrupted in its
+  // memtable entry by adding `corrupt_byte_addend_` to its original value. The
+  // test repeats until an attempt has been made on each byte in the encoded
+  // memtable entry. All attempts are expected to fail with `Status::Corruption`
+  SyncPoint::GetInstance()->SetCallBack(
+      "MemTable::Add:Encoded",
+      std::bind(&DbKvChecksumTest::CorruptNextByteCallBack, this,
+                std::placeholders::_1));
+
+  while (MoreBytesToCorrupt()) {
+    // Failed memtable insert always leads to read-only mode, so we have to
+    // reopen for every attempt.
+    Options options = CurrentOptions();
+    if (op_type_ == WriteBatchOpType::kMerge) {
+      options.merge_operator = MergeOperators::CreateStringAppendOperator();
+    }
+    Reopen(options);
+
+    SyncPoint::GetInstance()->EnableProcessing();
+    auto batch_and_status =
+        GetWriteBatch(0 /* ts_sz */, nullptr /* cf_handle */);
+    ASSERT_OK(batch_and_status.second);
+    ASSERT_TRUE(
+        db_->Write(WriteOptions(), &batch_and_status.first).IsCorruption());
+    SyncPoint::GetInstance()->DisableProcessing();
+  }
+}
+
+TEST_P(DbKvChecksumTest, MemTableAddWithColumnFamilyCorrupted) {
+  // This test repeatedly attempts to write `WriteBatch`es containing a single
+  // entry of type `op_type_` to a non-default column family. Each attempt has
+  // one byte corrupted in its memtable entry by adding `corrupt_byte_addend_`
+  // to its original value. The test repeats until an attempt has been made on
+  // each byte in the encoded memtable entry. All attempts are expected to fail
+  // with `Status::Corruption`.
+  Options options = CurrentOptions();
+  if (op_type_ == WriteBatchOpType::kMerge) {
+    options.merge_operator = MergeOperators::CreateStringAppendOperator();
+  }
+  CreateAndReopenWithCF({"pikachu"}, options);
+  SyncPoint::GetInstance()->SetCallBack(
+      "MemTable::Add:Encoded",
+      std::bind(&DbKvChecksumTest::CorruptNextByteCallBack, this,
+                std::placeholders::_1));
+
+  while (MoreBytesToCorrupt()) {
+    // Failed memtable insert always leads to read-only mode, so we have to
+    // reopen for every attempt.
+    ReopenWithColumnFamilies({kDefaultColumnFamilyName, "pikachu"}, options);
+
+    SyncPoint::GetInstance()->EnableProcessing();
+    auto batch_and_status = GetWriteBatch(0 /* ts_sz */, handles_[1]);
+    ASSERT_OK(batch_and_status.second);
+    ASSERT_TRUE(
+        db_->Write(WriteOptions(), &batch_and_status.first).IsCorruption());
+    SyncPoint::GetInstance()->DisableProcessing();
+  }
+}
+
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
@@ -13,6 +13,7 @@
 #if !defined(ROCKSDB_LITE)

 #include "db/db_test_util.h"
+#include "env/mock_env.h"
 #include "port/stack_trace.h"

 namespace ROCKSDB_NAMESPACE {
@@ -145,15 +145,25 @@ TEST_F(DBMemTableTest, DuplicateSeq) {
                               kMaxSequenceNumber, 0 /* column_family_id */);

  // Write some keys and make sure it returns false on duplicates
-  ASSERT_OK(mem->Add(seq, kTypeValue, "key", "value2"));
-  ASSERT_TRUE(mem->Add(seq, kTypeValue, "key", "value2").IsTryAgain());
+  ASSERT_OK(
+      mem->Add(seq, kTypeValue, "key", "value2", nullptr /* kv_prot_info */));
+  ASSERT_TRUE(
+      mem->Add(seq, kTypeValue, "key", "value2", nullptr /* kv_prot_info */)
+          .IsTryAgain());
  // Changing the type should still cause the duplicatae key
-  ASSERT_TRUE(mem->Add(seq, kTypeMerge, "key", "value2").IsTryAgain());
+  ASSERT_TRUE(
+      mem->Add(seq, kTypeMerge, "key", "value2", nullptr /* kv_prot_info */)
+          .IsTryAgain());
  // Changing the seq number will make the key fresh
-  ASSERT_OK(mem->Add(seq + 1, kTypeMerge, "key", "value2"));
+  ASSERT_OK(mem->Add(seq + 1, kTypeMerge, "key", "value2",
+                     nullptr /* kv_prot_info */));
  // Test with different types for duplicate keys
-  ASSERT_TRUE(mem->Add(seq, kTypeDeletion, "key", "").IsTryAgain());
-  ASSERT_TRUE(mem->Add(seq, kTypeSingleDeletion, "key", "").IsTryAgain());
+  ASSERT_TRUE(
+      mem->Add(seq, kTypeDeletion, "key", "", nullptr /* kv_prot_info */)
+          .IsTryAgain());
+  ASSERT_TRUE(
+      mem->Add(seq, kTypeSingleDeletion, "key", "", nullptr /* kv_prot_info */)
+          .IsTryAgain());

  // Test the duplicate keys under stress
  for (int i = 0; i < 10000; i++) {
@@ -161,7 +171,8 @@ TEST_F(DBMemTableTest, DuplicateSeq) {
    if (!insert_dup) {
      seq++;
    }
-    Status s = mem->Add(seq, kTypeValue, "foo", "value" + ToString(seq));
+    Status s = mem->Add(seq, kTypeValue, "foo", "value" + ToString(seq),
+                        nullptr /* kv_prot_info */);
    if (insert_dup) {
      ASSERT_TRUE(s.IsTryAgain());
    } else {
@@ -177,8 +188,11 @@ TEST_F(DBMemTableTest, DuplicateSeq) {
  mem = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb,
                     kMaxSequenceNumber, 0 /* column_family_id */);
  // Insert a duplicate key with _ in it
-  ASSERT_OK(mem->Add(seq, kTypeValue, "key_1", "value"));
-  ASSERT_TRUE(mem->Add(seq, kTypeValue, "key_1", "value").IsTryAgain());
+  ASSERT_OK(
+      mem->Add(seq, kTypeValue, "key_1", "value", nullptr /* kv_prot_info */));
+  ASSERT_TRUE(
+      mem->Add(seq, kTypeValue, "key_1", "value", nullptr /* kv_prot_info */)
+          .IsTryAgain());
  delete mem;

  // Test when InsertConcurrently will be invoked
@@ -187,11 +201,11 @@ TEST_F(DBMemTableTest, DuplicateSeq) {
  mem = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb,
                     kMaxSequenceNumber, 0 /* column_family_id */);
  MemTablePostProcessInfo post_process_info;
-  ASSERT_OK(
-      mem->Add(seq, kTypeValue, "key", "value", true, &post_process_info));
-  ASSERT_TRUE(
-      mem->Add(seq, kTypeValue, "key", "value", true, &post_process_info)
-          .IsTryAgain());
+  ASSERT_OK(mem->Add(seq, kTypeValue, "key", "value",
+                     nullptr /* kv_prot_info */, true, &post_process_info));
+  ASSERT_TRUE(mem->Add(seq, kTypeValue, "key", "value",
+                       nullptr /* kv_prot_info */, true, &post_process_info)
+                  .IsTryAgain());
  delete mem;
 }

@@ -217,7 +231,7 @@ TEST_F(DBMemTableTest, ConcurrentMergeWrite) {

  // Put 0 as the base
  PutFixed64(&value, static_cast<uint64_t>(0));
-  ASSERT_OK(mem->Add(0, kTypeValue, "key", value));
+  ASSERT_OK(mem->Add(0, kTypeValue, "key", value, nullptr /* kv_prot_info */));
  value.clear();

  // Write Merge concurrently
@@ -226,8 +240,8 @@ TEST_F(DBMemTableTest, ConcurrentMergeWrite) {
    std::string v1;
    for (int seq = 1; seq < num_ops / 2; seq++) {
      PutFixed64(&v1, seq);
-      ASSERT_OK(
-          mem->Add(seq, kTypeMerge, "key", v1, true, &post_process_info1));
+      ASSERT_OK(mem->Add(seq, kTypeMerge, "key", v1, nullptr /* kv_prot_info */,
+                         true, &post_process_info1));
      v1.clear();
    }
  });
@@ -236,8 +250,8 @@ TEST_F(DBMemTableTest, ConcurrentMergeWrite) {
    std::string v2;
    for (int seq = num_ops / 2; seq < num_ops; seq++) {
      PutFixed64(&v2, seq);
-      ASSERT_OK(
-          mem->Add(seq, kTypeMerge, "key", v2, true, &post_process_info2));
+      ASSERT_OK(mem->Add(seq, kTypeMerge, "key", v2, nullptr /* kv_prot_info */,
+                         true, &post_process_info2));
      v2.clear();
    }
  });
@@ -129,6 +129,83 @@ TEST_F(DBOptionsTest, GetLatestCFOptions) {
            GetMutableCFOptionsMap(dbfull()->GetOptions(handles_[1])));
 }

+TEST_F(DBOptionsTest, SetMutableTableOptions) {
+  Options options;
+  options.create_if_missing = true;
+  options.env = env_;
+  options.blob_file_size = 16384;
+  BlockBasedTableOptions bbto;
+  bbto.no_block_cache = true;
+  bbto.block_size = 8192;
+  bbto.block_restart_interval = 7;
+
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  Reopen(options);
+
+  ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
+  Options c_opts = dbfull()->GetOptions(cfh);
+  const auto* c_bbto =
+      c_opts.table_factory->GetOptions<BlockBasedTableOptions>();
+  ASSERT_NE(c_bbto, nullptr);
+  ASSERT_EQ(c_opts.blob_file_size, 16384);
+  ASSERT_EQ(c_bbto->no_block_cache, true);
+  ASSERT_EQ(c_bbto->block_size, 8192);
+  ASSERT_EQ(c_bbto->block_restart_interval, 7);
+  ASSERT_OK(dbfull()->SetOptions(
+      cfh, {{"table_factory.block_size", "16384"},
+            {"table_factory.block_restart_interval", "11"}}));
+  ASSERT_EQ(c_bbto->block_size, 16384);
+  ASSERT_EQ(c_bbto->block_restart_interval, 11);
+
+  // Now set an option that is not mutable - options should not change
+  ASSERT_NOK(
+      dbfull()->SetOptions(cfh, {{"table_factory.no_block_cache", "false"}}));
+  ASSERT_EQ(c_bbto->no_block_cache, true);
+  ASSERT_EQ(c_bbto->block_size, 16384);
+  ASSERT_EQ(c_bbto->block_restart_interval, 11);
+
+  // Set some that are mutable and some that are not - options should not change
+  ASSERT_NOK(dbfull()->SetOptions(
+      cfh, {{"table_factory.no_block_cache", "false"},
+            {"table_factory.block_size", "8192"},
+            {"table_factory.block_restart_interval", "7"}}));
+  ASSERT_EQ(c_bbto->no_block_cache, true);
+  ASSERT_EQ(c_bbto->block_size, 16384);
+  ASSERT_EQ(c_bbto->block_restart_interval, 11);
+
+  // Set some that are mutable and some that do not exist - options should not
+  // change
+  ASSERT_NOK(dbfull()->SetOptions(
+      cfh, {{"table_factory.block_size", "8192"},
+            {"table_factory.does_not_exist", "true"},
+            {"table_factory.block_restart_interval", "7"}}));
+  ASSERT_EQ(c_bbto->no_block_cache, true);
+  ASSERT_EQ(c_bbto->block_size, 16384);
+  ASSERT_EQ(c_bbto->block_restart_interval, 11);
+
+  // Trying to change the table factory fails
+  ASSERT_NOK(dbfull()->SetOptions(
+      cfh, {{"table_factory", TableFactory::kPlainTableName()}}));
+
+  // Set some on the table and some on the Column Family
+  ASSERT_OK(dbfull()->SetOptions(
+      cfh, {{"table_factory.block_size", "16384"},
+            {"blob_file_size", "32768"},
+            {"table_factory.block_restart_interval", "13"}}));
+  c_opts = dbfull()->GetOptions(cfh);
+  ASSERT_EQ(c_opts.blob_file_size, 32768);
+  ASSERT_EQ(c_bbto->block_size, 16384);
+  ASSERT_EQ(c_bbto->block_restart_interval, 13);
+  // Set some on the table and a bad one on the ColumnFamily - options should
+  // not change
+  ASSERT_NOK(dbfull()->SetOptions(
+      cfh, {{"table_factory.block_size", "1024"},
+            {"no_such_option", "32768"},
+            {"table_factory.block_restart_interval", "7"}}));
+  ASSERT_EQ(c_bbto->block_size, 16384);
+  ASSERT_EQ(c_bbto->block_restart_interval, 13);
+}
+
 TEST_F(DBOptionsTest, SetBytesPerSync) {
  const size_t kValueSize = 1024 * 1024;  // 1MB
  Options options;
@@ -1175,6 +1175,61 @@ class CountingDeleteTabPropCollectorFactory
  }
 };

+class BlockCountingTablePropertiesCollector : public TablePropertiesCollector {
+ public:
+  static const std::string kNumSampledBlocksPropertyName;
+
+  const char* Name() const override {
+    return "BlockCountingTablePropertiesCollector";
+  }
+
+  Status Finish(UserCollectedProperties* properties) override {
+    (*properties)[kNumSampledBlocksPropertyName] =
+        ToString(num_sampled_blocks_);
+    return Status::OK();
+  }
+
+  Status AddUserKey(const Slice& /*user_key*/, const Slice& /*value*/,
+                    EntryType /*type*/, SequenceNumber /*seq*/,
+                    uint64_t /*file_size*/) override {
+    return Status::OK();
+  }
+
+  void BlockAdd(uint64_t /* block_raw_bytes */,
+                uint64_t block_compressed_bytes_fast,
+                uint64_t block_compressed_bytes_slow) override {
+    if (block_compressed_bytes_fast > 0 || block_compressed_bytes_slow > 0) {
+      num_sampled_blocks_++;
+    }
+  }
+
+  UserCollectedProperties GetReadableProperties() const override {
+    return UserCollectedProperties{
+        {kNumSampledBlocksPropertyName, ToString(num_sampled_blocks_)},
+    };
+  }
+
+ private:
+  uint32_t num_sampled_blocks_ = 0;
+};
+
+const std::string
+    BlockCountingTablePropertiesCollector::kNumSampledBlocksPropertyName =
+        "NumSampledBlocks";
+
+class BlockCountingTablePropertiesCollectorFactory
+    : public TablePropertiesCollectorFactory {
+ public:
+  const char* Name() const override {
+    return "BlockCountingTablePropertiesCollectorFactory";
+  }
+
+  TablePropertiesCollector* CreateTablePropertiesCollector(
+      TablePropertiesCollectorFactory::Context /* context */) override {
+    return new BlockCountingTablePropertiesCollector();
+  }
+};
+
 #ifndef ROCKSDB_LITE
 TEST_F(DBPropertiesTest, GetUserDefinedTableProperties) {
  Options options = CurrentOptions();
@@ -1413,6 +1468,132 @@ TEST_F(DBPropertiesTest, NeedCompactHintPersistentTest) {
  }
 }

+// Excluded from RocksDB lite tests due to `GetPropertiesOfAllTables()` usage.
+TEST_F(DBPropertiesTest, BlockAddForCompressionSampling) {
+  // Sampled compression requires at least one of the following four types.
+  if (!Snappy_Supported() && !Zlib_Supported() && !LZ4_Supported() &&
+      !ZSTD_Supported()) {
+    return;
+  }
+
+  Options options = CurrentOptions();
+  options.disable_auto_compactions = true;
+  options.table_properties_collector_factories.emplace_back(
+      std::make_shared<BlockCountingTablePropertiesCollectorFactory>());
+
+  for (bool sample_for_compression : {false, true}) {
+    // For simplicity/determinism, sample 100% when enabled, or 0% when disabled
+    options.sample_for_compression = sample_for_compression ? 1 : 0;
+
+    DestroyAndReopen(options);
+
+    // Setup the following LSM:
+    //
+    // L0_0 ["a", "b"]
+    // L1_0 ["a", "b"]
+    //
+    // L0_0 was created by flush. L1_0 was created by compaction. Each file
+    // contains one data block.
+    for (int i = 0; i < 3; ++i) {
+      ASSERT_OK(Put("a", "val"));
+      ASSERT_OK(Put("b", "val"));
+      ASSERT_OK(Flush());
+      if (i == 1) {
+        ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+      }
+    }
+
+    // A `BlockAdd()` should have been seen for files generated by flush or
+    // compaction when `sample_for_compression` is enabled.
+    TablePropertiesCollection file_to_props;
+    ASSERT_OK(db_->GetPropertiesOfAllTables(&file_to_props));
+    ASSERT_EQ(2, file_to_props.size());
+    for (const auto& file_and_props : file_to_props) {
+      auto& user_props = file_and_props.second->user_collected_properties;
+      ASSERT_TRUE(user_props.find(BlockCountingTablePropertiesCollector::
+                                      kNumSampledBlocksPropertyName) !=
+                  user_props.end());
+      ASSERT_EQ(user_props.at(BlockCountingTablePropertiesCollector::
+                                  kNumSampledBlocksPropertyName),
+                ToString(sample_for_compression ? 1 : 0));
+    }
+  }
+}
+
+class CompressionSamplingDBPropertiesTest
+    : public DBPropertiesTest,
+      public ::testing::WithParamInterface<bool> {
+ public:
+  CompressionSamplingDBPropertiesTest() : fast_(GetParam()) {}
+
+ protected:
+  const bool fast_;
+};
+
+INSTANTIATE_TEST_CASE_P(CompressionSamplingDBPropertiesTest,
+                        CompressionSamplingDBPropertiesTest, ::testing::Bool());
+
+// Excluded from RocksDB lite tests due to `GetPropertiesOfAllTables()` usage.
+TEST_P(CompressionSamplingDBPropertiesTest,
+       EstimateDataSizeWithCompressionSampling) {
+  Options options = CurrentOptions();
+  if (fast_) {
+    // One of the following light compression libraries must be present.
+    if (LZ4_Supported()) {
+      options.compression = kLZ4Compression;
+    } else if (Snappy_Supported()) {
+      options.compression = kSnappyCompression;
+    } else {
+      return;
+    }
+  } else {
+    // One of the following heavy compression libraries must be present.
+    if (ZSTD_Supported()) {
+      options.compression = kZSTD;
+    } else if (Zlib_Supported()) {
+      options.compression = kZlibCompression;
+    } else {
+      return;
+    }
+  }
+  options.disable_auto_compactions = true;
+  // For simplicity/determinism, sample 100%.
+  options.sample_for_compression = 1;
+  Reopen(options);
+
+  // Setup the following LSM:
+  //
+  // L0_0 ["a", "b"]
+  // L1_0 ["a", "b"]
+  //
+  // L0_0 was created by flush. L1_0 was created by compaction. Each file
+  // contains one data block. The value consists of compressible data so the
+  // data block should be stored compressed.
+  std::string val(1024, 'a');
+  for (int i = 0; i < 3; ++i) {
+    ASSERT_OK(Put("a", val));
+    ASSERT_OK(Put("b", val));
+    ASSERT_OK(Flush());
+    if (i == 1) {
+      ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+    }
+  }
+
+  TablePropertiesCollection file_to_props;
+  ASSERT_OK(db_->GetPropertiesOfAllTables(&file_to_props));
+  ASSERT_EQ(2, file_to_props.size());
+  for (const auto& file_and_props : file_to_props) {
+    ASSERT_GT(file_and_props.second->data_size, 0);
+    if (fast_) {
+      ASSERT_EQ(file_and_props.second->data_size,
+                file_and_props.second->fast_compression_estimated_data_size);
+    } else {
+      ASSERT_EQ(file_and_props.second->data_size,
+                file_and_props.second->slow_compression_estimated_data_size);
+    }
+  }
+}
+
 TEST_F(DBPropertiesTest, EstimateNumKeysUnderflow) {
  Options options = CurrentOptions();
  Reopen(options);
@@ -73,6 +73,15 @@ TEST_F(DBRangeDelTest, FlushOutputHasOnlyRangeTombstones) {
  } while (ChangeOptions(kRangeDelSkipConfigs));
 }

