Fix windows build errors (rdtsc and fnptr) (#12008)

Summary:
Combining best parts of https://github.com/facebook/rocksdb/issues/11794 and https://github.com/facebook/rocksdb/issues/11766, fixing the CircleCI config in the latter. I was going to amend the latter but wasn't granted access.

Ideally this would be ported back to 8.4 branch and crc32c part into 8.3 branch.

BACKPORT NOTE: removed CircleCI config changes from this diff as they
depend (at least superficially) on changes not in this branch.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12008

Test Plan: CI

Reviewed By: hx235

Differential Revision: D50616172

Pulled By: pdillinger

fbshipit-source-id: fa7f778bc281e881a140522e774f480c6d1e5f48

.github/workflows/sanity_check.yml

@@ -33,9 +33,7 @@ jobs:
       run: pip install argparse
 
     - name: Download clang-format-diff.py
-      uses: wei/wget@v1
-      with:
-        args: https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
+      run: wget https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
 
     - name: Check format
       run: VERBOSE_CHECK=1 make check-format

.gitignore

@@ -95,3 +95,5 @@ fuzz/crash-*
 
 cmake-build-*
 third-party/folly/
+.cache
+*.sublime-*

CMakeLists.txt

@@ -253,33 +253,10 @@ if(CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
   endif(HAS_LOONGARCH64)
 endif(CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
 
-option(PORTABLE "build a portable binary" OFF)
-option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
-option(FORCE_AVX "force building with AVX, even when PORTABLE=ON" OFF)
-option(FORCE_AVX2 "force building with AVX2, even when PORTABLE=ON" OFF)
-if(PORTABLE)
-  add_definitions(-DROCKSDB_PORTABLE)
-
-  # MSVC does not need a separate compiler flag to enable SSE4.2; if nmmintrin.h
-  # is available, it is available by default.
-  if(FORCE_SSE42 AND NOT MSVC)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.2 -mpclmul")
-  endif()
-  if(MSVC)
-    if(FORCE_AVX)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX")
-    endif()
-    # MSVC automatically enables BMI / lzcnt with AVX2.
-    if(FORCE_AVX2)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
-    endif()
-  else()
-    if(FORCE_AVX)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mavx")
-    endif()
-    if(FORCE_AVX2)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mavx2 -mbmi -mlzcnt")
-    endif()
+set(PORTABLE 0 CACHE STRING "Minimum CPU arch to support, or 0 = current CPU, 1 = baseline CPU")
+if(PORTABLE STREQUAL 1)
+  # Usually nothing to do; compiler default is typically the most general
+  if(NOT MSVC)
     if(CMAKE_SYSTEM_PROCESSOR MATCHES "^s390x")
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=z196")
     endif()
@@ -287,10 +264,21 @@ if(PORTABLE)
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=loongarch64")
     endif()
   endif()
+elseif(PORTABLE MATCHES [^0]+)
+  # Name of a CPU arch spec or feature set to require
+  if(MSVC)
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:${PORTABLE}")
+  else()
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=${PORTABLE}")
+  endif()
 else()
   if(MSVC)
+    # NOTE: No auto-detection of current CPU, but instead assume some useful
+    # level of optimization is supported
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
   else()
+    # Require instruction set from current CPU (with some legacy or opt-out
+    # exceptions)
     if(CMAKE_SYSTEM_PROCESSOR MATCHES "^s390x" AND NOT HAS_S390X_MARCH_NATIVE)
       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=z196")
     elseif(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64" AND NOT HAS_ARMV8_CRC)
@@ -305,25 +293,6 @@ if(NOT MSVC)
   set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
 endif()
 
-CHECK_CXX_SOURCE_COMPILES("
-#include <cstdint>
-#include <nmmintrin.h>
-#include <wmmintrin.h>
-int main() {
-  volatile uint32_t x = _mm_crc32_u32(0, 0);
-  const auto a = _mm_set_epi64x(0, 0);
-  const auto b = _mm_set_epi64x(0, 0);
-  const auto c = _mm_clmulepi64_si128(a, b, 0x00);
-  auto d = _mm_cvtsi128_si64(c);
-}
-" HAVE_SSE42)
-if(HAVE_SSE42)
-  add_definitions(-DHAVE_SSE42)
-  add_definitions(-DHAVE_PCLMUL)
-elseif(FORCE_SSE42)
-  message(FATAL_ERROR "FORCE_SSE42=ON but unable to compile with SSE4.2 enabled")
-endif()
-
 # Check if -latomic is required or not
 if (NOT MSVC)
   set(CMAKE_REQUIRED_FLAGS "--std=c++17")
@@ -578,7 +547,7 @@ if(HAVE_SCHED_GETCPU)
   add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
 endif()
 
-check_cxx_symbol_exists(getauxval auvx.h HAVE_AUXV_GETAUXVAL)
+check_cxx_symbol_exists(getauxval "sys/auxv.h" HAVE_AUXV_GETAUXVAL)
 if(HAVE_AUXV_GETAUXVAL)
   add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
 endif()
@@ -896,6 +865,8 @@ set(SOURCES
         util/string_util.cc
         util/thread_local.cc
         util/threadpool_imp.cc
+        util/udt_util.cc
+        util/write_batch_util.cc
         util/xxhash.cc
         utilities/agg_merge/agg_merge.cc
         utilities/backup/backup_engine.cc
@@ -1010,12 +981,6 @@ if ( ROCKSDB_PLUGINS )
   endforeach()
 endif()
 
-if(HAVE_SSE42 AND NOT MSVC)
-  set_source_files_properties(
-    util/crc32c.cc
-    PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
-endif()
-
 if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
   list(APPEND SOURCES
     util/crc32c_ppc.c
@@ -1327,6 +1292,7 @@ if(WITH_TESTS)
         db/db_bloom_filter_test.cc
         db/db_compaction_filter_test.cc
         db/db_compaction_test.cc
+        db/db_clip_test.cc
         db/db_dynamic_level_test.cc
         db/db_encryption_test.cc
         db/db_flush_test.cc
@@ -1457,6 +1423,7 @@ if(WITH_TESTS)
         util/timer_test.cc
         util/thread_list_test.cc
         util/thread_local_test.cc
+        util/udt_util_test.cc
         util/work_queue_test.cc
         utilities/agg_merge/agg_merge_test.cc
         utilities/backup/backup_engine_test.cc
@@ -1625,3 +1592,6 @@ option(WITH_BENCHMARK "build benchmark tests" OFF)
 if(WITH_BENCHMARK)
   add_subdirectory(${PROJECT_SOURCE_DIR}/microbench/)
 endif()
+
+target_include_directories(${PROJECT_NAME} PUBLIC
+  $<BUILD_INTERFACE:${PROJECT_SOURCE_DIR}/include>)

HISTORY.md

@@ -1,5 +1,141 @@
 # Rocksdb Change Log
-## Unreleased
+> NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
+
+## 8.6.7 (09/26/2023)
+### Bug Fixes
+* Fixed a bug where compaction read under non direct IO still falls back to RocksDB internal prefetching after file system's prefetching returns non-OK status other than `Status::NotSupported()`
+
+### Behavior Changes
+* For non direct IO, eliminate the file system prefetching attempt for compaction read when `Options::compaction_readahead_size` is 0
+
+## 8.6.6 (09/25/2023)
+### Bug Fixes
+* Fix a bug with atomic_flush=true that can cause DB to stuck after a flush fails (#11872).
+* Fix a bug where RocksDB (with atomic_flush=false) can delete output SST files of pending flushes when a previous concurrent flush fails (#11865). This can result in DB entering read-only state with error message like `IO error: No such file or directory: While open a file for random read: /tmp/rocksdbtest-501/db_flush_test_87732_4230653031040984171/000013.sst`.
+* When the compressed secondary cache capacity is reduced to 0, it should be completely disabled. Before this fix, inserts and lookups would still go to the backing `LRUCache` before returning, thus incurring locking overhead. With this fix, inserts and lookups are no-ops and do not add any overhead.
+
+## 8.6.5 (09/15/2023)
+### Bug Fixes
+* Fixed a bug where `rocksdb.file.read.verify.file.checksums.micros` is not populated.
+
+## 8.6.4 (09/13/2023)
+### Public API changes
+* Add a column family option `default_temperature` that is used for file reading accounting purpose, such as io statistics, for files that don't have an explicitly set temperature.
+
+## 8.6.3 (09/12/2023)
+### Bug Fixes
+* Fix a bug where if there is an error reading from offset 0 of a file from L1+ and that the file is not the first file in the sorted run, data can be lost in compaction and read/scan can return incorrect results.
+* Fix a bug where iterator may return incorrect result for DeleteRange() users if there was an error reading from a file.
+
+## 8.6.2 (09/11/2023)
+### Bug Fixes
+* Add a fix for async_io where during seek, when reading a block for seeking a target key in a file without any readahead, the iterator aligned the read on a page boundary and reading more than necessary. This increased the storage read bandwidth usage.
+
+## 8.6.1 (08/30/2023)
+### Public API Changes
+* `Options::compaction_readahead_size` 's default value is changed from 0 to 2MB.
+
+### Behavior Changes
+* Compaction read performance will regress when `Options::compaction_readahead_size` is explicitly set to 0
+
+## 8.6.0 (08/18/2023)
+### New Features
+* Added enhanced data integrity checking on SST files with new format_version=6. Performance impact is very small or negligible. Previously if SST data was misplaced or re-arranged by the storage layer, it could pass block checksum with higher than 1 in 4 billion probability. With format_version=6, block checksums depend on what file they are in and location within the file. This way, misplaced SST data is no more likely to pass checksum verification than randomly corrupted data. Also in format_version=6, SST footers are checksum-protected.
+* Add a new feature to trim readahead_size during scans upto upper_bound when iterate_upper_bound is specified. It's enabled through ReadOptions.auto_readahead_size. Users must also specify ReadOptions.iterate_upper_bound.
+* RocksDB will compare the number of input keys to the number of keys processed after each compaction. Compaction will fail and report Corruption status if the verification fails. Option `compaction_verify_record_count` is introduced for this purpose and is enabled by default.
+* Add a CF option `bottommost_file_compaction_delay` to allow specifying the delay of bottommost level single-file compactions.
+* Add support to allow enabling / disabling user-defined timestamps feature for an existing column family in combination with the in-Memtable only feature.
+* Implement a new admission policy for the compressed secondary cache that admits blocks evicted from the primary cache with the hit bit set. This policy can be specified in TieredVolatileCacheOptions by setting the newly added adm_policy option.
+* Add a column family option `memtable_max_range_deletions` that limits the number of range deletions in a memtable. RocksDB will try to do an automatic flush after the limit is reached. (#11358)
+* Add PutEntity API in sst_file_writer
+* Add `timeout` in microsecond option to `WaitForCompactOptions` to allow timely termination of prolonged waiting in scenarios like recurring recoverable errors, such as out-of-space situations and continuous write streams that sustain ongoing flush and compactions
+* New statistics `rocksdb.file.read.{get|multiget|db.iterator|verify.checksum|verify.file.checksums}.micros` measure read time of block-based SST tables or blob files during db open, `Get()`, `MultiGet()`, using db iterator, `VerifyFileChecksums()` and `VerifyChecksum()`. They require stats level greater than `StatsLevel::kExceptDetailedTimers`.
+* Add close_db option to `WaitForCompactOptions` to call Close() after waiting is done.
+* Add a new compression option `CompressionOptions::checksum` for enabling ZSTD's checksum feature to detect corruption during decompression.
+
+### Public API Changes
+* Mark `Options::access_hint_on_compaction_start` related APIs as deprecated. See #11631 for alternative behavior.
+
+### Behavior Changes
+* Statistics `rocksdb.sst.read.micros` now includes time spent on multi read and async read into the file
+* For Universal Compaction users, periodic compaction (option `periodic_compaction_seconds`) will be set to 30 days by default if block based table is used.
+
+### Bug Fixes
+* Fix a bug in FileTTLBooster that can cause users with a large number of levels (more than 65) to see errors like "runtime error: shift exponent .. is too large.." (#11673).
+
+## 8.5.0 (07/21/2023)
+### Public API Changes
+* Removed recently added APIs `GeneralCache` and `MakeSharedGeneralCache()` as our plan changed to stop exposing a general-purpose cache interface. The old forms of these APIs, `Cache` and `NewLRUCache()`, are still available, although general-purpose caching support will be dropped eventually.
+
+### Behavior Changes
+* Option `periodic_compaction_seconds` no longer supports FIFO compaction: setting it has no effect on FIFO compactions. FIFO compaction users should only set option `ttl` instead.
+* Move prefetching responsibility to page cache for compaction read for non directIO use case
+
+### Performance Improvements
+* In case of direct_io, if buffer passed by callee is already aligned, RandomAccessFileRead::Read will avoid realloacting a new buffer, reducing memcpy and use already passed aligned buffer.
+* Small efficiency improvement to HyperClockCache by reducing chance of compiler-generated heap allocations
+
+### Bug Fixes
+* Fix use_after_free bug in async_io MultiReads when underlying FS enabled kFSBuffer. kFSBuffer is when underlying FS pass their own buffer instead of using RocksDB scratch in FSReadRequest. Right now it's an experimental feature.
+
+## 8.4.0 (06/26/2023)
+### New Features
+* Add FSReadRequest::fs_scratch which is a data buffer allocated and provided by underlying FileSystem to RocksDB during reads, when FS wants to provide its own buffer with data instead of using RocksDB provided FSReadRequest::scratch. This can help in cpu optimization by avoiding copy from file system's buffer to RocksDB buffer. More details on how to use/enable it in file_system.h. Right now its supported only for MultiReads(async + sync) with non direct io.
+* Start logging non-zero user-defined timestamp sizes in WAL to signal user key format in subsequent records and use it during recovery. This change will break recovery from WAL files written by early versions that contain user-defined timestamps. The workaround is to ensure there are no WAL files to recover (i.e. by flushing before close) before upgrade.
+* Added new property "rocksdb.obsolete-sst-files-size-property" that reports the size of SST files that have become obsolete but have not yet been deleted or scheduled for deletion
+* Start to record the value of the flag `AdvancedColumnFamilyOptions.persist_user_defined_timestamps` in the Manifest and table properties for a SST file when it is created. And use the recorded flag when creating a table reader for the SST file. This flag is only explicitly record if it's false.
+* Add a new option OptimisticTransactionDBOptions::shared_lock_buckets that enables sharing mutexes for validating transactions between DB instances, for better balancing memory efficiency and validation contention across DB instances. Different column families and DBs also now use different hash seeds in this validation, so that the same set of key names will not contend across DBs or column families.
+* Add a new ticker `rocksdb.files.marked.trash.deleted` to track the number of trash files deleted by background thread from the trash queue.
+* Add an API NewTieredVolatileCache() in include/rocksdb/cache.h to allocate an instance of a block cache with a primary block cache tier and a compressed secondary cache tier. A cache of this type distributes memory reservations against the block cache, such as WriteBufferManager, table reader memory etc., proportionally across both the primary and compressed secondary cache.
+* Add `WaitForCompact()` to wait for all flush and compactions jobs to finish. Jobs to wait include the unscheduled (queued, but not scheduled yet).
+* Add `WriteBatch::Release()` that releases the batch's serialized data to the caller.
+
+### Public API Changes
+* Add C API `rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio`.
+* change the FileSystem::use_async_io() API to SupportedOps API in order to extend it to various operations supported by underlying FileSystem. Right now it contains FSSupportedOps::kAsyncIO and FSSupportedOps::kFSBuffer. More details about FSSupportedOps in filesystem.h
+* Add new tickers: `rocksdb.error.handler.bg.error.count`, `rocksdb.error.handler.bg.io.error.count`, `rocksdb.error.handler.bg.retryable.io.error.count` to replace the misspelled ones: `rocksdb.error.handler.bg.errro.count`, `rocksdb.error.handler.bg.io.errro.count`, `rocksdb.error.handler.bg.retryable.io.errro.count` ('error' instead of 'errro'). Users should switch to use the new tickers before 9.0 release as the misspelled old tickers will be completely removed then.
+* Overload the API CreateColumnFamilyWithImport() to support creating ColumnFamily by importing multiple ColumnFamilies It requires that CFs should not overlap in user key range.
+
+### Behavior Changes
+* Change the default value for option `level_compaction_dynamic_level_bytes` to true. This affects users who use leveled compaction and do not set this option explicitly. These users may see additional background compactions following DB open. These compactions help to shape the LSM according to `level_compaction_dynamic_level_bytes` such that the size of each level Ln is approximately size of Ln-1 * `max_bytes_for_level_multiplier`. Turning on this option has other benefits too: see more detail in wiki: https://github.com/facebook/rocksdb/wiki/Leveled-Compaction#option-level_compaction_dynamic_level_bytes-and-levels-target-size and in option comment in advanced_options.h (#11525).
+* For Leveled Compaction users, `CompactRange()` will now always try to compact to the last non-empty level. (#11468)
+For Leveled Compaction users, `CompactRange()` with `bottommost_level_compaction = BottommostLevelCompaction::kIfHaveCompactionFilter` will behave similar to `kForceOptimized` in that it will skip files created during this manual compaction when compacting files in the bottommost level. (#11468)
+* RocksDB will try to drop range tombstones during non-bottommost compaction when it is safe to do so. (#11459)
+* When a DB is openend with `allow_ingest_behind=true` (currently only Universal compaction is supported), files in the last level, i.e. the ingested files,  will not be included in any compaction. (#11489)
+* Statistics `rocksdb.sst.read.micros` scope is expanded to all SST reads except for file ingestion and column family import (some compaction reads were previously excluded).
+
+### Bug Fixes
+* Reduced cases of illegally using Env::Default() during static destruction by never destroying the internal PosixEnv itself (except for builds checking for memory leaks). (#11538)
+* Fix extra prefetching during seek in async_io when BlockBasedTableOptions.num_file_reads_for_auto_readahead is 1 leading to extra reads than required.
+* Fix a bug where compactions that are qualified to be run as 2 subcompactions were only run as one subcompaction.
+* Fix a use-after-move bug in block.cc.
+
+## 8.3.0 (05/19/2023)
+### New Features
+* Introduced a new option `block_protection_bytes_per_key`, which can be used to enable per key-value integrity protection for in-memory blocks in block cache (#11287).
+* Added `JemallocAllocatorOptions::num_arenas`. Setting `num_arenas > 1` may mitigate mutex contention in the allocator, particularly in scenarios where block allocations commonly bypass jemalloc tcache.
+* Improve the operational safety of publishing a DB or SST files to many hosts by using different block cache hash seeds on different hosts. The exact behavior is controlled by new option `ShardedCacheOptions::hash_seed`, which also documents the solved problem in more detail.
+* Introduced a new option `CompactionOptionsFIFO::file_temperature_age_thresholds` that allows FIFO compaction to compact files to different temperatures based on key age (#11428).
+* Added a new ticker stat to count how many times RocksDB detected a corruption while verifying a block checksum: `BLOCK_CHECKSUM_MISMATCH_COUNT`.
+* New statistics `rocksdb.file.read.db.open.micros` that measures read time of block-based SST tables or blob files during db open.
+* New statistics tickers for various iterator seek behaviors and relevant filtering, as \*`_LEVEL_SEEK_`\*. (#11460)
+
+### Public API Changes
+* EXPERIMENTAL: Add new API `DB::ClipColumnFamily` to clip the key in CF to a certain range. It will physically deletes all keys outside the range including tombstones.
+* Add `MakeSharedCache()` construction functions to various cache Options objects, and deprecated the `NewWhateverCache()` functions with long parameter lists.
+* Changed the meaning of various Bloom filter stats (prefix vs. whole key), with iterator-related filtering only being tracked in the new \*`_LEVEL_SEEK_`\*. stats. (#11460)
+
+### Behavior changes
+* For x86, CPU features are no longer detected at runtime nor in build scripts, but in source code using common preprocessor defines. This will likely unlock some small performance improvements on some newer hardware, but could hurt performance of the kCRC32c checksum, which is no longer the default, on some "portable" builds. See PR #11419 for details.
+
+### Bug Fixes
+* Delete an empty WAL file on DB open if the log number is less than the min log number to keep
+* Delete temp OPTIONS file on DB open if there is a failure to write it out or rename it
+
+### Performance Improvements
+* Improved the I/O efficiency of prefetching SST metadata by recording more information in the DB manifest. Opening files written with previous versions will still rely on heuristics for how much to prefetch (#11406).
+
+## 8.2.0 (04/24/2023)
 ### Public API Changes
 * `SstFileWriter::DeleteRange()` now returns `Status::InvalidArgument` if the range's end key comes before its start key according to the user comparator. Previously the behavior was undefined.
 * Add `multi_get_for_update` to C API.
@@ -14,6 +150,7 @@
 
 ### Bug Fixes
 * In the DB::VerifyFileChecksums API, ensure that file system reads of SST files are equal to the readahead_size in ReadOptions, if specified. Previously, each read was 2x the readahead_size.
+* In block cache tracing, fixed some cases of bad hit/miss information (and more) with MultiGet.
 
 ### New Features
 * Add experimental `PerfContext` counters `iter_{next|prev|seek}_count` for db iterator, each counting the times of corresponding API being called.
@@ -21,9 +158,6 @@
 * Added statistics tickers BYTES_COMPRESSED_FROM, BYTES_COMPRESSED_TO, BYTES_COMPRESSION_BYPASSED, BYTES_COMPRESSION_REJECTED, NUMBER_BLOCK_COMPRESSION_BYPASSED, and NUMBER_BLOCK_COMPRESSION_REJECTED. Disabled/deprecated histograms BYTES_COMPRESSED and BYTES_DECOMPRESSED, and ticker NUMBER_BLOCK_NOT_COMPRESSED. The new tickers offer more inight into compression ratios, rejected vs. disabled compression, etc. (#11388)
 * New statistics `rocksdb.file.read.{flush|compaction}.micros` that measure read time of block-based SST tables or blob files during flush or compaction.
 
-### Bug Fixes
-* In block cache tracing, fixed some cases of bad hit/miss information (and more) with MultiGet.
-
 ## 8.1.0 (03/18/2023)
 ### Behavior changes
 * Compaction output file cutting logic now considers range tombstone start keys. For example, SST partitioner now may receive ParitionRequest for range tombstone start keys.

INSTALL.md

@@ -20,12 +20,15 @@ There are few options when compiling RocksDB:
 depend on gflags. You will need to have gflags installed to run `make all`. This will compile RocksDB in debug mode. Don't
 use binaries compiled by `make all` in production.
 
-* By default the binary we produce is optimized for the platform you're compiling on
-(`-march=native` or the equivalent). SSE4.2 will thus be enabled automatically if your
-CPU supports it. To print a warning if your CPU does not support SSE4.2, build with
-`USE_SSE=1 make static_lib` or, if using CMake, `cmake -DFORCE_SSE42=ON`. If you want
-to build a portable binary, add `PORTABLE=1` before your make commands, like this:
-`PORTABLE=1 make static_lib`.
+* By default the binary we produce is optimized for the CPU you're compiling on
+(`-march=native` or the equivalent). To build a binary compatible with the most
+general architecture supported by your CPU and compiler, set `PORTABLE=1` for
+the build, but performance will suffer as many operations benefit from newer
+and wider instructions. In addition to `PORTABLE=0` (default) and `PORTABLE=1`,
+it can be set to an architecture name recognized by your compiler. For example,
+on 64-bit x86, a reasonable compromise is `PORTABLE=haswell` which supports
+many or most of the available optimizations while still being compatible with
+most processors made since roughly 2013.
 
 ## Dependencies
 

Makefile

@@ -88,6 +88,25 @@ endif
 
 $(info $$DEBUG_LEVEL is $(DEBUG_LEVEL), $$LIB_MODE is $(LIB_MODE))
 
+# Detect what platform we're building on.
+# 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="$(COMPILE_WITH_UBSAN)"; \
+                  export PORTABLE="$(PORTABLE)"; \
+                  export ROCKSDB_NO_FBCODE="$(ROCKSDB_NO_FBCODE)"; \
+                  export USE_CLANG="$(USE_CLANG)"; \
+                  export LIB_MODE="$(LIB_MODE)"; \
+		  export ROCKSDB_CXX_STANDARD="$(ROCKSDB_CXX_STANDARD)"; \
+		  export USE_FOLLY="$(USE_FOLLY)"; \
+                  "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
+# this file is generated by the previous line to set build flags and sources
+include make_config.mk
+
 # Figure out optimize level.
 ifneq ($(DEBUG_LEVEL), 2)
 	OPTIMIZE_LEVEL ?= -O2
@@ -223,25 +242,6 @@ am__v_AR_1 =
 AM_LINK = $(AM_V_CCLD)$(CXX) -L. $(patsubst lib%.a, -l%, $(patsubst lib%.$(PLATFORM_SHARED_EXT), -l%, $^)) $(EXEC_LDFLAGS) -o $@ $(LDFLAGS) $(COVERAGEFLAGS)
 AM_SHARE = $(AM_V_CCLD) $(CXX) $(PLATFORM_SHARED_LDFLAGS)$@ -L. $(patsubst lib%.$(PLATFORM_SHARED_EXT), -l%, $^) $(EXEC_LDFLAGS) $(LDFLAGS) -o $@
 
-# Detect what platform we're building on.
-# 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="$(COMPILE_WITH_UBSAN)"; \
-                  export PORTABLE="$(PORTABLE)"; \
-                  export ROCKSDB_NO_FBCODE="$(ROCKSDB_NO_FBCODE)"; \
-                  export USE_CLANG="$(USE_CLANG)"; \
-                  export LIB_MODE="$(LIB_MODE)"; \
-		  export ROCKSDB_CXX_STANDARD="$(ROCKSDB_CXX_STANDARD)"; \
-		  export USE_FOLLY="$(USE_FOLLY)"; \
-                  "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
-# this file is generated by the previous line to set build flags and sources
-include make_config.mk
-
 ROCKSDB_PLUGIN_MKS = $(foreach plugin, $(ROCKSDB_PLUGINS), plugin/$(plugin)/*.mk)
 include $(ROCKSDB_PLUGIN_MKS)
 ROCKSDB_PLUGIN_PROTO =ROCKSDB_NAMESPACE::ObjectLibrary\&, const std::string\&
@@ -337,8 +337,8 @@ ifneq ($(MACHINE), arm64)
 # linking with jemalloc (as it won't be arm64-compatible) and remove some other options
 # set during platform detection
 DISABLE_JEMALLOC=1
-PLATFORM_CCFLAGS := $(filter-out -march=native -DHAVE_SSE42 -DHAVE_AVX2, $(PLATFORM_CCFLAGS))
-PLATFORM_CXXFLAGS := $(filter-out -march=native -DHAVE_SSE42 -DHAVE_AVX2, $(PLATFORM_CXXFLAGS))
+PLATFORM_CCFLAGS := $(filter-out -march=native, $(PLATFORM_CCFLAGS))
+PLATFORM_CXXFLAGS := $(filter-out -march=native, $(PLATFORM_CXXFLAGS))
 endif
 endif
 endif
@@ -1417,6 +1417,9 @@ thread_local_test: $(OBJ_DIR)/util/thread_local_test.o $(TEST_LIBRARY) $(LIBRARY
 work_queue_test: $(OBJ_DIR)/util/work_queue_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+udt_util_test: $(OBJ_DIR)/util/udt_util_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 corruption_test: $(OBJ_DIR)/db/corruption_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -1480,6 +1483,9 @@ db_compaction_filter_test: $(OBJ_DIR)/db/db_compaction_filter_test.o $(TEST_LIBR
 db_compaction_test: $(OBJ_DIR)/db/db_compaction_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
+db_clip_test: $(OBJ_DIR)/db/db_clip_test.o $(TEST_LIBRARY) $(LIBRARY)
+	$(AM_LINK)
+
 db_dynamic_level_test: $(OBJ_DIR)/db/db_dynamic_level_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
@@ -2435,6 +2441,8 @@ checkout_folly:
 	@# NOTE: this hack is required for gcc in some cases
 	perl -pi -e 's/(__has_include.<experimental.memory_resource>.)/__cpp_rtti && $$1/' third-party/folly/folly/memory/MemoryResource.h
 
+CXX_M_FLAGS = $(filter -m%, $(CXXFLAGS))
+
 build_folly:
 	FOLLY_INST_PATH=`cd third-party/folly; $(PYTHON) build/fbcode_builder/getdeps.py show-inst-dir`; \
 	if [ "$$FOLLY_INST_PATH" ]; then \
@@ -2445,8 +2453,8 @@ build_folly:
 	fi
 	# Restore the original version of Invoke.h with boost dependency
 	cd third-party/folly && ${GIT_COMMAND} checkout folly/functional/Invoke.h
-	cd third-party/folly && MAYBE_AVX2=`echo $(CXXFLAGS) | grep -o -- -DHAVE_AVX2 | sed 's/-DHAVE_AVX2/-mavx2/g' || true` && \
-		CXXFLAGS=" $$MAYBE_AVX2 -DHAVE_CXX11_ATOMIC " $(PYTHON) build/fbcode_builder/getdeps.py build --no-tests
+	cd third-party/folly && \
+		CXXFLAGS=" $(CXX_M_FLAGS) -DHAVE_CXX11_ATOMIC " $(PYTHON) build/fbcode_builder/getdeps.py build --no-tests
 
 # ---------------------------------------------------------------------------
 #   Build size testing

PLUGINS.md

@@ -5,3 +5,4 @@ This is the list of all known third-party plugins for RocksDB. If something is m
 * [ZenFS](https://github.com/westerndigitalcorporation/zenfs): a file system for zoned block devices
 * [RADOS](https://github.com/riversand963/rocksdb-rados-env): an Env used for interacting with RADOS. Migrated from RocksDB main repo.
 * [PMEM](https://github.com/pmem/pmem-rocksdb-plugin): a collection of plugins to enable Persistent Memory on RocksDB.
+* [IPPCP](https://github.com/intel/ippcp-plugin-rocksdb): a plugin to enable encryption on RocksDB based on Intel optimized open source IPP-Crypto library.