+TEST_F(DBRangeDelTest, DictionaryCompressionWithOnlyRangeTombstones) {
+  Options opts = CurrentOptions();
+  opts.compression_opts.max_dict_bytes = 16384;
+  Reopen(opts);
+  ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), "dr1",
+                             "dr2"));
+  ASSERT_OK(db_->Flush(FlushOptions()));
+}
+
 TEST_F(DBRangeDelTest, CompactionOutputHasOnlyRangeTombstone) {
  do {
    Options opts = CurrentOptions();
@@ -459,20 +459,6 @@ TEST_F(DBSecondaryTest, MissingTableFileDuringOpen) {
 }

 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;
@@ -499,7 +485,6 @@ TEST_F(DBSecondaryTest, MissingTableFile) {
  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),
@@ -615,10 +600,7 @@ TEST_F(DBSecondaryTest, SwitchManifest) {
  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) {
+TEST_F(DBSecondaryTest, SwitchManifestTwice) {
  Options options;
  options.env = env_;
  options.disable_auto_compactions = true;
@@ -640,10 +622,15 @@ TEST_F(DBSecondaryTest, SkipSnapshotAfterManifestSwitch) {

  Reopen(options);
  ASSERT_OK(dbfull()->SetOptions({{"disable_auto_compactions", "false"}}));
+  Reopen(options);
+  ASSERT_OK(Put("0", "value1"));
  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
+
+  ASSERT_OK(db_secondary_->Get(ropts, "0", &value));
+  ASSERT_EQ("value1", value);
 }

-TEST_F(DBSecondaryTest, SwitchWAL) {
+TEST_F(DBSecondaryTest, DISABLED_SwitchWAL) {
  const int kNumKeysPerMemtable = 1;
  Options options;
  options.env = env_;
@@ -692,7 +679,7 @@ TEST_F(DBSecondaryTest, SwitchWAL) {
  }
 }

-TEST_F(DBSecondaryTest, SwitchWALMultiColumnFamilies) {
+TEST_F(DBSecondaryTest, DISABLED_SwitchWALMultiColumnFamilies) {
  const int kNumKeysPerMemtable = 1;
  SyncPoint::GetInstance()->DisableProcessing();
  SyncPoint::GetInstance()->LoadDependency(
@@ -306,13 +306,13 @@ TEST_F(DBSSTTest, DBWithSstFileManager) {
    ASSERT_OK(dbfull()->TEST_WaitForCompact());
    // Verify that we are tracking all sst files in dbname_
    std::unordered_map<std::string, uint64_t> files_in_db;
-    ASSERT_OK(GetAllSSTFiles(&files_in_db));
+    ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db));
    ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
  }
  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));

  std::unordered_map<std::string, uint64_t> files_in_db;
-  ASSERT_OK(GetAllSSTFiles(&files_in_db));
+  ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db));
  // Verify that we are tracking all sst files in dbname_
  ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
  // Verify the total files size
@@ -346,6 +346,260 @@ TEST_F(DBSSTTest, DBWithSstFileManager) {
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
 }

+TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFiles) {
+  std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
+  auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
+
+  int files_added = 0;
+  int files_deleted = 0;
+  int files_moved = 0;
+  int files_scheduled_to_delete = 0;
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::OnAddFile", [&](void* arg) {
+        const std::string* const file_path =
+            static_cast<const std::string*>(arg);
+        if (file_path->find(".blob") != std::string::npos) {
+          files_added++;
+        }
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::OnDeleteFile", [&](void* arg) {
+        const std::string* const file_path =
+            static_cast<const std::string*>(arg);
+        if (file_path->find(".blob") != std::string::npos) {
+          files_deleted++;
+        }
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::ScheduleFileDeletion", [&](void* arg) {
+        assert(arg);
+        const std::string* const file_path =
+            static_cast<const std::string*>(arg);
+        if (file_path->find(".blob") != std::string::npos) {
+          ++files_scheduled_to_delete;
+        }
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::OnMoveFile", [&](void* /*arg*/) { files_moved++; });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  Options options = CurrentOptions();
+  options.sst_file_manager = sst_file_manager;
+  options.enable_blob_files = true;
+  options.blob_file_size = 32;  // create one blob per file
+  DestroyAndReopen(options);
+  Random rnd(301);
+
+  for (int i = 0; i < 10; i++) {
+    ASSERT_OK(Put("Key_" + std::to_string(i), "Value_" + std::to_string(i)));
+    ASSERT_OK(Flush());
+    ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+    // Verify that we are tracking all sst and blob files in dbname_
+    std::unordered_map<std::string, uint64_t> files_in_db;
+    ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db));
+    ASSERT_OK(GetAllDataFiles(kBlobFile, &files_in_db));
+    ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
+  }
+
+  std::vector<uint64_t> blob_files = GetBlobFileNumbers();
+  ASSERT_EQ(files_added, blob_files.size());
+  // No blob file is obsoleted.
+  ASSERT_EQ(files_deleted, 0);
+  ASSERT_EQ(files_scheduled_to_delete, 0);
+  // No files were moved.
+  ASSERT_EQ(files_moved, 0);
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+
+  std::unordered_map<std::string, uint64_t> files_in_db;
+  ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db));
+  ASSERT_OK(GetAllDataFiles(kBlobFile, &files_in_db));
+
+  // Verify that we are tracking all sst and blob files in dbname_
+  ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
+  // Verify the total files size
+  uint64_t total_files_size = 0;
+  for (auto& file_to_size : files_in_db) {
+    total_files_size += file_to_size.second;
+  }
+  ASSERT_EQ(sfm->GetTotalSize(), total_files_size);
+  Close();
+
+  Reopen(options);
+  ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
+  ASSERT_EQ(sfm->GetTotalSize(), total_files_size);
+
+  // Verify that we track all the files again after the DB is closed and opened.
+  Close();
+
+  sst_file_manager.reset(NewSstFileManager(env_));
+  options.sst_file_manager = sst_file_manager;
+  sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
+
+  Reopen(options);
+
+  ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
+  ASSERT_EQ(sfm->GetTotalSize(), total_files_size);
+
+  // Destroy DB and it will remove all the blob files from sst file manager and
+  // blob files deletion will go through ScheduleFileDeletion.
+  ASSERT_EQ(files_deleted, 0);
+  ASSERT_EQ(files_scheduled_to_delete, 0);
+  Close();
+  ASSERT_OK(DestroyDB(dbname_, options));
+  ASSERT_EQ(files_deleted, blob_files.size());
+  ASSERT_EQ(files_scheduled_to_delete, blob_files.size());
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFilesWithGC) {
+  std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
+  auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
+  Options options = CurrentOptions();
+  options.sst_file_manager = sst_file_manager;
+  options.enable_blob_files = true;
+  options.blob_file_size = 32;  // create one blob per file
+  options.disable_auto_compactions = true;
+  options.enable_blob_garbage_collection = true;
+  options.blob_garbage_collection_age_cutoff = 0.5;
+
+  int files_added = 0;
+  int files_deleted = 0;
+  int files_moved = 0;
+  int files_scheduled_to_delete = 0;
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::OnAddFile", [&](void* arg) {
+        const std::string* const file_path =
+            static_cast<const std::string*>(arg);
+        if (file_path->find(".blob") != std::string::npos) {
+          files_added++;
+        }
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::OnDeleteFile", [&](void* arg) {
+        const std::string* const file_path =
+            static_cast<const std::string*>(arg);
+        if (file_path->find(".blob") != std::string::npos) {
+          files_deleted++;
+        }
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::ScheduleFileDeletion", [&](void* arg) {
+        assert(arg);
+        const std::string* const file_path =
+            static_cast<const std::string*>(arg);
+        if (file_path->find(".blob") != std::string::npos) {
+          ++files_scheduled_to_delete;
+        }
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::OnMoveFile", [&](void* /*arg*/) { files_moved++; });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  DestroyAndReopen(options);
+  Random rnd(301);
+
+  constexpr char first_key[] = "first_key";
+  constexpr char first_value[] = "first_value";
+  constexpr char second_key[] = "second_key";
+  constexpr char second_value[] = "second_value";
+
+  ASSERT_OK(Put(first_key, first_value));
+  ASSERT_OK(Put(second_key, second_value));
+  ASSERT_OK(Flush());
+
+  constexpr char third_key[] = "third_key";
+  constexpr char third_value[] = "third_value";
+  constexpr char fourth_key[] = "fourth_key";
+  constexpr char fourth_value[] = "fourth_value";
+  constexpr char fifth_key[] = "fifth_key";
+  constexpr char fifth_value[] = "fifth_value";
+
+  ASSERT_OK(Put(third_key, third_value));
+  ASSERT_OK(Put(fourth_key, fourth_value));
+  ASSERT_OK(Put(fifth_key, fifth_value));
+  ASSERT_OK(Flush());
+
+  const std::vector<uint64_t> original_blob_files = GetBlobFileNumbers();
+
+  ASSERT_EQ(original_blob_files.size(), 5);
+  ASSERT_EQ(files_added, 5);
+  ASSERT_EQ(files_deleted, 0);
+  ASSERT_EQ(files_scheduled_to_delete, 0);
+  ASSERT_EQ(files_moved, 0);
+  {
+    // Verify that we are tracking all sst and blob files in dbname_
+    std::unordered_map<std::string, uint64_t> files_in_db;
+    ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db));
+    ASSERT_OK(GetAllDataFiles(kBlobFile, &files_in_db));
+    ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
+  }
+
+  const size_t cutoff_index = static_cast<size_t>(
+      options.blob_garbage_collection_age_cutoff * original_blob_files.size());
+
+  size_t expected_number_of_files = original_blob_files.size();
+  // Note: turning off enable_blob_files before the compaction results in
+  // garbage collected values getting inlined.
+  ASSERT_OK(db_->SetOptions({{"enable_blob_files", "false"}}));
+  expected_number_of_files -= cutoff_index;
+  files_added = 0;
+
+  constexpr Slice* begin = nullptr;
+  constexpr Slice* end = nullptr;
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), begin, end));
+
+  ASSERT_EQ(Get(first_key), first_value);
+  ASSERT_EQ(Get(second_key), second_value);
+  ASSERT_EQ(Get(third_key), third_value);
+  ASSERT_EQ(Get(fourth_key), fourth_value);
+  ASSERT_EQ(Get(fifth_key), fifth_value);
+
+  const std::vector<uint64_t> new_blob_files = GetBlobFileNumbers();
+
+  ASSERT_EQ(new_blob_files.size(), expected_number_of_files);
+  // No new file is added.
+  ASSERT_EQ(files_added, 0);
+  ASSERT_EQ(files_deleted, cutoff_index);
+  ASSERT_EQ(files_scheduled_to_delete, cutoff_index);
+  ASSERT_EQ(files_moved, 0);
+
+  // Original blob files below the cutoff should be gone, original blob files at
+  // or above the cutoff should be still there
+  for (size_t i = cutoff_index; i < original_blob_files.size(); ++i) {
+    ASSERT_EQ(new_blob_files[i - cutoff_index], original_blob_files[i]);
+  }
+
+  {
+    // Verify that we are tracking all sst and blob files in dbname_
+    std::unordered_map<std::string, uint64_t> files_in_db;
+    ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db));
+    ASSERT_OK(GetAllDataFiles(kBlobFile, &files_in_db));
+    ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
+  }
+
+  Close();
+  ASSERT_OK(DestroyDB(dbname_, options));
+  ASSERT_EQ(files_deleted, 5);
+  ASSERT_EQ(files_scheduled_to_delete, 5);
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
 TEST_F(DBSSTTest, RateLimitedDelete) {
  Destroy(last_options_);
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
@@ -497,10 +751,11 @@ TEST_F(DBSSTTest, RateLimitedWALDelete) {
 }

 class DBWALTestWithParam
-    : public DBSSTTest,
+    : public DBTestBase,
      public testing::WithParamInterface<std::tuple<std::string, bool>> {
 public:
-  DBWALTestWithParam() {
+  explicit DBWALTestWithParam()
+      : DBTestBase("/db_wal_test_with_params", /*env_do_fsync=*/true) {
    wal_dir_ = std::get<0>(GetParam());
    wal_dir_same_as_dbname_ = std::get<1>(GetParam());
  }
@@ -780,7 +1035,7 @@ TEST_F(DBSSTTest, DBWithMaxSpaceAllowed) {

  uint64_t first_file_size = 0;
  std::unordered_map<std::string, uint64_t> files_in_db;
-  ASSERT_OK(GetAllSSTFiles(&files_in_db, &first_file_size));
+  ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db, &first_file_size));
  ASSERT_EQ(sfm->GetTotalSize(), first_file_size);

  // Set the maximum allowed space usage to the current total size
@@ -791,6 +1046,68 @@ TEST_F(DBSSTTest, DBWithMaxSpaceAllowed) {
  ASSERT_NOK(Flush());
 }

+TEST_F(DBSSTTest, DBWithMaxSpaceAllowedWithBlobFiles) {
+  std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
+  auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
+
+  Options options = CurrentOptions();
+  options.sst_file_manager = sst_file_manager;
+  options.disable_auto_compactions = true;
+  options.enable_blob_files = true;
+  DestroyAndReopen(options);
+
+  Random rnd(301);
+
+  // Generate a file containing keys.
+  for (int i = 0; i < 10; i++) {
+    ASSERT_OK(Put(Key(i), rnd.RandomString(50)));
+  }
+  ASSERT_OK(Flush());
+
+  uint64_t files_size = 0;
+  uint64_t total_files_size = 0;
+  std::unordered_map<std::string, uint64_t> files_in_db;
+
+  ASSERT_OK(GetAllDataFiles(kBlobFile, &files_in_db, &files_size));
+  // Make sure blob files are considered by SSTFileManage in size limits.
+  ASSERT_GT(files_size, 0);
+  total_files_size = files_size;
+  ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db, &files_size));
+  total_files_size += files_size;
+  ASSERT_EQ(sfm->GetTotalSize(), total_files_size);
+
+  // Set the maximum allowed space usage to the current total size.
+  sfm->SetMaxAllowedSpaceUsage(files_size + 1);
+
+  bool max_allowed_space_reached = false;
+  bool delete_blob_file = false;
+  // Sync point called after blob file is closed and max allowed space is
+  // checked.
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BlobFileCompletionCallback::CallBack::MaxAllowedSpaceReached",
+      [&](void* /*arg*/) { max_allowed_space_reached = true; });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "BuildTable::AfterDeleteFile",
+      [&](void* /*arg*/) { delete_blob_file = true; });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+      {
+          "BuildTable::AfterDeleteFile",
+          "DBSSTTest::DBWithMaxSpaceAllowedWithBlobFiles:1",
+      },
+  });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_OK(Put("key1", "val1"));
+  // This flush will fail
+  ASSERT_NOK(Flush());
+  ASSERT_TRUE(max_allowed_space_reached);
+
+  TEST_SYNC_POINT("DBSSTTest::DBWithMaxSpaceAllowedWithBlobFiles:1");
+  ASSERT_TRUE(delete_blob_file);
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+}
+
 TEST_F(DBSSTTest, CancellingCompactionsWorks) {
  std::shared_ptr<SstFileManager> sst_file_manager(NewSstFileManager(env_));
  auto sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
@@ -821,7 +1138,7 @@ TEST_F(DBSSTTest, CancellingCompactionsWorks) {
  ASSERT_OK(Flush());
  uint64_t total_file_size = 0;
  std::unordered_map<std::string, uint64_t> files_in_db;
-  ASSERT_OK(GetAllSSTFiles(&files_in_db, &total_file_size));
+  ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db, &total_file_size));
  // Set the maximum allowed space usage to the current total size
  sfm->SetMaxAllowedSpaceUsage(2 * total_file_size + 1);

@@ -869,7 +1186,7 @@ TEST_F(DBSSTTest, CancellingManualCompactionsWorks) {
  ASSERT_OK(Flush());
  uint64_t total_file_size = 0;
  std::unordered_map<std::string, uint64_t> files_in_db;
-  ASSERT_OK(GetAllSSTFiles(&files_in_db, &total_file_size));
+  ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db, &total_file_size));
  // Set the maximum allowed space usage to the current total size
  sfm->SetMaxAllowedSpaceUsage(2 * total_file_size + 1);

@@ -986,7 +1303,7 @@ TEST_F(DBSSTTest, DBWithMaxSpaceAllowedRandomized) {
    ASSERT_TRUE(bg_error_set);
    uint64_t total_sst_files_size = 0;
    std::unordered_map<std::string, uint64_t> files_in_db;
-    ASSERT_OK(GetAllSSTFiles(&files_in_db, &total_sst_files_size));
+    ASSERT_OK(GetAllDataFiles(kTableFile, &files_in_db, &total_sst_files_size));
    ASSERT_GE(total_sst_files_size, limit_mb * 1024 * 1024);
    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
  }
@@ -247,17 +247,21 @@ TEST_F(DBTest, SkipDelay) {
      wo.sync = sync;
      wo.disableWAL = disableWAL;
      wo.no_slowdown = true;
-      dbfull()->Put(wo, "foo", "bar");
+      // Large enough to exceed allowance for one time interval
+      std::string large_value(1024, 'x');
+      // Perhaps ideally this first write would fail because of delay, but
+      // the current implementation does not guarantee that.
+      dbfull()->Put(wo, "foo", large_value).PermitUncheckedError();
      // We need the 2nd write to trigger delay. This is because delay is
      // estimated based on the last write size which is 0 for the first write.
-      ASSERT_NOK(dbfull()->Put(wo, "foo2", "bar2"));
+      ASSERT_NOK(dbfull()->Put(wo, "foo2", large_value));
      ASSERT_GE(sleep_count.load(), 0);
      ASSERT_GE(wait_count.load(), 0);
      token.reset();