TARGETS

@@ -264,6 +264,8 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "util/string_util.cc",
         "util/thread_local.cc",
         "util/threadpool_imp.cc",
+        "util/udt_util.cc",
+        "util/write_batch_util.cc",
         "util/xxhash.cc",
         "utilities/agg_merge/agg_merge.cc",
         "utilities/backup/backup_engine.cc",
@@ -354,351 +356,7 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "//folly/synchronization:distributed_mutex",
     ], headers=None, link_whole=False, extra_test_libs=False)
 
-cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[
-        "cache/cache.cc",
-        "cache/cache_entry_roles.cc",
-        "cache/cache_helpers.cc",
-        "cache/cache_key.cc",
-        "cache/cache_reservation_manager.cc",
-        "cache/charged_cache.cc",
-        "cache/clock_cache.cc",
-        "cache/compressed_secondary_cache.cc",
-        "cache/lru_cache.cc",
-        "cache/secondary_cache.cc",
-        "cache/secondary_cache_adapter.cc",
-        "cache/sharded_cache.cc",
-        "db/arena_wrapped_db_iter.cc",
-        "db/blob/blob_contents.cc",
-        "db/blob/blob_fetcher.cc",
-        "db/blob/blob_file_addition.cc",
-        "db/blob/blob_file_builder.cc",
-        "db/blob/blob_file_cache.cc",
-        "db/blob/blob_file_garbage.cc",
-        "db/blob/blob_file_meta.cc",
-        "db/blob/blob_file_reader.cc",
-        "db/blob/blob_garbage_meter.cc",
-        "db/blob/blob_log_format.cc",
-        "db/blob/blob_log_sequential_reader.cc",
-        "db/blob/blob_log_writer.cc",
-        "db/blob/blob_source.cc",
-        "db/blob/prefetch_buffer_collection.cc",
-        "db/builder.cc",
-        "db/c.cc",
-        "db/column_family.cc",
-        "db/compaction/compaction.cc",
-        "db/compaction/compaction_iterator.cc",
-        "db/compaction/compaction_job.cc",
-        "db/compaction/compaction_outputs.cc",
-        "db/compaction/compaction_picker.cc",
-        "db/compaction/compaction_picker_fifo.cc",
-        "db/compaction/compaction_picker_level.cc",
-        "db/compaction/compaction_picker_universal.cc",
-        "db/compaction/compaction_service_job.cc",
-        "db/compaction/compaction_state.cc",
-        "db/compaction/sst_partitioner.cc",
-        "db/compaction/subcompaction_state.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_compaction_flush.cc",
-        "db/db_impl/db_impl_debug.cc",
-        "db/db_impl/db_impl_experimental.cc",
-        "db/db_impl/db_impl_files.cc",
-        "db/db_impl/db_impl_open.cc",
-        "db/db_impl/db_impl_readonly.cc",
-        "db/db_impl/db_impl_secondary.cc",
-        "db/db_impl/db_impl_write.cc",
-        "db/db_info_dumper.cc",
-        "db/db_iter.cc",
-        "db/dbformat.cc",
-        "db/error_handler.cc",
-        "db/event_helpers.cc",
-        "db/experimental.cc",
-        "db/external_sst_file_ingestion_job.cc",
-        "db/file_indexer.cc",
-        "db/flush_job.cc",
-        "db/flush_scheduler.cc",
-        "db/forward_iterator.cc",
-        "db/import_column_family_job.cc",
-        "db/internal_stats.cc",
-        "db/log_reader.cc",
-        "db/log_writer.cc",
-        "db/logs_with_prep_tracker.cc",
-        "db/malloc_stats.cc",
-        "db/memtable.cc",
-        "db/memtable_list.cc",
-        "db/merge_helper.cc",
-        "db/merge_operator.cc",
-        "db/output_validator.cc",
-        "db/periodic_task_scheduler.cc",
-        "db/range_del_aggregator.cc",
-        "db/range_tombstone_fragmenter.cc",
-        "db/repair.cc",
-        "db/seqno_to_time_mapping.cc",
-        "db/snapshot_impl.cc",
-        "db/table_cache.cc",
-        "db/table_properties_collector.cc",
-        "db/transaction_log_impl.cc",
-        "db/trim_history_scheduler.cc",
-        "db/version_builder.cc",
-        "db/version_edit.cc",
-        "db/version_edit_handler.cc",
-        "db/version_set.cc",
-        "db/wal_edit.cc",
-        "db/wal_manager.cc",
-        "db/wide/wide_column_serialization.cc",
-        "db/wide/wide_columns.cc",
-        "db/write_batch.cc",
-        "db/write_batch_base.cc",
-        "db/write_controller.cc",
-        "db/write_stall_stats.cc",
-        "db/write_thread.cc",
-        "env/composite_env.cc",
-        "env/env.cc",
-        "env/env_chroot.cc",
-        "env/env_encryption.cc",
-        "env/env_posix.cc",
-        "env/file_system.cc",
-        "env/file_system_tracer.cc",
-        "env/fs_posix.cc",
-        "env/fs_remap.cc",
-        "env/io_posix.cc",
-        "env/mock_env.cc",
-        "env/unique_id_gen.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",
-        "file/sequence_file_reader.cc",
-        "file/sst_file_manager_impl.cc",
-        "file/writable_file_writer.cc",
-        "logging/auto_roll_logger.cc",
-        "logging/event_logger.cc",
-        "logging/log_buffer.cc",
-        "memory/arena.cc",
-        "memory/concurrent_arena.cc",
-        "memory/jemalloc_nodump_allocator.cc",
-        "memory/memkind_kmem_allocator.cc",
-        "memory/memory_allocator.cc",
-        "memtable/alloc_tracker.cc",
-        "memtable/hash_linklist_rep.cc",
-        "memtable/hash_skiplist_rep.cc",
-        "memtable/skiplistrep.cc",
-        "memtable/vectorrep.cc",
-        "memtable/write_buffer_manager.cc",
-        "monitoring/histogram.cc",
-        "monitoring/histogram_windowing.cc",
-        "monitoring/in_memory_stats_history.cc",
-        "monitoring/instrumented_mutex.cc",
-        "monitoring/iostats_context.cc",
-        "monitoring/perf_context.cc",
-        "monitoring/perf_level.cc",
-        "monitoring/persistent_stats_history.cc",
-        "monitoring/statistics.cc",
-        "monitoring/thread_status_impl.cc",
-        "monitoring/thread_status_updater.cc",
-        "monitoring/thread_status_updater_debug.cc",
-        "monitoring/thread_status_util.cc",
-        "monitoring/thread_status_util_debug.cc",
-        "options/cf_options.cc",
-        "options/configurable.cc",
-        "options/customizable.cc",
-        "options/db_options.cc",
-        "options/options.cc",
-        "options/options_helper.cc",
-        "options/options_parser.cc",
-        "port/mmap.cc",
-        "port/port_posix.cc",
-        "port/stack_trace.cc",
-        "port/win/env_default.cc",
-        "port/win/env_win.cc",
-        "port/win/io_win.cc",
-        "port/win/port_win.cc",
-        "port/win/win_logger.cc",
-        "port/win/win_thread.cc",
-        "table/adaptive/adaptive_table_factory.cc",
-        "table/block_based/binary_search_index_reader.cc",
-        "table/block_based/block.cc",
-        "table/block_based/block_based_table_builder.cc",
-        "table/block_based/block_based_table_factory.cc",
-        "table/block_based/block_based_table_iterator.cc",
-        "table/block_based/block_based_table_reader.cc",
-        "table/block_based/block_builder.cc",
-        "table/block_based/block_cache.cc",
-        "table/block_based/block_prefetcher.cc",
-        "table/block_based/block_prefix_index.cc",
-        "table/block_based/data_block_footer.cc",
-        "table/block_based/data_block_hash_index.cc",
-        "table/block_based/filter_block_reader_common.cc",
-        "table/block_based/filter_policy.cc",
-        "table/block_based/flush_block_policy.cc",
-        "table/block_based/full_filter_block.cc",
-        "table/block_based/hash_index_reader.cc",
-        "table/block_based/index_builder.cc",
-        "table/block_based/index_reader_common.cc",
-        "table/block_based/parsed_full_filter_block.cc",
-        "table/block_based/partitioned_filter_block.cc",
-        "table/block_based/partitioned_index_iterator.cc",
-        "table/block_based/partitioned_index_reader.cc",
-        "table/block_based/reader_common.cc",
-        "table/block_based/uncompression_dict_reader.cc",
-        "table/block_fetcher.cc",
-        "table/compaction_merging_iterator.cc",
-        "table/cuckoo/cuckoo_table_builder.cc",
-        "table/cuckoo/cuckoo_table_factory.cc",
-        "table/cuckoo/cuckoo_table_reader.cc",
-        "table/format.cc",
-        "table/get_context.cc",
-        "table/iterator.cc",
-        "table/merging_iterator.cc",
-        "table/meta_blocks.cc",
-        "table/persistent_cache_helper.cc",
-        "table/plain/plain_table_bloom.cc",
-        "table/plain/plain_table_builder.cc",
-        "table/plain/plain_table_factory.cc",
-        "table/plain/plain_table_index.cc",
-        "table/plain/plain_table_key_coding.cc",
-        "table/plain/plain_table_reader.cc",
-        "table/sst_file_dumper.cc",
-        "table/sst_file_reader.cc",
-        "table/sst_file_writer.cc",
-        "table/table_factory.cc",
-        "table/table_properties.cc",
-        "table/two_level_iterator.cc",
-        "table/unique_id.cc",
-        "test_util/sync_point.cc",
-        "test_util/sync_point_impl.cc",
-        "test_util/transaction_test_util.cc",
-        "tools/dump/db_dump_tool.cc",
-        "tools/io_tracer_parser_tool.cc",
-        "tools/ldb_cmd.cc",
-        "tools/ldb_tool.cc",
-        "tools/sst_dump_tool.cc",
-        "trace_replay/block_cache_tracer.cc",
-        "trace_replay/io_tracer.cc",
-        "trace_replay/trace_record.cc",
-        "trace_replay/trace_record_handler.cc",
-        "trace_replay/trace_record_result.cc",
-        "trace_replay/trace_replay.cc",
-        "util/async_file_reader.cc",
-        "util/build_version.cc",
-        "util/cleanable.cc",
-        "util/coding.cc",
-        "util/compaction_job_stats_impl.cc",
-        "util/comparator.cc",
-        "util/compression.cc",
-        "util/compression_context_cache.cc",
-        "util/concurrent_task_limiter_impl.cc",
-        "util/crc32c.cc",
-        "util/crc32c_arm64.cc",
-        "util/data_structure.cc",
-        "util/dynamic_bloom.cc",
-        "util/file_checksum_helper.cc",
-        "util/hash.cc",
-        "util/murmurhash.cc",
-        "util/random.cc",
-        "util/rate_limiter.cc",
-        "util/ribbon_config.cc",
-        "util/slice.cc",
-        "util/status.cc",
-        "util/stderr_logger.cc",
-        "util/string_util.cc",
-        "util/thread_local.cc",
-        "util/threadpool_imp.cc",
-        "util/xxhash.cc",
-        "utilities/agg_merge/agg_merge.cc",
-        "utilities/backup/backup_engine.cc",
-        "utilities/blob_db/blob_compaction_filter.cc",
-        "utilities/blob_db/blob_db.cc",
-        "utilities/blob_db/blob_db_impl.cc",
-        "utilities/blob_db/blob_db_impl_filesnapshot.cc",
-        "utilities/blob_db/blob_dump_tool.cc",
-        "utilities/blob_db/blob_file.cc",
-        "utilities/cache_dump_load.cc",
-        "utilities/cache_dump_load_impl.cc",
-        "utilities/cassandra/cassandra_compaction_filter.cc",
-        "utilities/cassandra/format.cc",
-        "utilities/cassandra/merge_operator.cc",
-        "utilities/checkpoint/checkpoint_impl.cc",
-        "utilities/compaction_filters.cc",
-        "utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc",
-        "utilities/convenience/info_log_finder.cc",
-        "utilities/counted_fs.cc",
-        "utilities/debug.cc",
-        "utilities/env_mirror.cc",
-        "utilities/env_timed.cc",
-        "utilities/fault_injection_env.cc",
-        "utilities/fault_injection_fs.cc",
-        "utilities/fault_injection_secondary_cache.cc",
-        "utilities/leveldb_options/leveldb_options.cc",
-        "utilities/memory/memory_util.cc",
-        "utilities/merge_operators.cc",
-        "utilities/merge_operators/bytesxor.cc",
-        "utilities/merge_operators/max.cc",
-        "utilities/merge_operators/put.cc",
-        "utilities/merge_operators/sortlist.cc",
-        "utilities/merge_operators/string_append/stringappend.cc",
-        "utilities/merge_operators/string_append/stringappend2.cc",
-        "utilities/merge_operators/uint64add.cc",
-        "utilities/object_registry.cc",
-        "utilities/option_change_migration/option_change_migration.cc",
-        "utilities/options/options_util.cc",
-        "utilities/persistent_cache/block_cache_tier.cc",
-        "utilities/persistent_cache/block_cache_tier_file.cc",
-        "utilities/persistent_cache/block_cache_tier_metadata.cc",
-        "utilities/persistent_cache/persistent_cache_tier.cc",
-        "utilities/persistent_cache/volatile_tier_impl.cc",
-        "utilities/simulator_cache/cache_simulator.cc",
-        "utilities/simulator_cache/sim_cache.cc",
-        "utilities/table_properties_collectors/compact_on_deletion_collector.cc",
-        "utilities/trace/file_trace_reader_writer.cc",
-        "utilities/trace/replayer_impl.cc",
-        "utilities/transactions/lock/lock_manager.cc",
-        "utilities/transactions/lock/point/point_lock_manager.cc",
-        "utilities/transactions/lock/point/point_lock_tracker.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/keyrange.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/lock_request.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/locktree.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/manager.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/range_buffer.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/treenode.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/txnid_set.cc",
-        "utilities/transactions/lock/range/range_tree/lib/locktree/wfg.cc",
-        "utilities/transactions/lock/range/range_tree/lib/standalone_port.cc",
-        "utilities/transactions/lock/range/range_tree/lib/util/dbt.cc",
-        "utilities/transactions/lock/range/range_tree/lib/util/memarena.cc",
-        "utilities/transactions/lock/range/range_tree/range_tree_lock_manager.cc",
-        "utilities/transactions/lock/range/range_tree/range_tree_lock_tracker.cc",
-        "utilities/transactions/optimistic_transaction.cc",
-        "utilities/transactions/optimistic_transaction_db_impl.cc",
-        "utilities/transactions/pessimistic_transaction.cc",
-        "utilities/transactions/pessimistic_transaction_db.cc",
-        "utilities/transactions/snapshot_checker.cc",
-        "utilities/transactions/transaction_base.cc",
-        "utilities/transactions/transaction_db_mutex_impl.cc",
-        "utilities/transactions/transaction_util.cc",
-        "utilities/transactions/write_prepared_txn.cc",
-        "utilities/transactions/write_prepared_txn_db.cc",
-        "utilities/transactions/write_unprepared_txn.cc",
-        "utilities/transactions/write_unprepared_txn_db.cc",
-        "utilities/ttl/db_ttl_impl.cc",
-        "utilities/wal_filter.cc",
-        "utilities/write_batch_with_index/write_batch_with_index.cc",
-        "utilities/write_batch_with_index/write_batch_with_index_internal.cc",
-    ], deps=[
-        "//folly/container:f14_hash",
-        "//folly/experimental/coro:blocking_wait",
-        "//folly/experimental/coro:collect",
-        "//folly/experimental/coro:coroutine",
-        "//folly/experimental/coro:task",
-        "//folly/synchronization:distributed_mutex",
-    ], headers=None, link_whole=True, extra_test_libs=False)
+cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[], deps=[":rocksdb_lib"], headers=None, link_whole=True, extra_test_libs=False)
 
 cpp_library_wrapper(name="rocksdb_test_lib", srcs=[
         "db/db_test_util.cc",
@@ -736,6 +394,7 @@ rocks_cpp_library_wrapper(name="rocksdb_stress_lib", srcs=[
         "db_stress_tool/db_stress_test_base.cc",
         "db_stress_tool/db_stress_tool.cc",
         "db_stress_tool/expected_state.cc",
+        "db_stress_tool/expected_value.cc",
         "db_stress_tool/multi_ops_txns_stress.cc",
         "db_stress_tool/no_batched_ops_stress.cc",
         "test_util/testutil.cc",
@@ -5093,6 +4752,12 @@ cpp_unittest_wrapper(name="db_bloom_filter_test",
             extra_compiler_flags=[])
 
 
+cpp_unittest_wrapper(name="db_clip_test",
+            srcs=["db/db_clip_test.cc"],
+            deps=[":rocksdb_test_lib"],
+            extra_compiler_flags=[])
+
+
 cpp_unittest_wrapper(name="db_compaction_filter_test",
             srcs=["db/db_compaction_filter_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -5845,6 +5510,12 @@ cpp_unittest_wrapper(name="ttl_test",
             extra_compiler_flags=[])
 
 
+cpp_unittest_wrapper(name="udt_util_test",
+            srcs=["util/udt_util_test.cc"],
+            deps=[":rocksdb_test_lib"],
+            extra_compiler_flags=[])
+
+
 cpp_unittest_wrapper(name="util_merge_operators_test",
             srcs=["utilities/util_merge_operators_test.cc"],
             deps=[":rocksdb_test_lib"],

USERS.md

@@ -15,6 +15,25 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
 
 [2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/
 
+## Bilibili
+[Bilibili](bilibili.com) [uses](https://www.alluxio.io/blog/when-ai-meets-alluxio-at-bilibili-building-an-efficient-ai-platform-for-data-preprocessing-and-model-training/) Alluxio to speed up its ML training workloads, and Alluxio uses RocksDB to store its filesystem metadata, so Bilibili uses RocksDB.
+
+Bilibili's [real-time platform](https://www.alibabacloud.com/blog/architecture-and-practices-of-bilibilis-real-time-platform_596676) uses Flink, and uses RocksDB as Flink's state store.
+
+## TikTok
+TikTok, or its parent company ByteDance, uses RocksDB as the storage engine for some storage systems, such as its distributed graph database [ByteGraph](https://vldb.org/pvldb/vol15/p3306-li.pdf). 
+
+Also, TikTok uses [Alluxio](alluxio.io) to [speed up Presto queries](https://www.alluxio.io/resources/videos/improving-presto-performance-with-alluxio-at-tiktok/), and Alluxio stores the files' metadata in RocksDB.
+
+## FoundationDB
+[FoundationDB](https://www.foundationdb.org/) [uses](https://github.com/apple/foundationdb/blob/377f1f692da6ab2fe5bdac57035651db3e5fb66d/fdbserver/KeyValueStoreRocksDB.actor.cpp) RocksDB to implement a [key-value store interface](https://github.com/apple/foundationdb/blob/377f1f692da6ab2fe5bdac57035651db3e5fb66d/fdbserver/KeyValueStoreRocksDB.actor.cpp#L1127) in its server backend.
+
+## Apple
+Apple [uses](https://opensource.apple.com/projects/foundationdb/) FoundationDB, so it also uses RocksDB.
+
+## Snowflake
+Snowflake [uses](https://www.snowflake.com/blog/how-foundationdb-powers-snowflake-metadata-forward/) FoundationDB, so it also uses RocksDB.
+
 ## Microsoft
 The Bing search engine from Microsoft uses RocksDB as the storage engine for its web data platform: https://blogs.bing.com/Engineering-Blog/october-2021/RocksDB-in-Microsoft-Bing
 
@@ -85,9 +104,18 @@ quasardb uses a heavily tuned RocksDB as its persistence layer.
 ## TiKV
 [TiKV](https://github.com/pingcap/tikv) is a GEO-replicated, high-performance, distributed, transactional key-value database. TiKV is powered by Rust and Raft. TiKV uses RocksDB as its persistence layer.
 
+## TiDB
+[TiDB](https://github.com/pingcap/tidb) uses the TiKV distributed key-value database, so it uses RocksDB.
+
+## PingCAP
+[PingCAP](https://www.pingcap.com/) is the company behind TiDB, its cloud database service uses RocksDB.
+
 ## Apache Spark
 [Spark Structured Streaming](https://docs.databricks.com/structured-streaming/rocksdb-state-store.html) uses RocksDB as the local state store.
 
+## Databricks
+[Databricks](https://www.databricks.com/) [replaces AWS RDS with TiDB](https://www.pingcap.com/case-study/how-databricks-tackles-the-scalability-limit-with-a-mysql-alternative/) for scalability, so it uses RocksDB.
+
 ## Apache Flink
 [Apache Flink](https://flink.apache.org/news/2016/03/08/release-1.0.0.html) uses RocksDB to store state locally on a machine.
 

buckifier/buckify_rocksdb.py

@@ -154,16 +154,9 @@ def generate_targets(repo_path, deps_map):
     # 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=[
-            "//folly/container:f14_hash",
-            "//folly/experimental/coro:blocking_wait",
-            "//folly/experimental/coro:collect",
-            "//folly/experimental/coro:coroutine",
-            "//folly/experimental/coro:task",
-            "//folly/synchronization:distributed_mutex",
+            ":rocksdb_lib",
         ],
         headers=None,
         extra_external_deps="",

build_tools/build_detect_platform

@@ -419,7 +419,7 @@ EOF
 
     if ! test $ROCKSDB_DISABLE_JEMALLOC; then
         # Test whether jemalloc is available
-        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o -ljemalloc \
+        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS $LDFLAGS -x c++ - -o test.o -ljemalloc \
           2>/dev/null; then
             # This will enable some preprocessor identifiers in the Makefile
             JEMALLOC=1
@@ -428,12 +428,19 @@ EOF
             WITH_JEMALLOC_FLAG=1
             # check for JEMALLOC installed with HomeBrew
             if [ "$PLATFORM" == "OS_MACOSX" ]; then
+                if [ "$TARGET_ARCHITECTURE" = "arm64" ]; then
+                    # on M1 Macs, homebrew installs here instead of /usr/local
+                    JEMALLOC_PREFIX="/opt/homebrew"
+                else
+                    JEMALLOC_PREFIX="/usr/local"
+                fi
                 if hash brew 2>/dev/null && brew ls --versions jemalloc > /dev/null; then
                     JEMALLOC_VER=$(brew ls --versions jemalloc | tail -n 1 | cut -f 2 -d ' ')
-                    JEMALLOC_INCLUDE="-I/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/include"
-                    JEMALLOC_LIB="/usr/local/Cellar/jemalloc/${JEMALLOC_VER}/lib/libjemalloc_pic.a"
-                    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS $JEMALLOC_LIB"
-                    JAVA_STATIC_LDFLAGS="$JAVA_STATIC_LDFLAGS $JEMALLOC_LIB"
+                    JEMALLOC_INCLUDE="-I${JEMALLOC_PREFIX}/Cellar/jemalloc/${JEMALLOC_VER}/include"
+                    JEMALLOC_LIB="${JEMALLOC_PREFIX}/Cellar/jemalloc/${JEMALLOC_VER}/lib/libjemalloc_pic.a"
+                    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -L${JEMALLOC_PREFIX}/lib $JEMALLOC_LIB"
+                    JAVA_LDFLAGS="$JAVA_LDFLAGS -L${JEMALLOC_PREFIX}/lib $JEMALLOC_LIB"
+                    JAVA_STATIC_LDFLAGS="$JAVA_STATIC_LDFLAGS -L${JEMALLOC_PREFIX}/lib $JEMALLOC_LIB"
                 fi
             fi
         fi
@@ -621,7 +628,7 @@ EOF
   fi
 fi
 
-if test "0$PORTABLE" -eq 0; then
+if [ "$PORTABLE" == "" ] || [ "$PORTABLE" == 0 ]; then
   if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
     # Tune for this POWER processor, treating '+' models as base models
     POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
@@ -644,37 +651,36 @@ if test "0$PORTABLE" -eq 0; then
     COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
   elif [ "$TARGET_OS" == "IOS" ]; then
     COMMON_FLAGS="$COMMON_FLAGS"
-  elif [ "$TARGET_OS" == "AIX" ] || [ "$TARGET_OS" == "SunOS" ]; then
-    # TODO: Not sure why we don't use -march=native on these OSes
-    if test "$USE_SSE"; then
-      TRY_SSE_ETC="1"
-    fi
   else
     COMMON_FLAGS="$COMMON_FLAGS -march=native "
   fi
 else
-  # PORTABLE=1
-  if test "$USE_SSE"; then
-    TRY_SSE_ETC="1"
-  fi
-
-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
-    COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
-  fi
-
-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
-    RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
-    COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
+  # PORTABLE specified
+  if [ "$PORTABLE" == 1 ]; then
+    if test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
+      COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
+    elif test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
+      RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
+      COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
+    elif test "$USE_SSE"; then
+      # USE_SSE is DEPRECATED
+      # This is a rough approximation of the old USE_SSE behavior
+      COMMON_FLAGS="$COMMON_FLAGS -march=haswell"
+    fi
+    # Other than those cases, not setting -march= here.
+  else
+    # Assume PORTABLE is a minimum assumed cpu type, e.g. PORTABLE=haswell
+    COMMON_FLAGS="$COMMON_FLAGS -march=${PORTABLE}"
   fi
 
   if [[ "${PLATFORM}" == "OS_MACOSX" ]]; then
-    # For portability compile for macOS 10.13 (2017) or newer
-    COMMON_FLAGS="$COMMON_FLAGS -mmacosx-version-min=10.13"
-    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -mmacosx-version-min=10.13"
+    # For portability compile for macOS 10.14 or newer
+    COMMON_FLAGS="$COMMON_FLAGS -mmacosx-version-min=10.14"
+    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -mmacosx-version-min=10.14"
     # -mmacosx-version-min must come first here.
-    PLATFORM_SHARED_LDFLAGS="-mmacosx-version-min=10.13 $PLATFORM_SHARED_LDFLAGS"
-    PLATFORM_CMAKE_FLAGS="-DCMAKE_OSX_DEPLOYMENT_TARGET=10.13"
-    JAVA_STATIC_DEPS_COMMON_FLAGS="-mmacosx-version-min=10.13"
+    PLATFORM_SHARED_LDFLAGS="-mmacosx-version-min=10.14 $PLATFORM_SHARED_LDFLAGS"
+    PLATFORM_CMAKE_FLAGS="-DCMAKE_OSX_DEPLOYMENT_TARGET=10.14"
+    JAVA_STATIC_DEPS_COMMON_FLAGS="-mmacosx-version-min=10.14"
     JAVA_STATIC_DEPS_LDFLAGS="$JAVA_STATIC_DEPS_COMMON_FLAGS"
     JAVA_STATIC_DEPS_CCFLAGS="$JAVA_STATIC_DEPS_COMMON_FLAGS"
     JAVA_STATIC_DEPS_CXXFLAGS="$JAVA_STATIC_DEPS_COMMON_FLAGS"
@@ -698,101 +704,6 @@ EOF
   fi
 fi
 
-if test "$TRY_SSE_ETC"; then
-  # The USE_SSE flag now means "attempt to compile with widely-available
-  # Intel architecture extensions utilized by specific optimizations in the
-  # source code." It's a qualifier on PORTABLE=1 that means "mostly portable."
-  # It doesn't even really check that your current CPU is compatible.
-  #
-  # SSE4.2 available since nehalem, ca. 2008-2010
-  # Includes POPCNT for BitsSetToOne, BitParity
-  TRY_SSE42="-msse4.2"
-  # PCLMUL available since westmere, ca. 2010-2011
-  TRY_PCLMUL="-mpclmul"
-  # AVX2 available since haswell, ca. 2013-2015
-  TRY_AVX2="-mavx2"
-  # BMI available since haswell, ca. 2013-2015
-  # Primarily for TZCNT for CountTrailingZeroBits
-  TRY_BMI="-mbmi"
-  # LZCNT available since haswell, ca. 2013-2015
-  # For FloorLog2
-  TRY_LZCNT="-mlzcnt"
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <nmmintrin.h>
-  int main() {
-    volatile uint32_t x = _mm_crc32_u32(0, 0);
-    (void)x;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_SSE42 -DHAVE_SSE42"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <wmmintrin.h>
-  int main() {
-    const auto a = _mm_set_epi64x(0, 0);
-    const auto b = _mm_set_epi64x(0, 0);
-    const auto c = _mm_clmulepi64_si128(a, b, 0x00);
-    auto d = _mm_cvtsi128_si64(c);
-    (void)d;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_PCLMUL -DHAVE_PCLMUL"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main() {
-    const auto a = _mm256_setr_epi32(0, 1, 2, 3, 4, 7, 6, 5);
-    const auto b = _mm256_permutevar8x32_epi32(a, a);
-    (void)b;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_AVX2 -DHAVE_AVX2"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use AVX2 intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_BMI -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main(int argc, char *argv[]) {
-    (void)argv;
-    return (int)_tzcnt_u64((uint64_t)argc);
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_BMI -DHAVE_BMI"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use BMI intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_LZCNT -x c++ - -o test.o 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main(int argc, char *argv[]) {
-    (void)argv;
-    return (int)_lzcnt_u64((uint64_t)argc);
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_LZCNT -DHAVE_LZCNT"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use LZCNT intrinsics, disabling" >&2
-fi
-
 $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o test.o 2>/dev/null <<EOF
   #include <cstdint>
   int main() {

build_tools/fbcode_config.sh

@@ -147,7 +147,7 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT"
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"

build_tools/fbcode_config_platform010.sh

@@ -154,7 +154,7 @@ CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
 CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_IOURING_PRESENT"
 CXXFLAGS+=" $CFLAGS"
 
 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"

cache/cache_bench_tool.cc

@@ -31,6 +31,7 @@
 #include "util/hash.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
+#include "util/stderr_logger.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 
@@ -49,8 +50,11 @@ DEFINE_double(resident_ratio, 0.25,
               "Ratio of keys fitting in cache to keyspace.");
 DEFINE_uint64(ops_per_thread, 2000000U, "Number of operations per thread.");
 DEFINE_uint32(value_bytes, 8 * KiB, "Size of each value added.");
+DEFINE_uint32(value_bytes_estimate, 0,
+              "If > 0, overrides estimated_entry_charge or "
+              "min_avg_entry_charge depending on cache_type.");
 
-DEFINE_uint32(skew, 5, "Degree of skew in key selection");
+DEFINE_uint32(skew, 5, "Degree of skew in key selection. 0 = no skew");
 DEFINE_bool(populate_cache, true, "Populate cache before operations");
 
 DEFINE_uint32(lookup_insert_percent, 87,
@@ -71,12 +75,22 @@ DEFINE_uint32(
 
 DEFINE_uint32(gather_stats_entries_per_lock, 256,
               "For Cache::ApplyToAllEntries");
-DEFINE_bool(skewed, false, "If true, skew the key access distribution");
 
 DEFINE_bool(lean, false,
             "If true, no additional computation is performed besides cache "
             "operations.");
 
+DEFINE_bool(early_exit, false,
+            "Exit before deallocating most memory. Good for malloc stats, e.g."
+            "MALLOC_CONF=\"stats_print:true\"");
+
+DEFINE_bool(histograms, true,
+            "Whether to track and print histogram statistics.");
+
+DEFINE_bool(report_problems, true, "Whether to ReportProblems() at the end.");
+
+DEFINE_uint32(seed, 0, "Hashing/random seed to use. 0 = choose at random");
+
 DEFINE_string(secondary_cache_uri, "",
               "Full URI for creating a custom secondary cache object");
 static class std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache> secondary_cache;
@@ -145,9 +159,6 @@ class SharedState {
  public:
   explicit SharedState(CacheBench* cache_bench)
       : cv_(&mu_),
-        num_initialized_(0),
-        start_(false),
-        num_done_(0),
         cache_bench_(cache_bench) {}
 
   ~SharedState() {}
@@ -170,15 +181,27 @@ class SharedState {
 
   bool Started() const { return start_; }
 
+  void AddLookupStats(uint64_t hits, uint64_t misses) {
+    MutexLock l(&mu_);
+    lookup_count_ += hits + misses;
+    lookup_hits_ += hits;
+  }
+
+  double GetLookupHitRatio() const {
+    return 1.0 * lookup_hits_ / lookup_count_;
+  }
+
  private:
   port::Mutex mu_;
   port::CondVar cv_;
 
-  uint64_t num_initialized_;
-  bool start_;
-  uint64_t num_done_;
-
   CacheBench* cache_bench_;
+
+  uint64_t num_initialized_ = 0;
+  bool start_ = false;
+  uint64_t num_done_ = 0;
+  uint64_t lookup_count_ = 0;
+  uint64_t lookup_hits_ = 0;
 };
 