-      token = dbfull()->TEST_write_controler().GetDelayToken(1000000000);
+      token = dbfull()->TEST_write_controler().GetDelayToken(1000000);
      wo.no_slowdown = false;
-      ASSERT_OK(dbfull()->Put(wo, "foo3", "bar3"));
+      ASSERT_OK(dbfull()->Put(wo, "foo3", large_value));
      ASSERT_GE(sleep_count.load(), 1);
      token.reset();
    }
@@ -2332,6 +2336,13 @@ TEST_F(DBTest, ReadonlyDBGetLiveManifestSize) {
 }

 TEST_F(DBTest, GetLiveBlobFiles) {
+  // Note: the following prevents an otherwise harmless data race between the
+  // test setup code (AddBlobFile) below and the periodic stat dumping thread.
+  Options options = CurrentOptions();
+  options.stats_dump_period_sec = 0;
+
+  Reopen(options);
+
  VersionSet* const versions = dbfull()->TEST_GetVersionSet();
  assert(versions);
  assert(versions->GetColumnFamilySet());
@@ -154,8 +154,14 @@ class PartitionedIndexTestListener : public EventListener {
 };

 TEST_F(DBTest2, PartitionedIndexUserToInternalKey) {
+  const int kValueSize = 10500;
+  const int kNumEntriesPerFile = 1000;
+  const int kNumFiles = 3;
+  const int kNumDistinctKeys = 30;
+
  BlockBasedTableOptions table_options;
  Options options = CurrentOptions();
+  options.disable_auto_compactions = true;
  table_options.index_type = BlockBasedTableOptions::kTwoLevelIndexSearch;
  PartitionedIndexTestListener* listener = new PartitionedIndexTestListener();
  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
@@ -164,14 +170,15 @@ TEST_F(DBTest2, PartitionedIndexUserToInternalKey) {
  Reopen(options);
  Random rnd(301);

-  for (int i = 0; i < 3000; i++) {
-    int j = i % 30;
-    std::string value = rnd.RandomString(10500);
-    ASSERT_OK(Put("keykey_" + std::to_string(j), value));
-    snapshots.push_back(db_->GetSnapshot());
+  for (int i = 0; i < kNumFiles; i++) {
+    for (int j = 0; j < kNumEntriesPerFile; j++) {
+      int key_id = (i * kNumEntriesPerFile + j) % kNumDistinctKeys;
+      std::string value = rnd.RandomString(kValueSize);
+      ASSERT_OK(Put("keykey_" + std::to_string(key_id), value));
+      snapshots.push_back(db_->GetSnapshot());
+    }
+    ASSERT_OK(Flush());
  }
-  ASSERT_OK(Flush());
-  dbfull()->TEST_WaitForFlushMemTable();

  for (auto s : snapshots) {
    db_->ReleaseSnapshot(s);
@@ -1410,67 +1417,94 @@ INSTANTIATE_TEST_CASE_P(

 TEST_P(PresetCompressionDictTest, Flush) {
  // Verifies that dictionary is generated and written during flush only when
-  // `ColumnFamilyOptions::compression` enables dictionary.
+  // `ColumnFamilyOptions::compression` enables dictionary. Also verifies the
+  // size of the dictionary is within expectations according to the limit on
+  // buffering set by `CompressionOptions::max_dict_buffer_bytes`.
  const size_t kValueLen = 256;
  const size_t kKeysPerFile = 1 << 10;
-  const size_t kDictLen = 4 << 10;
+  const size_t kDictLen = 16 << 10;
+  const size_t kBlockLen = 4 << 10;

  Options options = CurrentOptions();
  if (bottommost_) {
    options.bottommost_compression = compression_type_;
    options.bottommost_compression_opts.enabled = true;
    options.bottommost_compression_opts.max_dict_bytes = kDictLen;
+    options.bottommost_compression_opts.max_dict_buffer_bytes = kBlockLen;
  } else {
    options.compression = compression_type_;
    options.compression_opts.max_dict_bytes = kDictLen;
+    options.compression_opts.max_dict_buffer_bytes = kBlockLen;
  }
  options.memtable_factory.reset(new SpecialSkipListFactory(kKeysPerFile));
  options.statistics = CreateDBStatistics();
  BlockBasedTableOptions bbto;
+  bbto.block_size = kBlockLen;
  bbto.cache_index_and_filter_blocks = true;
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  Reopen(options);

-  uint64_t prev_compression_dict_misses =
-      TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS);
  Random rnd(301);
  for (size_t i = 0; i <= kKeysPerFile; ++i) {
    ASSERT_OK(Put(Key(static_cast<int>(i)), rnd.RandomString(kValueLen)));
  }
  ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());

-  // If there's a compression dictionary, it should have been loaded when the
-  // flush finished, incurring a cache miss.
-  uint64_t expected_compression_dict_misses;
+  // We can use `BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT` to detect whether a
+  // compression dictionary exists since dictionaries would be preloaded when
+  // the flush finishes.
  if (bottommost_) {
-    expected_compression_dict_misses = prev_compression_dict_misses;
+    // Flush is never considered bottommost. This should change in the future
+    // since flushed files may have nothing underneath them, like the one in
+    // this test case.
+    ASSERT_EQ(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        0);
  } else {
-    expected_compression_dict_misses = prev_compression_dict_misses + 1;
+    ASSERT_GT(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        0);
+    // TODO(ajkr): fix the below assertion to work with ZSTD. The expectation on
+    // number of bytes needs to be adjusted in case the cached block is in
+    // ZSTD's digested dictionary format.
+    if (compression_type_ != kZSTD &&
+        compression_type_ != kZSTDNotFinalCompression) {
+      // Although we limited buffering to `kBlockLen`, there may be up to two
+      // blocks of data included in the dictionary since we only check limit
+      // after each block is built.
+      ASSERT_LE(TestGetTickerCount(options,
+                                   BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+                2 * kBlockLen);
+    }
  }
-  ASSERT_EQ(expected_compression_dict_misses,
-            TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
 }

 TEST_P(PresetCompressionDictTest, CompactNonBottommost) {
  // Verifies that dictionary is generated and written during compaction to
  // non-bottommost level only when `ColumnFamilyOptions::compression` enables
-  // dictionary.
+  // dictionary. Also verifies the size of the dictionary is within expectations
+  // according to the limit on buffering set by
+  // `CompressionOptions::max_dict_buffer_bytes`.
  const size_t kValueLen = 256;
  const size_t kKeysPerFile = 1 << 10;
-  const size_t kDictLen = 4 << 10;
+  const size_t kDictLen = 16 << 10;
+  const size_t kBlockLen = 4 << 10;

  Options options = CurrentOptions();
  if (bottommost_) {
    options.bottommost_compression = compression_type_;
    options.bottommost_compression_opts.enabled = true;
    options.bottommost_compression_opts.max_dict_bytes = kDictLen;
+    options.bottommost_compression_opts.max_dict_buffer_bytes = kBlockLen;
  } else {
    options.compression = compression_type_;
    options.compression_opts.max_dict_bytes = kDictLen;
+    options.compression_opts.max_dict_buffer_bytes = kBlockLen;
  }
  options.disable_auto_compactions = true;
  options.statistics = CreateDBStatistics();
  BlockBasedTableOptions bbto;
+  bbto.block_size = kBlockLen;
  bbto.cache_index_and_filter_blocks = true;
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  Reopen(options);
@@ -1492,8 +1526,8 @@ TEST_P(PresetCompressionDictTest, CompactNonBottommost) {
  ASSERT_EQ("2,0,1", FilesPerLevel(0));
 #endif  // ROCKSDB_LITE

-  uint64_t prev_compression_dict_misses =
-      TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS);
+  uint64_t prev_compression_dict_bytes_inserted =
+      TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT);
  // This L0->L1 compaction merges the two L0 files into L1. The produced L1
  // file is not bottommost due to the existing L2 file covering the same key-
  // range.
@@ -1501,38 +1535,58 @@ TEST_P(PresetCompressionDictTest, CompactNonBottommost) {
 #ifndef ROCKSDB_LITE
  ASSERT_EQ("0,1,1", FilesPerLevel(0));
 #endif  // ROCKSDB_LITE
-  // If there's a compression dictionary, it should have been loaded when the
-  // compaction finished, incurring a cache miss.
-  uint64_t expected_compression_dict_misses;
+  // We can use `BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT` to detect whether a
+  // compression dictionary exists since dictionaries would be preloaded when
+  // the compaction finishes.
  if (bottommost_) {
-    expected_compression_dict_misses = prev_compression_dict_misses;
+    ASSERT_EQ(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        prev_compression_dict_bytes_inserted);
  } else {
-    expected_compression_dict_misses = prev_compression_dict_misses + 1;
+    ASSERT_GT(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        prev_compression_dict_bytes_inserted);
+    // TODO(ajkr): fix the below assertion to work with ZSTD. The expectation on
+    // number of bytes needs to be adjusted in case the cached block is in
+    // ZSTD's digested dictionary format.
+    if (compression_type_ != kZSTD &&
+        compression_type_ != kZSTDNotFinalCompression) {
+      // Although we limited buffering to `kBlockLen`, there may be up to two
+      // blocks of data included in the dictionary since we only check limit
+      // after each block is built.
+      ASSERT_LE(TestGetTickerCount(options,
+                                   BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+                prev_compression_dict_bytes_inserted + 2 * kBlockLen);
+    }
  }
-  ASSERT_EQ(expected_compression_dict_misses,
-            TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
 }

 TEST_P(PresetCompressionDictTest, CompactBottommost) {
  // Verifies that dictionary is generated and written during compaction to
  // non-bottommost level only when either `ColumnFamilyOptions::compression` or
-  // `ColumnFamilyOptions::bottommost_compression` enables dictionary.
+  // `ColumnFamilyOptions::bottommost_compression` enables dictionary. Also
+  // verifies the size of the dictionary is within expectations according to the
+  // limit on buffering set by `CompressionOptions::max_dict_buffer_bytes`.
  const size_t kValueLen = 256;
  const size_t kKeysPerFile = 1 << 10;
-  const size_t kDictLen = 4 << 10;
+  const size_t kDictLen = 16 << 10;
+  const size_t kBlockLen = 4 << 10;

  Options options = CurrentOptions();
  if (bottommost_) {
    options.bottommost_compression = compression_type_;
    options.bottommost_compression_opts.enabled = true;
    options.bottommost_compression_opts.max_dict_bytes = kDictLen;
+    options.bottommost_compression_opts.max_dict_buffer_bytes = kBlockLen;
  } else {
    options.compression = compression_type_;
    options.compression_opts.max_dict_bytes = kDictLen;
+    options.compression_opts.max_dict_buffer_bytes = kBlockLen;
  }
  options.disable_auto_compactions = true;
  options.statistics = CreateDBStatistics();
  BlockBasedTableOptions bbto;
+  bbto.block_size = kBlockLen;
  bbto.cache_index_and_filter_blocks = true;
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  Reopen(options);
@@ -1548,17 +1602,28 @@ TEST_P(PresetCompressionDictTest, CompactBottommost) {
  ASSERT_EQ("2", FilesPerLevel(0));
 #endif  // ROCKSDB_LITE

-  uint64_t prev_compression_dict_misses =
-      TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS);
+  uint64_t prev_compression_dict_bytes_inserted =
+      TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT);
  CompactRangeOptions cro;
  ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
 #ifndef ROCKSDB_LITE
  ASSERT_EQ("0,1", FilesPerLevel(0));
 #endif  // ROCKSDB_LITE
-  // If there's a compression dictionary, it should have been loaded when the
-  // compaction finished, incurring a cache miss.
-  ASSERT_EQ(prev_compression_dict_misses + 1,
-            TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_MISS));
+  ASSERT_GT(
+      TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+      prev_compression_dict_bytes_inserted);
+  // TODO(ajkr): fix the below assertion to work with ZSTD. The expectation on
+  // number of bytes needs to be adjusted in case the cached block is in ZSTD's
+  // digested dictionary format.
+  if (compression_type_ != kZSTD &&
+      compression_type_ != kZSTDNotFinalCompression) {
+    // Although we limited buffering to `kBlockLen`, there may be up to two
+    // blocks of data included in the dictionary since we only check limit after
+    // each block is built.
+    ASSERT_LE(
+        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSION_DICT_BYTES_INSERT),
+        prev_compression_dict_bytes_inserted + 2 * kBlockLen);
+  }
 }

 class CompactionCompressionListener : public EventListener {
@@ -4051,7 +4116,7 @@ TEST_F(DBTest2, TraceWithFilter) {

  // Open another db, replay, and verify the data
  std::string value;
-  std::string dbname2 = test::TmpDir(env_) + "/db_replay";
+  std::string dbname2 = test::PerThreadDBPath(env_, "db_replay");
  ASSERT_OK(DestroyDB(dbname2, options));

  // Using a different name than db2, to pacify infer's use-after-lifetime
@@ -4102,7 +4167,7 @@ TEST_F(DBTest2, TraceWithFilter) {
  ASSERT_OK(DestroyDB(dbname2, options));

  // Set up a new db.
-  std::string dbname3 = test::TmpDir(env_) + "/db_not_trace_read";
+  std::string dbname3 = test::PerThreadDBPath(env_, "db_not_trace_read");
  ASSERT_OK(DestroyDB(dbname3, options));

  DB* db3_init = nullptr;
@@ -4519,7 +4584,7 @@ TEST_F(DBTest2, MultiDBParallelOpenTest) {
  Options options = CurrentOptions();
  std::vector<std::string> dbnames;
  for (int i = 0; i < kNumDbs; ++i) {
-    dbnames.emplace_back(test::TmpDir(env_) + "/db" + ToString(i));
+    dbnames.emplace_back(test::PerThreadDBPath(env_, "db" + ToString(i)));
    ASSERT_OK(DestroyDB(dbnames.back(), options));
  }

@@ -10,6 +10,7 @@
 #include "db/db_test_util.h"

 #include "db/forward_iterator.h"
+#include "env/mock_env.h"
 #include "rocksdb/convenience.h"
 #include "rocksdb/env_encryption.h"
 #include "rocksdb/utilities/object_registry.h"
@@ -499,6 +500,7 @@ Options DBTestBase::GetOptions(
      break;
    }
    case kBlockBasedTableWithPartitionedIndex: {
+      table_options.format_version = 3;
      table_options.index_type = BlockBasedTableOptions::kTwoLevelIndexSearch;
      options.prefix_extractor.reset(NewNoopTransform());
      break;
@@ -1125,8 +1127,34 @@ std::string DBTestBase::FilesPerLevel(int cf) {
  result.resize(last_non_zero_offset);
  return result;
 }
+
 #endif  // !ROCKSDB_LITE

+std::vector<uint64_t> DBTestBase::GetBlobFileNumbers() {
+  VersionSet* const versions = dbfull()->TEST_GetVersionSet();
+  assert(versions);
+
+  ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
+  assert(cfd);
+
+  Version* const current = cfd->current();
+  assert(current);
+
+  const VersionStorageInfo* const storage_info = current->storage_info();
+  assert(storage_info);
+
+  const auto& blob_files = storage_info->GetBlobFiles();
+
+  std::vector<uint64_t> result;
+  result.reserve(blob_files.size());
+
+  for (const auto& blob_file : blob_files) {
+    result.emplace_back(blob_file.first);
+  }
+
+  return result;
+}
+
 size_t DBTestBase::CountFiles() {
  size_t count = 0;
  std::vector<std::string> files;
@@ -1435,26 +1463,26 @@ void DBTestBase::CopyFile(const std::string& source,
  ASSERT_OK(destfile->Close());
 }

-Status DBTestBase::GetAllSSTFiles(
-    std::unordered_map<std::string, uint64_t>* sst_files,
+Status DBTestBase::GetAllDataFiles(
+    const FileType file_type, std::unordered_map<std::string, uint64_t>* files,
    uint64_t* total_size /* = nullptr */) {
  if (total_size) {
    *total_size = 0;
  }
-  std::vector<std::string> files;
-  Status s = env_->GetChildren(dbname_, &files);
+  std::vector<std::string> children;
+  Status s = env_->GetChildren(dbname_, &children);
  if (s.ok()) {
-    for (auto& file_name : files) {
+    for (auto& file_name : children) {
      uint64_t number;
      FileType type;
-      if (ParseFileName(file_name, &number, &type) && type == kTableFile) {
+      if (ParseFileName(file_name, &number, &type) && type == file_type) {
        std::string file_path = dbname_ + "/" + file_name;
        uint64_t file_size = 0;
        s = env_->GetFileSize(file_path, &file_size);
        if (!s.ok()) {
          break;
        }
-        (*sst_files)[file_path] = file_size;
+        (*files)[file_path] = file_size;
        if (total_size) {
          *total_size += file_size;
        }
@@ -23,7 +23,6 @@

 #include "db/db_impl/db_impl.h"
 #include "db/dbformat.h"
-#include "env/mock_env.h"
 #include "file/filename.h"
 #include "memtable/hash_linklist_rep.h"
 #include "rocksdb/cache.h"
@@ -40,7 +39,6 @@
 #include "rocksdb/utilities/checkpoint.h"
 #include "table/mock_table.h"
 #include "table/scoped_arena_iterator.h"
-#include "test_util/mock_time_env.h"
 #include "test_util/sync_point.h"
 #include "test_util/testharness.h"
 #include "util/cast_util.h"
@@ -50,6 +48,7 @@
 #include "utilities/merge_operators.h"

 namespace ROCKSDB_NAMESPACE {
+class MockEnv;

 namespace anon {
 class AtomicCounter {
@@ -230,6 +229,11 @@ class SpecialEnv : public EnvWrapper {
          return base_->Append(data);
        }
      }
+      Status Append(
+          const Slice& data,
+          const DataVerificationInfo& /* verification_info */) override {
+        return Append(data);
+      }
      Status PositionedAppend(const Slice& data, uint64_t offset) override {
        if (env_->table_write_callback_) {
          (*env_->table_write_callback_)();
@@ -244,6 +248,11 @@ class SpecialEnv : public EnvWrapper {
          return base_->PositionedAppend(data, offset);
        }
      }
+      Status PositionedAppend(
+          const Slice& data, uint64_t offset,
+          const DataVerificationInfo& /* verification_info */) override {
+        return PositionedAppend(data, offset);
+      }
      Status Truncate(uint64_t size) override { return base_->Truncate(size); }
      Status RangeSync(uint64_t offset, uint64_t nbytes) override {
        Status s = base_->RangeSync(offset, nbytes);
@@ -306,6 +315,12 @@ class SpecialEnv : public EnvWrapper {
          return base_->Append(data);
        }
      }
+      Status Append(
+          const Slice& data,
+          const DataVerificationInfo& /*verification_info*/) override {
+        return Append(data);
+      }
+
      Status Truncate(uint64_t size) override { return base_->Truncate(size); }
      Status Close() override { return base_->Close(); }
      Status Flush() override { return base_->Flush(); }
@@ -357,6 +372,11 @@ class SpecialEnv : public EnvWrapper {
 #endif
        return s;
      }
+      Status Append(
+          const Slice& data,
+          const DataVerificationInfo& /* verification_info */) override {
+        return Append(data);
+      }
      Status Truncate(uint64_t size) override { return base_->Truncate(size); }
      Status Close() override {
 // SyncPoint is not supported in Released Windows Mode.
@@ -395,6 +415,11 @@ class SpecialEnv : public EnvWrapper {
      OtherFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& b)
          : env_(env), base_(std::move(b)) {}
      Status Append(const Slice& data) override { return base_->Append(data); }
+      Status Append(
+          const Slice& data,
+          const DataVerificationInfo& /*verification_info*/) override {
+        return Append(data);
+      }
      Status Truncate(uint64_t size) override { return base_->Truncate(size); }
      Status Close() override { return base_->Close(); }
      Status Flush() override { return base_->Flush(); }
@@ -1065,6 +1090,8 @@ class DBTestBase : public testing::Test {
  int TotalTableFiles(int cf = 0, int levels = -1);
 #endif  // ROCKSDB_LITE