 // Per-thread state for concurrent executions of the same benchmark.
@@ -190,27 +213,19 @@ struct ThreadState {
   uint64_t duration_us = 0;
 
   ThreadState(uint32_t index, SharedState* _shared)
-      : tid(index), rnd(1000 + index), shared(_shared) {}
+      : tid(index), rnd(FLAGS_seed + 1 + index), shared(_shared) {}
 };
 
 struct KeyGen {
   char key_data[27];
 
-  Slice GetRand(Random64& rnd, uint64_t max_key, int max_log) {
-    uint64_t key = 0;
-    if (!FLAGS_skewed) {
-      uint64_t raw = rnd.Next();
-      // Skew according to setting
-      for (uint32_t i = 0; i < FLAGS_skew; ++i) {
-        raw = std::min(raw, rnd.Next());
-      }
-      key = FastRange64(raw, max_key);
-    } else {
-      key = rnd.Skewed(max_log);
-      if (key > max_key) {
-        key -= max_key;
-      }
+  Slice GetRand(Random64& rnd, uint64_t max_key, uint32_t skew) {
+    uint64_t raw = rnd.Next();
+    // Skew according to setting
+    for (uint32_t i = 0; i < skew; ++i) {
+      raw = std::min(raw, rnd.Next());
     }
+    uint64_t key = FastRange64(raw, max_key);
     // Variable size and alignment
     size_t off = key % 8;
     key_data[0] = char{42};
@@ -281,31 +296,38 @@ class CacheBench {
         lookup_threshold_(insert_threshold_ +
                           kHundredthUint64 * FLAGS_lookup_percent),
         erase_threshold_(lookup_threshold_ +
-                         kHundredthUint64 * FLAGS_erase_percent),
-        skewed_(FLAGS_skewed) {
+                         kHundredthUint64 * FLAGS_erase_percent) {
     if (erase_threshold_ != 100U * kHundredthUint64) {
       fprintf(stderr, "Percentages must add to 100.\n");
       exit(1);
     }
 
-    max_log_ = 0;
-    if (skewed_) {
-      uint64_t max_key = max_key_;
-      while (max_key >>= 1) max_log_++;
-      if (max_key > (static_cast<uint64_t>(1) << max_log_)) max_log_++;
-    }
-
     if (FLAGS_cache_type == "clock_cache") {
       fprintf(stderr, "Old clock cache implementation has been removed.\n");
       exit(1);
-    } else if (FLAGS_cache_type == "hyper_clock_cache") {
-      cache_ = HyperClockCacheOptions(FLAGS_cache_size, FLAGS_value_bytes,
-                                      FLAGS_num_shard_bits)
-                   .MakeSharedCache();
+    } else if (EndsWith(FLAGS_cache_type, "hyper_clock_cache")) {
+      HyperClockCacheOptions opts(
+          FLAGS_cache_size, /*estimated_entry_charge=*/0, FLAGS_num_shard_bits);
+      opts.hash_seed = BitwiseAnd(FLAGS_seed, INT32_MAX);
+      if (FLAGS_cache_type == "fixed_hyper_clock_cache" ||
+          FLAGS_cache_type == "hyper_clock_cache") {
+        opts.estimated_entry_charge = FLAGS_value_bytes_estimate > 0
+                                          ? FLAGS_value_bytes_estimate
+                                          : FLAGS_value_bytes;
+      } else if (FLAGS_cache_type == "auto_hyper_clock_cache") {
+        if (FLAGS_value_bytes_estimate > 0) {
+          opts.min_avg_entry_charge = FLAGS_value_bytes_estimate;
+        }
+      } else {
+        fprintf(stderr, "Cache type not supported.");
+        exit(1);
+      }
+      cache_ = opts.MakeSharedCache();
     } else if (FLAGS_cache_type == "lru_cache") {
       LRUCacheOptions opts(FLAGS_cache_size, FLAGS_num_shard_bits,
                            false /* strict_capacity_limit */,
                            0.5 /* high_pri_pool_ratio */);
+      opts.hash_seed = BitwiseAnd(FLAGS_seed, INT32_MAX);
       if (!FLAGS_secondary_cache_uri.empty()) {
         Status s = SecondaryCache::CreateFromString(
             ConfigOptions(), FLAGS_secondary_cache_uri, &secondary_cache);
@@ -329,13 +351,50 @@ class CacheBench {
   ~CacheBench() {}
 
   void PopulateCache() {
-    Random64 rnd(1);
+    Random64 rnd(FLAGS_seed);
     KeyGen keygen;
-    for (uint64_t i = 0; i < 2 * FLAGS_cache_size; i += FLAGS_value_bytes) {
-      Status s = cache_->Insert(keygen.GetRand(rnd, max_key_, max_log_),
-                                createValue(rnd), &helper1, FLAGS_value_bytes);
+    size_t max_occ = 0;
+    size_t inserts_since_max_occ_increase = 0;
+    size_t keys_since_last_not_found = 0;
+
+    // Avoid redundant insertions by checking Lookup before Insert.
+    // Loop until insertions consistently fail to increase max occupancy or
+    // it becomes difficult to find keys not already inserted.
+    while (inserts_since_max_occ_increase < 100 &&
+           keys_since_last_not_found < 100) {
+      Slice key = keygen.GetRand(rnd, max_key_, FLAGS_skew);
+
+      Cache::Handle* handle = cache_->Lookup(key);
+      if (handle != nullptr) {
+        cache_->Release(handle);
+        ++keys_since_last_not_found;
+        continue;
+      }
+      keys_since_last_not_found = 0;
+
+      Status s =
+          cache_->Insert(key, createValue(rnd), &helper1, FLAGS_value_bytes);
       assert(s.ok());
+
+      handle = cache_->Lookup(key);
+      if (!handle) {
+        fprintf(stderr, "Failed to lookup key just inserted.\n");
+        assert(false);
+        exit(42);
+      } else {
+        cache_->Release(handle);
+      }
+
+      size_t occ = cache_->GetOccupancyCount();
+      if (occ > max_occ) {
+        max_occ = occ;
+        inserts_since_max_occ_increase = 0;
+      } else {
+        ++inserts_since_max_occ_increase;
+      }
     }
+    printf("Population complete (%zu entries, %g average charge)\n", max_occ,
+           1.0 * FLAGS_cache_size / max_occ);
   }
 
   bool Run() {
@@ -394,19 +453,33 @@ class CacheBench {
                                         FLAGS_ops_per_thread / elapsed_secs);
     printf("Thread ops/sec = %u\n", ops_per_sec);
 
-    printf("\nOperation latency (ns):\n");
-    HistogramImpl combined;
-    for (uint32_t i = 0; i < FLAGS_threads; i++) {
-      combined.Merge(threads[i]->latency_ns_hist);
-    }
-    printf("%s", combined.ToString().c_str());
+    printf("Lookup hit ratio: %g\n", shared.GetLookupHitRatio());
 
-    if (FLAGS_gather_stats) {
-      printf("\nGather stats latency (us):\n");
-      printf("%s", stats_hist.ToString().c_str());
+    size_t occ = cache_->GetOccupancyCount();
+    size_t slot = cache_->GetTableAddressCount();
+    printf("Final load factor: %g (%zu / %zu)\n", 1.0 * occ / slot, occ, slot);
+
+    if (FLAGS_histograms) {
+      printf("\nOperation latency (ns):\n");
+      HistogramImpl combined;
+      for (uint32_t i = 0; i < FLAGS_threads; i++) {
+        combined.Merge(threads[i]->latency_ns_hist);
+      }
+      printf("%s", combined.ToString().c_str());
+
+      if (FLAGS_gather_stats) {
+        printf("\nGather stats latency (us):\n");
+        printf("%s", stats_hist.ToString().c_str());
+      }
     }
 
-    printf("\n%s", stats_report.c_str());
+    if (FLAGS_report_problems) {
+      printf("\n");
+      std::shared_ptr<Logger> logger =
+          std::make_shared<StderrLogger>(InfoLogLevel::DEBUG_LEVEL);
+      cache_->ReportProblems(logger);
+    }
+    printf("%s", stats_report.c_str());
 
     return true;
   }
@@ -419,8 +492,6 @@ class CacheBench {
   const uint64_t insert_threshold_;
   const uint64_t lookup_threshold_;
   const uint64_t erase_threshold_;
-  const bool skewed_;
-  int max_log_;
 
   // A benchmark version of gathering stats on an active block cache by
   // iterating over it. The primary purpose is to measure the impact of
@@ -453,7 +524,7 @@ class CacheBench {
         for (;;) {
           if (shared->AllDone()) {
             std::ostringstream ostr;
-            ostr << "Most recent cache entry stats:\n"
+            ostr << "\nMost recent cache entry stats:\n"
                  << "Number of entries: " << total_entry_count << "\n"
                  << "Table occupancy: " << table_occupancy << " / "
                  << table_size << " = "
@@ -490,13 +561,17 @@ class CacheBench {
         // Something slightly more expensive as in stats by category
         helpers.insert(helper);
       };
-      timer.Start();
+      if (FLAGS_histograms) {
+        timer.Start();
+      }
       Cache::ApplyToAllEntriesOptions opts;
       opts.average_entries_per_lock = FLAGS_gather_stats_entries_per_lock;
       shared->GetCacheBench()->cache_->ApplyToAllEntries(fn, opts);
       table_occupancy = shared->GetCacheBench()->cache_->GetOccupancyCount();
       table_size = shared->GetCacheBench()->cache_->GetTableAddressCount();
-      stats_hist->Add(timer.ElapsedNanos() / 1000);
+      if (FLAGS_histograms) {
+        stats_hist->Add(timer.ElapsedNanos() / 1000);
+      }
     }
   }
 
@@ -527,6 +602,8 @@ class CacheBench {
   void OperateCache(ThreadState* thread) {
     // To use looked-up values
     uint64_t result = 0;
+    uint64_t lookup_misses = 0;
+    uint64_t lookup_hits = 0;
     // To hold handles for a non-trivial amount of time
     Cache::Handle* handle = nullptr;
     KeyGen gen;
@@ -535,10 +612,12 @@ class CacheBench {
     StopWatchNano timer(clock);
 
     for (uint64_t i = 0; i < FLAGS_ops_per_thread; i++) {
-      Slice key = gen.GetRand(thread->rnd, max_key_, max_log_);
+      Slice key = gen.GetRand(thread->rnd, max_key_, FLAGS_skew);
       uint64_t random_op = thread->rnd.Next();
 
-      timer.Start();
+      if (FLAGS_histograms) {
+        timer.Start();
+      }
 
       if (random_op < lookup_insert_threshold_) {
         if (handle) {
@@ -549,12 +628,14 @@ class CacheBench {
         handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
                                 Cache::Priority::LOW);
         if (handle) {
+          ++lookup_hits;
           if (!FLAGS_lean) {
             // do something with the data
             result += NPHash64(static_cast<char*>(cache_->Value(handle)),
                                FLAGS_value_bytes);
           }
         } else {
+          ++lookup_misses;
           // do insert
           Status s = cache_->Insert(key, createValue(thread->rnd), &helper2,
                                     FLAGS_value_bytes, &handle);
@@ -578,11 +659,14 @@ class CacheBench {
         handle = cache_->Lookup(key, &helper2, /*context*/ nullptr,
                                 Cache::Priority::LOW);
         if (handle) {
+          ++lookup_hits;
           if (!FLAGS_lean) {
             // do something with the data
             result += NPHash64(static_cast<char*>(cache_->Value(handle)),
                                FLAGS_value_bytes);
           }
+        } else {
+          ++lookup_misses;
         }
       } else if (random_op < erase_threshold_) {
         // do erase
@@ -591,7 +675,14 @@ class CacheBench {
         // Should be extremely unlikely (noop)
         assert(random_op >= kHundredthUint64 * 100U);
       }
-      thread->latency_ns_hist.Add(timer.ElapsedNanos());
+      if (FLAGS_histograms) {
+        thread->latency_ns_hist.Add(timer.ElapsedNanos());
+      }
+      thread->shared->AddLookupStats(lookup_hits, lookup_misses);
+    }
+    if (FLAGS_early_exit) {
+      MutexLock l(thread->shared->GetMutex());
+      exit(0);
     }
     if (handle) {
       cache_->Release(handle);
@@ -613,7 +704,9 @@ class CacheBench {
 #ifndef NDEBUG
     printf("WARNING: Assertions are enabled; benchmarks unnecessarily slow\n");
 #endif
+    printf("----------------------------\n");
     printf("RocksDB version     : %d.%d\n", kMajorVersion, kMinorVersion);
+    printf("Cache impl name     : %s\n", cache_->Name());
     printf("DMutex impl name    : %s\n", DMutex::kName());
     printf("Number of threads   : %u\n", FLAGS_threads);
     printf("Ops per thread      : %" PRIu64 "\n", FLAGS_ops_per_thread);
@@ -952,11 +1045,14 @@ int cache_bench_tool(int argc, char** argv) {
     exit(1);
   }
 
+  if (FLAGS_seed == 0) {
+    FLAGS_seed = static_cast<uint32_t>(port::GetProcessID());
+    printf("Using seed = %" PRIu32 "\n", FLAGS_seed);
+  }
+
   ROCKSDB_NAMESPACE::CacheBench bench;
   if (FLAGS_populate_cache) {
     bench.PopulateCache();
-    printf("Population complete\n");
-    printf("----------------------------\n");
   }
   if (bench.Run()) {
     return 0;

cache/cache_test.cc

@@ -21,6 +21,7 @@
 #include "test_util/secondary_cache_test_util.h"
 #include "test_util/testharness.h"
 #include "util/coding.h"
+#include "util/hash_containers.h"
 #include "util/string_util.h"
 
 // HyperClockCache only supports 16-byte keys, so some of the tests
@@ -69,18 +70,11 @@ const Cache::CacheItemHelper kDumbHelper{
     CacheEntryRole::kMisc,
     [](Cache::ObjectPtr /*value*/, MemoryAllocator* /*alloc*/) {}};
 
-const Cache::CacheItemHelper kEraseOnDeleteHelper1{
+const Cache::CacheItemHelper kInvokeOnDeleteHelper{
     CacheEntryRole::kMisc,
     [](Cache::ObjectPtr value, MemoryAllocator* /*alloc*/) {
-      Cache* cache = static_cast<Cache*>(value);
-      cache->Erase("foo");
-    }};
-
-const Cache::CacheItemHelper kEraseOnDeleteHelper2{
-    CacheEntryRole::kMisc,
-    [](Cache::ObjectPtr value, MemoryAllocator* /*alloc*/) {
-      Cache* cache = static_cast<Cache*>(value);
-      cache->Erase(EncodeKey16Bytes(1234));
+      auto& fn = *static_cast<std::function<void()>*>(value);
+      fn();
     }};
 }  // anonymous namespace
 
@@ -119,8 +113,7 @@ class CacheTest : public testing::Test,
   // Currently, HyperClockCache requires keys to be 16B long, whereas
   // LRUCache doesn't, so the encoding depends on the cache type.
   std::string EncodeKey(int k) {
-    auto type = GetParam();
-    if (type == kHyperClock) {
+    if (IsHyperClock()) {
       return EncodeKey16Bytes(k);
     } else {
       return EncodeKey32Bits(k);
@@ -128,8 +121,7 @@ class CacheTest : public testing::Test,
   }
 
   int DecodeKey(const Slice& k) {
-    auto type = GetParam();
-    if (type == kHyperClock) {
+    if (IsHyperClock()) {
       return DecodeKey16Bytes(k);
     } else {
       return DecodeKey32Bits(k);
@@ -181,15 +173,13 @@ std::string CacheTest::type_;
 class LRUCacheTest : public CacheTest {};
 
 TEST_P(CacheTest, UsageTest) {
-  auto type = GetParam();
-
   // cache is std::shared_ptr and will be automatically cleaned up.
   const size_t kCapacity = 100000;
   auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
   auto precise_cache = NewCache(kCapacity, 0, false, kFullChargeCacheMetadata);
   ASSERT_EQ(0, cache->GetUsage());
   size_t baseline_meta_usage = precise_cache->GetUsage();
-  if (type != kHyperClock) {
+  if (!IsHyperClock()) {
     ASSERT_EQ(0, baseline_meta_usage);
   }
 
@@ -197,18 +187,13 @@ TEST_P(CacheTest, UsageTest) {
   char value[10] = "abcdef";
   // make sure everything will be cached
   for (int i = 1; i < 100; ++i) {
-    std::string key;
-    if (type == kLRU) {
-      key = std::string(i, 'a');
-    } else {
-      key = EncodeKey(i);
-    }
+    std::string key = EncodeKey(i);
     auto kv_size = key.size() + 5;
     ASSERT_OK(cache->Insert(key, value, &kDumbHelper, kv_size));
     ASSERT_OK(precise_cache->Insert(key, value, &kDumbHelper, kv_size));
     usage += kv_size;
     ASSERT_EQ(usage, cache->GetUsage());
-    if (type == kHyperClock) {
+    if (IsHyperClock()) {
       ASSERT_EQ(baseline_meta_usage + usage, precise_cache->GetUsage());
     } else {
       ASSERT_LT(usage, precise_cache->GetUsage());
@@ -222,12 +207,7 @@ TEST_P(CacheTest, UsageTest) {
 
   // make sure the cache will be overloaded
   for (size_t i = 1; i < kCapacity; ++i) {
-    std::string key;
-    if (type == kLRU) {
-      key = std::to_string(i);
-    } else {
-      key = EncodeKey(static_cast<int>(1000 + i));
-    }
+    std::string key = EncodeKey(static_cast<int>(1000 + i));
     ASSERT_OK(cache->Insert(key, value, &kDumbHelper, key.size() + 5));
     ASSERT_OK(precise_cache->Insert(key, value, &kDumbHelper, key.size() + 5));
   }
@@ -236,7 +216,7 @@ TEST_P(CacheTest, UsageTest) {
   ASSERT_GT(kCapacity, cache->GetUsage());
   ASSERT_GT(kCapacity, precise_cache->GetUsage());
   ASSERT_LT(kCapacity * 0.95, cache->GetUsage());
-  if (type != kHyperClock) {
+  if (!IsHyperClock()) {
     ASSERT_LT(kCapacity * 0.95, precise_cache->GetUsage());
   } else {
     // estimated value size of 1 is weird for clock cache, because
@@ -247,22 +227,20 @@ TEST_P(CacheTest, UsageTest) {
   }
 }
 
-// TODO: This test takes longer than expected on ClockCache. This is
-// because the values size estimate at construction is too sloppy.
+// TODO: This test takes longer than expected on FixedHyperClockCache.
+// This is because the values size estimate at construction is too sloppy.
 // Fix this.
 // Why is it so slow? The cache is constructed with an estimate of 1, but
 // then the charge is claimed to be 21. This will cause the hash table
 // to be extremely sparse, which in turn means clock needs to scan too
 // many slots to find victims.
 TEST_P(CacheTest, PinnedUsageTest) {
-  auto type = GetParam();
-
   // cache is std::shared_ptr and will be automatically cleaned up.
   const size_t kCapacity = 200000;
   auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
   auto precise_cache = NewCache(kCapacity, 8, false, kFullChargeCacheMetadata);
   size_t baseline_meta_usage = precise_cache->GetUsage();
-  if (type != kHyperClock) {
+  if (!IsHyperClock()) {
     ASSERT_EQ(0, baseline_meta_usage);
   }
 
@@ -275,12 +253,7 @@ TEST_P(CacheTest, PinnedUsageTest) {
   // Add entries. Unpin some of them after insertion. Then, pin some of them
   // again. Check GetPinnedUsage().
   for (int i = 1; i < 100; ++i) {
-    std::string key;
-    if (type == kLRU) {
-      key = std::string(i, 'a');
-    } else {
-      key = EncodeKey(i);
-    }
+    std::string key = EncodeKey(i);
     auto kv_size = key.size() + 5;
     Cache::Handle* handle;
     Cache::Handle* handle_in_precise_cache;
@@ -321,12 +294,7 @@ TEST_P(CacheTest, PinnedUsageTest) {
 
   // check that overloading the cache does not change the pinned usage
   for (size_t i = 1; i < 2 * kCapacity; ++i) {
-    std::string key;
-    if (type == kLRU) {
-      key = std::to_string(i);
-    } else {
-      key = EncodeKey(static_cast<int>(1000 + i));
-    }
+    std::string key = EncodeKey(static_cast<int>(1000 + i));
     ASSERT_OK(cache->Insert(key, value, &kDumbHelper, key.size() + 5));
     ASSERT_OK(precise_cache->Insert(key, value, &kDumbHelper, key.size() + 5));
   }
@@ -367,7 +335,7 @@ TEST_P(CacheTest, HitAndMiss) {
   ASSERT_EQ(-1, Lookup(300));
 
   Insert(100, 102);
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     // ClockCache usually doesn't overwrite on Insert
     ASSERT_EQ(101, Lookup(100));
   } else {
@@ -377,7 +345,7 @@ TEST_P(CacheTest, HitAndMiss) {
   ASSERT_EQ(-1, Lookup(300));
 
   ASSERT_EQ(1U, deleted_values_.size());
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ASSERT_EQ(102, deleted_values_[0]);
   } else {
     ASSERT_EQ(101, deleted_values_[0]);
@@ -385,7 +353,7 @@ TEST_P(CacheTest, HitAndMiss) {
 }
 
 TEST_P(CacheTest, InsertSameKey) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS(
         "ClockCache doesn't guarantee Insert overwrite same key.");
     return;
@@ -414,7 +382,7 @@ TEST_P(CacheTest, Erase) {
 }
 
 TEST_P(CacheTest, EntriesArePinned) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS(
         "ClockCache doesn't guarantee Insert overwrite same key.");
     return;
@@ -478,7 +446,7 @@ TEST_P(CacheTest, ExternalRefPinsEntries) {
       Insert(1000 + j, 2000 + j);
     }
     // Clock cache is even more stateful and needs more churn to evict
-    if (GetParam() == kHyperClock) {
+    if (IsHyperClock()) {
       for (int j = 0; j < kCacheSize; j++) {
         Insert(11000 + j, 11000 + j);
       }
@@ -516,20 +484,20 @@ TEST_P(CacheTest, EvictionPolicyRef) {
   // Check whether the entries inserted in the beginning
   // are evicted. Ones without extra ref are evicted and
   // those with are not.
-  ASSERT_EQ(-1, Lookup(100));
-  ASSERT_EQ(-1, Lookup(101));
-  ASSERT_EQ(-1, Lookup(102));
-  ASSERT_EQ(-1, Lookup(103));
+  EXPECT_EQ(-1, Lookup(100));
+  EXPECT_EQ(-1, Lookup(101));
+  EXPECT_EQ(-1, Lookup(102));
+  EXPECT_EQ(-1, Lookup(103));
 
-  ASSERT_EQ(-1, Lookup(300));
-  ASSERT_EQ(-1, Lookup(301));
-  ASSERT_EQ(-1, Lookup(302));
-  ASSERT_EQ(-1, Lookup(303));
+  EXPECT_EQ(-1, Lookup(300));
+  EXPECT_EQ(-1, Lookup(301));
+  EXPECT_EQ(-1, Lookup(302));
+  EXPECT_EQ(-1, Lookup(303));
 
-  ASSERT_EQ(101, Lookup(200));
-  ASSERT_EQ(102, Lookup(201));
-  ASSERT_EQ(103, Lookup(202));
-  ASSERT_EQ(104, Lookup(203));
+  EXPECT_EQ(101, Lookup(200));
+  EXPECT_EQ(102, Lookup(201));
+  EXPECT_EQ(103, Lookup(202));
+  EXPECT_EQ(104, Lookup(203));
 
   // Cleaning up all the handles
   cache_->Release(h201);
@@ -539,37 +507,22 @@ TEST_P(CacheTest, EvictionPolicyRef) {
 }
 
 TEST_P(CacheTest, EvictEmptyCache) {
-  auto type = GetParam();
-
   // Insert item large than capacity to trigger eviction on empty cache.
   auto cache = NewCache(1, 0, false);
-  if (type == kLRU) {
-    ASSERT_OK(cache->Insert("foo", nullptr, &kDumbHelper, 10));
-  } else {
-    ASSERT_OK(cache->Insert(EncodeKey(1000), nullptr, &kDumbHelper, 10));
-  }
+  ASSERT_OK(cache->Insert(EncodeKey(1000), nullptr, &kDumbHelper, 10));
 }
 
 TEST_P(CacheTest, EraseFromDeleter) {
-  auto type = GetParam();
-
   // Have deleter which will erase item from cache, which will re-enter
   // the cache at that point.
   std::shared_ptr<Cache> cache = NewCache(10, 0, false);
-  std::string foo, bar;
-  const Cache::CacheItemHelper* erase_helper;
-  if (type == kLRU) {
-    foo = "foo";
-    bar = "bar";
-    erase_helper = &kEraseOnDeleteHelper1;
-  } else {
-    foo = EncodeKey(1234);
-    bar = EncodeKey(5678);
-    erase_helper = &kEraseOnDeleteHelper2;
-  }
+  std::string foo = EncodeKey(1234);
+  std::string bar = EncodeKey(5678);
+
+  std::function<void()> erase_fn = [&]() { cache->Erase(foo); };
 
   ASSERT_OK(cache->Insert(foo, nullptr, &kDumbHelper, 1));
-  ASSERT_OK(cache->Insert(bar, cache.get(), erase_helper, 1));
+  ASSERT_OK(cache->Insert(bar, &erase_fn, &kInvokeOnDeleteHelper, 1));
 
   cache->Erase(bar);
   ASSERT_EQ(nullptr, cache->Lookup(foo));
@@ -677,10 +630,10 @@ using TypedHandle = SharedCache::TypedHandle;
 }  // namespace
 
 TEST_P(CacheTest, SetCapacity) {
-  auto type = GetParam();
-  if (type == kHyperClock) {
+  if (IsHyperClock()) {
+    // TODO: update test & code for limited supoort
     ROCKSDB_GTEST_BYPASS(
-        "FastLRUCache and HyperClockCache don't support arbitrary capacity "
+        "HyperClockCache doesn't support arbitrary capacity "
         "adjustments.");
     return;
   }
@@ -810,7 +763,7 @@ TEST_P(CacheTest, OverCapacity) {
     cache.Release(handles[i]);
   }
 
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     // Make sure eviction is triggered.
     ASSERT_OK(cache.Insert(EncodeKey(-1), nullptr, 1, &handles[0]));
 
@@ -922,8 +875,7 @@ TEST_P(CacheTest, DefaultShardBits) {
   // Prevent excessive allocation (to save time & space)
   estimated_value_size_ = 100000;
   // Implementations use different minimum shard sizes
-  size_t min_shard_size =
-      (GetParam() == kHyperClock ? 32U * 1024U : 512U) * 1024U;
+  size_t min_shard_size = (IsHyperClock() ? 32U * 1024U : 512U) * 1024U;
 
   std::shared_ptr<Cache> cache = NewCache(32U * min_shard_size);
   ShardedCacheBase* sc = dynamic_cast<ShardedCacheBase*>(cache.get());
@@ -955,6 +907,97 @@ TEST_P(CacheTest, GetChargeAndDeleter) {
   cache_->Release(h1);
 }
 
+namespace {
+bool AreTwoCacheKeysOrdered(Cache* cache) {
+  std::vector<std::string> keys;
+  const auto callback = [&](const Slice& key, Cache::ObjectPtr /*value*/,
+                            size_t /*charge*/,
+                            const Cache::CacheItemHelper* /*helper*/) {
+    keys.push_back(key.ToString());
+  };
+  cache->ApplyToAllEntries(callback, /*opts*/ {});
+  EXPECT_EQ(keys.size(), 2U);
+  EXPECT_NE(keys[0], keys[1]);
+  return keys[0] < keys[1];
+}
+}  // namespace
+
+TEST_P(CacheTest, CacheUniqueSeeds) {
+  // kQuasiRandomHashSeed should generate unique seeds (up to 2 billion before
+  // repeating)
+  UnorderedSet<uint32_t> seeds_seen;
+  // Roughly sqrt(number of possible values) for a decent chance at detecting
+  // a random collision if it's possible (shouldn't be)
+  uint16_t kSamples = 20000;
+  seeds_seen.reserve(kSamples);
+
+  // Hash seed should affect ordering of entries in the table, so we should
+  // have extremely high chance of seeing two entries ordered both ways.
+  bool seen_forward_order = false;
+  bool seen_reverse_order = false;
+
+  for (int i = 0; i < kSamples; ++i) {
+    auto cache = NewCache(2, [=](ShardedCacheOptions& opts) {
+      opts.hash_seed = LRUCacheOptions::kQuasiRandomHashSeed;
+      opts.num_shard_bits = 0;
+      opts.metadata_charge_policy = kDontChargeCacheMetadata;
+    });
+    auto val = cache->GetHashSeed();
+    ASSERT_TRUE(seeds_seen.insert(val).second);
+
+    ASSERT_OK(cache->Insert(EncodeKey(1), nullptr, &kHelper, /*charge*/ 1));
+    ASSERT_OK(cache->Insert(EncodeKey(2), nullptr, &kHelper, /*charge*/ 1));
+
+    if (AreTwoCacheKeysOrdered(cache.get())) {
+      seen_forward_order = true;
+    } else {
+      seen_reverse_order = true;
+    }
+  }
+
+  ASSERT_TRUE(seen_forward_order);
+  ASSERT_TRUE(seen_reverse_order);
+}
+
+TEST_P(CacheTest, CacheHostSeed) {
+  // kHostHashSeed should generate a consistent seed within this process
+  // (and other processes on the same host, but not unit testing that).
+  // And we should be able to use that chosen seed as an explicit option
+  // (for debugging).
+  // And we should verify consistent ordering of entries.
+  uint32_t expected_seed = 0;
+  bool expected_order = false;
+  // 10 iterations -> chance of a random seed falsely appearing consistent
+  // should be low, just 1 in 2^9.
+  for (int i = 0; i < 10; ++i) {
+    auto cache = NewCache(2, [=](ShardedCacheOptions& opts) {
+      if (i != 5) {
+        opts.hash_seed = LRUCacheOptions::kHostHashSeed;
+      } else {
+        // Can be used as explicit seed
+        opts.hash_seed = static_cast<int32_t>(expected_seed);
+        ASSERT_GE(opts.hash_seed, 0);
+      }
+      opts.num_shard_bits = 0;
+      opts.metadata_charge_policy = kDontChargeCacheMetadata;
+    });
+    ASSERT_OK(cache->Insert(EncodeKey(1), nullptr, &kHelper, /*charge*/ 1));
+    ASSERT_OK(cache->Insert(EncodeKey(2), nullptr, &kHelper, /*charge*/ 1));
+    uint32_t val = cache->GetHashSeed();
+    bool order = AreTwoCacheKeysOrdered(cache.get());
+    if (i != 0) {
+      ASSERT_EQ(val, expected_seed);
+      ASSERT_EQ(order, expected_order);
+    } else {
+      expected_seed = val;
+      expected_order = order;
+    }
+  }
+  // Printed for reference in case it's needed to reproduce other unit test
+  // failures on another host
+  fprintf(stderr, "kHostHashSeed -> %u\n", (unsigned)expected_seed);
+}
+
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                         secondary_cache_test_util::GetTestingCacheTypes());
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest,

cache/clock_cache.h

@@ -24,12 +24,14 @@
 #include "rocksdb/cache.h"
 #include "rocksdb/secondary_cache.h"
 #include "util/autovector.h"
+#include "util/math.h"
 
 namespace ROCKSDB_NAMESPACE {
 
 namespace clock_cache {
 
 // Forward declaration of friend class.
+template <class ClockCache>
 class ClockCacheTest;
 
 // HyperClockCache is an alternative to LRUCache specifically tailored for
@@ -281,29 +283,6 @@ class ClockCacheTest;
 
 // ----------------------------------------------------------------------- //
 
-// The load factor p is a real number in (0, 1) such that at all
-// times at most a fraction p of all slots, without counting tombstones,
-// are occupied by elements. This means that the probability that a random
-// probe hits an occupied slot is at most p, and thus at most 1/p probes
-// are required on average. For example, p = 70% implies that between 1 and 2
-// probes are needed on average (bear in mind that this reasoning doesn't
-// consider the effects of clustering over time, which should be negligible
-// with double hashing).
-// Because the size of the hash table is always rounded up to the next
-// power of 2, p is really an upper bound on the actual load factor---the
-// actual load factor is anywhere between p/2 and p. This is a bit wasteful,
-// but bear in mind that slots only hold metadata, not actual values.
-// Since space cost is dominated by the values (the LSM blocks),
-// overprovisioning the table with metadata only increases the total cache space
-// usage by a tiny fraction.
-constexpr double kLoadFactor = 0.7;
-
-// The user can exceed kLoadFactor if the sizes of the inserted values don't
-// match estimated_value_size, or in some rare cases with
-// strict_capacity_limit == false. To avoid degenerate performance, we set a
-// strict upper bound on the load factor.
-constexpr double kStrictLoadFactor = 0.84;
-
 struct ClockHandleBasicData {
   Cache::ObjectPtr value = nullptr;
   const Cache::CacheItemHelper* helper = nullptr;
@@ -326,7 +305,7 @@ struct ClockHandle : public ClockHandleBasicData {
   // state of the handle. The meta word looks like this:
   // low bits                                                     high bits
   // -----------------------------------------------------------------------
-  // | acquire counter          | release counter           | state marker |
+  // | acquire counter      | release counter     | hit bit | state marker |
   // -----------------------------------------------------------------------
 
   // For reading or updating counters in meta word.
@@ -340,8 +319,13 @@ struct ClockHandle : public ClockHandleBasicData {
   static constexpr uint64_t kReleaseIncrement = uint64_t{1}
                                                 << kReleaseCounterShift;
 
+  // For setting the hit bit
+  static constexpr uint8_t kHitBitShift = 2U * kCounterNumBits;
+  static constexpr uint64_t kHitBitMask = uint64_t{1} << kHitBitShift;
+  ;
+
   // For reading or updating the state marker in meta word
-  static constexpr uint8_t kStateShift = 2U * kCounterNumBits;
+  static constexpr uint8_t kStateShift = kHitBitShift + 1;
 
   // Bits contribution to state marker.
   // Occupied means any state other than empty
@@ -371,14 +355,124 @@ struct ClockHandle : public ClockHandleBasicData {
   static constexpr uint8_t kMaxCountdown = kHighCountdown;
   // TODO: make these coundown values tuning parameters for eviction?
 
-  // See above
-  std::atomic<uint64_t> meta{};
-
-  // Anticipating use for SecondaryCache support
-  void* reserved_for_future_use = nullptr;
+  // See above. Mutable for read reference counting.
+  mutable std::atomic<uint64_t> meta{};
 };  // struct ClockHandle
 
-class HyperClockTable {
+class BaseClockTable {
+ public:
+  BaseClockTable(CacheMetadataChargePolicy metadata_charge_policy,
+                 MemoryAllocator* allocator,
+                 const Cache::EvictionCallback* eviction_callback,
+                 const uint32_t* hash_seed)
+      : metadata_charge_policy_(metadata_charge_policy),
+        allocator_(allocator),
+        eviction_callback_(*eviction_callback),
+        hash_seed_(*hash_seed) {}
+
+  template <class Table>
+  typename Table::HandleImpl* CreateStandalone(ClockHandleBasicData& proto,
+                                               size_t capacity,
+                                               bool strict_capacity_limit,
+                                               bool allow_uncharged);
+
+  template <class Table>
+  Status Insert(const ClockHandleBasicData& proto,
+                typename Table::HandleImpl** handle, Cache::Priority priority,
+                size_t capacity, bool strict_capacity_limit);
+
+  void Ref(ClockHandle& handle);
+
+  size_t GetOccupancy() const {
+    return occupancy_.load(std::memory_order_relaxed);
+  }
+
+  size_t GetUsage() const { return usage_.load(std::memory_order_relaxed); }
+
+  size_t GetStandaloneUsage() const {
+    return standalone_usage_.load(std::memory_order_relaxed);
+  }
+
+  uint32_t GetHashSeed() const { return hash_seed_; }
+
+  struct EvictionData {
+    size_t freed_charge = 0;
+    size_t freed_count = 0;
+  };
+
+  void TrackAndReleaseEvictedEntry(ClockHandle* h, EvictionData* data);
+
+#ifndef NDEBUG
+  // Acquire N references
+  void TEST_RefN(ClockHandle& handle, size_t n);
+  // Helper for TEST_ReleaseN
+  void TEST_ReleaseNMinus1(ClockHandle* handle, size_t n);
+#endif
+
+ private:  // fns
+  // Creates a "standalone" handle for returning from an Insert operation that
+  // cannot be completed by actually inserting into the table.
+  // Updates `standalone_usage_` but not `usage_` nor `occupancy_`.
+  template <class HandleImpl>
+  HandleImpl* StandaloneInsert(const ClockHandleBasicData& proto);
+
+  // Helper for updating `usage_` for new entry with given `total_charge`
+  // and evicting if needed under strict_capacity_limit=true rules. This
+  // means the operation might fail with Status::MemoryLimit. If
+  // `need_evict_for_occupancy`, then eviction of at least one entry is
+  // required, and the operation should fail if not possible.
+  // NOTE: Otherwise, occupancy_ is not managed in this function
+  template <class Table>
+  Status ChargeUsageMaybeEvictStrict(size_t total_charge, size_t capacity,
+                                     bool need_evict_for_occupancy,
+                                     typename Table::InsertState& state);
+
+  // Helper for updating `usage_` for new entry with given `total_charge`
+  // and evicting if needed under strict_capacity_limit=false rules. This
+  // means that updating `usage_` always succeeds even if forced to exceed
+  // capacity. If `need_evict_for_occupancy`, then eviction of at least one
+  // entry is required, and the operation should return false if such eviction
+  // is not possible. `usage_` is not updated in that case. Otherwise, returns
+  // true, indicating success.
+  // NOTE: occupancy_ is not managed in this function
+  template <class Table>
+  bool ChargeUsageMaybeEvictNonStrict(size_t total_charge, size_t capacity,
+                                      bool need_evict_for_occupancy,
+                                      typename Table::InsertState& state);
+
+ protected:  // data
+  // We partition the following members into different cache lines
+  // to avoid false sharing among Lookup, Release, Erase and Insert
+  // operations in ClockCacheShard.
+
+  // Clock algorithm sweep pointer.
+  std::atomic<uint64_t> clock_pointer_{};
+
+  // TODO: is this separation needed if we don't do background evictions?
+  ALIGN_AS(CACHE_LINE_SIZE)
+  // Number of elements in the table.
+  std::atomic<size_t> occupancy_{};
+
+  // Memory usage by entries tracked by the cache (including standalone)
+  std::atomic<size_t> usage_{};
+
+  // Part of usage by standalone entries (not in table)
+  std::atomic<size_t> standalone_usage_{};
+
+  ALIGN_AS(CACHE_LINE_SIZE)
+  const CacheMetadataChargePolicy metadata_charge_policy_;
+
+  // From Cache, for deleter
+  MemoryAllocator* const allocator_;
+
+  // A reference to Cache::eviction_callback_
+  const Cache::EvictionCallback& eviction_callback_;
+
+  // A reference to ShardedCacheBase::hash_seed_
+  const uint32_t& hash_seed_;
+};
+
+class FixedHyperClockTable : public BaseClockTable {
  public:
   // Target size to be exactly a common cache line size (see static_assert in
   // clock_cache.cc)
@@ -400,86 +494,104 @@ class HyperClockTable {
   };  // struct HandleImpl
 
   struct Opts {
+    explicit Opts(size_t _estimated_value_size)
+        : estimated_value_size(_estimated_value_size) {}
+    explicit Opts(const HyperClockCacheOptions& opts) {
+      assert(opts.estimated_entry_charge > 0);
+      estimated_value_size = opts.estimated_entry_charge;
+    }
     size_t estimated_value_size;
   };
 
-  HyperClockTable(size_t capacity, bool strict_capacity_limit,
-                  CacheMetadataChargePolicy metadata_charge_policy,
-                  MemoryAllocator* allocator,
-                  const Cache::EvictionCallback* eviction_callback,
-                  const Opts& opts);
-  ~HyperClockTable();
+  FixedHyperClockTable(size_t capacity, bool strict_capacity_limit,
+                       CacheMetadataChargePolicy metadata_charge_policy,
+                       MemoryAllocator* allocator,
+                       const Cache::EvictionCallback* eviction_callback,
+                       const uint32_t* hash_seed, const Opts& opts);
+  ~FixedHyperClockTable();
 
-  Status Insert(const ClockHandleBasicData& proto, HandleImpl** handle,
-                Cache::Priority priority, size_t capacity,
-                bool strict_capacity_limit);
+  // For BaseClockTable::Insert
+  struct InsertState {};
 
-  HandleImpl* CreateStandalone(ClockHandleBasicData& proto, size_t capacity,
-                               bool strict_capacity_limit,
-                               bool allow_uncharged);
+  void StartInsert(InsertState& state);
+
+  // Returns true iff there is room for the proposed number of entries.
+  bool GrowIfNeeded(size_t new_occupancy, InsertState& state);
+
+  HandleImpl* DoInsert(const ClockHandleBasicData& proto,
+                       uint64_t initial_countdown, bool take_ref,
+                       InsertState& state);
+
+  // Runs the clock eviction algorithm trying to reclaim at least
+  // requested_charge. Returns how much is evicted, which could be less
+  // if it appears impossible to evict the requested amount without blocking.
+  void Evict(size_t requested_charge, InsertState& state, EvictionData* data);
 
   HandleImpl* Lookup(const UniqueId64x2& hashed_key);
 
   bool Release(HandleImpl* handle, bool useful, bool erase_if_last_ref);
 
-  void Ref(HandleImpl& handle);
-
   void Erase(const UniqueId64x2& hashed_key);
 
-  void ConstApplyToEntriesRange(std::function<void(const HandleImpl&)> func,
-                                size_t index_begin, size_t index_end,
-                                bool apply_if_will_be_deleted) const;
-
   void EraseUnRefEntries();
 
   size_t GetTableSize() const { return size_t{1} << length_bits_; }
 
-  int GetLengthBits() const { return length_bits_; }
-
-  size_t GetOccupancy() const {
-    return occupancy_.load(std::memory_order_relaxed);
-  }
-
   size_t GetOccupancyLimit() const { return occupancy_limit_; }
 
-  size_t GetUsage() const { return usage_.load(std::memory_order_relaxed); }
+  const HandleImpl* HandlePtr(size_t idx) const { return &array_[idx]; }
 
-  size_t GetStandaloneUsage() const {
-    return standalone_usage_.load(std::memory_order_relaxed);
+#ifndef NDEBUG
+  size_t& TEST_MutableOccupancyLimit() {
+    return const_cast<size_t&>(occupancy_limit_);
   }
 
-  // Acquire/release N references
-  void TEST_RefN(HandleImpl& handle, size_t n);
+  // Release N references
   void TEST_ReleaseN(HandleImpl* handle, size_t n);
+#endif
+
+  // The load factor p is a real number in (0, 1) such that at all
+  // times at most a fraction p of all slots, without counting tombstones,
+  // are occupied by elements. This means that the probability that a random
+  // probe hits an occupied slot is at most p, and thus at most 1/p probes
+  // are required on average. For example, p = 70% implies that between 1 and 2
+  // probes are needed on average (bear in mind that this reasoning doesn't
+  // consider the effects of clustering over time, which should be negligible
+  // with double hashing).
+  // Because the size of the hash table is always rounded up to the next
+  // power of 2, p is really an upper bound on the actual load factor---the
+  // actual load factor is anywhere between p/2 and p. This is a bit wasteful,
+  // but bear in mind that slots only hold metadata, not actual values.
+  // Since space cost is dominated by the values (the LSM blocks),
+  // overprovisioning the table with metadata only increases the total cache
+  // space usage by a tiny fraction.
+  static constexpr double kLoadFactor = 0.7;
+
+  // The user can exceed kLoadFactor if the sizes of the inserted values don't
+  // match estimated_value_size, or in some rare cases with
+  // strict_capacity_limit == false. To avoid degenerate performance, we set a
+  // strict upper bound on the load factor.
+  static constexpr double kStrictLoadFactor = 0.84;
 
  private:  // functions
   // Returns x mod 2^{length_bits_}.
   inline size_t ModTableSize(uint64_t x) {
-    return static_cast<size_t>(x) & length_bits_mask_;
+    return BitwiseAnd(x, length_bits_mask_);
   }
 
-  // Runs the clock eviction algorithm trying to reclaim at least
-  // requested_charge. Returns how much is evicted, which could be less
-  // if it appears impossible to evict the requested amount without blocking.
-  inline void Evict(size_t requested_charge, size_t* freed_charge,
-                    size_t* freed_count);
-
-  // Returns the first slot in the probe sequence, starting from the given
-  // probe number, with a handle e such that match(e) is true. At every
-  // step, the function first tests whether match(e) holds. If this is false,
-  // it evaluates abort(e) to decide whether the search should be aborted,
-  // and in the affirmative returns -1. For every handle e probed except
-  // the last one, the function runs update(e).
-  // The probe parameter is modified as follows. We say a probe to a handle
-  // e is aborting if match(e) is false and abort(e) is true. Then the final
-  // value of probe is one more than the last non-aborting probe during the
-  // call. This is so that that the variable can be used to keep track of
-  // progress across consecutive calls to FindSlot.
+  // Returns the first slot in the probe sequence with a handle e such that
+  // match_fn(e) is true. At every step, the function first tests whether
+  // match_fn(e) holds. If this is false, it evaluates abort_fn(e) to decide
+  // whether the search should be aborted, and if so, FindSlot immediately
+  // returns nullptr. For every handle e that is not a match and not aborted,
+  // FindSlot runs update_fn(e, is_last) where is_last is set to true iff that
+  // slot will be the last probed because the next would cycle back to the first
+  // slot probed. This function uses templates instead of std::function to
+  // minimize the risk of heap-allocated closures being created.
+  template <typename MatchFn, typename AbortFn, typename UpdateFn>
   inline HandleImpl* FindSlot(const UniqueId64x2& hashed_key,
-                              std::function<bool(HandleImpl*)> match,
-                              std::function<bool(HandleImpl*)> stop,
-                              std::function<void(HandleImpl*)> update,
-                              size_t& probe);
+                              const MatchFn& match_fn, const AbortFn& abort_fn,
+                              const UpdateFn& update_fn);
 
   // Re-decrement all displacements in probe path starting from beginning
   // until (not including) the given handle
@@ -492,33 +604,6 @@ class HyperClockTable {
   // before releasing it so that it can be provided to this function.
   inline void ReclaimEntryUsage(size_t total_charge);
 
-  // Helper for updating `usage_` for new entry with given `total_charge`
-  // and evicting if needed under strict_capacity_limit=true rules. This
-  // means the operation might fail with Status::MemoryLimit. If
-  // `need_evict_for_occupancy`, then eviction of at least one entry is
-  // required, and the operation should fail if not possible.
-  // NOTE: Otherwise, occupancy_ is not managed in this function
-  inline Status ChargeUsageMaybeEvictStrict(size_t total_charge,
-                                            size_t capacity,
-                                            bool need_evict_for_occupancy);
-
-  // Helper for updating `usage_` for new entry with given `total_charge`
-  // and evicting if needed under strict_capacity_limit=false rules. This
-  // means that updating `usage_` always succeeds even if forced to exceed
-  // capacity. If `need_evict_for_occupancy`, then eviction of at least one
-  // entry is required, and the operation should return false if such eviction
-  // is not possible. `usage_` is not updated in that case. Otherwise, returns
-  // true, indicating success.
-  // NOTE: occupancy_ is not managed in this function
-  inline bool ChargeUsageMaybeEvictNonStrict(size_t total_charge,
-                                             size_t capacity,
-                                             bool need_evict_for_occupancy);
-
-  // Creates a "standalone" handle for returning from an Insert operation that
-  // cannot be completed by actually inserting into the table.
-  // Updates `standalone_usage_` but not `usage_` nor `occupancy_`.
-  inline HandleImpl* StandaloneInsert(const ClockHandleBasicData& proto);
-
   MemoryAllocator* GetAllocator() const { return allocator_; }
 
   // Returns the number of bits used to hash an element in the hash
@@ -539,41 +624,25 @@ class HyperClockTable {
 
   // Array of slots comprising the hash table.
   const std::unique_ptr<HandleImpl[]> array_;
+};  // class FixedHyperClockTable
 
-  // From Cache, for deleter
-  MemoryAllocator* const allocator_;
-
-  // A reference to Cache::eviction_callback_
-  const Cache::EvictionCallback& eviction_callback_;
-
-  // We partition the following members into different cache lines
-  // to avoid false sharing among Lookup, Release, Erase and Insert
-  // operations in ClockCacheShard.
-
-  ALIGN_AS(CACHE_LINE_SIZE)
-  // Clock algorithm sweep pointer.
-  std::atomic<uint64_t> clock_pointer_{};
-
-  ALIGN_AS(CACHE_LINE_SIZE)
-  // Number of elements in the table.
-  std::atomic<size_t> occupancy_{};
-
-  // Memory usage by entries tracked by the cache (including standalone)
-  std::atomic<size_t> usage_{};
-
-  // Part of usage by standalone entries (not in table)
-  std::atomic<size_t> standalone_usage_{};
-};  // class HyperClockTable
+// Placeholder for future automatic table variant
+// For now, just use FixedHyperClockTable.
+class AutoHyperClockTable : public FixedHyperClockTable {
+ public:
+  using FixedHyperClockTable::FixedHyperClockTable;
+};  // class AutoHyperClockTable
 
 // A single shard of sharded cache.
-template <class Table>
+template <class TableT>
 class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
  public:
+  using Table = TableT;
   ClockCacheShard(size_t capacity, bool strict_capacity_limit,
                   CacheMetadataChargePolicy metadata_charge_policy,
                   MemoryAllocator* allocator,
                   const Cache::EvictionCallback* eviction_callback,
-                  const typename Table::Opts& opts);
+                  const uint32_t* hash_seed, const typename Table::Opts& opts);
 
   // For CacheShard concept
   using HandleImpl = typename Table::HandleImpl;
@@ -583,22 +652,23 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
   static inline uint32_t HashPieceForSharding(HashCref hash) {
     return Upper32of64(hash[0]);
   }
-  static inline HashVal ComputeHash(const Slice& key) {
+  static inline HashVal ComputeHash(const Slice& key, uint32_t seed) {
     assert(key.size() == kCacheKeySize);
     HashVal in;
     HashVal out;
     // NOTE: endian dependence
     // TODO: use GetUnaligned?
     std::memcpy(&in, key.data(), kCacheKeySize);
-    BijectiveHash2x64(in[1], in[0], &out[1], &out[0]);
+    BijectiveHash2x64(in[1], in[0] ^ seed, &out[1], &out[0]);
     return out;
   }
 
   // For reconstructing key from hashed_key. Requires the caller to provide
   // backing storage for the Slice in `unhashed`
   static inline Slice ReverseHash(const UniqueId64x2& hashed,
-                                  UniqueId64x2* unhashed) {
+                                  UniqueId64x2* unhashed, uint32_t seed) {
     BijectiveUnhash2x64(hashed[1], hashed[0], &(*unhashed)[1], &(*unhashed)[0]);
+    (*unhashed)[0] ^= seed;
     // NOTE: endian dependence
     return Slice(reinterpret_cast<const char*>(unhashed), kCacheKeySize);
   }
@@ -660,9 +730,17 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
     return Lookup(key, hashed_key);
   }
 
+  Table& GetTable() { return table_; }
+  const Table& GetTable() const { return table_; }
+
+#ifndef NDEBUG
+  size_t& TEST_MutableOccupancyLimit() {
+    return table_.TEST_MutableOccupancyLimit();
+  }
   // Acquire/release N references
   void TEST_RefN(HandleImpl* handle, size_t n);
   void TEST_ReleaseN(HandleImpl* handle, size_t n);
+#endif
 
  private:  // data
   Table table_;
@@ -674,20 +752,14 @@ class ALIGN_AS(CACHE_LINE_SIZE) ClockCacheShard final : public CacheShardBase {
   std::atomic<bool> strict_capacity_limit_;
 };  // class ClockCacheShard
 
-class HyperClockCache
-#ifdef NDEBUG
-    final
-#endif
-    : public ShardedCache<ClockCacheShard<HyperClockTable>> {
+template <class Table>
+class BaseHyperClockCache : public ShardedCache<ClockCacheShard<Table>> {
  public:
-  using Shard = ClockCacheShard<HyperClockTable>;
+  using Shard = ClockCacheShard<Table>;
+  using Handle = Cache::Handle;
+  using CacheItemHelper = Cache::CacheItemHelper;
 
-  HyperClockCache(size_t capacity, size_t estimated_value_size,
-                  int num_shard_bits, bool strict_capacity_limit,
-                  CacheMetadataChargePolicy metadata_charge_policy,
-                  std::shared_ptr<MemoryAllocator> memory_allocator);
-
-  const char* Name() const override { return "HyperClockCache"; }
+  explicit BaseHyperClockCache(const HyperClockCacheOptions& opts);
 
   Cache::ObjectPtr Value(Handle* handle) override;
 
@@ -697,7 +769,33 @@ class HyperClockCache
 
   void ReportProblems(
       const std::shared_ptr<Logger>& /*info_log*/) const override;
-};  // class HyperClockCache
+};
+
+class FixedHyperClockCache
+#ifdef NDEBUG
+    final
+#endif
+    : public BaseHyperClockCache<FixedHyperClockTable> {
+ public:
+  using BaseHyperClockCache::BaseHyperClockCache;
+
+  const char* Name() const override { return "FixedHyperClockCache"; }
+
+  void ReportProblems(
+      const std::shared_ptr<Logger>& /*info_log*/) const override;
+};  // class FixedHyperClockCache
+
+// Placeholder for future automatic HCC variant
+class AutoHyperClockCache
+#ifdef NDEBUG
+    final
+#endif
+    : public BaseHyperClockCache<AutoHyperClockTable> {
+ public:
+  using BaseHyperClockCache::BaseHyperClockCache;
+
+  const char* Name() const override { return "AutoHyperClockCache"; }
+};  // class AutoHyperClockCache
 
 }  // namespace clock_cache
 

cache/compressed_secondary_cache.cc

@@ -9,7 +9,7 @@
 #include <cstdint>
 #include <memory>
 
-#include "memory/memory_allocator.h"
+#include "memory/memory_allocator_impl.h"
 #include "monitoring/perf_context_imp.h"
 #include "util/compression.h"
 #include "util/string_util.h"
@@ -17,31 +17,27 @@
 namespace ROCKSDB_NAMESPACE {
 
 CompressedSecondaryCache::CompressedSecondaryCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio, double low_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    CompressionType compression_type, uint32_t compress_format_version,
-    bool enable_custom_split_merge,
-    const CacheEntryRoleSet& do_not_compress_roles)
-    : cache_options_(capacity, num_shard_bits, strict_capacity_limit,
-                     high_pri_pool_ratio, low_pri_pool_ratio, memory_allocator,
-                     use_adaptive_mutex, metadata_charge_policy,
-                     compression_type, compress_format_version,
-                     enable_custom_split_merge, do_not_compress_roles) {
-  cache_ =
-      NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
-                  high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-                  metadata_charge_policy, low_pri_pool_ratio);
-}
+    const CompressedSecondaryCacheOptions& opts)
+    : cache_(opts.LRUCacheOptions::MakeSharedCache()),
+      cache_options_(opts),
+      cache_res_mgr_(std::make_shared<ConcurrentCacheReservationManager>(
+          std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
+              cache_))),
+      disable_cache_(opts.capacity == 0) {}
 
-CompressedSecondaryCache::~CompressedSecondaryCache() { cache_.reset(); }
+CompressedSecondaryCache::~CompressedSecondaryCache() {
+  assert(cache_res_mgr_->GetTotalReservedCacheSize() == 0);
+}
 
 std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
     const Slice& key, const Cache::CacheItemHelper* helper,
     Cache::CreateContext* create_context, bool /*wait*/, bool advise_erase,
     bool& kept_in_sec_cache) {
   assert(helper);
+  if (disable_cache_) {
+    return nullptr;
+  }
+
   std::unique_ptr<SecondaryCacheResultHandle> handle;
   kept_in_sec_cache = false;
   Cache::Handle* lru_handle = cache_->Lookup(key);
@@ -118,20 +114,27 @@ std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
 
 Status CompressedSecondaryCache::Insert(const Slice& key,
                                         Cache::ObjectPtr value,
-                                        const Cache::CacheItemHelper* helper) {
+                                        const Cache::CacheItemHelper* helper,
+                                        bool force_insert) {
   if (value == nullptr) {
     return Status::InvalidArgument();
   }
 
-  Cache::Handle* lru_handle = cache_->Lookup(key);
+  if (disable_cache_) {
+    return Status::OK();
+  }
+
   auto internal_helper = GetHelper(cache_options_.enable_custom_split_merge);
-  if (lru_handle == nullptr) {
-    PERF_COUNTER_ADD(compressed_sec_cache_insert_dummy_count, 1);
-    // Insert a dummy handle if the handle is evicted for the first time.
-    return cache_->Insert(key, /*obj=*/nullptr, internal_helper,
-                          /*charge=*/0);
-  } else {
-    cache_->Release(lru_handle, /*erase_if_last_ref=*/false);
+  if (!force_insert) {
+    Cache::Handle* lru_handle = cache_->Lookup(key);
+    if (lru_handle == nullptr) {
+      PERF_COUNTER_ADD(compressed_sec_cache_insert_dummy_count, 1);
+      // Insert a dummy handle if the handle is evicted for the first time.
+      return cache_->Insert(key, /*obj=*/nullptr, internal_helper,
+                            /*charge=*/0);
+    } else {
+      cache_->Release(lru_handle, /*erase_if_last_ref=*/false);
+    }
   }
 
   size_t size = (*helper->size_cb)(value);
@@ -149,7 +152,8 @@ Status CompressedSecondaryCache::Insert(const Slice& key,
       !cache_options_.do_not_compress_roles.Contains(helper->role)) {
     PERF_COUNTER_ADD(compressed_sec_cache_uncompressed_bytes, size);
     CompressionOptions compression_opts;
-    CompressionContext compression_context(cache_options_.compression_type);
+    CompressionContext compression_context(cache_options_.compression_type,
+                                           compression_opts);
     uint64_t sample_for_compression{0};
     CompressionInfo compression_info(
         compression_opts, compression_context, CompressionDict::GetEmptyDict(),
@@ -191,6 +195,7 @@ Status CompressedSecondaryCache::SetCapacity(size_t capacity) {
   MutexLock l(&capacity_mutex_);
   cache_options_.capacity = capacity;
   cache_->SetCapacity(capacity);
+  disable_cache_ = capacity == 0;
   return Status::OK();
 }
 
@@ -311,31 +316,17 @@ const Cache::CacheItemHelper* CompressedSecondaryCache::GetHelper(
   }
 }
 
-std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio, double low_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    CompressionType compression_type, uint32_t compress_format_version,
-    bool enable_custom_split_merge,
-    const CacheEntryRoleSet& do_not_compress_roles) {
-  return std::make_shared<CompressedSecondaryCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      low_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-      metadata_charge_policy, compression_type, compress_format_version,
-      enable_custom_split_merge, do_not_compress_roles);
+std::shared_ptr<SecondaryCache>
+CompressedSecondaryCacheOptions::MakeSharedSecondaryCache() const {
+  return std::make_shared<CompressedSecondaryCache>(*this);
 }
 
-std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
-    const CompressedSecondaryCacheOptions& opts) {
-  // The secondary_cache is disabled for this LRUCache instance.
-  assert(opts.secondary_cache == nullptr);
-  return NewCompressedSecondaryCache(
-      opts.capacity, opts.num_shard_bits, opts.strict_capacity_limit,
-      opts.high_pri_pool_ratio, opts.low_pri_pool_ratio, opts.memory_allocator,
-      opts.use_adaptive_mutex, opts.metadata_charge_policy,
-      opts.compression_type, opts.compress_format_version,
-      opts.enable_custom_split_merge, opts.do_not_compress_roles);
+Status CompressedSecondaryCache::Deflate(size_t decrease) {
+  return cache_res_mgr_->UpdateCacheReservation(decrease, /*increase=*/true);
+}
+
+Status CompressedSecondaryCache::Inflate(size_t increase) {
+  return cache_res_mgr_->UpdateCacheReservation(increase, /*increase=*/false);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

cache/compressed_secondary_cache.h

@@ -9,8 +9,9 @@
 #include <cstddef>
 #include <memory>
 
+#include "cache/cache_reservation_manager.h"
 #include "cache/lru_cache.h"
-#include "memory/memory_allocator.h"
+#include "memory/memory_allocator_impl.h"
 #include "rocksdb/secondary_cache.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/status.h"
@@ -69,24 +70,15 @@ class CompressedSecondaryCacheResultHandle : public SecondaryCacheResultHandle {
 
 class CompressedSecondaryCache : public SecondaryCache {
  public:
-  CompressedSecondaryCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      double high_pri_pool_ratio, double low_pri_pool_ratio,
-      std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-      bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-      CacheMetadataChargePolicy metadata_charge_policy =
-          kDefaultCacheMetadataChargePolicy,
-      CompressionType compression_type = CompressionType::kLZ4Compression,
-      uint32_t compress_format_version = 2,
-      bool enable_custom_split_merge = false,
-      const CacheEntryRoleSet& do_not_compress_roles = {
-          CacheEntryRole::kFilterBlock});
+  explicit CompressedSecondaryCache(
+      const CompressedSecondaryCacheOptions& opts);
   ~CompressedSecondaryCache() override;
 
   const char* Name() const override { return "CompressedSecondaryCache"; }
 
   Status Insert(const Slice& key, Cache::ObjectPtr value,
-                const Cache::CacheItemHelper* helper) override;
+                const Cache::CacheItemHelper* helper,
+                bool force_insert) override;
 
   std::unique_ptr<SecondaryCacheResultHandle> Lookup(
       const Slice& key, const Cache::CacheItemHelper* helper,
@@ -103,8 +95,14 @@ class CompressedSecondaryCache : public SecondaryCache {
 
   Status GetCapacity(size_t& capacity) override;
 