+  std::vector<uint64_t> GetBlobFileNumbers();
+
  // Return spread of files per level
  std::string FilesPerLevel(int cf = 0);

@@ -1154,8 +1181,9 @@ class DBTestBase : public testing::Test {
  void CopyFile(const std::string& source, const std::string& destination,
                uint64_t size = 0);

-  Status GetAllSSTFiles(std::unordered_map<std::string, uint64_t>* sst_files,
-                        uint64_t* total_size = nullptr);
+  Status GetAllDataFiles(const FileType file_type,
+                         std::unordered_map<std::string, uint64_t>* sst_files,
+                         uint64_t* total_size = nullptr);

  std::vector<std::uint64_t> ListTableFiles(Env* env, const std::string& path);

@@ -8,12 +8,13 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

 #include "db/db_test_util.h"
-#include "env/composite_env_wrapper.h"
 #include "options/options_helper.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
+#include "rocksdb/file_system.h"
 #include "test_util/sync_point.h"
 #include "utilities/fault_injection_env.h"
+#include "utilities/fault_injection_fs.h"

 namespace ROCKSDB_NAMESPACE {
 class DBWALTestBase : public DBTestBase {
@@ -23,13 +24,37 @@ class DBWALTestBase : public DBTestBase {

 #if defined(ROCKSDB_PLATFORM_POSIX)
 public:
+#if defined(ROCKSDB_FALLOCATE_PRESENT)
+  bool IsFallocateSupported() {
+    // Test fallocate support of running file system.
+    // Skip this test if fallocate is not supported.
+    std::string fname_test_fallocate = dbname_ + "/preallocate_testfile";
+    int fd = -1;
+    do {
+      fd = open(fname_test_fallocate.c_str(), O_CREAT | O_RDWR | O_TRUNC, 0644);
+    } while (fd < 0 && errno == EINTR);
+    assert(fd > 0);
+    int alloc_status = fallocate(fd, 0, 0, 1);
+    int err_number = errno;
+    close(fd);
+    assert(env_->DeleteFile(fname_test_fallocate) == Status::OK());
+    if (err_number == ENOSYS || err_number == EOPNOTSUPP) {
+      fprintf(stderr, "Skipped preallocated space check: %s\n",
+              errnoStr(err_number).c_str());
+      return false;
+    }
+    assert(alloc_status == 0);
+    return true;
+  }
+#endif  // ROCKSDB_FALLOCATE_PRESENT
+
  uint64_t GetAllocatedFileSize(std::string file_name) {
    struct stat sbuf;
    int err = stat(file_name.c_str(), &sbuf);
    assert(err == 0);
    return sbuf.st_blocks * 512;
  }
-#endif
+#endif  // ROCKSDB_PLATFORM_POSIX
 };

 class DBWALTest : public DBWALTestBase {
@@ -424,28 +449,174 @@ TEST_F(DBWALTest, RecoverWithBlob) {
  const InternalStats* const internal_stats = cfd->internal_stats();
  ASSERT_NE(internal_stats, nullptr);

-  const uint64_t expected_bytes =
-      table_file->fd.GetFileSize() + blob_file->GetTotalBlobBytes();
-
  const auto& compaction_stats = internal_stats->TEST_GetCompactionStats();
  ASSERT_FALSE(compaction_stats.empty());
-  ASSERT_EQ(compaction_stats[0].bytes_written, expected_bytes);
-  ASSERT_EQ(compaction_stats[0].num_output_files, 2);
+  ASSERT_EQ(compaction_stats[0].bytes_written, table_file->fd.GetFileSize());
+  ASSERT_EQ(compaction_stats[0].bytes_written_blob,
+            blob_file->GetTotalBlobBytes());
+  ASSERT_EQ(compaction_stats[0].num_output_files, 1);
+  ASSERT_EQ(compaction_stats[0].num_output_files_blob, 1);

  const uint64_t* const cf_stats_value = internal_stats->TEST_GetCFStatsValue();
-  ASSERT_EQ(cf_stats_value[InternalStats::BYTES_FLUSHED], expected_bytes);
+  ASSERT_EQ(cf_stats_value[InternalStats::BYTES_FLUSHED],
+            compaction_stats[0].bytes_written +
+                compaction_stats[0].bytes_written_blob);
 #endif  // ROCKSDB_LITE
 }

+TEST_F(DBWALTest, RecoverWithBlobMultiSST) {
+  // Write several large (4 KB) values without flushing. Note that blob files
+  // are not actually enabled at this point.
+  std::string large_value(1 << 12, 'a');
+
+  constexpr int num_keys = 64;
+
+  for (int i = 0; i < num_keys; ++i) {
+    ASSERT_OK(Put(Key(i), large_value));
+  }
+
+  // There should be no files just yet since we haven't flushed.
+  {
+    VersionSet* const versions = dbfull()->TEST_GetVersionSet();
+    ASSERT_NE(versions, nullptr);
+
+    ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
+    ASSERT_NE(cfd, nullptr);
+
+    Version* const current = cfd->current();
+    ASSERT_NE(current, nullptr);
+
+    const VersionStorageInfo* const storage_info = current->storage_info();
+    ASSERT_NE(storage_info, nullptr);
+
+    ASSERT_EQ(storage_info->num_non_empty_levels(), 0);
+    ASSERT_TRUE(storage_info->GetBlobFiles().empty());
+  }
+
+  // Reopen the database with blob files enabled and write buffer size set to a
+  // smaller value. Multiple table files+blob files should be written and added
+  // to the Version during recovery.
+  Options options;
+  options.write_buffer_size = 1 << 16;  // 64 KB
+  options.enable_blob_files = true;
+  options.avoid_flush_during_recovery = false;
+  options.disable_auto_compactions = true;
+  options.env = env_;
+
+  Reopen(options);
+
+  for (int i = 0; i < num_keys; ++i) {
+    ASSERT_EQ(Get(Key(i)), large_value);
+  }
+
+  VersionSet* const versions = dbfull()->TEST_GetVersionSet();
+  ASSERT_NE(versions, nullptr);
+
+  ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
+  ASSERT_NE(cfd, nullptr);
+
+  Version* const current = cfd->current();
+  ASSERT_NE(current, nullptr);
+
+  const VersionStorageInfo* const storage_info = current->storage_info();
+  ASSERT_NE(storage_info, nullptr);
+
+  const auto& l0_files = storage_info->LevelFiles(0);
+  ASSERT_GT(l0_files.size(), 1);
+
+  const auto& blob_files = storage_info->GetBlobFiles();
+  ASSERT_GT(blob_files.size(), 1);
+
+  ASSERT_EQ(l0_files.size(), blob_files.size());
+}
+
+TEST_F(DBWALTest, WALWithChecksumHandoff) {
+#ifndef ROCKSDB_ASSERT_STATUS_CHECKED
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem or non-encrypted environment");
+    return;
+  }
+  std::shared_ptr<FaultInjectionTestFS> fault_fs(
+      new FaultInjectionTestFS(FileSystem::Default()));
+  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
+  do {
+    Options options = CurrentOptions();
+
+    options.checksum_handoff_file_types.Add(FileType::kWalFile);
+    options.env = fault_fs_env.get();
+    fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+
+    CreateAndReopenWithCF({"pikachu"}, options);
+    WriteOptions writeOpt = WriteOptions();
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v1"));
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v1"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    ASSERT_EQ("v1", Get(1, "foo"));
+    ASSERT_EQ("v1", Get(1, "bar"));
+
+    writeOpt.disableWAL = false;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v2"));
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v2"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    // Both value's should be present.
+    ASSERT_EQ("v2", Get(1, "bar"));
+    ASSERT_EQ("v2", Get(1, "foo"));
+
+    writeOpt.disableWAL = true;
+    // This put, data is persisted by Flush
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v3"));
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    writeOpt.disableWAL = false;
+    // Data is persisted in the WAL
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "zoo", "v3"));
+    // The hash does not match, write fails
+    fault_fs->SetChecksumHandoffFuncType(ChecksumType::kxxHash);
+    writeOpt.disableWAL = false;
+    ASSERT_NOK(dbfull()->Put(writeOpt, handles_[1], "foo", "v3"));
+
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    // Due to the write failure, Get should not find
+    ASSERT_NE("v3", Get(1, "foo"));
+    ASSERT_EQ("v3", Get(1, "zoo"));
+    ASSERT_EQ("v3", Get(1, "bar"));
+
+    fault_fs->SetChecksumHandoffFuncType(ChecksumType::kCRC32c);
+    // Each write will be similated as corrupted.
+    fault_fs->IngestDataCorruptionBeforeWrite();
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v4"));
+    writeOpt.disableWAL = false;
+    ASSERT_NOK(dbfull()->Put(writeOpt, handles_[1], "foo", "v4"));
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    ASSERT_NE("v4", Get(1, "foo"));
+    ASSERT_NE("v4", Get(1, "bar"));
+    fault_fs->NoDataCorruptionBeforeWrite();
+
+    fault_fs->SetChecksumHandoffFuncType(ChecksumType::kNoChecksum);
+    // The file system does not provide checksum method and verification.
+    writeOpt.disableWAL = true;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v5"));
+    writeOpt.disableWAL = false;
+    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v5"));
+    ReopenWithColumnFamilies({"default", "pikachu"}, options);
+    ASSERT_EQ("v5", Get(1, "foo"));
+    ASSERT_EQ("v5", Get(1, "bar"));
+
+    Destroy(options);
+  } while (ChangeWalOptions());
+#endif  // ROCKSDB_ASSERT_STATUS_CHECKED
+}
+
 class DBRecoveryTestBlobError
    : public DBWALTest,
      public testing::WithParamInterface<std::string> {
 public:
-  DBRecoveryTestBlobError()
-      : fault_injection_env_(env_), sync_point_(GetParam()) {}
-  ~DBRecoveryTestBlobError() { Close(); }
+  DBRecoveryTestBlobError() : sync_point_(GetParam()) {}

-  FaultInjectionTestEnv fault_injection_env_;
  std::string sync_point_;
 };

@@ -460,21 +631,19 @@ TEST_P(DBRecoveryTestBlobError, RecoverWithBlobError) {

  // Reopen with blob files enabled but make blob file writing fail during
  // recovery.
-  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
-    fault_injection_env_.SetFilesystemActive(false,
-                                             Status::IOError(sync_point_));
+  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* arg) {
+    Status* const s = static_cast<Status*>(arg);
+    assert(s);
+
+    (*s) = Status::IOError(sync_point_);
  });
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeDeleteFile", [this](void* /* arg */) {
-        fault_injection_env_.SetFilesystemActive(true);
-      });
  SyncPoint::GetInstance()->EnableProcessing();

  Options options;
  options.enable_blob_files = true;
  options.avoid_flush_during_recovery = false;
  options.disable_auto_compactions = true;
-  options.env = &fault_injection_env_;
+  options.env = env_;

  ASSERT_NOK(TryReopen(options));

@@ -1086,7 +1255,7 @@ class RecoveryTestHelper {
    *count = 0;

    std::shared_ptr<Cache> table_cache = NewLRUCache(50, 0);
-    EnvOptions env_options;
+    FileOptions file_options;
    WriteBufferManager write_buffer_manager(db_options.db_write_buffer_size);

    std::unique_ptr<VersionSet> versions;
@@ -1094,22 +1263,22 @@ class RecoveryTestHelper {
    WriteController write_controller;

    versions.reset(new VersionSet(
-        test->dbname_, &db_options, env_options, table_cache.get(),
+        test->dbname_, &db_options, file_options, table_cache.get(),
        &write_buffer_manager, &write_controller,
        /*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr));

    wal_manager.reset(
-        new WalManager(db_options, env_options, /*io_tracer=*/nullptr));
+        new WalManager(db_options, file_options, /*io_tracer=*/nullptr));

    std::unique_ptr<log::Writer> current_log_writer;

    for (size_t j = kWALFileOffset; j < wal_count + kWALFileOffset; j++) {
      uint64_t current_log_number = j;
      std::string fname = LogFileName(test->dbname_, current_log_number);
-      std::unique_ptr<WritableFile> file;
-      ASSERT_OK(db_options.env->NewWritableFile(fname, &file, env_options));
-      std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-          NewLegacyWritableFileWrapper(std::move(file)), fname, env_options));
+      std::unique_ptr<WritableFileWriter> file_writer;
+      ASSERT_OK(WritableFileWriter::Create(db_options.env->GetFileSystem(),
+                                           fname, file_options, &file_writer,
+                                           nullptr));
      current_log_writer.reset(
          new log::Writer(std::move(file_writer), current_log_number,
                          db_options.recycle_log_file_num > 0));
@@ -1704,23 +1873,9 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithoutFlush) {
    ROCKSDB_GTEST_SKIP("Test requires non-mem environment");
    return;
  }
-  // Test fallocate support of running file system.
-  // Skip this test if fallocate is not supported.
-  std::string fname_test_fallocate = dbname_ + "/preallocate_testfile";
-  int fd = -1;
-  do {
-    fd = open(fname_test_fallocate.c_str(), O_CREAT | O_RDWR | O_TRUNC, 0644);
-  } while (fd < 0 && errno == EINTR);
-  ASSERT_GT(fd, 0);
-  int alloc_status = fallocate(fd, 0, 0, 1);
-  int err_number = errno;
-  close(fd);
-  ASSERT_OK(options.env->DeleteFile(fname_test_fallocate));
-  if (err_number == ENOSYS || err_number == EOPNOTSUPP) {
-    fprintf(stderr, "Skipped preallocated space check: %s\n", strerror(err_number));
+  if (!IsFallocateSupported()) {
    return;
  }
-  ASSERT_EQ(0, alloc_status);

  DestroyAndReopen(options);
  size_t preallocated_size =
@@ -1743,6 +1898,120 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithoutFlush) {
  ASSERT_LT(GetAllocatedFileSize(dbname_ + file_before->PathName()),
            preallocated_size);
 }
+// Tests that we will truncate the preallocated space of the last log from
+// previous.
+TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithFlush) {
+  constexpr size_t kKB = 1024;
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.avoid_flush_during_recovery = false;
+  options.avoid_flush_during_shutdown = true;
+  if (mem_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem environment");
+    return;
+  }
+  if (!IsFallocateSupported()) {
+    return;
+  }
+
+  DestroyAndReopen(options);
+  size_t preallocated_size =
+      dbfull()->TEST_GetWalPreallocateBlockSize(options.write_buffer_size);
+  ASSERT_OK(Put("foo", "v1"));
+  VectorLogPtr log_files_before;
+  ASSERT_OK(dbfull()->GetSortedWalFiles(log_files_before));
+  ASSERT_EQ(1, log_files_before.size());
+  auto& file_before = log_files_before[0];
+  ASSERT_LT(file_before->SizeFileBytes(), 1 * kKB);
+  ASSERT_GE(GetAllocatedFileSize(dbname_ + file_before->PathName()),
+            preallocated_size);
+  // The log file has preallocated space.
+  Close();
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::PurgeObsoleteFiles:Begin",
+        "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterRecover"},
+       {"DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterTruncate",
+        "DBImpl::DeleteObsoleteFileImpl::BeforeDeletion"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  port::Thread reopen_thread([&]() { Reopen(options); });
+
+  TEST_SYNC_POINT(
+      "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterRecover");
+  // After the flush during Open, the log file should get deleted.  However,
+  // if  the process is in a crash loop, the log file may not get
+  // deleted and thte preallocated space will keep accumulating. So we need
+  // to ensure it gets trtuncated.
+  EXPECT_LT(GetAllocatedFileSize(dbname_ + file_before->PathName()),
+            preallocated_size);
+  TEST_SYNC_POINT(
+      "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterTruncate");
+  reopen_thread.join();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_F(DBWALTest, TruncateLastLogAfterRecoverWALEmpty) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.avoid_flush_during_recovery = false;
+  if (mem_env_ || encrypted_env_) {
+    ROCKSDB_GTEST_SKIP("Test requires non-mem/non-encrypted  environment");
+    return;
+  }
+  if (!IsFallocateSupported()) {
+    return;
+  }
+
+  DestroyAndReopen(options);
+  size_t preallocated_size =
+      dbfull()->TEST_GetWalPreallocateBlockSize(options.write_buffer_size);
+  Close();
+  std::vector<std::string> filenames;
+  std::string last_log;
+  uint64_t last_log_num = 0;
+  ASSERT_OK(env_->GetChildren(dbname_, &filenames));
+  for (auto fname : filenames) {
+    uint64_t number;
+    FileType type;
+    if (ParseFileName(fname, &number, &type, nullptr)) {
+      if (type == kWalFile && number > last_log_num) {
+        last_log = fname;
+      }
+    }
+  }
+  ASSERT_NE(last_log, "");
+  last_log = dbname_ + '/' + last_log;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::PurgeObsoleteFiles:Begin",
+        "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterRecover"},
+       {"DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterTruncate",
+        "DBImpl::DeleteObsoleteFileImpl::BeforeDeletion"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "PosixWritableFile::Close",
+      [](void* arg) { *(reinterpret_cast<size_t*>(arg)) = 0; });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  // Preallocate space for the empty log file. This could happen if WAL data
+  // was buffered in memory and the process crashed.
+  std::unique_ptr<WritableFile> log_file;
+  ASSERT_OK(env_->ReopenWritableFile(last_log, &log_file, EnvOptions()));
+  log_file->SetPreallocationBlockSize(preallocated_size);
+  log_file->PrepareWrite(0, 4096);
+  log_file.reset();
+
+  ASSERT_GE(GetAllocatedFileSize(last_log), preallocated_size);
+
+  port::Thread reopen_thread([&]() { Reopen(options); });
+
+  TEST_SYNC_POINT(
+      "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterRecover");
+  // The preallocated space should be truncated.
+  EXPECT_LT(GetAllocatedFileSize(last_log), preallocated_size);
+  TEST_SYNC_POINT(
+      "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterTruncate");
+  reopen_thread.join();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
 #endif  // ROCKSDB_FALLOCATE_PRESENT
 #endif  // ROCKSDB_PLATFORM_POSIX

@@ -223,6 +223,111 @@ TEST_F(DBBasicTestWithTimestamp, CompactRangeWithSpecifiedRange) {
  Close();
 }

+TEST_F(DBBasicTestWithTimestamp, UpdateFullHistoryTsLow) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.create_if_missing = true;
+  const size_t kTimestampSize = Timestamp(0, 0).size();
+  TestComparator test_cmp(kTimestampSize);
+  options.comparator = &test_cmp;
+  DestroyAndReopen(options);
+
+  const std::string kKey = "test kKey";
+
+  // Test set ts_low first and flush()
+  int current_ts_low = 5;
+  std::string ts_low_str = Timestamp(current_ts_low, 0);
+  Slice ts_low = ts_low_str;
+  CompactRangeOptions comp_opts;
+  comp_opts.full_history_ts_low = &ts_low;
+  comp_opts.bottommost_level_compaction = BottommostLevelCompaction::kForce;
+
+  ASSERT_OK(db_->CompactRange(comp_opts, nullptr, nullptr));
+
+  auto* cfd =
+      static_cast_with_check<ColumnFamilyHandleImpl>(db_->DefaultColumnFamily())
+          ->cfd();
+  auto result_ts_low = cfd->GetFullHistoryTsLow();
+
+  ASSERT_TRUE(test_cmp.CompareTimestamp(ts_low, result_ts_low) == 0);
+
+  for (int i = 0; i < 10; i++) {
+    WriteOptions write_opts;
+    std::string ts_str = Timestamp(i, 0);
+    Slice ts = ts_str;
+    write_opts.timestamp = &ts;
+    ASSERT_OK(db_->Put(write_opts, kKey, Key(i)));
+  }
+  ASSERT_OK(Flush());
+
+  for (int i = 0; i < 10; i++) {
+    ReadOptions read_opts;
+    std::string ts_str = Timestamp(i, 0);
+    Slice ts = ts_str;
+    read_opts.timestamp = &ts;
+    std::string value;
+    Status status = db_->Get(read_opts, kKey, &value);
+    if (i < current_ts_low) {
+      ASSERT_TRUE(status.IsNotFound());
+    } else {
+      ASSERT_OK(status);
+      ASSERT_TRUE(value.compare(Key(i)) == 0);
+    }
+  }
+
+  // Test set ts_low and then trigger compaction
+  for (int i = 10; i < 20; i++) {
+    WriteOptions write_opts;
+    std::string ts_str = Timestamp(i, 0);
+    Slice ts = ts_str;
+    write_opts.timestamp = &ts;
+    ASSERT_OK(db_->Put(write_opts, kKey, Key(i)));
+  }
+
+  ASSERT_OK(Flush());
+
+  current_ts_low = 15;
+  ts_low_str = Timestamp(current_ts_low, 0);
+  ts_low = ts_low_str;
+  comp_opts.full_history_ts_low = &ts_low;
+  ASSERT_OK(db_->CompactRange(comp_opts, nullptr, nullptr));
+  result_ts_low = cfd->GetFullHistoryTsLow();
+  ASSERT_TRUE(test_cmp.CompareTimestamp(ts_low, result_ts_low) == 0);
+
+  for (int i = 0; i < 20; i++) {
+    ReadOptions read_opts;
+    std::string ts_str = Timestamp(i, 0);
+    Slice ts = ts_str;
+    read_opts.timestamp = &ts;
+    std::string value;
+    Status status = db_->Get(read_opts, kKey, &value);
+    if (i < current_ts_low) {
+      ASSERT_TRUE(status.IsNotFound());
+    } else {
+      ASSERT_OK(status);
+      ASSERT_TRUE(value.compare(Key(i)) == 0);
+    }
+  }
+
+  // Test invalid compaction with range
+  Slice start(kKey), end(kKey);
+  Status s = db_->CompactRange(comp_opts, &start, &end);
+  ASSERT_TRUE(s.IsInvalidArgument());
+  s = db_->CompactRange(comp_opts, &start, nullptr);
+  ASSERT_TRUE(s.IsInvalidArgument());
+  s = db_->CompactRange(comp_opts, nullptr, &end);
+  ASSERT_TRUE(s.IsInvalidArgument());
+
+  // Test invalid compaction with the decreasing ts_low
+  ts_low_str = Timestamp(current_ts_low - 1, 0);
+  ts_low = ts_low_str;
+  comp_opts.full_history_ts_low = &ts_low;
+  s = db_->CompactRange(comp_opts, nullptr, nullptr);
+  ASSERT_TRUE(s.IsInvalidArgument());
+
+  Close();
+}
+
 TEST_F(DBBasicTestWithTimestamp, GetApproximateSizes) {
  Options options = CurrentOptions();
  options.write_buffer_size = 100000000;  // Large write buffer
@@ -297,12 +402,11 @@ TEST_F(DBBasicTestWithTimestamp, GetApproximateSizes) {
  ASSERT_OK(
      db_->GetApproximateSizes(size_approx_options, default_cf, &r, 1, &size));
  ASSERT_EQ(size, 0);
-  std::cout << size << std::endl;

  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterate) {
+TEST_F(DBBasicTestWithTimestamp, SimpleIterate) {
  const int kNumKeysPerFile = 128;
  const uint64_t kMaxKey = 1024;
  Options options = CurrentOptions();
@@ -334,6 +438,7 @@ TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterate) {
    std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
    int count = 0;
    uint64_t key = 0;
+    // Forward iterate.
    for (it->Seek(Key1(0)), key = start_keys[i]; it->Valid();
         it->Next(), ++count, ++key) {
      CheckIterUserEntry(it.get(), Key1(key), kTypeValue,
@@ -342,7 +447,16 @@ TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterate) {
    size_t expected_count = kMaxKey - start_keys[i] + 1;
    ASSERT_EQ(expected_count, count);

-    // SeekToFirst() with lower bound.
+    // Backward iterate.
+    count = 0;
+    for (it->SeekForPrev(Key1(kMaxKey)), key = kMaxKey; it->Valid();
+         it->Prev(), ++count, --key) {
+      CheckIterUserEntry(it.get(), Key1(key), kTypeValue,
+                         "value" + std::to_string(i), write_timestamps[i]);
+    }
+    ASSERT_EQ(static_cast<size_t>(kMaxKey) - start_keys[i] + 1, count);
+
+    // SeekToFirst()/SeekToLast() with lower/upper bounds.
    // Then iter with lower and upper bounds.
    uint64_t l = 0;
    uint64_t r = kMaxKey + 1;
@@ -360,6 +474,12 @@ TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterate) {
                           "value" + std::to_string(i), write_timestamps[i]);
      }
      ASSERT_EQ(r - std::max(l, start_keys[i]), count);
+
+      for (it->SeekToLast(), key = std::min(r, kMaxKey + 1), count = 0;
+           it->Valid(); it->Prev(), --key, ++count) {
+        CheckIterUserEntry(it.get(), Key1(key - 1), kTypeValue,
+                           "value" + std::to_string(i), write_timestamps[i]);
+      }
      l += (kMaxKey / 100);
      r -= (kMaxKey / 100);
    }
@@ -367,7 +487,93 @@ TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterate) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, SeekWithPrefixLessThanKey) {
+class DBBasicTestWithTimestampTableOptions
+    : public DBBasicTestWithTimestampBase,
+      public testing::WithParamInterface<BlockBasedTableOptions::IndexType> {
+ public:
+  explicit DBBasicTestWithTimestampTableOptions()
+      : DBBasicTestWithTimestampBase(
+            "db_basic_test_with_timestamp_table_options") {}
+};
+
+INSTANTIATE_TEST_CASE_P(
+    Timestamp, DBBasicTestWithTimestampTableOptions,
+    testing::Values(
+        BlockBasedTableOptions::IndexType::kBinarySearch,
+        BlockBasedTableOptions::IndexType::kHashSearch,
+        BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch,
+        BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey));
+
+TEST_P(DBBasicTestWithTimestampTableOptions, GetAndMultiGet) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(3));
+  options.compression = kNoCompression;
+  BlockBasedTableOptions bbto;
+  bbto.index_type = GetParam();
+  bbto.block_size = 100;
+  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  const size_t kTimestampSize = Timestamp(0, 0).size();
+  TestComparator cmp(kTimestampSize);
+  options.comparator = &cmp;
+  DestroyAndReopen(options);
+  constexpr uint64_t kNumKeys = 1024;
+  for (uint64_t k = 0; k < kNumKeys; ++k) {
+    WriteOptions write_opts;
+    std::string ts_str = Timestamp(1, 0);
+    Slice ts = ts_str;
+    write_opts.timestamp = &ts;
+    ASSERT_OK(db_->Put(write_opts, Key1(k), "value" + std::to_string(k)));
+  }
+  ASSERT_OK(Flush());
+  {
+    ReadOptions read_opts;
+    read_opts.total_order_seek = true;
+    std::string ts_str = Timestamp(2, 0);
+    Slice ts = ts_str;
+    read_opts.timestamp = &ts;
+    std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
+    // verify Get()
+    for (it->SeekToFirst(); it->Valid(); it->Next()) {
+      std::string value_from_get;
+      std::string key_str(it->key().data(), it->key().size());
+      std::string timestamp;
+      ASSERT_OK(db_->Get(read_opts, key_str, &value_from_get, &timestamp));
+      ASSERT_EQ(it->value(), value_from_get);
+      ASSERT_EQ(Timestamp(1, 0), timestamp);
+    }
+
+    // verify MultiGet()
+    constexpr uint64_t step = 2;
+    static_assert(0 == (kNumKeys % step),
+                  "kNumKeys must be a multiple of step");
+    for (uint64_t k = 0; k < kNumKeys; k += 2) {
+      std::vector<std::string> key_strs;
+      std::vector<Slice> keys;
+      for (size_t i = 0; i < step; ++i) {
+        key_strs.push_back(Key1(k + i));
+      }
+      for (size_t i = 0; i < step; ++i) {
+        keys.emplace_back(key_strs[i]);
+      }
+      std::vector<std::string> values;
+      std::vector<std::string> timestamps;
+      std::vector<Status> statuses =
+          db_->MultiGet(read_opts, keys, &values, &timestamps);
+      ASSERT_EQ(step, statuses.size());
+      ASSERT_EQ(step, values.size());
+      ASSERT_EQ(step, timestamps.size());
+      for (uint64_t i = 0; i < step; ++i) {
+        ASSERT_OK(statuses[i]);
+        ASSERT_EQ("value" + std::to_string(k + i), values[i]);
+        ASSERT_EQ(Timestamp(1, 0), timestamps[i]);
+      }
+    }
+  }
+  Close();
+}
+
+TEST_P(DBBasicTestWithTimestampTableOptions, SeekWithPrefixLessThanKey) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -378,6 +584,7 @@ TEST_F(DBBasicTestWithTimestamp, SeekWithPrefixLessThanKey) {
  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
  bbto.cache_index_and_filter_blocks = true;
  bbto.whole_key_filtering = true;
+  bbto.index_type = GetParam();
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  const size_t kTimestampSize = Timestamp(0, 0).size();
  TestComparator test_cmp(kTimestampSize);
@@ -422,7 +629,7 @@ TEST_F(DBBasicTestWithTimestamp, SeekWithPrefixLessThanKey) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, SeekWithPrefixLargerThanKey) {
+TEST_P(DBBasicTestWithTimestampTableOptions, SeekWithPrefixLongerThanKey) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -433,6 +640,7 @@ TEST_F(DBBasicTestWithTimestamp, SeekWithPrefixLargerThanKey) {
  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
  bbto.cache_index_and_filter_blocks = true;
  bbto.whole_key_filtering = true;
+  bbto.index_type = GetParam();
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  const size_t kTimestampSize = Timestamp(0, 0).size();
  TestComparator test_cmp(kTimestampSize);
@@ -475,7 +683,7 @@ TEST_F(DBBasicTestWithTimestamp, SeekWithPrefixLargerThanKey) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, SeekWithBound) {
+TEST_P(DBBasicTestWithTimestampTableOptions, SeekWithBound) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -484,6 +692,7 @@ TEST_F(DBBasicTestWithTimestamp, SeekWithBound) {
  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
  bbto.cache_index_and_filter_blocks = true;
  bbto.whole_key_filtering = true;
+  bbto.index_type = GetParam();
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  const size_t kTimestampSize = Timestamp(0, 0).size();
  TestComparator test_cmp(kTimestampSize);
@@ -495,38 +704,135 @@ TEST_F(DBBasicTestWithTimestamp, SeekWithBound) {
  Slice ts = ts_str;
  write_opts.timestamp = &ts;

-  ASSERT_OK(db_->Put(write_opts, "foo1", "bar"));
+  ASSERT_OK(db_->Put(write_opts, "foo1", "bar1"));
  ASSERT_OK(Flush());

-  ASSERT_OK(db_->Put(write_opts, "foo2", "bar"));
+  ASSERT_OK(db_->Put(write_opts, "foo2", "bar2"));
  ASSERT_OK(Flush());

  // Move sst file to next level
  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));

-  ASSERT_OK(db_->Put(write_opts, "foo3", "bar"));
+  for (int i = 3; i < 9; ++i) {
+    ASSERT_OK(db_->Put(write_opts, "foo" + std::to_string(i),
+                       "bar" + std::to_string(i)));
+  }
  ASSERT_OK(Flush());

  ReadOptions read_opts;
  std::string read_ts = Timestamp(2, 0);
  ts = read_ts;
  read_opts.timestamp = &ts;
-  std::string up_bound = "foo5";
+  std::string up_bound = "foo5";  // exclusive
  Slice up_bound_slice = up_bound;
+  std::string lo_bound = "foo2";  // inclusive
+  Slice lo_bound_slice = lo_bound;
  read_opts.iterate_upper_bound = &up_bound_slice;
+  read_opts.iterate_lower_bound = &lo_bound_slice;
  read_opts.auto_prefix_mode = true;
  {
    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
    // Make sure the prefix extractor doesn't include timestamp, otherwise it
    // may return invalid result.
    iter->Seek("foo");
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_OK(iter->status());
+    CheckIterUserEntry(iter.get(), lo_bound, kTypeValue, "bar2",
+                       Timestamp(1, 0));
+    iter->SeekToFirst();
+    CheckIterUserEntry(iter.get(), lo_bound, kTypeValue, "bar2",
+                       Timestamp(1, 0));
+    iter->SeekForPrev("g");
+    CheckIterUserEntry(iter.get(), "foo4", kTypeValue, "bar4", Timestamp(1, 0));
+    iter->SeekToLast();
+    CheckIterUserEntry(iter.get(), "foo4", kTypeValue, "bar4", Timestamp(1, 0));
  }

  Close();
 }

+TEST_F(DBBasicTestWithTimestamp, ChangeIterationDirection) {
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.env = env_;
+  const size_t kTimestampSize = Timestamp(0, 0).size();
+  TestComparator test_cmp(kTimestampSize);
+  options.comparator = &test_cmp;
+  options.prefix_extractor.reset(NewFixedPrefixTransform(1));
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  DestroyAndReopen(options);
+  const std::vector<std::string> timestamps = {Timestamp(1, 1), Timestamp(0, 2),
+                                               Timestamp(4, 3)};
+  const std::vector<std::tuple<std::string, std::string>> kvs = {
+      std::make_tuple("aa", "value1"), std::make_tuple("ab", "value2")};
+  for (const auto& ts : timestamps) {
+    WriteBatch wb(0, 0, kTimestampSize);
+    for (const auto& kv : kvs) {
+      const std::string& key = std::get<0>(kv);
+      const std::string& value = std::get<1>(kv);
+      ASSERT_OK(wb.Put(key, value));
+    }
+
+    ASSERT_OK(wb.AssignTimestamp(ts));
+    ASSERT_OK(db_->Write(WriteOptions(), &wb));
+  }
+  std::string read_ts_str = Timestamp(5, 3);
+  Slice read_ts = read_ts_str;
+  ReadOptions read_opts;
+  read_opts.timestamp = &read_ts;
+  std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
+
+  it->SeekToFirst();
+  ASSERT_TRUE(it->Valid());
+  it->Prev();
+  ASSERT_FALSE(it->Valid());
+
+  it->SeekToLast();
+  ASSERT_TRUE(it->Valid());
+  uint64_t prev_reseek_count =
+      options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION);
+  ASSERT_EQ(0, prev_reseek_count);
+  it->Next();
+  ASSERT_FALSE(it->Valid());
+  ASSERT_EQ(1 + prev_reseek_count,
+            options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
+
+  it->Seek(std::get<0>(kvs[0]));
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[0]), kTypeValue,
+                     std::get<1>(kvs[0]), Timestamp(4, 3));
+  it->Next();
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[1]), kTypeValue,
+                     std::get<1>(kvs[1]), Timestamp(4, 3));
+  it->Prev();
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[0]), kTypeValue,
+                     std::get<1>(kvs[0]), Timestamp(4, 3));
+
+  prev_reseek_count =
+      options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION);
+  ASSERT_EQ(1, prev_reseek_count);
+  it->Next();
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[1]), kTypeValue,
+                     std::get<1>(kvs[1]), Timestamp(4, 3));
+  ASSERT_EQ(1 + prev_reseek_count,
+            options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
+
+  it->SeekForPrev(std::get<0>(kvs[1]));
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[1]), kTypeValue,
+                     std::get<1>(kvs[1]), Timestamp(4, 3));
+  it->Prev();
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[0]), kTypeValue,
+                     std::get<1>(kvs[0]), Timestamp(4, 3));
+
+  prev_reseek_count =
+      options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION);
+  it->Next();
+  CheckIterUserEntry(it.get(), std::get<0>(kvs[1]), kTypeValue,
+                     std::get<1>(kvs[1]), Timestamp(4, 3));
+  ASSERT_EQ(1 + prev_reseek_count,
+            options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
+
+  it.reset();
+  Close();
+}
+
 TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterateLowerTsBound) {
  constexpr int kNumKeysPerFile = 128;
  constexpr uint64_t kMaxKey = 1024;
@@ -725,6 +1031,16 @@ TEST_F(DBBasicTestWithTimestamp, ReseekToTargetTimestamp) {
    CheckIterUserEntry(iter.get(), "foo", kTypeValue, "value0", ts_str);
    ASSERT_EQ(
        1, options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
+
+    ts_str = Timestamp(kNumKeys, 0);
+    ts = ts_str;
+    read_opts.timestamp = &ts;
+    iter.reset(db_->NewIterator(read_opts));
+    iter->SeekToLast();
+    CheckIterUserEntry(iter.get(), "foo", kTypeValue,
+                       "value" + std::to_string(kNumKeys - 1), ts_str);
+    ASSERT_EQ(
+        2, options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
  }
  Close();
 }
@@ -775,6 +1091,47 @@ TEST_F(DBBasicTestWithTimestamp, ReseekToNextUserKey) {
  Close();
 }