+  Status Deflate(size_t decrease) override;
+
+  Status Inflate(size_t increase) override;
+
   std::string GetPrintableOptions() const override;
 
+  size_t TEST_GetUsage() { return cache_->GetUsage(); }
+
  private:
   friend class CompressedSecondaryCacheTestBase;
   static constexpr std::array<uint16_t, 8> malloc_bin_sizes_{
@@ -137,6 +135,8 @@ class CompressedSecondaryCache : public SecondaryCache {
   std::shared_ptr<Cache> cache_;
   CompressedSecondaryCacheOptions cache_options_;
   mutable port::Mutex capacity_mutex_;
+  std::shared_ptr<ConcurrentCacheReservationManager> cache_res_mgr_;
+  bool disable_cache_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

cache/compressed_secondary_cache_test.cc

@@ -10,11 +10,14 @@
 #include <memory>
 #include <tuple>
 
+#include "cache/secondary_cache_adapter.h"
 #include "memory/jemalloc_nodump_allocator.h"
+#include "rocksdb/cache.h"
 #include "rocksdb/convenience.h"
 #include "test_util/secondary_cache_test_util.h"
 #include "test_util/testharness.h"
 #include "test_util/testutil.h"
+#include "util/cast_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -49,7 +52,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     std::string str1(rnd.RandomString(1000));
     TestItem item1(str1.data(), str1.length());
     // A dummy handle is inserted if the item is inserted for the first time.
-    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_dummy_count, 1);
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_uncompressed_bytes, 0);
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_compressed_bytes, 0);
@@ -60,7 +63,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     ASSERT_EQ(handle1_1, nullptr);
 
     // Insert and Lookup the item k1 for the second time and advise erasing it.
-    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_real_count, 1);
 
     std::unique_ptr<SecondaryCacheResultHandle> handle1_2 =
@@ -92,14 +95,14 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     // Insert and Lookup the item k2.
     std::string str2(rnd.RandomString(1000));
     TestItem item2(str2.data(), str2.length());
-    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper(), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_dummy_count, 2);
     std::unique_ptr<SecondaryCacheResultHandle> handle2_1 =
         sec_cache->Lookup(key2, GetHelper(), this, true, /*advise_erase=*/false,
                           kept_in_sec_cache);
     ASSERT_EQ(handle2_1, nullptr);
 
-    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper(), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_real_count, 2);
     if (sec_cache_is_compressed) {
       ASSERT_EQ(get_perf_context()->compressed_sec_cache_uncompressed_bytes,
@@ -181,15 +184,15 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     std::string str1(rnd.RandomString(1000));
     TestItem item1(str1.data(), str1.length());
     // Insert a dummy handle.
-    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
     // Insert k1.
-    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
 
     // Insert and Lookup the second item.
     std::string str2(rnd.RandomString(200));
     TestItem item2(str2.data(), str2.length());
     // Insert a dummy handle, k1 is not evicted.
-    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper(), false));
     bool kept_in_sec_cache{false};
     std::unique_ptr<SecondaryCacheResultHandle> handle1 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/false,
@@ -197,7 +200,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     ASSERT_EQ(handle1, nullptr);
 
     // Insert k2 and k1 is evicted.
-    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key2, &item2, GetHelper(), false));
     std::unique_ptr<SecondaryCacheResultHandle> handle2 =
         sec_cache->Lookup(key2, GetHelper(), this, true, /*advise_erase=*/false,
                           kept_in_sec_cache);
@@ -208,7 +211,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     ASSERT_EQ(memcmp(val2->Buf(), item2.Buf(), item2.Size()), 0);
 
     // Insert k1 again and a dummy handle is inserted.
-    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper()));
+    ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
 
     std::unique_ptr<SecondaryCacheResultHandle> handle1_1 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/false,
@@ -226,8 +229,8 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     std::string str3 = rnd.RandomString(10);
     TestItem item3(str3.data(), str3.length());
     // The Status is OK because a dummy handle is inserted.
-    ASSERT_OK(sec_cache->Insert(key3, &item3, GetHelperFail()));
-    ASSERT_NOK(sec_cache->Insert(key3, &item3, GetHelperFail()));
+    ASSERT_OK(sec_cache->Insert(key3, &item3, GetHelperFail(), false));
+    ASSERT_NOK(sec_cache->Insert(key3, &item3, GetHelperFail(), false));
 
     sec_cache.reset();
   }
@@ -626,8 +629,9 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 
     using CacheValueChunk = CompressedSecondaryCache::CacheValueChunk;
     std::unique_ptr<CompressedSecondaryCache> sec_cache =
-        std::make_unique<CompressedSecondaryCache>(1000, 0, true, 0.5, 0.0,
-                                                   allocator);
+        std::make_unique<CompressedSecondaryCache>(
+            CompressedSecondaryCacheOptions(1000, 0, true, 0.5, 0.0,
+                                            allocator));
     Random rnd(301);
     // 8500 = 8169 + 233 + 98, so there should be 3 chunks after split.
     size_t str_size{8500};
@@ -678,7 +682,8 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     std::string str = str1 + str2 + str3;
 
     std::unique_ptr<CompressedSecondaryCache> sec_cache =
-        std::make_unique<CompressedSecondaryCache>(1000, 0, true, 0.5, 0.0);
+        std::make_unique<CompressedSecondaryCache>(
+            CompressedSecondaryCacheOptions(1000, 0, true, 0.5, 0.0));
     size_t charge{0};
     CacheAllocationPtr value =
         sec_cache->MergeChunksIntoValue(chunks_head, charge);
@@ -708,8 +713,9 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 
     using CacheValueChunk = CompressedSecondaryCache::CacheValueChunk;
     std::unique_ptr<CompressedSecondaryCache> sec_cache =
-        std::make_unique<CompressedSecondaryCache>(1000, 0, true, 0.5, 0.0,
-                                                   allocator);
+        std::make_unique<CompressedSecondaryCache>(
+            CompressedSecondaryCacheOptions(1000, 0, true, 0.5, 0.0,
+                                            allocator));
     Random rnd(301);
     // 8500 = 8169 + 233 + 98, so there should be 3 chunks after split.
     size_t str_size{8500};
@@ -732,7 +738,7 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
 class CompressedSecondaryCacheTest
     : public CompressedSecondaryCacheTestBase,
       public testing::WithParamInterface<std::string> {
-  const std::string& Type() override { return GetParam(); }
+  const std::string& Type() const override { return GetParam(); }
 };
 
 INSTANTIATE_TEST_CASE_P(CompressedSecondaryCacheTest,
@@ -747,7 +753,7 @@ class CompressedSecCacheTestWithCompressAndAllocatorParam
     sec_cache_is_compressed_ = std::get<0>(GetParam());
     use_jemalloc_ = std::get<1>(GetParam());
   }
-  const std::string& Type() override { return std::get<2>(GetParam()); }
+  const std::string& Type() const override { return std::get<2>(GetParam()); }
   bool sec_cache_is_compressed_;
   bool use_jemalloc_;
 };
@@ -768,7 +774,7 @@ class CompressedSecondaryCacheTestWithCompressionParam
   CompressedSecondaryCacheTestWithCompressionParam() {
     sec_cache_is_compressed_ = std::get<0>(GetParam());
   }
-  const std::string& Type() override { return std::get<1>(GetParam()); }
+  const std::string& Type() const override { return std::get<1>(GetParam()); }
   bool sec_cache_is_compressed_;
 };
 
@@ -899,10 +905,10 @@ TEST_P(CompressedSecondaryCacheTestWithCompressionParam, EntryRoles) {
     Slice ith_key = Slice(junk.data(), 16);
 
     get_perf_context()->Reset();
-    ASSERT_OK(sec_cache->Insert(ith_key, &item, GetHelper(role)));
+    ASSERT_OK(sec_cache->Insert(ith_key, &item, GetHelper(role), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_dummy_count, 1U);
 
-    ASSERT_OK(sec_cache->Insert(ith_key, &item, GetHelper(role)));
+    ASSERT_OK(sec_cache->Insert(ith_key, &item, GetHelper(role), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_real_count, 1U);
 
     bool kept_in_sec_cache{true};
@@ -945,7 +951,7 @@ class CompressedSecCacheTestWithCompressAndSplitParam
     sec_cache_is_compressed_ = std::get<0>(GetParam());
     enable_custom_split_merge_ = std::get<1>(GetParam());
   }
-  const std::string& Type() override { return std::get<2>(GetParam()); }
+  const std::string& Type() const override { return std::get<2>(GetParam()); }
   bool sec_cache_is_compressed_;
   bool enable_custom_split_merge_;
 };
@@ -971,6 +977,202 @@ TEST_P(CompressedSecondaryCacheTest, SplictValueAndMergeChunksTest) {
   SplictValueAndMergeChunksTest();
 }
 
+using secondary_cache_test_util::WithCacheType;
+
+class CompressedSecCacheTestWithTiered
+    : public testing::Test,
+      public WithCacheType,
+      public testing::WithParamInterface<
+          std::tuple<PrimaryCacheType, TieredAdmissionPolicy>> {
+ public:
+  using secondary_cache_test_util::WithCacheType::TestItem;
+  CompressedSecCacheTestWithTiered() {
+    LRUCacheOptions lru_opts;
+    HyperClockCacheOptions hcc_opts(
+        /*_capacity=*/70 << 20,
+        /*_estimated_entry_charge=*/256 << 10,
+        /*_num_shard_bits=*/0);
+    TieredVolatileCacheOptions opts;
+    lru_opts.capacity = 70 << 20;
+    lru_opts.num_shard_bits = 0;
+    lru_opts.high_pri_pool_ratio = 0;
+    opts.cache_type = std::get<0>(GetParam());
+    if (opts.cache_type == PrimaryCacheType::kCacheTypeLRU) {
+      opts.cache_opts = &lru_opts;
+    } else {
+      opts.cache_opts = &hcc_opts;
+    }
+    opts.adm_policy = std::get<1>(GetParam());
+    ;
+    opts.comp_cache_opts.capacity = 30 << 20;
+    opts.comp_cache_opts.num_shard_bits = 0;
+    cache_ = NewTieredVolatileCache(opts);
+    cache_res_mgr_ =
+        std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
+            cache_);
+  }
+
+  const std::string& Type() const override {
+    if (std::get<0>(GetParam()) == PrimaryCacheType::kCacheTypeLRU) {
+      return lru_str;
+    } else {
+      return hcc_str;
+    }
+  }
+
+ protected:
+  CacheReservationManager* cache_res_mgr() { return cache_res_mgr_.get(); }
+
+  Cache* GetTieredCache() { return cache_.get(); }
+
+  Cache* GetCache() {
+    return static_cast_with_check<CacheWithSecondaryAdapter, Cache>(
+               cache_.get())
+        ->TEST_GetCache();
+  }
+
+  SecondaryCache* GetSecondaryCache() {
+    return static_cast_with_check<CacheWithSecondaryAdapter, Cache>(
+               cache_.get())
+        ->TEST_GetSecondaryCache();
+  }
+
+  size_t GetPercent(size_t val, unsigned int percent) {
+    return static_cast<size_t>(val * percent / 100);
+  }
+
+ private:
+  std::shared_ptr<Cache> cache_;
+  std::shared_ptr<CacheReservationManager> cache_res_mgr_;
+  static std::string lru_str;
+  static std::string hcc_str;
+};
+
+std::string CompressedSecCacheTestWithTiered::lru_str(WithCacheType::kLRU);
+std::string CompressedSecCacheTestWithTiered::hcc_str(
+    WithCacheType::kFixedHyperClock);
+
+bool CacheUsageWithinBounds(size_t val1, size_t val2, size_t error) {
+  return ((val1 < (val2 + error)) && (val1 > (val2 - error)));
+}
+
+TEST_P(CompressedSecCacheTestWithTiered, CacheReservationManager) {
+  CompressedSecondaryCache* sec_cache =
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+
+  // Use EXPECT_PRED3 instead of EXPECT_NEAR to void too many size_t to
+  // double explicit casts
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+
+  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(10 << 20));
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (37 << 20),
+               GetPercent(37 << 20, 1));
+  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (3 << 20),
+               GetPercent(3 << 20, 1));
+
+  ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(0));
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+}
+
+TEST_P(CompressedSecCacheTestWithTiered,
+       CacheReservationManagerMultipleUpdate) {
+  CompressedSecondaryCache* sec_cache =
+      reinterpret_cast<CompressedSecondaryCache*>(GetSecondaryCache());
+
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+
+  int i;
+  for (i = 0; i < 10; ++i) {
+    ASSERT_OK(cache_res_mgr()->UpdateCacheReservation((1 + i) << 20));
+  }
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (37 << 20),
+               GetPercent(37 << 20, 1));
+  EXPECT_PRED3(CacheUsageWithinBounds, sec_cache->TEST_GetUsage(), (3 << 20),
+               GetPercent(3 << 20, 1));
+
+  for (i = 10; i > 0; --i) {
+    ASSERT_OK(cache_res_mgr()->UpdateCacheReservation(((i - 1) << 20)));
+  }
+  EXPECT_PRED3(CacheUsageWithinBounds, GetCache()->GetUsage(), (30 << 20),
+               GetPercent(30 << 20, 1));
+  EXPECT_EQ(sec_cache->TEST_GetUsage(), 0);
+}
+
+TEST_P(CompressedSecCacheTestWithTiered, AdmissionPolicy) {
+  if (!LZ4_Supported()) {
+    ROCKSDB_GTEST_BYPASS("This test requires LZ4 support\n");
+    return;
+  }
+
+  Cache* tiered_cache = GetTieredCache();
+  Cache* cache = GetCache();
+  std::vector<CacheKey> keys;
+  std::vector<std::string> vals;
+  // Make the item size slightly less than 10MB to ensure we can fit the
+  // expected number of items in the cache
+  int item_size = (10 << 20) - (1 << 18);
+  int i;
+  Random rnd(301);
+  for (i = 0; i < 14; ++i) {
+    keys.emplace_back(CacheKey::CreateUniqueForCacheLifetime(cache));
+    vals.emplace_back(rnd.RandomString(item_size));
+  }
+
+  for (i = 0; i < 7; ++i) {
+    TestItem* item = new TestItem(vals[i].data(), vals[i].length());
+    ASSERT_OK(tiered_cache->Insert(keys[i].AsSlice(), item, GetHelper(),
+                                   vals[i].length()));
+  }
+
+  Cache::Handle* handle1;
+  handle1 = tiered_cache->Lookup(keys[0].AsSlice(), GetHelper(),
+                                 /*context*/ this, Cache::Priority::LOW);
+  ASSERT_NE(handle1, nullptr);
+  Cache::Handle* handle2;
+  handle2 = tiered_cache->Lookup(keys[1].AsSlice(), GetHelper(),
+                                 /*context*/ this, Cache::Priority::LOW);
+  ASSERT_NE(handle2, nullptr);
+  tiered_cache->Release(handle1);
+  tiered_cache->Release(handle2);
+
+  // Flush all previous entries out of the primary cache
+  for (i = 7; i < 14; ++i) {
+    TestItem* item = new TestItem(vals[i].data(), vals[i].length());
+    ASSERT_OK(tiered_cache->Insert(keys[i].AsSlice(), item, GetHelper(),
+                                   vals[i].length()));
+  }
+  // keys 0 and 1 should be found as they had the hit bit set
+  handle1 = tiered_cache->Lookup(keys[0].AsSlice(), GetHelper(),
+                                 /*context*/ this, Cache::Priority::LOW);
+  ASSERT_NE(handle1, nullptr);
+  handle2 = tiered_cache->Lookup(keys[1].AsSlice(), GetHelper(),
+                                 /*context*/ this, Cache::Priority::LOW);
+  ASSERT_NE(handle2, nullptr);
+  tiered_cache->Release(handle1);
+  tiered_cache->Release(handle2);
+
+  handle1 = tiered_cache->Lookup(keys[2].AsSlice(), GetHelper(),
+                                 /*context*/ this, Cache::Priority::LOW);
+  ASSERT_EQ(handle1, nullptr);
+  handle1 = tiered_cache->Lookup(keys[3].AsSlice(), GetHelper(),
+                                 /*context*/ this, Cache::Priority::LOW);
+  ASSERT_EQ(handle1, nullptr);
+}
+
+INSTANTIATE_TEST_CASE_P(
+    CompressedSecCacheTests, CompressedSecCacheTestWithTiered,
+    ::testing::Values(
+        std::make_tuple(PrimaryCacheType::kCacheTypeLRU,
+                        TieredAdmissionPolicy::kAdmPolicyAllowCacheHits),
+        std::make_tuple(PrimaryCacheType::kCacheTypeHCC,
+                        TieredAdmissionPolicy::kAdmPolicyAllowCacheHits)));
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

cache/lru_cache.cc

@@ -16,7 +16,7 @@
 
 #include "cache/secondary_cache_adapter.h"
 #include "monitoring/perf_context_imp.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "port/lang.h"
 #include "util/distributed_mutex.h"
 
@@ -340,7 +340,8 @@ void LRUCacheShard::NotifyEvicted(
   for (LRUHandle* entry : evicted_handles) {
     if (eviction_callback_ &&
         eviction_callback_(entry->key(),
-                           reinterpret_cast<Cache::Handle*>(entry))) {
+                           reinterpret_cast<Cache::Handle*>(entry),
+                           entry->HasHit())) {
       // Callback took ownership of obj; just free handle
       free(entry);
     } else {
@@ -505,7 +506,8 @@ bool LRUCacheShard::Release(LRUHandle* e, bool /*useful*/,
     // Only call eviction callback if we're sure no one requested erasure
     // FIXME: disabled because of test churn
     if (false && was_in_cache && !erase_if_last_ref && eviction_callback_ &&
-        eviction_callback_(e->key(), reinterpret_cast<Cache::Handle*>(e))) {
+        eviction_callback_(e->key(), reinterpret_cast<Cache::Handle*>(e),
+                           e->HasHit())) {
       // Callback took ownership of obj; just free handle
       free(e);
     } else {
@@ -646,23 +648,15 @@ void LRUCacheShard::AppendPrintableOptions(std::string& str) const {
   str.append(buffer);
 }
 
-LRUCache::LRUCache(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit, double high_pri_pool_ratio,
-                   double low_pri_pool_ratio,
-                   std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex,
-                   CacheMetadataChargePolicy metadata_charge_policy)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
-                   std::move(allocator)) {
+LRUCache::LRUCache(const LRUCacheOptions& opts) : ShardedCache(opts) {
   size_t per_shard = GetPerShardCapacity();
   MemoryAllocator* alloc = memory_allocator();
-  const EvictionCallback* eviction_callback = &eviction_callback_;
-  InitShards([=](LRUCacheShard* cs) {
-    new (cs) LRUCacheShard(per_shard, strict_capacity_limit,
-                           high_pri_pool_ratio, low_pri_pool_ratio,
-                           use_adaptive_mutex, metadata_charge_policy,
-                           /* max_upper_hash_bits */ 32 - num_shard_bits, alloc,
-                           eviction_callback);
+  InitShards([&](LRUCacheShard* cs) {
+    new (cs) LRUCacheShard(per_shard, opts.strict_capacity_limit,
+                           opts.high_pri_pool_ratio, opts.low_pri_pool_ratio,
+                           opts.use_adaptive_mutex, opts.metadata_charge_policy,
+                           /* max_upper_hash_bits */ 32 - opts.num_shard_bits,
+                           alloc, &eviction_callback_);
   });
 }
 
@@ -692,13 +686,7 @@ double LRUCache::GetHighPriPoolRatio() {
 
 }  // namespace lru_cache
 
-std::shared_ptr<Cache> NewLRUCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    const std::shared_ptr<SecondaryCache>& secondary_cache,
-    double low_pri_pool_ratio) {
+std::shared_ptr<Cache> LRUCacheOptions::MakeSharedCache() const {
   if (num_shard_bits >= 20) {
     return nullptr;  // The cache cannot be sharded into too many fine pieces.
   }
@@ -714,36 +702,24 @@ std::shared_ptr<Cache> NewLRUCache(
     // Invalid high_pri_pool_ratio and low_pri_pool_ratio combination
     return nullptr;
   }
-  if (num_shard_bits < 0) {
-    num_shard_bits = GetDefaultCacheShardBits(capacity);
+  // For sanitized options
+  LRUCacheOptions opts = *this;
+  if (opts.num_shard_bits < 0) {
+    opts.num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  std::shared_ptr<Cache> cache = std::make_shared<LRUCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      low_pri_pool_ratio, std::move(memory_allocator), use_adaptive_mutex,
-      metadata_charge_policy);
+  std::shared_ptr<Cache> cache = std::make_shared<LRUCache>(opts);
   if (secondary_cache) {
     cache = std::make_shared<CacheWithSecondaryAdapter>(cache, secondary_cache);
   }
   return cache;
 }
 
-std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
-  return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
-                     cache_opts.strict_capacity_limit,
-                     cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-                     cache_opts.metadata_charge_policy,
-                     cache_opts.secondary_cache, cache_opts.low_pri_pool_ratio);
-}
-
-std::shared_ptr<Cache> NewLRUCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    double low_pri_pool_ratio) {
-  return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
-                     high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-                     metadata_charge_policy, nullptr, low_pri_pool_ratio);
+std::shared_ptr<RowCache> LRUCacheOptions::MakeSharedRowCache() const {
+  if (secondary_cache) {
+    // Not allowed for a RowCache
+    return nullptr;
+  }
+  // Works while RowCache is an alias for Cache
+  return MakeSharedCache();
 }
 }  // namespace ROCKSDB_NAMESPACE

cache/lru_cache.h

@@ -279,8 +279,8 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShardBase {
   using HashCref = uint32_t;
 
  public:  // Function definitions expected as parameter to ShardedCache
-  static inline HashVal ComputeHash(const Slice& key) {
-    return Lower32of64(GetSliceNPHash64(key));
+  static inline HashVal ComputeHash(const Slice& key, uint32_t seed) {
+    return Lower32of64(GetSliceNPHash64(key, seed));
   }
 
   // Separate from constructor so caller can easily make an array of LRUCache
@@ -446,12 +446,7 @@ class LRUCache
 #endif
     : public ShardedCache<LRUCacheShard> {
  public:
-  LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-           double high_pri_pool_ratio, double low_pri_pool_ratio,
-           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
+  explicit LRUCache(const LRUCacheOptions& opts);
   const char* Name() const override { return "LRUCache"; }
   ObjectPtr Value(Handle* handle) override;
   size_t GetCharge(Handle* handle) const override;

cache/lru_cache_test.cc

@@ -371,11 +371,12 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
 
 namespace clock_cache {
 
+template <class ClockCache>
 class ClockCacheTest : public testing::Test {
  public:
-  using Shard = HyperClockCache::Shard;
-  using Table = HyperClockTable;
-  using HandleImpl = Shard::HandleImpl;
+  using Shard = typename ClockCache::Shard;
+  using Table = typename Shard::Table;
+  using TableOpts = typename Table::Opts;
 
   ClockCacheTest() {}
   ~ClockCacheTest() override { DeleteShard(); }
@@ -393,11 +394,10 @@ class ClockCacheTest : public testing::Test {
     shard_ =
         reinterpret_cast<Shard*>(port::cacheline_aligned_alloc(sizeof(Shard)));
 
-    Table::Opts opts;
-    opts.estimated_value_size = 1;
+    TableOpts opts{1 /*value_size*/};
     new (shard_)
         Shard(capacity, strict_capacity_limit, kDontChargeCacheMetadata,
-              /*allocator*/ nullptr, &eviction_callback_, opts);
+              /*allocator*/ nullptr, &eviction_callback_, &hash_seed_, opts);
   }
 
   Status Insert(const UniqueId64x2& hashed_key,
@@ -455,45 +455,56 @@ class ClockCacheTest : public testing::Test {
 
  private:
   Cache::EvictionCallback eviction_callback_;
+  uint32_t hash_seed_ = 0;
 };
 
-TEST_F(ClockCacheTest, Misc) {
-  NewShard(3);
+using ClockCacheTypes =
+    ::testing::Types<AutoHyperClockCache, FixedHyperClockCache>;
+TYPED_TEST_CASE(ClockCacheTest, ClockCacheTypes);
+
+TYPED_TEST(ClockCacheTest, Misc) {
+  this->NewShard(3);
+  // NOTE: templated base class prevents simple naming of inherited members,
+  // so lots of `this->`
+  auto& shard = *this->shard_;
 
   // Key size stuff
-  EXPECT_OK(InsertWithLen('a', 16));
-  EXPECT_NOK(InsertWithLen('b', 15));
-  EXPECT_OK(InsertWithLen('b', 16));
-  EXPECT_NOK(InsertWithLen('c', 17));
-  EXPECT_NOK(InsertWithLen('d', 1000));
-  EXPECT_NOK(InsertWithLen('e', 11));
-  EXPECT_NOK(InsertWithLen('f', 0));
+  EXPECT_OK(this->InsertWithLen('a', 16));
+  EXPECT_NOK(this->InsertWithLen('b', 15));
+  EXPECT_OK(this->InsertWithLen('b', 16));
+  EXPECT_NOK(this->InsertWithLen('c', 17));
+  EXPECT_NOK(this->InsertWithLen('d', 1000));
+  EXPECT_NOK(this->InsertWithLen('e', 11));
+  EXPECT_NOK(this->InsertWithLen('f', 0));
 
   // Some of this is motivated by code coverage
   std::string wrong_size_key(15, 'x');
-  EXPECT_FALSE(Lookup(wrong_size_key, TestHashedKey('x')));
-  EXPECT_FALSE(shard_->Ref(nullptr));
-  EXPECT_FALSE(shard_->Release(nullptr));
-  shard_->Erase(wrong_size_key, TestHashedKey('x'));  // no-op
+  EXPECT_FALSE(this->Lookup(wrong_size_key, this->TestHashedKey('x')));
+  EXPECT_FALSE(shard.Ref(nullptr));
+  EXPECT_FALSE(shard.Release(nullptr));
+  shard.Erase(wrong_size_key, this->TestHashedKey('x'));  // no-op
 }
 
-TEST_F(ClockCacheTest, Limits) {
-  constexpr size_t kCapacity = 3;
-  NewShard(kCapacity, false /*strict_capacity_limit*/);
+TYPED_TEST(ClockCacheTest, Limits) {
+  constexpr size_t kCapacity = 64;
+  this->NewShard(kCapacity, false /*strict_capacity_limit*/);
+  auto& shard = *this->shard_;
+  using HandleImpl = typename ClockCacheTest<TypeParam>::Shard::HandleImpl;
+
   for (bool strict_capacity_limit : {false, true, false}) {
     SCOPED_TRACE("strict_capacity_limit = " +
                  std::to_string(strict_capacity_limit));
 
     // Also tests switching between strict limit and not
-    shard_->SetStrictCapacityLimit(strict_capacity_limit);
+    shard.SetStrictCapacityLimit(strict_capacity_limit);
 
-    UniqueId64x2 hkey = TestHashedKey('x');
+    UniqueId64x2 hkey = this->TestHashedKey('x');
 
     // Single entry charge beyond capacity
     {
-      Status s = shard_->Insert(TestKey(hkey), hkey, nullptr /*value*/,
-                                &kNoopCacheItemHelper, 5 /*charge*/,
-                                nullptr /*handle*/, Cache::Priority::LOW);
+      Status s = shard.Insert(this->TestKey(hkey), hkey, nullptr /*value*/,
+                              &kNoopCacheItemHelper, kCapacity + 2 /*charge*/,
+                              nullptr /*handle*/, Cache::Priority::LOW);
       if (strict_capacity_limit) {
         EXPECT_TRUE(s.IsMemoryLimit());
       } else {
@@ -504,11 +515,11 @@ TEST_F(ClockCacheTest, Limits) {
     // Single entry fills capacity
     {
       HandleImpl* h;
-      ASSERT_OK(shard_->Insert(TestKey(hkey), hkey, nullptr /*value*/,
-                               &kNoopCacheItemHelper, 3 /*charge*/, &h,
-                               Cache::Priority::LOW));
+      ASSERT_OK(shard.Insert(this->TestKey(hkey), hkey, nullptr /*value*/,
+                             &kNoopCacheItemHelper, kCapacity /*charge*/, &h,
+                             Cache::Priority::LOW));
       // Try to insert more
-      Status s = Insert('a');
+      Status s = this->Insert('a');
       if (strict_capacity_limit) {
         EXPECT_TRUE(s.IsMemoryLimit());
       } else {
@@ -516,22 +527,22 @@ TEST_F(ClockCacheTest, Limits) {
       }
       // Release entry filling capacity.
       // Cover useful = false case.
-      shard_->Release(h, false /*useful*/, false /*erase_if_last_ref*/);
+      shard.Release(h, false /*useful*/, false /*erase_if_last_ref*/);
     }
 
     // Insert more than table size can handle to exceed occupancy limit.
     // (Cleverly using mostly zero-charge entries, but some non-zero to
     // verify usage tracking on detached entries.)
     {
-      size_t n = shard_->GetTableAddressCount() + 1;
+      size_t n = shard.GetTableAddressCount() + 1;
       std::unique_ptr<HandleImpl* []> ha { new HandleImpl* [n] {} };
       Status s;
       for (size_t i = 0; i < n && s.ok(); ++i) {
         hkey[1] = i;
-        s = shard_->Insert(TestKey(hkey), hkey, nullptr /*value*/,
-                           &kNoopCacheItemHelper,
-                           (i + kCapacity < n) ? 0 : 1 /*charge*/, &ha[i],
-                           Cache::Priority::LOW);
+        s = shard.Insert(this->TestKey(hkey), hkey, nullptr /*value*/,
+                         &kNoopCacheItemHelper,
+                         (i + kCapacity < n) ? 0 : 1 /*charge*/, &ha[i],
+                         Cache::Priority::LOW);
         if (i == 0) {
           EXPECT_OK(s);
         }
@@ -542,7 +553,7 @@ TEST_F(ClockCacheTest, Limits) {
         EXPECT_OK(s);
       }
       // Same result if not keeping a reference
-      s = Insert('a');
+      s = this->Insert('a');
       if (strict_capacity_limit) {
         EXPECT_TRUE(s.IsMemoryLimit());
       } else {
@@ -550,122 +561,123 @@ TEST_F(ClockCacheTest, Limits) {
       }
 
       // Regardless, we didn't allow table to actually get full
-      EXPECT_LT(shard_->GetOccupancyCount(), shard_->GetTableAddressCount());
+      EXPECT_LT(shard.GetOccupancyCount(), shard.GetTableAddressCount());
 
       // Release handles
       for (size_t i = 0; i < n; ++i) {
         if (ha[i]) {
-          shard_->Release(ha[i]);
+          shard.Release(ha[i]);
         }
       }
     }
   }
 }
 
-TEST_F(ClockCacheTest, ClockEvictionTest) {
+TYPED_TEST(ClockCacheTest, ClockEvictionTest) {
   for (bool strict_capacity_limit : {false, true}) {
     SCOPED_TRACE("strict_capacity_limit = " +
                  std::to_string(strict_capacity_limit));
 
-    NewShard(6, strict_capacity_limit);
-    EXPECT_OK(Insert('a', Cache::Priority::BOTTOM));
-    EXPECT_OK(Insert('b', Cache::Priority::LOW));
-    EXPECT_OK(Insert('c', Cache::Priority::HIGH));
-    EXPECT_OK(Insert('d', Cache::Priority::BOTTOM));
-    EXPECT_OK(Insert('e', Cache::Priority::LOW));
-    EXPECT_OK(Insert('f', Cache::Priority::HIGH));
+    this->NewShard(6, strict_capacity_limit);
+    auto& shard = *this->shard_;
+    EXPECT_OK(this->Insert('a', Cache::Priority::BOTTOM));
+    EXPECT_OK(this->Insert('b', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('c', Cache::Priority::HIGH));
+    EXPECT_OK(this->Insert('d', Cache::Priority::BOTTOM));
+    EXPECT_OK(this->Insert('e', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('f', Cache::Priority::HIGH));
 
-    EXPECT_TRUE(Lookup('a', /*use*/ false));
-    EXPECT_TRUE(Lookup('b', /*use*/ false));
-    EXPECT_TRUE(Lookup('c', /*use*/ false));
-    EXPECT_TRUE(Lookup('d', /*use*/ false));
-    EXPECT_TRUE(Lookup('e', /*use*/ false));
-    EXPECT_TRUE(Lookup('f', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('a', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('b', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('c', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('d', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('e', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('f', /*use*/ false));
 
     // Ensure bottom are evicted first, even if new entries are low
-    EXPECT_OK(Insert('g', Cache::Priority::LOW));
-    EXPECT_OK(Insert('h', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('g', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('h', Cache::Priority::LOW));
 
-    EXPECT_FALSE(Lookup('a', /*use*/ false));
-    EXPECT_TRUE(Lookup('b', /*use*/ false));
-    EXPECT_TRUE(Lookup('c', /*use*/ false));
-    EXPECT_FALSE(Lookup('d', /*use*/ false));
-    EXPECT_TRUE(Lookup('e', /*use*/ false));
-    EXPECT_TRUE(Lookup('f', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('a', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('b', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('c', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('d', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('e', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('f', /*use*/ false));
     // Mark g & h useful
-    EXPECT_TRUE(Lookup('g', /*use*/ true));
-    EXPECT_TRUE(Lookup('h', /*use*/ true));
+    EXPECT_TRUE(this->Lookup('g', /*use*/ true));
+    EXPECT_TRUE(this->Lookup('h', /*use*/ true));
 
     // Then old LOW entries
-    EXPECT_OK(Insert('i', Cache::Priority::LOW));
-    EXPECT_OK(Insert('j', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('i', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('j', Cache::Priority::LOW));
 
-    EXPECT_FALSE(Lookup('b', /*use*/ false));
-    EXPECT_TRUE(Lookup('c', /*use*/ false));
-    EXPECT_FALSE(Lookup('e', /*use*/ false));
-    EXPECT_TRUE(Lookup('f', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('b', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('c', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('e', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('f', /*use*/ false));
     // Mark g & h useful once again
-    EXPECT_TRUE(Lookup('g', /*use*/ true));
-    EXPECT_TRUE(Lookup('h', /*use*/ true));
-    EXPECT_TRUE(Lookup('i', /*use*/ false));
-    EXPECT_TRUE(Lookup('j', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('g', /*use*/ true));
+    EXPECT_TRUE(this->Lookup('h', /*use*/ true));
+    EXPECT_TRUE(this->Lookup('i', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('j', /*use*/ false));
 
     // Then old HIGH entries
-    EXPECT_OK(Insert('k', Cache::Priority::LOW));
-    EXPECT_OK(Insert('l', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('k', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('l', Cache::Priority::LOW));
 
-    EXPECT_FALSE(Lookup('c', /*use*/ false));
-    EXPECT_FALSE(Lookup('f', /*use*/ false));
-    EXPECT_TRUE(Lookup('g', /*use*/ false));
-    EXPECT_TRUE(Lookup('h', /*use*/ false));
-    EXPECT_TRUE(Lookup('i', /*use*/ false));
-    EXPECT_TRUE(Lookup('j', /*use*/ false));
-    EXPECT_TRUE(Lookup('k', /*use*/ false));
-    EXPECT_TRUE(Lookup('l', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('c', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('f', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('g', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('h', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('i', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('j', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('k', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('l', /*use*/ false));
 
     // Then the (roughly) least recently useful
-    EXPECT_OK(Insert('m', Cache::Priority::HIGH));
-    EXPECT_OK(Insert('n', Cache::Priority::HIGH));
+    EXPECT_OK(this->Insert('m', Cache::Priority::HIGH));
+    EXPECT_OK(this->Insert('n', Cache::Priority::HIGH));
 
-    EXPECT_TRUE(Lookup('g', /*use*/ false));
-    EXPECT_TRUE(Lookup('h', /*use*/ false));
-    EXPECT_FALSE(Lookup('i', /*use*/ false));
-    EXPECT_FALSE(Lookup('j', /*use*/ false));
-    EXPECT_TRUE(Lookup('k', /*use*/ false));
-    EXPECT_TRUE(Lookup('l', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('g', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('h', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('i', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('j', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('k', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('l', /*use*/ false));
 
     // Now try changing capacity down
-    shard_->SetCapacity(4);
+    shard.SetCapacity(4);
     // Insert to ensure evictions happen
-    EXPECT_OK(Insert('o', Cache::Priority::LOW));
-    EXPECT_OK(Insert('p', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('o', Cache::Priority::LOW));
+    EXPECT_OK(this->Insert('p', Cache::Priority::LOW));
 
-    EXPECT_FALSE(Lookup('g', /*use*/ false));
-    EXPECT_FALSE(Lookup('h', /*use*/ false));
-    EXPECT_FALSE(Lookup('k', /*use*/ false));
-    EXPECT_FALSE(Lookup('l', /*use*/ false));
-    EXPECT_TRUE(Lookup('m', /*use*/ false));
-    EXPECT_TRUE(Lookup('n', /*use*/ false));
-    EXPECT_TRUE(Lookup('o', /*use*/ false));
-    EXPECT_TRUE(Lookup('p', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('g', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('h', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('k', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('l', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('m', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('n', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('o', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('p', /*use*/ false));
 
     // Now try changing capacity up
-    EXPECT_TRUE(Lookup('m', /*use*/ true));
-    EXPECT_TRUE(Lookup('n', /*use*/ true));
-    shard_->SetCapacity(6);
-    EXPECT_OK(Insert('q', Cache::Priority::HIGH));
-    EXPECT_OK(Insert('r', Cache::Priority::HIGH));
-    EXPECT_OK(Insert('s', Cache::Priority::HIGH));
-    EXPECT_OK(Insert('t', Cache::Priority::HIGH));
+    EXPECT_TRUE(this->Lookup('m', /*use*/ true));
+    EXPECT_TRUE(this->Lookup('n', /*use*/ true));
+    shard.SetCapacity(6);
+    EXPECT_OK(this->Insert('q', Cache::Priority::HIGH));
+    EXPECT_OK(this->Insert('r', Cache::Priority::HIGH));
+    EXPECT_OK(this->Insert('s', Cache::Priority::HIGH));
+    EXPECT_OK(this->Insert('t', Cache::Priority::HIGH));
 
-    EXPECT_FALSE(Lookup('o', /*use*/ false));
-    EXPECT_FALSE(Lookup('p', /*use*/ false));
-    EXPECT_TRUE(Lookup('m', /*use*/ false));
-    EXPECT_TRUE(Lookup('n', /*use*/ false));
-    EXPECT_TRUE(Lookup('q', /*use*/ false));
-    EXPECT_TRUE(Lookup('r', /*use*/ false));
-    EXPECT_TRUE(Lookup('s', /*use*/ false));
-    EXPECT_TRUE(Lookup('t', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('o', /*use*/ false));
+    EXPECT_FALSE(this->Lookup('p', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('m', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('n', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('q', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('r', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('s', /*use*/ false));
+    EXPECT_TRUE(this->Lookup('t', /*use*/ false));
   }
 }
 
@@ -681,113 +693,178 @@ const Cache::CacheItemHelper kDeleteCounterHelper{
 }  // namespace
 
 // Testing calls to CorrectNearOverflow in Release
-TEST_F(ClockCacheTest, ClockCounterOverflowTest) {
-  NewShard(6, /*strict_capacity_limit*/ false);
+TYPED_TEST(ClockCacheTest, ClockCounterOverflowTest) {
+  this->NewShard(6, /*strict_capacity_limit*/ false);
+  auto& shard = *this->shard_;
+  using HandleImpl = typename ClockCacheTest<TypeParam>::Shard::HandleImpl;
+
   HandleImpl* h;
   DeleteCounter val;
-  UniqueId64x2 hkey = TestHashedKey('x');
-  ASSERT_OK(shard_->Insert(TestKey(hkey), hkey, &val, &kDeleteCounterHelper, 1,
-                           &h, Cache::Priority::HIGH));
+  UniqueId64x2 hkey = this->TestHashedKey('x');
+  ASSERT_OK(shard.Insert(this->TestKey(hkey), hkey, &val, &kDeleteCounterHelper,
+                         1, &h, Cache::Priority::HIGH));
 
   // Some large number outstanding
-  shard_->TEST_RefN(h, 123456789);
+  shard.TEST_RefN(h, 123456789);
   // Simulate many lookup/ref + release, plenty to overflow counters
   for (int i = 0; i < 10000; ++i) {
-    shard_->TEST_RefN(h, 1234567);
-    shard_->TEST_ReleaseN(h, 1234567);
+    shard.TEST_RefN(h, 1234567);
+    shard.TEST_ReleaseN(h, 1234567);
   }
   // Mark it invisible (to reach a different CorrectNearOverflow() in Release)
-  shard_->Erase(TestKey(hkey), hkey);
+  shard.Erase(this->TestKey(hkey), hkey);
   // Simulate many more lookup/ref + release (one-by-one would be too
   // expensive for unit test)
   for (int i = 0; i < 10000; ++i) {
-    shard_->TEST_RefN(h, 1234567);
-    shard_->TEST_ReleaseN(h, 1234567);
+    shard.TEST_RefN(h, 1234567);
+    shard.TEST_ReleaseN(h, 1234567);
   }
   // Free all but last 1
-  shard_->TEST_ReleaseN(h, 123456789);
+  shard.TEST_ReleaseN(h, 123456789);
   // Still alive
   ASSERT_EQ(val.deleted, 0);
   // Free last ref, which will finalize erasure
-  shard_->Release(h);
+  shard.Release(h);
   // Deleted
   ASSERT_EQ(val.deleted, 1);
 }
 
+TYPED_TEST(ClockCacheTest, ClockTableFull) {
+  // Force clock cache table to fill up (not usually allowed) in order
+  // to test full probe sequence that is theoretically possible due to
+  // parallel operations
+  this->NewShard(6, /*strict_capacity_limit*/ false);
+  auto& shard = *this->shard_;
+  using HandleImpl = typename ClockCacheTest<TypeParam>::Shard::HandleImpl;
+
+  size_t size = shard.GetTableAddressCount();
+  ASSERT_LE(size + 3, 256);  // for using char keys
+  // Modify occupancy and capacity limits to attempt insert on full
+  shard.TEST_MutableOccupancyLimit() = size + 100;
+  shard.SetCapacity(size + 100);
+
+  DeleteCounter val;
+  std::vector<HandleImpl*> handles;
+  // NOTE: the three extra insertions should create standalone entries
+  for (size_t i = 0; i < size + 3; ++i) {
+    UniqueId64x2 hkey = this->TestHashedKey(static_cast<char>(i));
+    ASSERT_OK(shard.Insert(this->TestKey(hkey), hkey, &val,
+                           &kDeleteCounterHelper, 1, &handles.emplace_back(),
+                           Cache::Priority::HIGH));
+  }
+
+  for (size_t i = 0; i < size + 3; ++i) {
+    UniqueId64x2 hkey = this->TestHashedKey(static_cast<char>(i));
+    HandleImpl* h = shard.Lookup(this->TestKey(hkey), hkey);
+    if (i < size) {
+      ASSERT_NE(h, nullptr);
+      shard.Release(h);
+    } else {
+      // Standalone entries not visible by lookup
+      ASSERT_EQ(h, nullptr);
+    }
+  }
+
+  for (size_t i = 0; i < size + 3; ++i) {
+    ASSERT_NE(handles[i], nullptr);
+    shard.Release(handles[i]);
+    if (i < size) {
+      // Everything still in cache
+      ASSERT_EQ(val.deleted, 0);
+    } else {
+      // Standalone entries freed on release
+      ASSERT_EQ(val.deleted, i + 1 - size);
+    }
+  }
+
+  for (size_t i = size + 3; i > 0; --i) {
+    UniqueId64x2 hkey = this->TestHashedKey(static_cast<char>(i - 1));
+    shard.Erase(this->TestKey(hkey), hkey);
+    if (i - 1 > size) {
+      ASSERT_EQ(val.deleted, 3);
+    } else {
+      ASSERT_EQ(val.deleted, 3 + size - (i - 1));
+    }
+  }
+}
+
 // This test is mostly to exercise some corner case logic, by forcing two
 // keys to have the same hash, and more
-TEST_F(ClockCacheTest, CollidingInsertEraseTest) {
-  NewShard(6, /*strict_capacity_limit*/ false);
+TYPED_TEST(ClockCacheTest, CollidingInsertEraseTest) {
+  this->NewShard(6, /*strict_capacity_limit*/ false);
+  auto& shard = *this->shard_;
+  using HandleImpl = typename ClockCacheTest<TypeParam>::Shard::HandleImpl;
+
   DeleteCounter val;
-  UniqueId64x2 hkey1 = TestHashedKey('x');
-  Slice key1 = TestKey(hkey1);
-  UniqueId64x2 hkey2 = TestHashedKey('y');
-  Slice key2 = TestKey(hkey2);
-  UniqueId64x2 hkey3 = TestHashedKey('z');
-  Slice key3 = TestKey(hkey3);
+  UniqueId64x2 hkey1 = this->TestHashedKey('x');
+  Slice key1 = this->TestKey(hkey1);
+  UniqueId64x2 hkey2 = this->TestHashedKey('y');
+  Slice key2 = this->TestKey(hkey2);
+  UniqueId64x2 hkey3 = this->TestHashedKey('z');
+  Slice key3 = this->TestKey(hkey3);
   HandleImpl* h1;
-  ASSERT_OK(shard_->Insert(key1, hkey1, &val, &kDeleteCounterHelper, 1, &h1,
-                           Cache::Priority::HIGH));
+  ASSERT_OK(shard.Insert(key1, hkey1, &val, &kDeleteCounterHelper, 1, &h1,
+                         Cache::Priority::HIGH));
   HandleImpl* h2;
-  ASSERT_OK(shard_->Insert(key2, hkey2, &val, &kDeleteCounterHelper, 1, &h2,
-                           Cache::Priority::HIGH));
+  ASSERT_OK(shard.Insert(key2, hkey2, &val, &kDeleteCounterHelper, 1, &h2,
+                         Cache::Priority::HIGH));
   HandleImpl* h3;
-  ASSERT_OK(shard_->Insert(key3, hkey3, &val, &kDeleteCounterHelper, 1, &h3,
-                           Cache::Priority::HIGH));
+  ASSERT_OK(shard.Insert(key3, hkey3, &val, &kDeleteCounterHelper, 1, &h3,
+                         Cache::Priority::HIGH));
 
   // Can repeatedly lookup+release despite the hash collision
   HandleImpl* tmp_h;
   for (bool erase_if_last_ref : {true, false}) {  // but not last ref
-    tmp_h = shard_->Lookup(key1, hkey1);
+    tmp_h = shard.Lookup(key1, hkey1);
     ASSERT_EQ(h1, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
 
-    tmp_h = shard_->Lookup(key2, hkey2);
+    tmp_h = shard.Lookup(key2, hkey2);
     ASSERT_EQ(h2, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
 
-    tmp_h = shard_->Lookup(key3, hkey3);
+    tmp_h = shard.Lookup(key3, hkey3);
     ASSERT_EQ(h3, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
   }
 
   // Make h1 invisible
-  shard_->Erase(key1, hkey1);
+  shard.Erase(key1, hkey1);
   // Redundant erase
-  shard_->Erase(key1, hkey1);
+  shard.Erase(key1, hkey1);
 
   // All still alive
   ASSERT_EQ(val.deleted, 0);
 
   // Invisible to Lookup
-  tmp_h = shard_->Lookup(key1, hkey1);
+  tmp_h = shard.Lookup(key1, hkey1);
   ASSERT_EQ(nullptr, tmp_h);
 
   // Can still find h2, h3
   for (bool erase_if_last_ref : {true, false}) {  // but not last ref
-    tmp_h = shard_->Lookup(key2, hkey2);
+    tmp_h = shard.Lookup(key2, hkey2);
     ASSERT_EQ(h2, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
 
-    tmp_h = shard_->Lookup(key3, hkey3);
+    tmp_h = shard.Lookup(key3, hkey3);
     ASSERT_EQ(h3, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
   }
 
   // Also Insert with invisible entry there
-  ASSERT_OK(shard_->Insert(key1, hkey1, &val, &kDeleteCounterHelper, 1, nullptr,
-                           Cache::Priority::HIGH));
-  tmp_h = shard_->Lookup(key1, hkey1);
+  ASSERT_OK(shard.Insert(key1, hkey1, &val, &kDeleteCounterHelper, 1, nullptr,
+                         Cache::Priority::HIGH));
+  tmp_h = shard.Lookup(key1, hkey1);
   // Found but distinct handle
   ASSERT_NE(nullptr, tmp_h);
   ASSERT_NE(h1, tmp_h);
-  ASSERT_TRUE(shard_->Release(tmp_h, /*erase_if_last_ref*/ true));
+  ASSERT_TRUE(shard.Release(tmp_h, /*erase_if_last_ref*/ true));
 
   // tmp_h deleted
   ASSERT_EQ(val.deleted--, 1);
 
   // Release last ref on h1 (already invisible)
-  ASSERT_TRUE(shard_->Release(h1, /*erase_if_last_ref*/ false));
+  ASSERT_TRUE(shard.Release(h1, /*erase_if_last_ref*/ false));
 
   // h1 deleted
   ASSERT_EQ(val.deleted--, 1);
@@ -795,57 +872,57 @@ TEST_F(ClockCacheTest, CollidingInsertEraseTest) {
 
   // Can still find h2, h3
   for (bool erase_if_last_ref : {true, false}) {  // but not last ref
-    tmp_h = shard_->Lookup(key2, hkey2);
+    tmp_h = shard.Lookup(key2, hkey2);
     ASSERT_EQ(h2, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
 
-    tmp_h = shard_->Lookup(key3, hkey3);
+    tmp_h = shard.Lookup(key3, hkey3);
     ASSERT_EQ(h3, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
   }
 
   // Release last ref on h2
-  ASSERT_FALSE(shard_->Release(h2, /*erase_if_last_ref*/ false));
+  ASSERT_FALSE(shard.Release(h2, /*erase_if_last_ref*/ false));
 
   // h2 still not deleted (unreferenced in cache)
   ASSERT_EQ(val.deleted, 0);
 
   // Can still find it
-  tmp_h = shard_->Lookup(key2, hkey2);
+  tmp_h = shard.Lookup(key2, hkey2);
   ASSERT_EQ(h2, tmp_h);
 
   // Release last ref on h2, with erase
-  ASSERT_TRUE(shard_->Release(h2, /*erase_if_last_ref*/ true));
+  ASSERT_TRUE(shard.Release(h2, /*erase_if_last_ref*/ true));
 
   // h2 deleted
   ASSERT_EQ(val.deleted--, 1);
-  tmp_h = shard_->Lookup(key2, hkey2);
+  tmp_h = shard.Lookup(key2, hkey2);
   ASSERT_EQ(nullptr, tmp_h);
 
   // Can still find h3
   for (bool erase_if_last_ref : {true, false}) {  // but not last ref
-    tmp_h = shard_->Lookup(key3, hkey3);
+    tmp_h = shard.Lookup(key3, hkey3);
     ASSERT_EQ(h3, tmp_h);
-    ASSERT_FALSE(shard_->Release(tmp_h, erase_if_last_ref));
+    ASSERT_FALSE(shard.Release(tmp_h, erase_if_last_ref));
   }
 
   // Release last ref on h3, without erase
-  ASSERT_FALSE(shard_->Release(h3, /*erase_if_last_ref*/ false));
+  ASSERT_FALSE(shard.Release(h3, /*erase_if_last_ref*/ false));
 
   // h3 still not deleted (unreferenced in cache)
   ASSERT_EQ(val.deleted, 0);
 
   // Explicit erase
-  shard_->Erase(key3, hkey3);
+  shard.Erase(key3, hkey3);
 
   // h3 deleted
   ASSERT_EQ(val.deleted--, 1);
-  tmp_h = shard_->Lookup(key3, hkey3);
+  tmp_h = shard.Lookup(key3, hkey3);
   ASSERT_EQ(nullptr, tmp_h);
 }
 
 // This uses the public API to effectively test CalcHashBits etc.
-TEST_F(ClockCacheTest, TableSizesTest) {
+TYPED_TEST(ClockCacheTest, TableSizesTest) {
   for (size_t est_val_size : {1U, 5U, 123U, 2345U, 345678U}) {
     SCOPED_TRACE("est_val_size = " + std::to_string(est_val_size));
     for (double est_count : {1.1, 2.2, 511.9, 512.1, 2345.0}) {
@@ -858,8 +935,10 @@ TEST_F(ClockCacheTest, TableSizesTest) {
                        /*memory_allocator*/ nullptr, kDontChargeCacheMetadata)
                        .MakeSharedCache();
       // Table sizes are currently only powers of two
-      EXPECT_GE(cache->GetTableAddressCount(), est_count / kLoadFactor);
-      EXPECT_LE(cache->GetTableAddressCount(), est_count / kLoadFactor * 2.0);
+      EXPECT_GE(cache->GetTableAddressCount(),
+                est_count / FixedHyperClockTable::kLoadFactor);
+      EXPECT_LE(cache->GetTableAddressCount(),
+                est_count / FixedHyperClockTable::kLoadFactor * 2.0);
       EXPECT_EQ(cache->GetUsage(), 0);
 
       // kFullChargeMetaData
@@ -876,9 +955,10 @@ TEST_F(ClockCacheTest, TableSizesTest) {
         double est_count_after_meta =
             (capacity - cache->GetUsage()) * 1.0 / est_val_size;
         EXPECT_GE(cache->GetTableAddressCount(),
-                  est_count_after_meta / kLoadFactor);
-        EXPECT_LE(cache->GetTableAddressCount(),
-                  est_count_after_meta / kLoadFactor * 2.0);
+                  est_count_after_meta / FixedHyperClockTable::kLoadFactor);
+        EXPECT_LE(
+            cache->GetTableAddressCount(),
+            est_count_after_meta / FixedHyperClockTable::kLoadFactor * 2.0);
       }
     }
   }
@@ -916,7 +996,8 @@ class TestSecondaryCache : public SecondaryCache {
   void ResetInjectFailure() { inject_failure_ = false; }
 
   Status Insert(const Slice& key, Cache::ObjectPtr value,
-                const Cache::CacheItemHelper* helper) override {
+                const Cache::CacheItemHelper* helper,
+                bool /*force_insert*/) override {
     if (inject_failure_) {
       return Status::Corruption("Insertion Data Corrupted");
     }
@@ -1366,7 +1447,7 @@ TEST_P(BasicSecondaryCacheTest, FullCapacityTest) {
         k2.AsSlice(),
         GetHelper(CacheEntryRole::kDataBlock, /*secondary_compatible=*/false),
         /*context*/ this, Cache::Priority::LOW);
-    if (strict_capacity_limit || GetParam() == kHyperClock) {
+    if (strict_capacity_limit || IsHyperClock()) {
       ASSERT_NE(handle2, nullptr);
       cache->Release(handle2);
       ASSERT_EQ(secondary_cache->num_inserts(), 1u);
@@ -1391,12 +1472,12 @@ TEST_P(BasicSecondaryCacheTest, FullCapacityTest) {
 // CORRECTION: this is not quite right. block_1 can be inserted into the block
 // cache because strict_capacity_limit=false, but it is removed from the cache
 // in Release() because of being over-capacity, without demoting to secondary
-// cache. HyperClockCache doesn't check capacity on release (for efficiency)
-// so can demote the over-capacity item to secondary cache. Also, we intend to
-// add support for demotion in Release, but that currently causes too much
-// unit test churn.
+// cache. FixedHyperClockCache doesn't check capacity on release (for
+// efficiency) so can demote the over-capacity item to secondary cache. Also, we
+// intend to add support for demotion in Release, but that currently causes too
+// much unit test churn.
 TEST_P(DBSecondaryCacheTest, TestSecondaryCacheCorrectness1) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     // See CORRECTION above
     ROCKSDB_GTEST_BYPASS("Test depends on LRUCache-specific behaviors");
     return;
@@ -1494,7 +1575,7 @@ TEST_P(DBSecondaryCacheTest, TestSecondaryCacheCorrectness1) {
 // insert and cache block_1 in the block cache (this is the different place
 // from TestSecondaryCacheCorrectness1)
 TEST_P(DBSecondaryCacheTest, TestSecondaryCacheCorrectness2) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS("Test depends on LRUCache-specific behaviors");
     return;
   }
@@ -1682,7 +1763,7 @@ TEST_P(DBSecondaryCacheTest, SecondaryCacheIntensiveTesting) {
 // if we try to insert block_1 to the block cache, it will always fails. Only
 // block_2 will be successfully inserted into the block cache.
 TEST_P(DBSecondaryCacheTest, SecondaryCacheFailureTest) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS("Test depends on LRUCache-specific behaviors");
     return;
   }
@@ -1792,7 +1873,7 @@ TEST_P(BasicSecondaryCacheTest, BasicWaitAllTest) {
                             str.length()));
   }
   // Force all entries to be evicted to the secondary cache
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     // HCC doesn't respond immediately to SetCapacity
     for (int i = 9000; i < 9030; ++i) {
       ASSERT_OK(cache->Insert(ock.WithOffset(i).AsSlice(), nullptr,
@@ -1847,7 +1928,7 @@ TEST_P(BasicSecondaryCacheTest, BasicWaitAllTest) {
 // a sync point callback in TestSecondaryCache::Lookup. We then control the
 // lookup result by setting the ResultMap.
 TEST_P(DBSecondaryCacheTest, TestSecondaryCacheMultiGet) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS("Test depends on LRUCache-specific behaviors");
     return;
   }
@@ -2348,7 +2429,7 @@ TEST_P(DBSecondaryCacheTest, TestSecondaryCacheOptionBasic) {
 // with new options, which set the lowest_used_cache_tier to
 // kNonVolatileBlockTier. So secondary cache will be used.
 TEST_P(DBSecondaryCacheTest, TestSecondaryCacheOptionChange) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS("Test depends on LRUCache-specific behaviors");
     return;
   }
@@ -2443,7 +2524,7 @@ TEST_P(DBSecondaryCacheTest, TestSecondaryCacheOptionChange) {
 // Two DB test. We create 2 DBs sharing the same block cache and secondary
 // cache. We diable the secondary cache option for DB2.
 TEST_P(DBSecondaryCacheTest, TestSecondaryCacheOptionTwoDB) {
-  if (GetParam() == kHyperClock) {
+  if (IsHyperClock()) {
     ROCKSDB_GTEST_BYPASS("Test depends on LRUCache-specific behaviors");
     return;
   }

cache/secondary_cache.cc

@@ -38,7 +38,8 @@ Status SecondaryCache::InsertSaved(const Slice& key, const Slice& saved) {
       CacheEntryRole::kMisc, &NoopDelete, &SliceSize,
       &SliceSaveTo,          &FailCreate, &helper_no_secondary};
   // NOTE: depends on Insert() being synchronous, not keeping pointer `&saved`
-  return Insert(key, const_cast<Slice*>(&saved), &helper);
+  return Insert(key, const_cast<Slice*>(&saved), &helper,
+                /*force_insert=*/true);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

cache/secondary_cache_adapter.cc

@@ -6,6 +6,7 @@
 #include "cache/secondary_cache_adapter.h"
 
 #include "monitoring/perf_context_imp.h"
+#include "util/cast_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -18,31 +19,116 @@ const Dummy kDummy{};
 Cache::ObjectPtr const kDummyObj = const_cast<Dummy*>(&kDummy);
 }  // namespace
 
+// When CacheWithSecondaryAdapter is constructed with the distribute_cache_res
+// parameter set to true, it manages the entire memory budget across the
+// primary and secondary cache. The secondary cache is assumed to be in
+// memory, such as the CompressedSecondaryCache. When a placeholder entry
+// is inserted by a CacheReservationManager instance to reserve memory,
+// the CacheWithSecondaryAdapter ensures that the reservation is distributed
+// proportionally across the primary/secondary caches.
+//
+// The primary block cache is initially sized to the sum of the primary cache
+// budget + teh secondary cache budget, as follows -
+//   |---------    Primary Cache Configured Capacity  -----------|
+//   |---Secondary Cache Budget----|----Primary Cache Budget-----|
+//
+// A ConcurrentCacheReservationManager member in the CacheWithSecondaryAdapter,
+// pri_cache_res_,
+// is used to help with tracking the distribution of memory reservations.
+// Initially, it accounts for the entire secondary cache budget as a
+// reservation against the primary cache. This shrinks the usable capacity of
+// the primary cache to the budget that the user originally desired.
+//
+//   |--Reservation for Sec Cache--|-Pri Cache Usable Capacity---|
+//
+// When a reservation placeholder is inserted into the adapter, it is inserted
+// directly into the primary cache. This means the entire charge of the
+// placeholder is counted against the primary cache. To compensate and count
+// a portion of it against the secondary cache, the secondary cache Deflate()
+// method is called to shrink it. Since the Deflate() causes the secondary
+// actual usage to shrink, it is refelcted here by releasing an equal amount
+// from the pri_cache_res_ reservation. The Deflate() in the secondary cache
+// can be, but is not required to be, implemented using its own cache
+// reservation manager.
+//
+// For example, if the pri/sec ratio is 70/30, and the combined capacity is
+// 100MB, the intermediate and final  state after inserting a reservation
+// placeholder for 10MB would be as follows -
+//
+//   |-Reservation for Sec Cache-|-Pri Cache Usable Capacity-|---R---|
+// 1. After inserting the placeholder in primary
+//   |-------  30MB -------------|------- 60MB -------------|-10MB--|
+// 2. After deflating the secondary and adjusting the reservation for
+//    secondary against the primary
+//   |-------  27MB -------------|------- 63MB -------------|-10MB--|
+//
+// Likewise, when the user inserted placeholder is released, the secondary
+// cache Inflate() method is called to grow it, and the pri_cache_res_
+// reservation is increased by an equal amount.
+//
+// Another way of implementing this would have been to simply split the user
+// reservation into primary and seconary components. However, this would
+// require allocating a structure to track the associated secondary cache
+// reservation, which adds some complexity and overhead.
+//
 CacheWithSecondaryAdapter::CacheWithSecondaryAdapter(
     std::shared_ptr<Cache> target,
-    std::shared_ptr<SecondaryCache> secondary_cache)
+    std::shared_ptr<SecondaryCache> secondary_cache,
+    TieredAdmissionPolicy adm_policy, bool distribute_cache_res)
     : CacheWrapper(std::move(target)),
-      secondary_cache_(std::move(secondary_cache)) {
-  target_->SetEvictionCallback([this](const Slice& key, Handle* handle) {
-    return EvictionHandler(key, handle);
-  });
+      secondary_cache_(std::move(secondary_cache)),
+      adm_policy_(adm_policy),
+      distribute_cache_res_(distribute_cache_res) {
+  target_->SetEvictionCallback(
+      [this](const Slice& key, Handle* handle, bool was_hit) {
+        return EvictionHandler(key, handle, was_hit);
+      });
+  if (distribute_cache_res_) {
+    size_t sec_capacity = 0;
+    pri_cache_res_ = std::make_shared<ConcurrentCacheReservationManager>(
+        std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
+            target_));
+    Status s = secondary_cache_->GetCapacity(sec_capacity);
+    assert(s.ok());
+    // Initially, the primary cache is sized to uncompressed cache budget plsu
+    // compressed secondary cache budget. The secondary cache budget is then
+    // taken away from the primary cache through cache reservations. Later,
+    // when a placeholder entry is inserted by the caller, its inserted
+    // into the primary cache and the portion that should be assigned to the
+    // secondary cache is freed from the reservation.
+    s = pri_cache_res_->UpdateCacheReservation(sec_capacity);
+    assert(s.ok());
+    sec_cache_res_ratio_ = (double)sec_capacity / target_->GetCapacity();
+  }
 }
 