+TEST_F(DBBasicTestWithTimestamp, ReseekToUserKeyBeforeSavedKey) {
+  Options options = GetDefaultOptions();
+  options.env = env_;
+  options.create_if_missing = true;
+  constexpr size_t kNumKeys = 16;
+  options.max_sequential_skip_in_iterations = kNumKeys / 2;
+  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  const size_t kTimestampSize = Timestamp(0, 0).size();
+  TestComparator test_cmp(kTimestampSize);
+  options.comparator = &test_cmp;
+  DestroyAndReopen(options);
+  for (size_t i = 0; i < kNumKeys; ++i) {
+    std::string ts_str = Timestamp(static_cast<uint64_t>(i + 1), 0);
+    Slice ts = ts_str;
+    WriteOptions write_opts;
+    write_opts.timestamp = &ts;
+    Status s = db_->Put(write_opts, "b", "value" + std::to_string(i));
+    ASSERT_OK(s);
+  }
+  {
+    std::string ts_str = Timestamp(1, 0);
+    Slice ts = ts_str;
+    WriteOptions write_opts;
+    write_opts.timestamp = &ts;
+    ASSERT_OK(db_->Put(write_opts, "a", "value"));
+  }
+  {
+    ReadOptions read_opts;
+    std::string ts_str = Timestamp(1, 0);
+    Slice ts = ts_str;
+    read_opts.timestamp = &ts;
+    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
+    iter->SeekToLast();
+    iter->Prev();
+    CheckIterUserEntry(iter.get(), "a", kTypeValue, "value", ts_str);
+    ASSERT_EQ(
+        1, options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
+  }
+  Close();
+}
+
 TEST_F(DBBasicTestWithTimestamp, MultiGetWithFastLocalBloom) {
  Options options = CurrentOptions();
  options.env = env_;
@@ -815,7 +1172,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetWithFastLocalBloom) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, MultiGetWithPrefix) {
+TEST_P(DBBasicTestWithTimestampTableOptions, MultiGetWithPrefix) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -824,6 +1181,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetWithPrefix) {
  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
  bbto.cache_index_and_filter_blocks = true;
  bbto.whole_key_filtering = false;
+  bbto.index_type = GetParam();
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  const size_t kTimestampSize = Timestamp(0, 0).size();
  TestComparator test_cmp(kTimestampSize);
@@ -856,7 +1214,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetWithPrefix) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, MultiGetWithMemBloomFilter) {
+TEST_P(DBBasicTestWithTimestampTableOptions, MultiGetWithMemBloomFilter) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -865,6 +1223,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetWithMemBloomFilter) {
  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
  bbto.cache_index_and_filter_blocks = true;
  bbto.whole_key_filtering = false;
+  bbto.index_type = GetParam();
  options.memtable_prefix_bloom_size_ratio = 0.1;
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  const size_t kTimestampSize = Timestamp(0, 0).size();
@@ -954,7 +1313,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetRangeFiltering) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, MultiGetPrefixFilter) {
+TEST_P(DBBasicTestWithTimestampTableOptions, MultiGetPrefixFilter) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -963,6 +1322,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetPrefixFilter) {
  bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
  bbto.cache_index_and_filter_blocks = true;
  bbto.whole_key_filtering = false;
+  bbto.index_type = GetParam();
  options.memtable_prefix_bloom_size_ratio = 0.1;
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  const size_t kTimestampSize = Timestamp(0, 0).size();
@@ -997,7 +1357,7 @@ TEST_F(DBBasicTestWithTimestamp, MultiGetPrefixFilter) {
  Close();
 }

-TEST_F(DBBasicTestWithTimestamp, MaxKeysSkipped) {
+TEST_F(DBBasicTestWithTimestamp, MaxKeysSkippedDuringNext) {
  Options options = CurrentOptions();
  options.env = env_;
  options.create_if_missing = true;
@@ -1036,6 +1396,45 @@ TEST_F(DBBasicTestWithTimestamp, MaxKeysSkipped) {
  Close();
 }

+TEST_F(DBBasicTestWithTimestamp, MaxKeysSkippedDuringPrev) {
+  Options options = GetDefaultOptions();
+  options.env = env_;
+  options.create_if_missing = true;
+  const size_t kTimestampSize = Timestamp(0, 0).size();
+  TestComparator test_cmp(kTimestampSize);
+  options.comparator = &test_cmp;
+  DestroyAndReopen(options);
+  constexpr size_t max_skippable_internal_keys = 2;
+  const size_t kNumKeys = max_skippable_internal_keys + 2;
+  WriteOptions write_opts;
+  Status s;
+  {
+    std::string ts_str = Timestamp(1, 0);
+    Slice ts = ts_str;
+    write_opts.timestamp = &ts;
+    ASSERT_OK(db_->Put(write_opts, "b", "value"));
+  }
+  for (size_t i = 0; i < kNumKeys; ++i) {
+    std::string ts_str = Timestamp(static_cast<uint64_t>(i + 1), 0);
+    Slice ts = ts_str;
+    write_opts.timestamp = &ts;
+    s = db_->Put(write_opts, "a", "value" + std::to_string(i));
+    ASSERT_OK(s);
+  }
+  {
+    ReadOptions read_opts;
+    read_opts.max_skippable_internal_keys = max_skippable_internal_keys;
+    std::string ts_str = Timestamp(1, 0);
+    Slice ts = ts_str;
+    read_opts.timestamp = &ts;
+    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
+    iter->SeekToLast();
+    iter->Prev();
+    ASSERT_TRUE(iter->status().IsIncomplete());
+  }
+  Close();
+}
+
 // Create two L0, and compact them to a new L1. In this test, L1 is L_bottom.
 // Two L0s:
 //       f1                                  f2
@@ -1099,7 +1498,8 @@ class DBBasicTestWithTimestampFilterPrefixSettings
    : public DBBasicTestWithTimestampBase,
      public testing::WithParamInterface<
          std::tuple<std::shared_ptr<const FilterPolicy>, bool, bool,
-                     std::shared_ptr<const SliceTransform>, bool, double>> {
+                     std::shared_ptr<const SliceTransform>, bool, double,
+                     BlockBasedTableOptions::IndexType>> {
 public:
  DBBasicTestWithTimestampFilterPrefixSettings()
      : DBBasicTestWithTimestampBase(
@@ -1114,6 +1514,7 @@ TEST_P(DBBasicTestWithTimestampFilterPrefixSettings, GetAndMultiGet) {
  bbto.filter_policy = std::get<0>(GetParam());
  bbto.whole_key_filtering = std::get<1>(GetParam());
  bbto.cache_index_and_filter_blocks = std::get<2>(GetParam());
+  bbto.index_type = std::get<6>(GetParam());
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  options.prefix_extractor = std::get<3>(GetParam());
  options.memtable_whole_key_filtering = std::get<4>(GetParam());
@@ -1218,7 +1619,12 @@ INSTANTIATE_TEST_CASE_P(
            std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(4)),
            std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(7)),
            std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(8))),
-        ::testing::Bool(), ::testing::Values(0, 0.1)));
+        ::testing::Bool(), ::testing::Values(0, 0.1),
+        ::testing::Values(
+            BlockBasedTableOptions::IndexType::kBinarySearch,
+            BlockBasedTableOptions::IndexType::kHashSearch,
+            BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch,
+            BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey)));

 class DataVisibilityTest : public DBBasicTestWithTimestampBase {
 public:
@@ -2299,14 +2705,15 @@ class DBBasicTestWithTimestampPrefixSeek
    : public DBBasicTestWithTimestampBase,
      public testing::WithParamInterface<
          std::tuple<std::shared_ptr<const SliceTransform>,
-                     std::shared_ptr<const FilterPolicy>, bool>> {
+                     std::shared_ptr<const FilterPolicy>, bool,
+                     BlockBasedTableOptions::IndexType>> {
 public:
  DBBasicTestWithTimestampPrefixSeek()
      : DBBasicTestWithTimestampBase(
            "/db_basic_test_with_timestamp_prefix_seek") {}
 };

-TEST_P(DBBasicTestWithTimestampPrefixSeek, ForwardIterateWithPrefix) {
+TEST_P(DBBasicTestWithTimestampPrefixSeek, IterateWithPrefix) {
  const size_t kNumKeysPerFile = 128;
  Options options = CurrentOptions();
  options.env = env_;
@@ -2318,6 +2725,7 @@ TEST_P(DBBasicTestWithTimestampPrefixSeek, ForwardIterateWithPrefix) {
  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
  BlockBasedTableOptions bbto;
  bbto.filter_policy = std::get<1>(GetParam());
+  bbto.index_type = std::get<3>(GetParam());
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  DestroyAndReopen(options);

@@ -2356,6 +2764,13 @@ TEST_P(DBBasicTestWithTimestampPrefixSeek, ForwardIterateWithPrefix) {
                         "value" + std::to_string(i), write_ts_list[i]);
      iter->Next();
      ASSERT_FALSE(iter->Valid());
+
+      // Seek to kMinKey
+      iter->Seek(Key1(kMinKey));
+      CheckIterUserEntry(iter.get(), Key1(kMinKey), kTypeValue,
+                         "value" + std::to_string(i), write_ts_list[i]);
+      iter->Prev();
+      ASSERT_FALSE(iter->Valid());
    }
    const std::vector<uint64_t> targets = {kMinKey, kMinKey + 0x10,
                                           kMinKey + 0x100, kMaxKey};
@@ -2371,6 +2786,7 @@ TEST_P(DBBasicTestWithTimestampPrefixSeek, ForwardIterateWithPrefix) {
      Slice read_ts = read_ts_list[i];
      read_opts.timestamp = &read_ts;
      std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
+      // Forward and backward iterate.
      for (size_t j = 0; j != targets.size(); ++j) {
        std::string start_key = Key1(targets[j]);
        uint64_t expected_ub =
@@ -2394,6 +2810,24 @@ TEST_P(DBBasicTestWithTimestampPrefixSeek, ForwardIterateWithPrefix) {
          it->Next();
        }
        ASSERT_EQ(expected_ub - targets[j] + 1, count);
+
+        count = 0;
+        expected_key = targets[j];
+        it->SeekForPrev(start_key);
+        uint64_t expected_lb = (targets[j] & kPrefixMask);
+        while (it->Valid()) {
+          // Out of prefix
+          if (!read_opts.prefix_same_as_start &&
+              pe->Transform(it->key()) != pe->Transform(start_key)) {
+            break;
+          }
+          CheckIterUserEntry(it.get(), Key1(expected_key), kTypeValue,
+                             "value" + std::to_string(i), write_ts_list[i]);
+          ++count;
+          --expected_key;
+          it->Prev();
+        }
+        ASSERT_EQ(targets[j] - std::max(expected_lb, kMinKey) + 1, count);
      }
    }
  }
@@ -2416,19 +2850,25 @@ INSTANTIATE_TEST_CASE_P(
                          std::shared_ptr<const FilterPolicy>(
                              NewBloomFilterPolicy(20 /*bits_per_key*/,
                                                   false))),
-        ::testing::Bool()));
+        ::testing::Bool(),
+        ::testing::Values(
+            BlockBasedTableOptions::IndexType::kBinarySearch,
+            BlockBasedTableOptions::IndexType::kHashSearch,
+            BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch,
+            BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey)));

 class DBBasicTestWithTsIterTombstones
    : public DBBasicTestWithTimestampBase,
      public testing::WithParamInterface<
          std::tuple<std::shared_ptr<const SliceTransform>,
-                     std::shared_ptr<const FilterPolicy>, int>> {
+                     std::shared_ptr<const FilterPolicy>, int,
+                     BlockBasedTableOptions::IndexType>> {
 public:
  DBBasicTestWithTsIterTombstones()
      : DBBasicTestWithTimestampBase("/db_basic_ts_iter_tombstones") {}
 };

-TEST_P(DBBasicTestWithTsIterTombstones, ForwardIterDelete) {
+TEST_P(DBBasicTestWithTsIterTombstones, IterWithDelete) {
  constexpr size_t kNumKeysPerFile = 128;
  Options options = CurrentOptions();
  options.env = env_;
@@ -2439,6 +2879,7 @@ TEST_P(DBBasicTestWithTsIterTombstones, ForwardIterDelete) {
  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
  BlockBasedTableOptions bbto;
  bbto.filter_policy = std::get<1>(GetParam());
+  bbto.index_type = std::get<3>(GetParam());
  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
  options.num_levels = std::get<2>(GetParam());
  DestroyAndReopen(options);
@@ -2458,7 +2899,7 @@ TEST_P(DBBasicTestWithTsIterTombstones, ForwardIterDelete) {
    }
    ++key;
  } while (true);
-  // Delete them all
+
  ts = write_ts_strs[1];
  write_opts.timestamp = &ts;
  for (key = kMaxKey; key >= kMinKey; --key) {
@@ -2485,6 +2926,13 @@ TEST_P(DBBasicTestWithTsIterTombstones, ForwardIterDelete) {
      ASSERT_EQ("value1" + std::to_string(key), iter->value());
    }
    ASSERT_EQ((kMaxKey - kMinKey + 1) / 2, count);
+
+    for (iter->SeekToLast(), count = 0, key = kMaxKey; iter->Valid();
+         key -= 2, ++count, iter->Prev()) {
+      ASSERT_EQ(Key1(key), iter->key());
+      ASSERT_EQ("value1" + std::to_string(key), iter->value());
+    }
+    ASSERT_EQ((kMaxKey - kMinKey + 1) / 2, count);
  }
  Close();
 }
@@ -2500,7 +2948,12 @@ INSTANTIATE_TEST_CASE_P(
                              NewBloomFilterPolicy(10, false)),
                          std::shared_ptr<const FilterPolicy>(
                              NewBloomFilterPolicy(20, false))),
-        ::testing::Values(2, 6)));
+        ::testing::Values(2, 6),
+        ::testing::Values(
+            BlockBasedTableOptions::IndexType::kBinarySearch,
+            BlockBasedTableOptions::IndexType::kHashSearch,
+            BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch,
+            BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey)));

 }  // namespace ROCKSDB_NAMESPACE

@@ -122,7 +122,7 @@ struct ParsedInternalKey {

  void SetTimestamp(const Slice& ts) {
    assert(ts.size() <= user_key.size());
-    const char* addr = user_key.data() - ts.size();
+    const char* addr = user_key.data() + user_key.size() - ts.size();
    memcpy(const_cast<char*>(addr), ts.data(), ts.size());
  }
 };
@@ -146,8 +146,10 @@ inline void UnPackSequenceAndType(uint64_t packed, uint64_t* seq,
  *seq = packed >> 8;
  *t = static_cast<ValueType>(packed & 0xff);

-  assert(*seq <= kMaxSequenceNumber);
-  assert(IsExtendedValueType(*t));
+  // Commented the following two assertions in order to test key-value checksum
+  // on corrupted keys without crashing ("DbKvChecksumTest").
+  // assert(*seq <= kMaxSequenceNumber);
+  // assert(IsExtendedValueType(*t));
 }

 EntryType GetEntryType(ValueType value_type);
@@ -510,6 +512,7 @@ class IterKey {

  bool IsKeyPinned() const { return (key_ != buf_); }

+  // user_key does not have timestamp.
  void SetInternalKey(const Slice& key_prefix, const Slice& user_key,
                      SequenceNumber s,
                      ValueType value_type = kValueTypeForSeek,
@@ -613,7 +616,7 @@ class IterKey {
  void EnlargeBuffer(size_t key_size);
 };

-// Convert from a SliceTranform of user keys, to a SliceTransform of
+// Convert from a SliceTransform of user keys, to a SliceTransform of
 // user keys.
 class InternalKeySliceTransform : public SliceTransform {
 public:
@@ -4,9 +4,11 @@
 //  (found in the LICENSE.Apache file in the root directory).
 //
 #include "db/error_handler.h"
+
 #include "db/db_impl/db_impl.h"
 #include "db/event_helpers.h"
 #include "file/sst_file_manager_impl.h"
+#include "logging/logging.h"

 namespace ROCKSDB_NAMESPACE {

@@ -274,6 +276,12 @@ const Status& ErrorHandler::SetBGError(const Status& bg_err,
    return bg_err;
  }