 CacheWithSecondaryAdapter::~CacheWithSecondaryAdapter() {
   // `*this` will be destroyed before `*target_`, so we have to prevent
   // use after free
   target_->SetEvictionCallback({});
+#ifndef NDEBUG
+  if (distribute_cache_res_) {
+    size_t sec_capacity = 0;
+    Status s = secondary_cache_->GetCapacity(sec_capacity);
+    assert(s.ok());
+    assert(pri_cache_res_->GetTotalReservedCacheSize() == sec_capacity);
+  }
+#endif  // NDEBUG
 }
 
 bool CacheWithSecondaryAdapter::EvictionHandler(const Slice& key,
-                                                Handle* handle) {
+                                                Handle* handle, bool was_hit) {
   auto helper = GetCacheItemHelper(handle);
   if (helper->IsSecondaryCacheCompatible()) {
     auto obj = target_->Value(handle);
     // Ignore dummy entry
     if (obj != kDummyObj) {
+      bool hit = false;
+      if (adm_policy_ == TieredAdmissionPolicy::kAdmPolicyAllowCacheHits) {
+        hit = was_hit;
+      }
       // Spill into secondary cache.
-      secondary_cache_->Insert(key, obj, helper).PermitUncheckedError();
+      secondary_cache_->Insert(key, obj, helper, hit).PermitUncheckedError();
     }
   }
   // Never takes ownership of obj
@@ -136,6 +222,22 @@ Cache::Handle* CacheWithSecondaryAdapter::Promote(
   return result;
 }
 
+Status CacheWithSecondaryAdapter::Insert(const Slice& key, ObjectPtr value,
+                                         const CacheItemHelper* helper,
+                                         size_t charge, Handle** handle,
+                                         Priority priority) {
+  Status s = target_->Insert(key, value, helper, charge, handle, priority);
+  if (s.ok() && value == nullptr && distribute_cache_res_) {
+    size_t sec_charge = static_cast<size_t>(charge * (sec_cache_res_ratio_));
+    s = secondary_cache_->Deflate(sec_charge);
+    assert(s.ok());
+    s = pri_cache_res_->UpdateCacheReservation(sec_charge, /*increase=*/false);
+    assert(s.ok());
+  }
+
+  return s;
+}
+
 Cache::Handle* CacheWithSecondaryAdapter::Lookup(const Slice& key,
                                                  const CacheItemHelper* helper,
                                                  CreateContext* create_context,
@@ -162,6 +264,22 @@ Cache::Handle* CacheWithSecondaryAdapter::Lookup(const Slice& key,
   return result;
 }
 
+bool CacheWithSecondaryAdapter::Release(Handle* handle,
+                                        bool erase_if_last_ref) {
+  if (erase_if_last_ref) {
+    ObjectPtr v = target_->Value(handle);
+    if (v == nullptr && distribute_cache_res_) {
+      size_t charge = target_->GetCharge(handle);
+      size_t sec_charge = static_cast<size_t>(charge * (sec_cache_res_ratio_));
+      Status s = secondary_cache_->Inflate(sec_charge);
+      assert(s.ok());
+      s = pri_cache_res_->UpdateCacheReservation(sec_charge, /*increase=*/true);
+      assert(s.ok());
+    }
+  }
+  return target_->Release(handle, erase_if_last_ref);
+}
+
 Cache::ObjectPtr CacheWithSecondaryAdapter::Value(Handle* handle) {
   ObjectPtr v = target_->Value(handle);
   // TODO with stacked secondaries: might fail in EvictionHandler
@@ -265,7 +383,7 @@ void CacheWithSecondaryAdapter::WaitAll(AsyncLookupHandle* async_handles,
     for (AsyncLookupHandle* cur : my_pending) {
       my_secondary_handles.push_back(cur->pending_handle);
     }
-    secondary_cache_->WaitAll(my_secondary_handles);
+    secondary_cache_->WaitAll(std::move(my_secondary_handles));
   }
 
   // Process results
@@ -292,4 +410,37 @@ const char* CacheWithSecondaryAdapter::Name() const {
   // a secondary cache. So we pretend to be that cache
   return target_->Name();
 }
+
+std::shared_ptr<Cache> NewTieredVolatileCache(
+    TieredVolatileCacheOptions& opts) {
+  if (!opts.cache_opts) {
+    return nullptr;
+  }
+
+  if (opts.adm_policy >= TieredAdmissionPolicy::kAdmPolicyMax) {
+    return nullptr;
+  }
+
+  std::shared_ptr<Cache> cache;
+  if (opts.cache_type == PrimaryCacheType::kCacheTypeLRU) {
+    LRUCacheOptions cache_opts =
+        *(static_cast_with_check<LRUCacheOptions, ShardedCacheOptions>(
+            opts.cache_opts));
+    cache_opts.capacity += opts.comp_cache_opts.capacity;
+    cache = cache_opts.MakeSharedCache();
+  } else if (opts.cache_type == PrimaryCacheType::kCacheTypeHCC) {
+    HyperClockCacheOptions cache_opts =
+        *(static_cast_with_check<HyperClockCacheOptions, ShardedCacheOptions>(
+            opts.cache_opts));
+    cache_opts.capacity += opts.comp_cache_opts.capacity;
+    cache = cache_opts.MakeSharedCache();
+  } else {
+    return nullptr;
+  }
+  std::shared_ptr<SecondaryCache> sec_cache;
+  sec_cache = NewCompressedSecondaryCache(opts.comp_cache_opts);
+
+  return std::make_shared<CacheWithSecondaryAdapter>(
+      cache, sec_cache, opts.adm_policy, /*distribute_cache_res=*/true);
+}
 }  // namespace ROCKSDB_NAMESPACE

cache/secondary_cache_adapter.h

@@ -5,6 +5,7 @@
 
 #pragma once
 
+#include "cache/cache_reservation_manager.h"
 #include "rocksdb/secondary_cache.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -13,15 +14,25 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
  public:
   explicit CacheWithSecondaryAdapter(
       std::shared_ptr<Cache> target,
-      std::shared_ptr<SecondaryCache> secondary_cache);
+      std::shared_ptr<SecondaryCache> secondary_cache,
+      TieredAdmissionPolicy adm_policy = TieredAdmissionPolicy::kAdmPolicyAuto,
+      bool distribute_cache_res = false);
 
   ~CacheWithSecondaryAdapter() override;
 
+  Status Insert(const Slice& key, ObjectPtr value,
+                const CacheItemHelper* helper, size_t charge,
+                Handle** handle = nullptr,
+                Priority priority = Priority::LOW) override;
+
   Handle* Lookup(const Slice& key, const CacheItemHelper* helper,
                  CreateContext* create_context,
                  Priority priority = Priority::LOW,
                  Statistics* stats = nullptr) override;
 
+  using Cache::Release;
+  bool Release(Handle* handle, bool erase_if_last_ref = false) override;
+
   ObjectPtr Value(Handle* handle) override;
 
   void StartAsyncLookup(AsyncLookupHandle& async_handle) override;
@@ -32,8 +43,12 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
 
   const char* Name() const override;
 
+  Cache* TEST_GetCache() { return target_.get(); }
+
+  SecondaryCache* TEST_GetSecondaryCache() { return secondary_cache_.get(); }
+
  private:
-  bool EvictionHandler(const Slice& key, Handle* handle);
+  bool EvictionHandler(const Slice& key, Handle* handle, bool was_hit);
 
   void StartAsyncLookupOnMySecondary(AsyncLookupHandle& async_handle);
 
@@ -47,6 +62,17 @@ class CacheWithSecondaryAdapter : public CacheWrapper {
   void CleanupCacheObject(ObjectPtr obj, const CacheItemHelper* helper);
 
   std::shared_ptr<SecondaryCache> secondary_cache_;
+  TieredAdmissionPolicy adm_policy_;
+  // Whether to proportionally distribute cache memory reservations, i.e
+  // placeholder entries with null value and a non-zero charge, across
+  // the primary and secondary caches.
+  bool distribute_cache_res_;
+  // A cache reservation manager to keep track of secondary cache memory
+  // usage by reserving equivalent capacity against the primary cache
+  std::shared_ptr<ConcurrentCacheReservationManager> pri_cache_res_;
+  // Fraction of a cache memory reservation to be assigned to the secondary
+  // cache
+  double sec_cache_res_ratio_;
 };
 
 }  // namespace ROCKSDB_NAMESPACE

cache/sharded_cache.cc

@@ -13,20 +13,57 @@
 #include <cstdint>
 #include <memory>
 
+#include "env/unique_id_gen.h"
+#include "rocksdb/env.h"
 #include "util/hash.h"
 #include "util/math.h"
 #include "util/mutexlock.h"
 
 namespace ROCKSDB_NAMESPACE {
+namespace {
+// The generated seeds must fit in 31 bits so that
+// ShardedCacheOptions::hash_seed can be set to it explicitly, for
+// diagnostic/debugging purposes.
+constexpr uint32_t kSeedMask = 0x7fffffff;
+uint32_t DetermineSeed(int32_t hash_seed_option) {
+  if (hash_seed_option >= 0) {
+    // User-specified exact seed
+    return static_cast<uint32_t>(hash_seed_option);
+  }
+  static SemiStructuredUniqueIdGen gen;
+  if (hash_seed_option == ShardedCacheOptions::kHostHashSeed) {
+    std::string hostname;
+    Status s = Env::Default()->GetHostNameString(&hostname);
+    if (s.ok()) {
+      return GetSliceHash(hostname) & kSeedMask;
+    } else {
+      // Fall back on something stable within the process.
+      return BitwiseAnd(gen.GetBaseUpper(), kSeedMask);
+    }
+  } else {
+    // for kQuasiRandomHashSeed and fallback
+    uint32_t val = gen.GenerateNext<uint32_t>() & kSeedMask;
+    // Perform some 31-bit bijective transformations so that we get
+    // quasirandom, not just incrementing. (An incrementing seed from a
+    // random starting point would be fine, but hard to describe in a name.)
+    // See https://en.wikipedia.org/wiki/Quasirandom and using a murmur-like
+    // transformation here for our bijection in the lower 31 bits.
+    // See https://en.wikipedia.org/wiki/MurmurHash
+    val *= /*31-bit prime*/ 1150630961;
+    val ^= (val & kSeedMask) >> 17;
+    val *= /*31-bit prime*/ 1320603883;
+    return val & kSeedMask;
+  }
+}
+}  // namespace
 
-ShardedCacheBase::ShardedCacheBase(size_t capacity, int num_shard_bits,
-                                   bool strict_capacity_limit,
-                                   std::shared_ptr<MemoryAllocator> allocator)
-    : Cache(std::move(allocator)),
+ShardedCacheBase::ShardedCacheBase(const ShardedCacheOptions& opts)
+    : Cache(opts.memory_allocator),
       last_id_(1),
-      shard_mask_((uint32_t{1} << num_shard_bits) - 1),
-      strict_capacity_limit_(strict_capacity_limit),
-      capacity_(capacity) {}
+      shard_mask_((uint32_t{1} << opts.num_shard_bits) - 1),
+      hash_seed_(DetermineSeed(opts.hash_seed)),
+      strict_capacity_limit_(opts.strict_capacity_limit),
+      capacity_(opts.capacity) {}
 
 size_t ShardedCacheBase::ComputePerShardCapacity(size_t capacity) const {
   uint32_t num_shards = GetNumShards();

cache/sharded_cache.h

@@ -34,8 +34,8 @@ class CacheShardBase {
   std::string GetPrintableOptions() const { return ""; }
   using HashVal = uint64_t;
   using HashCref = uint64_t;
-  static inline HashVal ComputeHash(const Slice& key) {
-    return GetSliceNPHash64(key);
+  static inline HashVal ComputeHash(const Slice& key, uint32_t seed) {
+    return GetSliceNPHash64(key, seed);
   }
   static inline uint32_t HashPieceForSharding(HashCref hash) {
     return Lower32of64(hash);
@@ -89,9 +89,7 @@ class CacheShardBase {
 // Portions of ShardedCache that do not depend on the template parameter
 class ShardedCacheBase : public Cache {
  public:
-  ShardedCacheBase(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit,
-                   std::shared_ptr<MemoryAllocator> memory_allocator);
+  explicit ShardedCacheBase(const ShardedCacheOptions& opts);
   virtual ~ShardedCacheBase() = default;
 
   int GetNumShardBits() const;
@@ -106,6 +104,8 @@ class ShardedCacheBase : public Cache {
   size_t GetUsage(Handle* handle) const override;
   std::string GetPrintableOptions() const override;
 
+  uint32_t GetHashSeed() const override { return hash_seed_; }
+
  protected:  // fns
   virtual void AppendPrintableOptions(std::string& str) const = 0;
   size_t GetPerShardCapacity() const;
@@ -114,6 +114,7 @@ class ShardedCacheBase : public Cache {
  protected:                        // data
   std::atomic<uint64_t> last_id_;  // For NewId
   const uint32_t shard_mask_;
+  const uint32_t hash_seed_;
 
   // Dynamic configuration parameters, guarded by config_mutex_
   bool strict_capacity_limit_;
@@ -134,10 +135,8 @@ class ShardedCache : public ShardedCacheBase {
   using HashCref = typename CacheShard::HashCref;
   using HandleImpl = typename CacheShard::HandleImpl;
 
-  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-               std::shared_ptr<MemoryAllocator> allocator)
-      : ShardedCacheBase(capacity, num_shard_bits, strict_capacity_limit,
-                         allocator),
+  explicit ShardedCache(const ShardedCacheOptions& opts)
+      : ShardedCacheBase(opts),
         shards_(reinterpret_cast<CacheShard*>(port::cacheline_aligned_alloc(
             sizeof(CacheShard) * GetNumShards()))),
         destroy_shards_in_dtor_(false) {}
@@ -175,7 +174,7 @@ class ShardedCache : public ShardedCacheBase {
                 size_t charge, Handle** handle = nullptr,
                 Priority priority = Priority::LOW) override {
     assert(helper);
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     auto h_out = reinterpret_cast<HandleImpl**>(handle);
     return GetShard(hash).Insert(key, hash, obj, helper, charge, h_out,
                                  priority);
@@ -185,7 +184,7 @@ class ShardedCache : public ShardedCacheBase {
                            const CacheItemHelper* helper, size_t charge,
                            bool allow_uncharged) override {
     assert(helper);
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     HandleImpl* result = GetShard(hash).CreateStandalone(
         key, hash, obj, helper, charge, allow_uncharged);
     return reinterpret_cast<Handle*>(result);
@@ -195,14 +194,14 @@ class ShardedCache : public ShardedCacheBase {
                  CreateContext* create_context = nullptr,
                  Priority priority = Priority::LOW,
                  Statistics* stats = nullptr) override {
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     HandleImpl* result = GetShard(hash).Lookup(key, hash, helper,
                                                create_context, priority, stats);
     return reinterpret_cast<Handle*>(result);
   }
 
   void Erase(const Slice& key) override {
-    HashVal hash = CacheShard::ComputeHash(key);
+    HashVal hash = CacheShard::ComputeHash(key, hash_seed_);
     GetShard(hash).Erase(key, hash);
   }
 
@@ -274,6 +273,14 @@ class ShardedCache : public ShardedCacheBase {
     }
   }
 
+  inline void ForEachShard(
+      const std::function<void(const CacheShard*)>& fn) const {
+    uint32_t num_shards = GetNumShards();
+    for (uint32_t i = 0; i < num_shards; i++) {
+      fn(shards_ + i);
+    }
+  }
+
   inline size_t SumOverShards(
       const std::function<size_t(CacheShard&)>& fn) const {
     uint32_t num_shards = GetNumShards();

crash_test.mk

@@ -21,6 +21,8 @@ CRASHTEST_PY=$(PYTHON) -u tools/db_crashtest.py --stress_cmd=$(DB_STRESS_CMD) --
 	blackbox_crash_test_with_multiops_wp_txn \
 	crash_test_with_tiered_storage blackbox_crash_test_with_tiered_storage \
 	whitebox_crash_test_with_tiered_storage \
+	whitebox_crash_test_with_optimistic_txn \
+	blackbox_crash_test_with_optimistic_txn \
 
 crash_test: $(DB_STRESS_CMD)
 # Do not parallelize
@@ -37,6 +39,11 @@ crash_test_with_txn: $(DB_STRESS_CMD)
 	$(CRASHTEST_MAKE) whitebox_crash_test_with_txn
 	$(CRASHTEST_MAKE) blackbox_crash_test_with_txn
 
+crash_test_with_optimistic_txn: $(DB_STRESS_CMD)
+# Do not parallelize
+	$(CRASHTEST_MAKE) whitebox_crash_test_with_optimistic_txn
+	$(CRASHTEST_MAKE) blackbox_crash_test_with_optimistic_txn
+
 crash_test_with_best_efforts_recovery: blackbox_crash_test_with_best_efforts_recovery
 
 crash_test_with_ts: $(DB_STRESS_CMD)
@@ -80,6 +87,9 @@ blackbox_crash_test_with_multiops_wp_txn: $(DB_STRESS_CMD)
 blackbox_crash_test_with_tiered_storage: $(DB_STRESS_CMD)
 	$(CRASHTEST_PY) --test_tiered_storage blackbox $(CRASH_TEST_EXT_ARGS)
 
+blackbox_crash_test_with_optimistic_txn: $(DB_STRESS_CMD)
+	$(CRASHTEST_PY) --optimistic_txn blackbox $(CRASH_TEST_EXT_ARGS)
+
 ifeq ($(CRASH_TEST_KILL_ODD),)
   CRASH_TEST_KILL_ODD=888887
 endif
@@ -105,3 +115,7 @@ whitebox_crash_test_with_ts: $(DB_STRESS_CMD)
 whitebox_crash_test_with_tiered_storage: $(DB_STRESS_CMD)
 	$(CRASHTEST_PY) --test_tiered_storage whitebox --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+
+whitebox_crash_test_with_optimistic_txn: $(DB_STRESS_CMD)
+	$(CRASHTEST_PY) --optimistic_txn whitebox --random_kill_odd \
+      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

db/arena_wrapped_db_iter.cc

@@ -47,7 +47,9 @@ void ArenaWrappedDBIter::Init(
   read_options_ = read_options;
   allow_refresh_ = allow_refresh;
   memtable_range_tombstone_iter_ = nullptr;
-  if (!env->GetFileSystem()->use_async_io()) {
+
+  if (!CheckFSFeatureSupport(env->GetFileSystem().get(),
+                             FSSupportedOps::kAsyncIO)) {
     read_options_.async_io = false;
   }
 }

db/blob/blob_contents.h

@@ -7,7 +7,7 @@
 
 #include <memory>
 
-#include "memory/memory_allocator.h"
+#include "memory/memory_allocator_impl.h"
 #include "rocksdb/advanced_cache.h"
 #include "rocksdb/rocksdb_namespace.h"
 #include "rocksdb/slice.h"

db/blob/blob_file_builder.cc

@@ -261,7 +261,7 @@ Status BlobFileBuilder::CompressBlobIfNeeded(
 
   // TODO: allow user CompressionOptions, including max_compressed_bytes_per_kb
   CompressionOptions opts;
-  CompressionContext context(blob_compression_type_);
+  CompressionContext context(blob_compression_type_, opts);
   constexpr uint64_t sample_for_compression = 0;
 
   CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),

db/blob/blob_file_builder_test.cc

@@ -406,7 +406,7 @@ TEST_F(BlobFileBuilderTest, Compression) {
   ASSERT_EQ(blob_file_addition.GetTotalBlobCount(), 1);
 
   CompressionOptions opts;
-  CompressionContext context(kSnappyCompression);
+  CompressionContext context(kSnappyCompression, opts);
   constexpr uint64_t sample_for_compression = 0;
 
   CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),

db/blob/blob_file_cache.cc

@@ -25,7 +25,7 @@ BlobFileCache::BlobFileCache(Cache* cache,
                              HistogramImpl* blob_file_read_hist,
                              const std::shared_ptr<IOTracer>& io_tracer)
     : cache_(cache),
-      mutex_(kNumberOfMutexStripes, kGetSliceNPHash64UnseededFnPtr),
+      mutex_(kNumberOfMutexStripes),
       immutable_options_(immutable_options),
       file_options_(file_options),
       column_family_id_(column_family_id),
@@ -55,7 +55,7 @@ Status BlobFileCache::GetBlobFileReader(
   TEST_SYNC_POINT("BlobFileCache::GetBlobFileReader:DoubleCheck");
 
   // Check again while holding mutex
-  MutexLock lock(mutex_.get(key));
+  MutexLock lock(&mutex_.Get(key));
 
   handle = cache_.Lookup(key);
   if (handle) {

db/blob/blob_file_cache.h

@@ -43,7 +43,7 @@ class BlobFileCache {
   CacheInterface cache_;
   // Note: mutex_ below is used to guard against multiple threads racing to open
   // the same file.
-  Striped<port::Mutex, Slice> mutex_;
+  Striped<CacheAlignedWrapper<port::Mutex>> mutex_;
   const ImmutableOptions* immutable_options_;
   const FileOptions* file_options_;
   uint32_t column_family_id_;

db/blob/blob_file_reader.cc

@@ -12,7 +12,7 @@
 #include "db/blob/blob_log_format.h"
 #include "file/file_prefetch_buffer.h"
 #include "file/filename.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "options/cf_options.h"
 #include "rocksdb/file_system.h"
 #include "rocksdb/slice.h"
@@ -154,11 +154,9 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
     constexpr uint64_t read_offset = 0;
     constexpr size_t read_size = BlobLogHeader::kSize;
 
-    // TODO: rate limit reading headers from blob files.
     const Status s =
         ReadFromFile(file_reader, read_options, read_offset, read_size,
-                     statistics, &header_slice, &buf, &aligned_buf,
-                     Env::IO_TOTAL /* rate_limiter_priority */);
+                     statistics, &header_slice, &buf, &aligned_buf);
     if (!s.ok()) {
       return s;
     }
@@ -207,11 +205,9 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
     const uint64_t read_offset = file_size - BlobLogFooter::kSize;
     constexpr size_t read_size = BlobLogFooter::kSize;
 
-    // TODO: rate limit reading footers from blob files.
     const Status s =
         ReadFromFile(file_reader, read_options, read_offset, read_size,
-                     statistics, &footer_slice, &buf, &aligned_buf,
-                     Env::IO_TOTAL /* rate_limiter_priority */);
+                     statistics, &footer_slice, &buf, &aligned_buf);
     if (!s.ok()) {
       return s;
     }
@@ -242,8 +238,7 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
                                     const ReadOptions& read_options,
                                     uint64_t read_offset, size_t read_size,
                                     Statistics* statistics, Slice* slice,
-                                    Buffer* buf, AlignedBuf* aligned_buf,
-                                    Env::IOPriority rate_limiter_priority) {
+                                    Buffer* buf, AlignedBuf* aligned_buf) {
   assert(slice);
   assert(buf);
   assert(aligned_buf);
@@ -264,13 +259,13 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
     constexpr char* scratch = nullptr;
 
     s = file_reader->Read(io_options, read_offset, read_size, slice, scratch,
-                          aligned_buf, rate_limiter_priority);
+                          aligned_buf);
   } else {
     buf->reset(new char[read_size]);
     constexpr AlignedBuf* aligned_scratch = nullptr;
 
     s = file_reader->Read(io_options, read_offset, read_size, slice, buf->get(),
-                          aligned_scratch, rate_limiter_priority);
+                          aligned_scratch);
   }
 
   if (!s.ok()) {
@@ -345,8 +340,7 @@ Status BlobFileReader::GetBlob(
     }
     prefetched = prefetch_buffer->TryReadFromCache(
         io_options, file_reader_.get(), record_offset,
-        static_cast<size_t>(record_size), &record_slice, &s,
-        read_options.rate_limiter_priority, for_compaction);
+        static_cast<size_t>(record_size), &record_slice, &s, for_compaction);
     if (!s.ok()) {
       return s;
     }
@@ -357,10 +351,10 @@ Status BlobFileReader::GetBlob(
     PERF_COUNTER_ADD(blob_read_count, 1);
     PERF_COUNTER_ADD(blob_read_byte, record_size);
     PERF_TIMER_GUARD(blob_read_time);
-    const Status s = ReadFromFile(
-        file_reader_.get(), read_options, record_offset,
-        static_cast<size_t>(record_size), statistics_, &record_slice, &buf,
-        &aligned_buf, read_options.rate_limiter_priority);
+    const Status s =
+        ReadFromFile(file_reader_.get(), read_options, record_offset,
+                     static_cast<size_t>(record_size), statistics_,
+                     &record_slice, &buf, &aligned_buf);
     if (!s.ok()) {
       return s;
     }
@@ -439,11 +433,11 @@ void BlobFileReader::MultiGetBlob(
     assert(req->offset >= adjustment);
     adjustments.push_back(adjustment);
 
-    FSReadRequest read_req = {};
+    FSReadRequest read_req;
     read_req.offset = req->offset - adjustment;
     read_req.len = req->len + adjustment;
-    read_reqs.emplace_back(read_req);
     total_len += read_req.len;
+    read_reqs.emplace_back(std::move(read_req));
   }
 
   RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_READ, total_len);
@@ -468,9 +462,12 @@ void BlobFileReader::MultiGetBlob(
   TEST_SYNC_POINT("BlobFileReader::MultiGetBlob:ReadFromFile");
   PERF_COUNTER_ADD(blob_read_count, num_blobs);
   PERF_COUNTER_ADD(blob_read_byte, total_len);
-  s = file_reader_->MultiRead(IOOptions(), read_reqs.data(), read_reqs.size(),
-                              direct_io ? &aligned_buf : nullptr,
-                              read_options.rate_limiter_priority);
+  IOOptions opts;
+  s = file_reader_->PrepareIOOptions(read_options, opts);
+  if (s.ok()) {
+    s = file_reader_->MultiRead(opts, read_reqs.data(), read_reqs.size(),
+                                direct_io ? &aligned_buf : nullptr);
+  }
   if (!s.ok()) {
     for (auto& req : read_reqs) {
       req.status.PermitUncheckedError();

db/blob/blob_file_reader.h

@@ -89,8 +89,7 @@ class BlobFileReader {
                              const ReadOptions& read_options,
                              uint64_t read_offset, size_t read_size,
                              Statistics* statistics, Slice* slice, Buffer* buf,
-                             AlignedBuf* aligned_buf,
-                             Env::IOPriority rate_limiter_priority);
+                             AlignedBuf* aligned_buf);
 
   static Status VerifyBlob(const Slice& record_slice, const Slice& user_key,
                            uint64_t value_size);

db/blob/blob_file_reader_test.cc

@@ -74,7 +74,7 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
     }
   } else {
     CompressionOptions opts;
-    CompressionContext context(compression);
+    CompressionContext context(compression, opts);
     constexpr uint64_t sample_for_compression = 0;
     CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
                          compression, sample_for_compression);

db/blob/blob_log_sequential_reader.cc

@@ -7,7 +7,7 @@
 #include "db/blob/blob_log_sequential_reader.h"
 
 #include "file/random_access_file_reader.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "util/stop_watch.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -29,9 +29,8 @@ Status BlobLogSequentialReader::ReadSlice(uint64_t size, Slice* slice,
 
   StopWatch read_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
   // TODO: rate limit `BlobLogSequentialReader` reads (it appears unused?)
-  Status s =
-      file_->Read(IOOptions(), next_byte_, static_cast<size_t>(size), slice,
-                  buf, nullptr, Env::IO_TOTAL /* rate_limiter_priority */);
+  Status s = file_->Read(IOOptions(), next_byte_, static_cast<size_t>(size),
+                         slice, buf, nullptr);
   next_byte_ += size;
   if (!s.ok()) {
     return s;

db/blob/blob_log_writer.cc

@@ -10,7 +10,7 @@
 
 #include "db/blob/blob_log_format.h"
 #include "file/writable_file_writer.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "rocksdb/system_clock.h"
 #include "test_util/sync_point.h"
 #include "util/coding.h"

db/blob/blob_source.cc

@@ -13,7 +13,7 @@
 #include "db/blob/blob_contents.h"
 #include "db/blob/blob_file_reader.h"
 #include "db/blob/blob_log_format.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "options/cf_options.h"
 #include "table/get_context.h"
 #include "table/multiget_context.h"

db/blob/blob_source_test.cc

@@ -76,7 +76,7 @@ void WriteBlobFile(const ImmutableOptions& immutable_options,
     }
   } else {
     CompressionOptions opts;
-    CompressionContext context(compression);
+    CompressionContext context(compression, opts);
     constexpr uint64_t sample_for_compression = 0;
     CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
                          compression, sample_for_compression);

db/builder.cc

@@ -15,6 +15,7 @@
 
 #include "db/blob/blob_file_builder.h"
 #include "db/compaction/compaction_iterator.h"
+#include "db/dbformat.h"
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
@@ -202,24 +203,42 @@ Status BuildTable(
         blob_file_builder.get(), ioptions.allow_data_in_errors,
         ioptions.enforce_single_del_contracts,
         /*manual_compaction_canceled=*/kManualCompactionCanceledFalse,
+        true /* must_count_input_entries */,
         /*compaction=*/nullptr, compaction_filter.get(),
         /*shutting_down=*/nullptr, db_options.info_log, full_history_ts_low);
 
+    const size_t ts_sz = ucmp->timestamp_size();
+    const bool strip_timestamp =
+        ts_sz > 0 && !ioptions.persist_user_defined_timestamps;
+
+    std::string key_after_flush_buf;
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
       const ParsedInternalKey& ikey = c_iter.ikey();
-      // Generate a rolling 64-bit hash of the key and values
-      // Note :
-      // Here "key" integrates 'sequence_number'+'kType'+'user key'.
-      s = output_validator.Add(key, value);
+      Slice key_after_flush = key;
+      // If user defined timestamps will be stripped from user key after flush,
+      // the in memory version of the key act logically the same as one with a
+      // minimum timestamp. We update the timestamp here so file boundary and
+      // output validator, block builder all see the effect of the stripping.
+      if (strip_timestamp) {
+        key_after_flush_buf.clear();
+        ReplaceInternalKeyWithMinTimestamp(&key_after_flush_buf, key, ts_sz);
+        key_after_flush = key_after_flush_buf;
+      }
+
+      //  Generate a rolling 64-bit hash of the key and values
+      //  Note :
+      //  Here "key" integrates 'sequence_number'+'kType'+'user key'.
+      s = output_validator.Add(key_after_flush, value);
       if (!s.ok()) {
         break;
       }
-      builder->Add(key, value);
+      builder->Add(key_after_flush, value);
 