+  if (bg_error_stats_ != nullptr) {
+    RecordTick(bg_error_stats_.get(), ERROR_HANDLER_BG_ERROR_COUNT);
+  }
+  ROCKS_LOG_INFO(db_options_.info_log,
+                 "ErrorHandler: Set regular background error\n");
+
  bool paranoid = db_options_.paranoid_checks;
  Status::Severity sev = Status::Severity::kFatalError;
  Status new_bg_err;
@@ -399,6 +407,13 @@ const Status& ErrorHandler::SetBGError(const IOStatus& bg_io_err,
    if (recovery_in_prog_ && recovery_error_.ok()) {
      recovery_error_ = bg_err;
    }
+    if (bg_error_stats_ != nullptr) {
+      RecordTick(bg_error_stats_.get(), ERROR_HANDLER_BG_ERROR_COUNT);
+      RecordTick(bg_error_stats_.get(), ERROR_HANDLER_BG_IO_ERROR_COUNT);
+    }
+    ROCKS_LOG_INFO(
+        db_options_.info_log,
+        "ErrorHandler: Set background IO error as unrecoverable error\n");
    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason,
                                          &bg_err, db_mutex_, &auto_recovery);
    recover_context_ = context;
@@ -416,12 +431,26 @@ const Status& ErrorHandler::SetBGError(const IOStatus& bg_io_err,
    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason,
                                          &new_bg_io_err, db_mutex_,
                                          &auto_recovery);
+    if (bg_error_stats_ != nullptr) {
+      RecordTick(bg_error_stats_.get(), ERROR_HANDLER_BG_ERROR_COUNT);
+      RecordTick(bg_error_stats_.get(), ERROR_HANDLER_BG_IO_ERROR_COUNT);
+      RecordTick(bg_error_stats_.get(),
+                 ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT);
+    }
+    ROCKS_LOG_INFO(db_options_.info_log,
+                   "ErrorHandler: Set background retryable IO error\n");
    if (BackgroundErrorReason::kCompaction == reason) {
-      Status bg_err(new_bg_io_err, Status::Severity::kSoftError);
-      if (bg_err.severity() > bg_error_.severity()) {
-        bg_error_ = bg_err;
+      // We map the retryable IO error during compaction to soft error. Since
+      // compaction can reschedule by itself. We will not set the BG error in
+      // this case
+      // TODO:  a better way to set or clean the retryable IO error which
+      // happens during compaction SST file write.
+      if (bg_error_stats_ != nullptr) {
+        RecordTick(bg_error_stats_.get(), ERROR_HANDLER_AUTORESUME_COUNT);
      }
-      recover_context_ = context;
+      ROCKS_LOG_INFO(
+          db_options_.info_log,
+          "ErrorHandler: Compaction will schedule by itself to resume\n");
      return bg_error_;
    } else if (BackgroundErrorReason::kFlushNoWAL == reason ||
               BackgroundErrorReason::kManifestWriteNoWAL == reason) {
@@ -455,6 +484,9 @@ const Status& ErrorHandler::SetBGError(const IOStatus& bg_io_err,
      return StartRecoverFromRetryableBGIOError(bg_io_err);
    }
  } else {
+    if (bg_error_stats_ != nullptr) {
+      RecordTick(bg_error_stats_.get(), ERROR_HANDLER_BG_IO_ERROR_COUNT);
+    }
    return SetBGError(new_bg_io_err, reason);
  }
 }
@@ -603,7 +635,12 @@ const Status& ErrorHandler::StartRecoverFromRetryableBGIOError(
    // Auto resume BG error is not enabled, directly return bg_error_.
    return bg_error_;
  }
-
+  if (bg_error_stats_ != nullptr) {
+    RecordTick(bg_error_stats_.get(), ERROR_HANDLER_AUTORESUME_COUNT);
+  }
+  ROCKS_LOG_INFO(
+      db_options_.info_log,
+      "ErrorHandler: Call StartRecoverFromRetryableBGIOError to resume\n");
  if (recovery_thread_) {
    // In this case, if recovery_in_prog_ is false, current thread should
    // wait the previous recover thread to finish and create a new thread
@@ -642,6 +679,7 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
  DBRecoverContext context = recover_context_;
  int resume_count = db_options_.max_bgerror_resume_count;
  uint64_t wait_interval = db_options_.bgerror_resume_retry_interval;
+  uint64_t retry_count = 0;
  // Recover from the retryable error. Create a separate thread to do it.
  while (resume_count > 0) {
    if (end_recovery_) {
@@ -651,15 +689,24 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
    TEST_SYNC_POINT("RecoverFromRetryableBGIOError:BeforeResume1");
    recovery_io_error_ = IOStatus::OK();
    recovery_error_ = Status::OK();
+    retry_count++;
    Status s = db_->ResumeImpl(context);
    TEST_SYNC_POINT("RecoverFromRetryableBGIOError:AfterResume0");
    TEST_SYNC_POINT("RecoverFromRetryableBGIOError:AfterResume1");
+    if (bg_error_stats_ != nullptr) {
+      RecordTick(bg_error_stats_.get(),
+                 ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT);
+    }
    if (s.IsShutdownInProgress() ||
        bg_error_.severity() >= Status::Severity::kFatalError) {
      // If DB shutdown in progress or the error severity is higher than
      // Hard Error, stop auto resume and returns.
      TEST_SYNC_POINT("RecoverFromRetryableBGIOError:RecoverFail0");
      recovery_in_prog_ = false;
+      if (bg_error_stats_ != nullptr) {
+        RecordInHistogram(bg_error_stats_.get(),
+                          ERROR_HANDLER_AUTORESUME_RETRY_COUNT, retry_count);
+      }
      return;
    }
    if (!recovery_io_error_.ok() &&
@@ -670,7 +717,7 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
      // a period of time and redo auto resume if it is allowed.
      TEST_SYNC_POINT("RecoverFromRetryableBGIOError:BeforeWait0");
      TEST_SYNC_POINT("RecoverFromRetryableBGIOError:BeforeWait1");
-      int64_t wait_until = db_->env_->NowMicros() + wait_interval;
+      int64_t wait_until = db_options_.clock->NowMicros() + wait_interval;
      cv_.TimedWait(wait_until);
      TEST_SYNC_POINT("RecoverFromRetryableBGIOError:AfterWait0");
    } else {
@@ -686,6 +733,12 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
        bg_error_.PermitUncheckedError();
        EventHelpers::NotifyOnErrorRecoveryCompleted(db_options_.listeners,
                                                     old_bg_error, db_mutex_);
+        if (bg_error_stats_ != nullptr) {
+          RecordTick(bg_error_stats_.get(),
+                     ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT);
+          RecordInHistogram(bg_error_stats_.get(),
+                            ERROR_HANDLER_AUTORESUME_RETRY_COUNT, retry_count);
+        }
        recovery_in_prog_ = false;
        if (soft_error_no_bg_work_) {
          soft_error_no_bg_work_ = false;
@@ -696,6 +749,10 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
        // In this case: 1) recovery_io_error is more serious or not retryable
        // 2) other Non IO recovery_error happens. The auto recovery stops.
        recovery_in_prog_ = false;
+        if (bg_error_stats_ != nullptr) {
+          RecordInHistogram(bg_error_stats_.get(),
+                            ERROR_HANDLER_AUTORESUME_RETRY_COUNT, retry_count);
+        }
        return;
      }
    }
@@ -703,6 +760,10 @@ void ErrorHandler::RecoverFromRetryableBGIOError() {
  }
  recovery_in_prog_ = false;
  TEST_SYNC_POINT("RecoverFromRetryableBGIOError:LoopOut");
+  if (bg_error_stats_ != nullptr) {
+    RecordInHistogram(bg_error_stats_.get(),
+                      ERROR_HANDLER_AUTORESUME_RETRY_COUNT, retry_count);
+  }
  return;
 #else
  return;
@@ -37,7 +37,8 @@ class ErrorHandler {
         db_mutex_(db_mutex),
         auto_recovery_(false),
         recovery_in_prog_(false),
-         soft_error_no_bg_work_(false) {
+         soft_error_no_bg_work_(false),
+         bg_error_stats_(db_options.statistics) {
     // Clear the checked flag for uninitialized errors
     bg_error_.PermitUncheckedError();
     recovery_error_.PermitUncheckedError();
@@ -102,12 +103,15 @@ class ErrorHandler {
    bool auto_recovery_;
    bool recovery_in_prog_;
    // A flag to indicate that for the soft error, we should not allow any
-    // backrgound work execpt the work is from recovery.
+    // background work except the work is from recovery.
    bool soft_error_no_bg_work_;

    // Used to store the context for recover, such as flush reason.
    DBRecoverContext recover_context_;

+    // The pointer of DB statistics.
+    std::shared_ptr<Statistics> bg_error_stats_;
+
    Status OverrideNoSpaceError(const Status& bg_error, bool* auto_recovery);
    void RecoverFromNoSpace();
    const Status& StartRecoverFromRetryableBGIOError(const IOStatus& io_error);
@@ -9,9 +9,9 @@
 #ifndef ROCKSDB_LITE

 #include "db/db_test_util.h"
+#include "file/sst_file_manager_impl.h"
 #include "port/stack_trace.h"
 #include "rocksdb/io_status.h"
-#include "rocksdb/perf_context.h"
 #include "rocksdb/sst_file_manager.h"
 #if !defined(ROCKSDB_LITE)
 #include "test_util/sync_point.h"
@@ -158,6 +158,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWriteError) {
  options.env = fault_env_.get();
  options.create_if_missing = true;
  options.listeners.emplace_back(listener);
+  options.statistics = CreateDBStatistics();
  Status s;

  listener->EnableAutoRecovery(false);
@@ -174,13 +175,25 @@ TEST_F(DBErrorHandlingFSTest, FLushWriteError) {
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
  ASSERT_OK(s);
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_IO_ERROR_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT));

  Reopen(options);
  ASSERT_EQ("val", Get(Key(0)));
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritRetryableError) {
+TEST_F(DBErrorHandlingFSTest, FLushWriteRetryableError) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
  Options options = GetDefaultOptions();
@@ -188,6 +201,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableError) {
  options.create_if_missing = true;
  options.listeners.emplace_back(listener);
  options.max_bgerror_resume_count = 0;
+  options.statistics = CreateDBStatistics();
  Status s;

  listener->EnableAutoRecovery(false);
@@ -202,11 +216,23 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
  ASSERT_OK(s);
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_IO_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT));
  Reopen(options);
  ASSERT_EQ("val1", Get(Key(1)));

@@ -216,7 +242,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
@@ -230,7 +256,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
@@ -241,7 +267,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableError) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritFileScopeError) {
+TEST_F(DBErrorHandlingFSTest, FLushWriteFileScopeError) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
  Options options = GetDefaultOptions();
@@ -266,7 +292,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritFileScopeError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
@@ -280,7 +306,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritFileScopeError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
@@ -294,7 +320,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritFileScopeError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
@@ -314,7 +340,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritFileScopeError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  s = dbfull()->Resume();
@@ -325,6 +351,95 @@ TEST_F(DBErrorHandlingFSTest, FLushWritFileScopeError) {
  Destroy(options);
 }

+TEST_F(DBErrorHandlingFSTest, FLushWALWriteRetryableError) {
+  std::shared_ptr<ErrorHandlerFSListener> listener(
+      new ErrorHandlerFSListener());
+  Options options = GetDefaultOptions();
+  options.env = fault_env_.get();
+  options.create_if_missing = true;
+  options.listeners.emplace_back(listener);
+  options.max_bgerror_resume_count = 0;
+  Status s;
+
+  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
+  error_msg.SetRetryable(true);
+
+  listener->EnableAutoRecovery(false);
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::SyncClosedLogs:Start",
+      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  CreateAndReopenWithCF({"pikachu, sdfsdfsdf"}, options);
+
+  WriteOptions wo = WriteOptions();
+  wo.disableWAL = false;
+  ASSERT_OK(Put(Key(1), "val1", wo));
+
+  s = Flush();
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  fault_fs_->SetFilesystemActive(true);
+  auto cfh = dbfull()->GetColumnFamilyHandle(1);
+  s = dbfull()->DropColumnFamily(cfh);
+
+  s = dbfull()->Resume();
+  ASSERT_OK(s);
+  ASSERT_EQ("val1", Get(Key(1)));
+  ASSERT_OK(Put(Key(3), "val3", wo));
+  ASSERT_EQ("val3", Get(Key(3)));
+  s = Flush();
+  ASSERT_OK(s);
+  ASSERT_EQ("val3", Get(Key(3)));
+
+  Destroy(options);
+}
+
+TEST_F(DBErrorHandlingFSTest, FLushWALAtomicWriteRetryableError) {
+  std::shared_ptr<ErrorHandlerFSListener> listener(
+      new ErrorHandlerFSListener());
+  Options options = GetDefaultOptions();
+  options.env = fault_env_.get();
+  options.create_if_missing = true;
+  options.listeners.emplace_back(listener);
+  options.max_bgerror_resume_count = 0;
+  options.atomic_flush = true;
+  Status s;
+
+  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
+  error_msg.SetRetryable(true);
+
+  listener->EnableAutoRecovery(false);
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::SyncClosedLogs:Start",
+      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  CreateAndReopenWithCF({"pikachu, sdfsdfsdf"}, options);
+
+  WriteOptions wo = WriteOptions();
+  wo.disableWAL = false;
+  ASSERT_OK(Put(Key(1), "val1", wo));
+
+  s = Flush();
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  fault_fs_->SetFilesystemActive(true);
+  auto cfh = dbfull()->GetColumnFamilyHandle(1);
+  s = dbfull()->DropColumnFamily(cfh);
+
+  s = dbfull()->Resume();
+  ASSERT_OK(s);
+  ASSERT_EQ("val1", Get(Key(1)));
+  ASSERT_OK(Put(Key(3), "val3", wo));
+  ASSERT_EQ("val3", Get(Key(3)));
+  s = Flush();
+  ASSERT_OK(s);
+  ASSERT_EQ("val3", Get(Key(3)));
+
+  Destroy(options);
+}
+
 TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableError1) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
@@ -333,6 +448,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableError1) {
  options.create_if_missing = true;
  options.listeners.emplace_back(listener);
  options.max_bgerror_resume_count = 0;
+  options.statistics = CreateDBStatistics();
  Status s;

  listener->EnableAutoRecovery(false);
@@ -363,11 +479,23 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableError1) {
  s = Flush();
  ASSERT_OK(s);
  ASSERT_EQ("val3", Get(Key(3)));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_IO_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT));

  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableError2) {
+TEST_F(DBErrorHandlingFSTest, FLushWriteNoWALRetryableError2) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
  Options options = GetDefaultOptions();
@@ -410,7 +538,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableError2) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableError3) {
+TEST_F(DBErrorHandlingFSTest, FLushWriteNoWALRetryableError3) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
  Options options = GetDefaultOptions();
@@ -521,7 +649,7 @@ TEST_F(DBErrorHandlingFSTest, ManifestWriteRetryableError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
@@ -567,7 +695,7 @@ TEST_F(DBErrorHandlingFSTest, ManifestWriteFileScopeError) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
@@ -864,7 +992,7 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteError) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, CompactionWriteRetryableError) {
+TEST_F(DBErrorHandlingFSTest, DISABLED_CompactionWriteRetryableError) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
  Options options = GetDefaultOptions();
@@ -892,15 +1020,17 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteRetryableError) {
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "CompactionJob::OpenCompactionOutputFile",
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundCompaction:Finish",
+      [&](void*) { CancelAllBackgroundWork(dbfull()); });
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();

  ASSERT_OK(Put(Key(1), "val"));
  s = Flush();
  ASSERT_OK(s);

-  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
-
+  s = dbfull()->TEST_GetBGError();
+  ASSERT_OK(s);
  fault_fs_->SetFilesystemActive(true);
  SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();
@@ -909,7 +1039,7 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteRetryableError) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, CompactionWriteFileScopeError) {
+TEST_F(DBErrorHandlingFSTest, DISABLED_CompactionWriteFileScopeError) {
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
  Options options = GetDefaultOptions();
@@ -940,14 +1070,17 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteFileScopeError) {
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "CompactionJob::OpenCompactionOutputFile",
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundCompaction:Finish",
+      [&](void*) { CancelAllBackgroundWork(dbfull()); });
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();

  ASSERT_OK(Put(Key(1), "val"));
  s = Flush();
  ASSERT_OK(s);

-  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
+  s = dbfull()->TEST_GetBGError();
+  ASSERT_OK(s);

  fault_fs_->SetFilesystemActive(true);
  SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -1005,6 +1138,7 @@ TEST_F(DBErrorHandlingFSTest, AutoRecoverFlushError) {
  options.env = fault_env_.get();
  options.create_if_missing = true;
  options.listeners.emplace_back(listener);
+  options.statistics = CreateDBStatistics();
  Status s;

  listener->EnableAutoRecovery();
@@ -1023,6 +1157,18 @@ TEST_F(DBErrorHandlingFSTest, AutoRecoverFlushError) {

  s = Put(Key(1), "val");
  ASSERT_OK(s);
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_IO_ERROR_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT));
+  ASSERT_EQ(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT));

  Reopen(options);
  ASSERT_EQ("val", Get(Key(0)));
@@ -1391,6 +1537,10 @@ TEST_F(DBErrorHandlingFSTest, MultiDBCompactionError) {
    EXPECT_EQ(atoi(prop.c_str()), 1);
  }

+  SstFileManagerImpl* sfmImpl =
+      static_cast_with_check<SstFileManagerImpl>(sfm.get());
+  sfmImpl->Close();
+
  for (auto i = 0; i < kNumDbInstances; ++i) {
    char buf[16];
    snprintf(buf, sizeof(buf), "_%d", i);
@@ -1524,6 +1674,10 @@ TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
    EXPECT_EQ(atoi(prop.c_str()), 1);
  }

+  SstFileManagerImpl* sfmImpl =
+      static_cast_with_check<SstFileManagerImpl>(sfm.get());
+  sfmImpl->Close();
+
  for (auto i = 0; i < kNumDbInstances; ++i) {
    char buf[16];
    snprintf(buf, sizeof(buf), "_%d", i);
@@ -1544,7 +1698,7 @@ TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
 // to soft error and trigger auto resume. During auto resume, SwitchMemtable
 // is disabled to avoid small SST tables. Write can still be applied before
 // the bg error is cleaned unless the memtable is full.
-TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover1) {
+TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableErrorAutoRecover1) {
  // Activate the FS before the first resume
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
@@ -1554,6 +1708,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover1) {
  options.listeners.emplace_back(listener);
  options.max_bgerror_resume_count = 2;
  options.bgerror_resume_retry_interval = 100000;  // 0.1 second
+  options.statistics = CreateDBStatistics();
  Status s;

  listener->EnableAutoRecovery(false);
@@ -1581,6 +1736,22 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover1) {
  ASSERT_EQ("val1", Get(Key(1)));
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
+  ASSERT_EQ(3, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_ERROR_COUNT));
+  ASSERT_EQ(3, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_IO_ERROR_COUNT));
+  ASSERT_EQ(3, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_COUNT));
+  ASSERT_LE(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT));
+  ASSERT_LE(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT));
+  HistogramData autoresume_retry;
+  options.statistics->histogramData(ERROR_HANDLER_AUTORESUME_RETRY_COUNT,
+                                    &autoresume_retry);
+  ASSERT_GE(autoresume_retry.max, 0);
  ASSERT_OK(Put(Key(2), "val2", wo));
  s = Flush();
  // Since auto resume fails, the bg error is not cleand, flush will
@@ -1597,7 +1768,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover1) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover2) {
+TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableErrorAutoRecover2) {
  // Activate the FS before the first resume
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
@@ -1607,6 +1778,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover2) {
  options.listeners.emplace_back(listener);
  options.max_bgerror_resume_count = 2;
  options.bgerror_resume_retry_interval = 100000;  // 0.1 second
+  options.statistics = CreateDBStatistics();
  Status s;

  listener->EnableAutoRecovery(false);
@@ -1630,6 +1802,22 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover2) {
  fault_fs_->SetFilesystemActive(true);
  ASSERT_EQ(listener->WaitForRecovery(5000000), true);
  ASSERT_EQ("val1", Get(Key(1)));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_IO_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_BG_RETRYABLE_IO_ERROR_COUNT));
+  ASSERT_EQ(1, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_COUNT));
+  ASSERT_LE(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_RETRY_TOTAL_COUNT));
+  ASSERT_LE(0, options.statistics->getAndResetTickerCount(
+                   ERROR_HANDLER_AUTORESUME_SUCCESS_COUNT));
+  HistogramData autoresume_retry;
+  options.statistics->histogramData(ERROR_HANDLER_AUTORESUME_RETRY_COUNT,
+                                    &autoresume_retry);
+  ASSERT_GE(autoresume_retry.max, 0);
  ASSERT_OK(Put(Key(2), "val2", wo));
  s = Flush();
  // Since auto resume is successful, the bg error is cleaned, flush will
@@ -1639,56 +1827,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritNoWALRetryableeErrorAutoRecover2) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, DISABLED_FLushWritRetryableeErrorAutoRecover1) {
-  // Fail the first resume and make the second resume successful
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_env_.get();
-  options.create_if_missing = true;
-  options.listeners.emplace_back(listener);
-  options.max_bgerror_resume_count = 2;
-  options.bgerror_resume_retry_interval = 100000;  // 0.1 second
-  Status s;
-
-  listener->EnableAutoRecovery(false);
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  ASSERT_OK(Put(Key(1), "val1"));
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"RecoverFromRetryableBGIOError:BeforeWait0",
-        "FLushWritRetryableeErrorAutoRecover1:0"},
-       {"FLushWritRetryableeErrorAutoRecover1:1",
-        "RecoverFromRetryableBGIOError:BeforeWait1"},
-       {"RecoverFromRetryableBGIOError:RecoverSuccess",
-        "FLushWritRetryableeErrorAutoRecover1:2"}});
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeFinishBuildTable",
-      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover1:0");
-  fault_fs_->SetFilesystemActive(true);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover1:1");
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover1:2");
-  SyncPoint::GetInstance()->DisableProcessing();
-
-  ASSERT_EQ("val1", Get(Key(1)));
-  Reopen(options);
-  ASSERT_EQ("val1", Get(Key(1)));
-  ASSERT_OK(Put(Key(2), "val2"));
-  ASSERT_OK(Flush());
-  ASSERT_EQ("val2", Get(Key(2)));
-
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover2) {
+TEST_F(DBErrorHandlingFSTest, FLushWritRetryableErrorAutoRecover1) {
  // Activate the FS before the first resume
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
@@ -1713,7 +1852,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover2) {

  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  SyncPoint::GetInstance()->DisableProcessing();
  fault_fs_->SetFilesystemActive(true);
  ASSERT_EQ(listener->WaitForRecovery(5000000), true);
@@ -1728,7 +1867,7 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover2) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover3) {
+TEST_F(DBErrorHandlingFSTest, FLushWritRetryableErrorAutoRecover2) {
  // Fail all the resume and let user to resume
  std::shared_ptr<ErrorHandlerFSListener> listener(
      new ErrorHandlerFSListener());
@@ -1748,18 +1887,18 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover3) {

  ASSERT_OK(Put(Key(1), "val1"));
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"FLushWritRetryableeErrorAutoRecover3:0",
+      {{"FLushWritRetryableeErrorAutoRecover2:0",
        "RecoverFromRetryableBGIOError:BeforeStart"},
       {"RecoverFromRetryableBGIOError:LoopOut",
-        "FLushWritRetryableeErrorAutoRecover3:1"}});
+        "FLushWritRetryableeErrorAutoRecover2:1"}});
  SyncPoint::GetInstance()->SetCallBack(
      "BuildTable:BeforeFinishBuildTable",
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover3:0");
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover3:1");
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
+  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover2:0");
+  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover2:1");
  fault_fs_->SetFilesystemActive(true);
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();
@@ -1777,173 +1916,6 @@ TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover3) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, DISABLED_FLushWritRetryableeErrorAutoRecover4) {
-  // Fail the first resume and does not do resume second time because
-  // the IO error severity is Fatal Error and not Retryable.
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_env_.get();
-  options.create_if_missing = true;
-  options.listeners.emplace_back(listener);
-  options.max_bgerror_resume_count = 2;
-  options.bgerror_resume_retry_interval = 10;  // 0.1 second
-  Status s;
-
-  listener->EnableAutoRecovery(false);
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-  IOStatus nr_msg = IOStatus::IOError("No Retryable Fatal IO Error");
-  nr_msg.SetRetryable(false);
-
-  ASSERT_OK(Put(Key(1), "val1"));
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"RecoverFromRetryableBGIOError:BeforeStart",
-        "FLushWritRetryableeErrorAutoRecover4:0"},
-       {"FLushWritRetryableeErrorAutoRecover4:2",
-        "RecoverFromRetryableBGIOError:RecoverFail0"}});
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeFinishBuildTable",
-      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->SetCallBack(
-      "RecoverFromRetryableBGIOError:BeforeResume1",
-      [&](void*) { fault_fs_->SetFilesystemActive(false, nr_msg); });
-
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover4:0");
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover4:2");
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs_->SetFilesystemActive(true);
-  // Even the FS is recoverd, due to the Fatal Error in bg_error_ the resume
-  // and flush will all fail.
-  ASSERT_EQ("val1", Get(Key(1)));
-  ASSERT_NOK(dbfull()->Resume());
-  ASSERT_EQ("val1", Get(Key(1)));
-  ASSERT_OK(Put(Key(2), "val2"));
-  ASSERT_NOK(Flush());
-  ASSERT_EQ("NOT_FOUND", Get(Key(2)));
-
-  Reopen(options);
-  ASSERT_EQ("val1", Get(Key(1)));
-  ASSERT_OK(Put(Key(2), "val2"));
-  ASSERT_OK(Flush());
-  ASSERT_EQ("val2", Get(Key(2)));
-
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingFSTest, DISABLED_FLushWritRetryableeErrorAutoRecover5) {
-  // During the resume, call DB->CLose, make sure the resume thread exist
-  // before close continues. Due to the shutdown, the resume is not successful
-  // and the FS does not become active, so close status is still IO error
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_env_.get();
-  options.create_if_missing = true;
-  options.listeners.emplace_back(listener);
-  options.max_bgerror_resume_count = 2;
-  options.bgerror_resume_retry_interval = 10;  // 0.1 second
-  Status s;
-
-  listener->EnableAutoRecovery(false);
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  ASSERT_OK(Put(Key(1), "val1"));
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"RecoverFromRetryableBGIOError:BeforeStart",
-        "FLushWritRetryableeErrorAutoRecover5:0"}});
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeFinishBuildTable",
-      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover5:0");
-  // The first resume will cause recovery_error and its severity is the
-  // Fatal error
-  s = dbfull()->Close();
-  ASSERT_NOK(s);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs_->SetFilesystemActive(true);
-
-  Reopen(options);
-  ASSERT_NE("val1", Get(Key(1)));
-  ASSERT_OK(Put(Key(2), "val2"));
-  s = Flush();
-  ASSERT_OK(s);
-  ASSERT_EQ("val2", Get(Key(2)));
-
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeErrorAutoRecover6) {
-  // During the resume, call DB->CLose, make sure the resume thread exist
-  // before close continues. Due to the shutdown, the resume is not successful
-  // and the FS does not become active, so close status is still IO error
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_env_.get();
-  options.create_if_missing = true;
-  options.listeners.emplace_back(listener);
-  options.max_bgerror_resume_count = 2;
-  options.bgerror_resume_retry_interval = 10;  // 0.1 second
-  Status s;
-
-  listener->EnableAutoRecovery(false);
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  ASSERT_OK(Put(Key(1), "val1"));
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"FLushWritRetryableeErrorAutoRecover6:0",
-        "RecoverFromRetryableBGIOError:BeforeStart"},
-       {"RecoverFromRetryableBGIOError:BeforeWait0",
-        "FLushWritRetryableeErrorAutoRecover6:1"},
-       {"FLushWritRetryableeErrorAutoRecover6:2",
-        "RecoverFromRetryableBGIOError:BeforeWait1"},
-       {"RecoverFromRetryableBGIOError:AfterWait0",
-        "FLushWritRetryableeErrorAutoRecover6:3"}});
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeFinishBuildTable",
-      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover6:0");
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover6:1");
-  fault_fs_->SetFilesystemActive(true);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover6:2");
-  TEST_SYNC_POINT("FLushWritRetryableeErrorAutoRecover6:3");
-  // The first resume will cause recovery_error and its severity is the
-  // Fatal error
-  s = dbfull()->Close();
-  ASSERT_OK(s);
-  SyncPoint::GetInstance()->DisableProcessing();
-
-  Reopen(options);
-  ASSERT_EQ("val1", Get(Key(1)));
-  ASSERT_OK(Put(Key(2), "val2"));
-  s = Flush();
-  ASSERT_OK(s);
-  ASSERT_EQ("val2", Get(Key(2)));
-
-  Destroy(options);
-}
-
 TEST_F(DBErrorHandlingFSTest, ManifestWriteRetryableErrorAutoRecover) {
  // Fail the first resume and let the second resume be successful
  std::shared_ptr<ErrorHandlerFSListener> listener(
@@ -1980,7 +1952,7 @@ TEST_F(DBErrorHandlingFSTest, ManifestWriteRetryableErrorAutoRecover) {
      [&](void*) { fault_fs_->SetFilesystemActive(false, error_msg); });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
+  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
  TEST_SYNC_POINT("ManifestWriteRetryableErrorAutoRecover:0");
  fault_fs_->SetFilesystemActive(true);
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -2190,8 +2162,7 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteRetryableErrorAutoRecover) {
  ASSERT_OK(s);

  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kSoftError);
-
+  ASSERT_OK(s);
  TEST_SYNC_POINT("CompactionWriteRetryableErrorAutoRecover0");
  SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();
@@ -2240,7 +2211,8 @@ TEST_F(DBErrorHandlingFSTest, WALWriteRetryableErrorAutoRecover1) {
      ASSERT_OK(batch.Put(Key(i), rnd.RandomString(1024)));
    }
    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-        {{"RecoverFromRetryableBGIOError:BeforeResume0", "WALWriteError1:0"},
+        {{"WALWriteErrorDone", "RecoverFromRetryableBGIOError:BeforeStart"},
+         {"RecoverFromRetryableBGIOError:BeforeResume0", "WALWriteError1:0"},
         {"WALWriteError1:1", "RecoverFromRetryableBGIOError:BeforeResume1"},
         {"RecoverFromRetryableBGIOError:RecoverSuccess", "WALWriteError1:2"}});

@@ -2256,6 +2228,7 @@ TEST_F(DBErrorHandlingFSTest, WALWriteRetryableErrorAutoRecover1) {
    wopts.sync = true;
    s = dbfull()->Write(wopts, &batch);
    ASSERT_EQ(true, s.IsIOError());
+    TEST_SYNC_POINT("WALWriteErrorDone");

    TEST_SYNC_POINT("WALWriteError1:0");
    fault_fs_->SetFilesystemActive(true);
@@ -125,8 +125,12 @@ void EventHelpers::LogAndNotifyTableFileCreationFinished(
              << table_properties.compression_options << "creation_time"
              << table_properties.creation_time << "oldest_key_time"
              << table_properties.oldest_key_time << "file_creation_time"
-              << table_properties.file_creation_time << "db_id"
-              << table_properties.db_id << "db_session_id"
+              << table_properties.file_creation_time
+              << "slow_compression_estimated_data_size"
+              << table_properties.slow_compression_estimated_data_size
+              << "fast_compression_estimated_data_size"
+              << table_properties.fast_compression_estimated_data_size
+              << "db_id" << table_properties.db_id << "db_session_id"
              << table_properties.db_session_id;

      // user collected properties
@@ -40,16 +40,25 @@ Status ExternalSstFileIngestionJob::Prepare(
    if (!status.ok()) {
      return status;
    }
-    files_to_ingest_.push_back(file_to_ingest);
-  }

-  for (const IngestedFileInfo& f : files_to_ingest_) {
-    if (f.cf_id !=
+    if (file_to_ingest.cf_id !=
            TablePropertiesCollectorFactory::Context::kUnknownColumnFamily &&
-        f.cf_id != cfd_->GetID()) {
+        file_to_ingest.cf_id != cfd_->GetID()) {
      return Status::InvalidArgument(
          "External file column family id don't match");
    }
+
+    if (file_to_ingest.num_entries == 0 &&
+        file_to_ingest.num_range_deletions == 0) {
+      return Status::InvalidArgument("File contain no entries");
+    }
+
+    if (!file_to_ingest.smallest_internal_key.Valid() ||
+        !file_to_ingest.largest_internal_key.Valid()) {
+      return Status::Corruption("Generated table have corrupted keys");
+    }
+
+    files_to_ingest_.emplace_back(std::move(file_to_ingest));
  }

  const Comparator* ucmp = cfd_->internal_comparator().user_comparator();
@@ -83,16 +92,6 @@ Status ExternalSstFileIngestionJob::Prepare(
    return Status::NotSupported("Files have overlapping ranges");
  }

-  for (IngestedFileInfo& f : files_to_ingest_) {
-    if (f.num_entries == 0 && f.num_range_deletions == 0) {
-      return Status::InvalidArgument("File contain no entries");
-    }
-
-    if (!f.smallest_internal_key.Valid() || !f.largest_internal_key.Valid()) {
-      return Status::Corruption("Generated table have corrupted keys");
-    }
-  }
-
  // Copy/Move external files into DB
  std::unordered_set<size_t> ingestion_path_ids;
  for (IngestedFileInfo& f : files_to_ingest_) {
@@ -293,12 +292,13 @@ Status ExternalSstFileIngestionJob::Prepare(

  // TODO: The following is duplicated with Cleanup().
  if (!status.ok()) {
+    IOOptions io_opts;
    // We failed, remove all files that we copied into the db
    for (IngestedFileInfo& f : files_to_ingest_) {
      if (f.internal_file_path.empty()) {
        continue;
      }
-      Status s = env_->DeleteFile(f.internal_file_path);
+      Status s = fs_->DeleteFile(f.internal_file_path, io_opts, nullptr);
      if (!s.ok()) {
        ROCKS_LOG_WARN(db_options_.info_log,
                       "AddFile() clean up for file %s failed : %s",
@@ -392,7 +392,7 @@ Status ExternalSstFileIngestionJob::Run() {
    int64_t temp_current_time = 0;
    uint64_t current_time = kUnknownFileCreationTime;
    uint64_t oldest_ancester_time = kUnknownOldestAncesterTime;
-    if (env_->GetCurrentTime(&temp_current_time).ok()) {
+    if (clock_->GetCurrentTime(&temp_current_time).ok()) {
      current_time = oldest_ancester_time =
          static_cast<uint64_t>(temp_current_time);
    }
@@ -410,7 +410,7 @@ void ExternalSstFileIngestionJob::UpdateStats() {
  // Update internal stats for new ingested files
  uint64_t total_keys = 0;
  uint64_t total_l0_files = 0;
-  uint64_t total_time = env_->NowMicros() - job_start_time_;
+  uint64_t total_time = clock_->NowMicros() - job_start_time_;

  EventLoggerStream stream = event_logger_->Log();
  stream << "event"
@@ -466,6 +466,7 @@ void ExternalSstFileIngestionJob::UpdateStats() {
 }

 void ExternalSstFileIngestionJob::Cleanup(const Status& status) {
+  IOOptions io_opts;
  if (!status.ok()) {
    // We failed to add the files to the database
    // remove all the files we copied
@@ -473,7 +474,7 @@ void ExternalSstFileIngestionJob::Cleanup(const Status& status) {
      if (f.internal_file_path.empty()) {
        continue;
      }
-      Status s = env_->DeleteFile(f.internal_file_path);
+      Status s = fs_->DeleteFile(f.internal_file_path, io_opts, nullptr);
      if (!s.ok()) {
        ROCKS_LOG_WARN(db_options_.info_log,
                       "AddFile() clean up for file %s failed : %s",
@@ -485,7 +486,7 @@ void ExternalSstFileIngestionJob::Cleanup(const Status& status) {
  } else if (status.ok() && ingestion_options_.move_files) {
    // The files were moved and added successfully, remove original file links
    for (IngestedFileInfo& f : files_to_ingest_) {
-      Status s = env_->DeleteFile(f.external_file_path);
+      Status s = fs_->DeleteFile(f.external_file_path, io_opts, nullptr);
      if (!s.ok()) {
        ROCKS_LOG_WARN(
            db_options_.info_log,
@@ -810,7 +811,8 @@ Status ExternalSstFileIngestionJob::AssignGlobalSeqnoForIngestedFile(
        fs_->NewRandomRWFile(file_to_ingest->internal_file_path, env_options_,
                             &rwfile, nullptr);
    if (status.ok()) {
-      FSRandomRWFilePtr fsptr(std::move(rwfile), io_tracer_);
+      FSRandomRWFilePtr fsptr(std::move(rwfile), io_tracer_,
+                              file_to_ingest->internal_file_path);
      std::string seqno_val;
      PutFixed64(&seqno_val, seqno);
      status = fsptr->Write(file_to_ingest->global_seqno_offset, seqno_val,
@@ -16,13 +16,14 @@
 #include "logging/event_logger.h"
 #include "options/db_options.h"
 #include "rocksdb/db.h"
-#include "rocksdb/env.h"
+#include "rocksdb/file_system.h"
 #include "rocksdb/sst_file_writer.h"
 #include "util/autovector.h"

 namespace ROCKSDB_NAMESPACE {

 class Directories;
+class SystemClock;

 struct IngestedFileInfo {
  // External file path
@@ -73,13 +74,13 @@ struct IngestedFileInfo {
 class ExternalSstFileIngestionJob {
 public:
  ExternalSstFileIngestionJob(
-      Env* env, VersionSet* versions, ColumnFamilyData* cfd,
+      VersionSet* versions, ColumnFamilyData* cfd,
      const ImmutableDBOptions& db_options, const EnvOptions& env_options,
      SnapshotList* db_snapshots,
      const IngestExternalFileOptions& ingestion_options,
      Directories* directories, EventLogger* event_logger,
      const std::shared_ptr<IOTracer>& io_tracer)
-      : env_(env),
+      : clock_(db_options.clock),
        fs_(db_options.fs, io_tracer),
        versions_(versions),
        cfd_(cfd),
@@ -89,7 +90,7 @@ class ExternalSstFileIngestionJob {
        ingestion_options_(ingestion_options),
        directories_(directories),
        event_logger_(event_logger),
-        job_start_time_(env_->NowMicros()),
+        job_start_time_(clock_->NowMicros()),
        consumed_seqno_count_(0),
        io_tracer_(io_tracer) {
    assert(directories != nullptr);
@@ -169,7 +170,7 @@ class ExternalSstFileIngestionJob {
  template <typename TWritableFile>
  Status SyncIngestedFile(TWritableFile* file);

-  Env* env_;
+  SystemClock* clock_;
  FileSystemPtr fs_;
  VersionSet* versions_;
  ColumnFamilyData* cfd_;
--- a/Show More
+++ b/Show More