-      s = meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
+      s = meta->UpdateBoundaries(key_after_flush, value, ikey.sequence,
+                                 ikey.type);
       if (!s.ok()) {
         break;
       }
@@ -244,6 +263,7 @@ Status BuildTable(
            range_del_it->Next()) {
         auto tombstone = range_del_it->Tombstone();
         auto kv = tombstone.Serialize();
+        // TODO(yuzhangyu): handle range deletion for UDT in memtables only.
         builder->Add(kv.first.Encode(), kv.second);
         InternalKey tombstone_end = tombstone.SerializeEndKey();
         meta->UpdateBoundariesForRange(kv.first, tombstone_end, tombstone.seq_,
@@ -267,8 +287,9 @@ Status BuildTable(
     TEST_SYNC_POINT("BuildTable:BeforeFinishBuildTable");
     const bool empty = builder->IsEmpty();
     if (num_input_entries != nullptr) {
+      assert(c_iter.HasNumInputEntryScanned());
       *num_input_entries =
-          c_iter.num_input_entry_scanned() + num_unfragmented_tombstones;
+          c_iter.NumInputEntryScanned() + num_unfragmented_tombstones;
     }
     if (!s.ok() || empty) {
       builder->Abandon();
@@ -291,7 +312,10 @@ Status BuildTable(
     if (s.ok() && !empty) {
       uint64_t file_size = builder->FileSize();
       meta->fd.file_size = file_size;
+      meta->tail_size = builder->GetTailSize();
       meta->marked_for_compaction = builder->NeedCompact();
+      meta->user_defined_timestamps_persisted =
+          ioptions.persist_user_defined_timestamps;
       assert(meta->fd.GetFileSize() > 0);
       tp = builder
                ->GetTableProperties();  // refresh now that builder is finished
@@ -351,6 +375,8 @@ Status BuildTable(
       s = *io_status;
     }
 
+    // TODO(yuzhangyu): handle the key copy in the blob when ts should be
+    // stripped.
     if (blob_file_builder) {
       if (s.ok()) {
         s = blob_file_builder->Finish();
@@ -380,7 +406,8 @@ Status BuildTable(
           MaxFileSizeForL0MetaPin(mutable_cf_options),
           /*smallest_compaction_key=*/nullptr,
           /*largest_compaction_key*/ nullptr,
-          /*allow_unprepared_value*/ false));
+          /*allow_unprepared_value*/ false,
+          mutable_cf_options.block_protection_bytes_per_key));
       s = it->status();
       if (s.ok() && paranoid_file_checks) {
         OutputValidator file_validator(tboptions.internal_comparator,

db/c.cc

@@ -77,6 +77,7 @@ using ROCKSDB_NAMESPACE::EnvOptions;
 using ROCKSDB_NAMESPACE::FileLock;
 using ROCKSDB_NAMESPACE::FilterPolicy;
 using ROCKSDB_NAMESPACE::FlushOptions;
+using ROCKSDB_NAMESPACE::HistogramData;
 using ROCKSDB_NAMESPACE::HyperClockCacheOptions;
 using ROCKSDB_NAMESPACE::InfoLogLevel;
 using ROCKSDB_NAMESPACE::IngestExternalFileOptions;
@@ -279,6 +280,11 @@ struct rocksdb_compactionfiltercontext_t {
   CompactionFilter::Context rep;
 };
 
+struct rocksdb_statistics_histogram_data_t {
+  rocksdb_statistics_histogram_data_t() : rep() {}
+  HistogramData rep;
+};
+
 struct rocksdb_compactionfilter_t : public CompactionFilter {
   void* state_;
   void (*destructor_)(void*);
@@ -1057,6 +1063,36 @@ rocksdb_column_family_handle_t* rocksdb_create_column_family(
   return handle;
 }
 
+rocksdb_column_family_handle_t** rocksdb_create_column_families(
+    rocksdb_t* db, const rocksdb_options_t* column_family_options,
+    int num_column_families, const char* const* column_family_names,
+    size_t* lencfs, char** errptr) {
+  std::vector<ColumnFamilyHandle*> handles;
+  std::vector<std::string> names;
+  for (int i = 0; i != num_column_families; ++i) {
+    names.push_back(std::string(column_family_names[i]));
+  }
+  SaveError(errptr, db->rep->CreateColumnFamilies(
+                        ColumnFamilyOptions(column_family_options->rep), names,
+                        &handles));
+
+  *lencfs = handles.size();
+  rocksdb_column_family_handle_t** c_handles =
+      static_cast<rocksdb_column_family_handle_t**>(
+          malloc(sizeof(rocksdb_column_family_handle_t*) * handles.size()));
+  for (size_t i = 0; i != handles.size(); ++i) {
+    c_handles[i] = new rocksdb_column_family_handle_t;
+    c_handles[i]->rep = handles[i];
+  }
+
+  return c_handles;
+}
+
+void rocksdb_create_column_families_destroy(
+    rocksdb_column_family_handle_t** list) {
+  free(list);
+}
+
 rocksdb_column_family_handle_t* rocksdb_create_column_family_with_ttl(
     rocksdb_t* db, const rocksdb_options_t* column_family_options,
     const char* column_family_name, int ttl, char** errptr) {
@@ -2993,6 +3029,29 @@ void rocksdb_options_enable_statistics(rocksdb_options_t* opt) {
   opt->rep.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
 }
 
+void rocksdb_options_set_statistics_level(rocksdb_options_t* opt, int level) {
+  if (!opt->rep.statistics) {
+    return;
+  }
+
+  if (level < rocksdb_statistics_level_disable_all) {
+    level = rocksdb_statistics_level_disable_all;
+  }
+  if (level > rocksdb_statistics_level_all) {
+    level = rocksdb_statistics_level_all;
+  }
+  opt->rep.statistics->set_stats_level(
+      static_cast<ROCKSDB_NAMESPACE::StatsLevel>(level));
+}
+
+int rocksdb_options_get_statistics_level(rocksdb_options_t* opt) {
+  if (!opt->rep.statistics) {
+    return ROCKSDB_NAMESPACE::StatsLevel::kDisableAll;
+  }
+
+  return static_cast<int>(opt->rep.statistics->get_stats_level());
+}
+
 void rocksdb_options_set_skip_stats_update_on_db_open(rocksdb_options_t* opt,
                                                       unsigned char val) {
   opt->rep.skip_stats_update_on_db_open = val;
@@ -3740,16 +3799,21 @@ void rocksdb_options_set_hash_link_list_rep(rocksdb_options_t* opt,
       ROCKSDB_NAMESPACE::NewHashLinkListRepFactory(bucket_count));
 }
 
-void rocksdb_options_set_plain_table_factory(rocksdb_options_t* opt,
-                                             uint32_t user_key_len,
-                                             int bloom_bits_per_key,
-                                             double hash_table_ratio,
-                                             size_t index_sparseness) {
+void rocksdb_options_set_plain_table_factory(
+    rocksdb_options_t* opt, uint32_t user_key_len, int bloom_bits_per_key,
+    double hash_table_ratio, size_t index_sparseness, size_t huge_page_tlb_size,
+    char encoding_type, unsigned char full_scan_mode,
+    unsigned char store_index_in_file) {
   ROCKSDB_NAMESPACE::PlainTableOptions options;
   options.user_key_len = user_key_len;
   options.bloom_bits_per_key = bloom_bits_per_key;
   options.hash_table_ratio = hash_table_ratio;
   options.index_sparseness = index_sparseness;
+  options.huge_page_tlb_size = huge_page_tlb_size;
+  options.encoding_type =
+      static_cast<ROCKSDB_NAMESPACE::EncodingType>(encoding_type);
+  options.full_scan_mode = full_scan_mode;
+  options.store_index_in_file = store_index_in_file;
 
   ROCKSDB_NAMESPACE::TableFactory* factory =
       ROCKSDB_NAMESPACE::NewPlainTableFactory(options);
@@ -3827,6 +3891,26 @@ char* rocksdb_options_statistics_get_string(rocksdb_options_t* opt) {
   return nullptr;
 }
 
+uint64_t rocksdb_options_statistics_get_ticker_count(rocksdb_options_t* opt,
+                                                     uint32_t ticker_type) {
+  ROCKSDB_NAMESPACE::Statistics* statistics = opt->rep.statistics.get();
+  if (statistics) {
+    return statistics->getTickerCount(ticker_type);
+  }
+  return 0;
+}
+
+void rocksdb_options_statistics_get_histogram_data(
+    rocksdb_options_t* opt, uint32_t type,
+    rocksdb_statistics_histogram_data_t* const data) {
+  ROCKSDB_NAMESPACE::Statistics* statistics = opt->rep.statistics.get();
+  if (statistics) {
+    statistics->histogramData(type, &data->rep);
+  } else {
+    *data = rocksdb_statistics_histogram_data_t{};
+  }
+}
+
 void rocksdb_options_set_ratelimiter(rocksdb_options_t* opt,
                                      rocksdb_ratelimiter_t* limiter) {
   if (limiter) {
@@ -3888,6 +3972,15 @@ void rocksdb_options_add_compact_on_deletion_collector_factory(
   opt->rep.table_properties_collector_factories.emplace_back(compact_on_del);
 }
 
+void rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio(
+    rocksdb_options_t* opt, size_t window_size, size_t num_dels_trigger,
+    double deletion_ratio) {
+  std::shared_ptr<ROCKSDB_NAMESPACE::TablePropertiesCollectorFactory>
+      compact_on_del = NewCompactOnDeletionCollectorFactory(
+          window_size, num_dels_trigger, deletion_ratio);
+  opt->rep.table_properties_collector_factories.emplace_back(compact_on_del);
+}
+
 void rocksdb_set_perf_level(int v) {
   PerfLevel level = static_cast<PerfLevel>(v);
   SetPerfLevel(level);
@@ -5150,7 +5243,8 @@ rocksdb_fifo_compaction_options_t* rocksdb_fifo_compaction_options_create() {
 }
 
 void rocksdb_fifo_compaction_options_set_allow_compaction(
-    rocksdb_fifo_compaction_options_t* fifo_opts, unsigned char allow_compaction) {
+    rocksdb_fifo_compaction_options_t* fifo_opts,
+    unsigned char allow_compaction) {
   fifo_opts->rep.allow_compaction = allow_compaction;
 }
 
@@ -5579,6 +5673,20 @@ int rocksdb_transactiondb_property_int(rocksdb_transactiondb_t* db,
   }
 }
 
+rocksdb_t* rocksdb_transactiondb_get_base_db(rocksdb_transactiondb_t* txn_db) {
+  DB* base_db = txn_db->rep->GetBaseDB();
+
+  if (base_db != nullptr) {
+    rocksdb_t* result = new rocksdb_t;
+    result->rep = base_db;
+    return result;
+  }
+
+  return nullptr;
+}
+
+void rocksdb_transactiondb_close_base_db(rocksdb_t* base_db) { delete base_db; }
+
 rocksdb_transaction_t* rocksdb_transaction_begin(
     rocksdb_transactiondb_t* txn_db,
     const rocksdb_writeoptions_t* write_options,
@@ -6556,4 +6664,59 @@ void rocksdb_enable_manual_compaction(rocksdb_t* db) {
   db->rep->EnableManualCompaction();
 }
 
+rocksdb_statistics_histogram_data_t*
+rocksdb_statistics_histogram_data_create() {
+  return new rocksdb_statistics_histogram_data_t{};
+}
+
+void rocksdb_statistics_histogram_data_destroy(
+    rocksdb_statistics_histogram_data_t* data) {
+  delete data;
+}
+
+double rocksdb_statistics_histogram_data_get_median(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.median;
+}
+
+double rocksdb_statistics_histogram_data_get_p95(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.percentile95;
+}
+
+double rocksdb_statistics_histogram_data_get_p99(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.percentile99;
+}
+
+double rocksdb_statistics_histogram_data_get_average(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.average;
+}
+
+double rocksdb_statistics_histogram_data_get_std_dev(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.standard_deviation;
+}
+
+double rocksdb_statistics_histogram_data_get_max(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.max;
+}
+
+uint64_t rocksdb_statistics_histogram_data_get_count(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.count;
+}
+
+uint64_t rocksdb_statistics_histogram_data_get_sum(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.sum;
+}
+
+double rocksdb_statistics_histogram_data_get_min(
+    rocksdb_statistics_histogram_data_t* data) {
+  return data->rep.min;
+}
+
 }  // end extern "C"

db/c_test.c

@@ -3,15 +3,14 @@
    found in the LICENSE file. See the AUTHORS file for names of contributors. */
 // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
-#include <stdio.h>
+#include "rocksdb/c.h"
 
 #include <assert.h>
 #include <stddef.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
-
-#include "rocksdb/c.h"
 #ifndef OS_WIN
 #include <unistd.h>
 #endif
@@ -721,6 +720,8 @@ int main(int argc, char** argv) {
 
   rocksdb_options_add_compact_on_deletion_collector_factory(options, 10000,
                                                             10001);
+  rocksdb_options_add_compact_on_deletion_collector_factory_del_ratio(
+      options, 10000, 10001, 0.0);
 
   StartPhase("destroy");
   rocksdb_destroy_db(options, dbname, &err);
@@ -1672,7 +1673,8 @@ int main(int argc, char** argv) {
     rocksdb_options_set_prefix_extractor(
         options, rocksdb_slicetransform_create_fixed_prefix(3));
     rocksdb_options_set_hash_skip_list_rep(options, 5000, 4, 4);
-    rocksdb_options_set_plain_table_factory(options, 4, 10, 0.75, 16);
+    rocksdb_options_set_plain_table_factory(options, 4, 10, 0.75, 16, 0, 0, 0,
+                                            0);
     rocksdb_options_set_allow_concurrent_memtable_write(options, 0);
 
     db = rocksdb_open(options, dbname, &err);
@@ -2058,6 +2060,15 @@ int main(int argc, char** argv) {
     CheckCondition(29.0 ==
                    rocksdb_options_get_experimental_mempurge_threshold(o));
 
+    CheckCondition(rocksdb_statistics_level_disable_all ==
+                   rocksdb_options_get_statistics_level(o));
+    rocksdb_options_enable_statistics(o);
+    CheckCondition(rocksdb_statistics_level_disable_all !=
+                   rocksdb_options_get_statistics_level(o));
+    rocksdb_options_set_statistics_level(o, rocksdb_statistics_level_all);
+    CheckCondition(rocksdb_statistics_level_all ==
+                   rocksdb_options_get_statistics_level(o));
+
     /* Blob Options */
     rocksdb_options_set_enable_blob_files(o, 1);
     CheckCondition(1 == rocksdb_options_get_enable_blob_files(o));
@@ -3119,6 +3130,17 @@ int main(int argc, char** argv) {
     CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
     CheckTxnDBPinGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
 
+    // memory usage
+    rocksdb_t* base_db = rocksdb_transactiondb_get_base_db(txn_db);
+    rocksdb_memory_consumers_t* consumers = rocksdb_memory_consumers_create();
+    rocksdb_memory_consumers_add_db(consumers, base_db);
+    rocksdb_memory_usage_t* usage =
+        rocksdb_approximate_memory_usage_create(consumers, &err);
+    CheckNoError(err);
+    rocksdb_approximate_memory_usage_destroy(usage);
+    rocksdb_memory_consumers_destroy(consumers);
+    rocksdb_transactiondb_close_base_db(base_db);
+
     // flush
     rocksdb_flushoptions_t* flush_options = rocksdb_flushoptions_create();
     rocksdb_flushoptions_set_wait(flush_options, 1);
@@ -3374,8 +3396,19 @@ int main(int argc, char** argv) {
     rocksdb_put(db, woptions, "key", 3, "value", 5, &err);
     CheckNoError(err);
     rocksdb_column_family_handle_t *cfh1, *cfh2;
-    cfh1 = rocksdb_create_column_family(db, db_options, "txn_db_cf1", &err);
-    cfh2 = rocksdb_create_column_family(db, db_options, "txn_db_cf2", &err);
+    char** list_const_cf_names = (char**)malloc(2 * sizeof(char*));
+    list_const_cf_names[0] = "txn_db_cf1";
+    list_const_cf_names[1] = "txn_db_cf2";
+    size_t cflen;
+    rocksdb_column_family_handle_t** list_cfh = rocksdb_create_column_families(
+        db, db_options, 2, (const char* const*)list_const_cf_names, &cflen,
+        &err);
+    free(list_const_cf_names);
+    CheckNoError(err);
+    assert(cflen == 2);
+    cfh1 = list_cfh[0];
+    cfh2 = list_cfh[1];
+    rocksdb_create_column_families_destroy(list_cfh);
     txn = rocksdb_optimistictransaction_begin(otxn_db, woptions, otxn_options,
                                               NULL);
     rocksdb_transaction_put_cf(txn, cfh1, "key_cf1", 7, "val_cf1", 7, &err);
@@ -3589,6 +3622,71 @@ int main(int argc, char** argv) {
     rocksdb_readoptions_destroy(ropts);
   }
 
+  StartPhase("statistics");
+  {
+    const uint32_t BYTES_WRITTEN_TICKER = 40;
+    const uint32_t DB_WRITE_HIST = 1;
+
+    rocksdb_statistics_histogram_data_t* hist =
+        rocksdb_statistics_histogram_data_create();
+    {
+      // zero by default
+      CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_median(hist));
+      CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_p95(hist));
+      CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_p99(hist));
+      CheckCondition(0.0 ==
+                     rocksdb_statistics_histogram_data_get_average(hist));
+      CheckCondition(0.0 ==
+                     rocksdb_statistics_histogram_data_get_std_dev(hist));
+      CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_max(hist));
+      CheckCondition(0 == rocksdb_statistics_histogram_data_get_count(hist));
+      CheckCondition(0 == rocksdb_statistics_histogram_data_get_sum(hist));
+      CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_min(hist));
+    }
+
+    rocksdb_close(db);
+    rocksdb_destroy_db(options, dbname, &err);
+    CheckNoError(err);
+
+    rocksdb_options_enable_statistics(options);
+    rocksdb_options_set_statistics_level(options, rocksdb_statistics_level_all);
+
+    db = rocksdb_open(options, dbname, &err);
+    CheckNoError(err);
+
+    CheckCondition(0 == rocksdb_options_statistics_get_ticker_count(
+                            options, BYTES_WRITTEN_TICKER));
+    rocksdb_options_statistics_get_histogram_data(options, DB_WRITE_HIST, hist);
+    CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_median(hist));
+    CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_p95(hist));
+    CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_p99(hist));
+    CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_average(hist));
+    CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_std_dev(hist));
+    CheckCondition(0.0 == rocksdb_statistics_histogram_data_get_max(hist));
+    CheckCondition(0 == rocksdb_statistics_histogram_data_get_count(hist));
+    CheckCondition(0 == rocksdb_statistics_histogram_data_get_sum(hist));
+
+    int i;
+    for (i = 0; i < 10; ++i) {
+      char key = '0' + (char)i;
+      rocksdb_put(db, woptions, &key, 1, "", 1, &err);
+      CheckNoError(err);
+    }
+    CheckCondition(0 != rocksdb_options_statistics_get_ticker_count(
+                            options, BYTES_WRITTEN_TICKER));
+    rocksdb_options_statistics_get_histogram_data(options, DB_WRITE_HIST, hist);
+    CheckCondition(0.0 != rocksdb_statistics_histogram_data_get_median(hist));
+    CheckCondition(0.0 != rocksdb_statistics_histogram_data_get_p95(hist));
+    CheckCondition(0.0 != rocksdb_statistics_histogram_data_get_p99(hist));
+    CheckCondition(0.0 != rocksdb_statistics_histogram_data_get_average(hist));
+    CheckCondition(0.0 != rocksdb_statistics_histogram_data_get_std_dev(hist));
+    CheckCondition(0.0 != rocksdb_statistics_histogram_data_get_max(hist));
+    CheckCondition(0 != rocksdb_statistics_histogram_data_get_count(hist));
+    CheckCondition(0 != rocksdb_statistics_histogram_data_get_sum(hist));
+
+    rocksdb_statistics_histogram_data_destroy(hist);
+  }
+
   StartPhase("cancel_all_background_work");
   rocksdb_cancel_all_background_work(db, 1);
 

db/column_family.cc

@@ -382,8 +382,9 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
 
   const uint64_t kAdjustedTtl = 30 * 24 * 60 * 60;
   if (result.ttl == kDefaultTtl) {
-    if (is_block_based_table &&
-        result.compaction_style != kCompactionStyleFIFO) {
+    if (is_block_based_table) {
+      // FIFO also requires max_open_files=-1, which is checked in
+      // ValidateOptions().
       result.ttl = kAdjustedTtl;
     } else {
       result.ttl = 0;
@@ -391,40 +392,35 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
   }
 
   const uint64_t kAdjustedPeriodicCompSecs = 30 * 24 * 60 * 60;
-
-  // Turn on periodic compactions and set them to occur once every 30 days if
-  // compaction filters are used and periodic_compaction_seconds is set to the
-  // default value.
-  if (result.compaction_style != kCompactionStyleFIFO) {
+  if (result.compaction_style == kCompactionStyleLevel) {
     if ((result.compaction_filter != nullptr ||
          result.compaction_filter_factory != nullptr) &&
         result.periodic_compaction_seconds == kDefaultPeriodicCompSecs &&
         is_block_based_table) {
       result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
     }
-  } else {
-    // result.compaction_style == kCompactionStyleFIFO
-    if (result.ttl == 0) {
-      if (is_block_based_table) {
-        if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-          result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-        }
-        result.ttl = result.periodic_compaction_seconds;
-      }
-    } else if (result.periodic_compaction_seconds != 0) {
-      result.ttl = std::min(result.ttl, result.periodic_compaction_seconds);
+  } else if (result.compaction_style == kCompactionStyleUniversal) {
+    if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs &&
+        is_block_based_table) {
+      result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
+    }
+  } else if (result.compaction_style == kCompactionStyleFIFO) {
+    if (result.periodic_compaction_seconds != kDefaultPeriodicCompSecs) {
+      ROCKS_LOG_WARN(
+          db_options.info_log.get(),
+          "periodic_compaction_seconds does not support FIFO compaction. You"
+          "may want to set option TTL instead.");
     }
   }
 
-  // TTL compactions would work similar to Periodic Compactions in Universal in
-  // most of the cases. So, if ttl is set, execute the periodic compaction
-  // codepath.
-  if (result.compaction_style == kCompactionStyleUniversal && result.ttl != 0) {
-    if (result.periodic_compaction_seconds != 0) {
+  // For universal compaction, `ttl` and `periodic_compaction_seconds` mean the
+  // same thing, take the stricter value.
+  if (result.compaction_style == kCompactionStyleUniversal) {
+    if (result.periodic_compaction_seconds == 0) {
+      result.periodic_compaction_seconds = result.ttl;
+    } else if (result.ttl != 0) {
       result.periodic_compaction_seconds =
           std::min(result.ttl, result.periodic_compaction_seconds);
-    } else {
-      result.periodic_compaction_seconds = result.ttl;
     }
   }
 
@@ -1245,30 +1241,11 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
   // (if no Scrape happens).
   assert(ptr != SuperVersion::kSVInUse);
   SuperVersion* sv = static_cast<SuperVersion*>(ptr);
-  if (sv == SuperVersion::kSVObsolete ||
-      sv->version_number != super_version_number_.load()) {
+  if (sv == SuperVersion::kSVObsolete) {
     RecordTick(ioptions_.stats, NUMBER_SUPERVERSION_ACQUIRES);
-    SuperVersion* sv_to_delete = nullptr;
-
-    if (sv && sv->Unref()) {
-      RecordTick(ioptions_.stats, NUMBER_SUPERVERSION_CLEANUPS);
-      db->mutex()->Lock();
-      // NOTE: underlying resources held by superversion (sst files) might
-      // not be released until the next background job.
-      sv->Cleanup();
-      if (db->immutable_db_options().avoid_unnecessary_blocking_io) {
-        db->AddSuperVersionsToFreeQueue(sv);
-        db->SchedulePurge();
-      } else {
-        sv_to_delete = sv;
-      }
-    } else {
-      db->mutex()->Lock();
-    }
+    db->mutex()->Lock();
     sv = super_version_->Ref();
     db->mutex()->Unlock();
-
-    delete sv_to_delete;
   }
   assert(sv != nullptr);
   return sv;
@@ -1399,6 +1376,33 @@ Status ColumnFamilyData::ValidateOptions(
     }
   }
 
+  const auto* ucmp = cf_options.comparator;
+  assert(ucmp);
+  if (ucmp->timestamp_size() > 0 &&
+      !cf_options.persist_user_defined_timestamps) {
+    if (db_options.atomic_flush) {
+      return Status::NotSupported(
+          "Not persisting user-defined timestamps feature is not supported"
+          "in combination with atomic flush.");
+    }
+    if (db_options.allow_concurrent_memtable_write) {
+      return Status::NotSupported(
+          "Not persisting user-defined timestamps feature is not supported"
+          " in combination with concurrent memtable write.");
+    }
+    const char* comparator_name = cf_options.comparator->Name();
+    size_t name_size = strlen(comparator_name);
+    const char* suffix = ".u64ts";
+    size_t suffix_size = strlen(suffix);
+    if (name_size <= suffix_size ||
+        strcmp(comparator_name + name_size - suffix_size, suffix) != 0) {
+      return Status::NotSupported(
+          "Not persisting user-defined timestamps"
+          "feature only support user-defined timestamps formatted as "
+          "uint64_t.");
+    }
+  }
+
   if (cf_options.enable_blob_garbage_collection) {
     if (cf_options.blob_garbage_collection_age_cutoff < 0.0 ||
         cf_options.blob_garbage_collection_age_cutoff > 1.0) {
@@ -1428,6 +1432,37 @@ Status ColumnFamilyData::ValidateOptions(
         "Memtable per key-value checksum protection only supports 0, 1, 2, 4 "
         "or 8 bytes per key.");
   }
+  if (std::find(supported.begin(), supported.end(),
+                cf_options.block_protection_bytes_per_key) == supported.end()) {
+    return Status::NotSupported(
+        "Block per key-value checksum protection only supports 0, 1, 2, 4 "
+        "or 8 bytes per key.");
+  }
+
+  if (!cf_options.compaction_options_fifo.file_temperature_age_thresholds
+           .empty()) {
+    if (cf_options.compaction_style != kCompactionStyleFIFO) {
+      return Status::NotSupported(
+          "Option file_temperature_age_thresholds only supports FIFO "
+          "compaction.");
+    } else if (cf_options.num_levels > 1) {
+      return Status::NotSupported(
+          "Option file_temperature_age_thresholds is only supported when "
+          "num_levels = 1.");
+    } else {
+      const auto& ages =
+          cf_options.compaction_options_fifo.file_temperature_age_thresholds;
+      assert(ages.size() >= 1);
+      // check that age is sorted
+      for (size_t i = 0; i < ages.size() - 1; ++i) {
+        if (ages[i].age >= ages[i + 1].age) {
+          return Status::NotSupported(
+              "Option file_temperature_age_thresholds requires elements to be "
+              "sorted in increasing order with respect to `age` field.");
+        }
+      }
+    }
+  }
   return s;
 }
 
@@ -1507,6 +1542,43 @@ FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
   return data_dirs_[path_id].get();
 }
 
+bool ColumnFamilyData::ShouldPostponeFlushToRetainUDT(
+    uint64_t max_memtable_id) {
+  const Comparator* ucmp = user_comparator();
+  const size_t ts_sz = ucmp->timestamp_size();
+  if (ts_sz == 0 || ioptions_.persist_user_defined_timestamps) {
+    return false;
+  }
+  // If users set the `persist_user_defined_timestamps` flag to false, they
+  // should also set the `full_history_ts_low` flag to indicate the range of
+  // user-defined timestamps to retain in memory. Otherwise, we do not
+  // explicitly postpone flush to retain UDTs.
+  const std::string& full_history_ts_low = GetFullHistoryTsLow();
+  if (full_history_ts_low.empty()) {
+    return false;
+  }
+#ifndef NDEBUG
+  Slice last_table_newest_udt;
+#endif /* !NDEBUG */
+  for (const Slice& table_newest_udt :
+       imm()->GetTablesNewestUDT(max_memtable_id)) {
+    assert(table_newest_udt.size() == full_history_ts_low.size());
+    assert(last_table_newest_udt.empty() ||
+           ucmp->CompareTimestamp(table_newest_udt, last_table_newest_udt) >=
+               0);
+    // Checking the newest UDT contained in MemTable with ascending ID up to
+    // `max_memtable_id`. MemTable with bigger ID will have newer UDT, return
+    // immediately on finding the first MemTable that needs postponing.
+    if (ucmp->CompareTimestamp(table_newest_udt, full_history_ts_low) >= 0) {
+      return true;
+    }
+#ifndef NDEBUG
+    last_table_newest_udt = table_newest_udt;
+#endif /* !NDEBUG */
+  }
+  return false;
+}
+
 void ColumnFamilyData::RecoverEpochNumbers() {
   assert(current_);
   auto* vstorage = current_->storage_info();
@@ -1609,6 +1681,13 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
       db_id_, db_session_id_);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
+  auto ucmp = new_cfd->user_comparator();
+  assert(ucmp);
+  size_t ts_sz = ucmp->timestamp_size();
+  running_ts_sz_.insert({id, ts_sz});
+  if (ts_sz > 0) {
+    ts_sz_for_record_.insert({id, ts_sz});
+  }
   max_column_family_ = std::max(max_column_family_, id);
   // add to linked list
   new_cfd->next_ = dummy_cfd_;
@@ -1624,10 +1703,13 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
 
 // under a DB mutex AND from a write thread
 void ColumnFamilySet::RemoveColumnFamily(ColumnFamilyData* cfd) {
-  auto cfd_iter = column_family_data_.find(cfd->GetID());
+  uint32_t cf_id = cfd->GetID();
+  auto cfd_iter = column_family_data_.find(cf_id);
   assert(cfd_iter != column_family_data_.end());
   column_family_data_.erase(cfd_iter);
   column_families_.erase(cfd->GetName());
+  running_ts_sz_.erase(cf_id);
+  ts_sz_for_record_.erase(cf_id);
 }
 
 // under a DB mutex OR from a write thread

db/column_family.h

@@ -506,6 +506,12 @@ class ColumnFamilyData {
     return full_history_ts_low_;
   }
 
+  // REQUIRES: DB mutex held.
+  // Return true if flushing up to MemTables with ID `max_memtable_id`
+  // should be postponed to retain user-defined timestamps according to the
+  // user's setting. Called by background flush job.
+  bool ShouldPostponeFlushToRetainUDT(uint64_t max_memtable_id);
+
   ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
   WriteBufferManager* write_buffer_mgr() { return write_buffer_manager_; }
   std::shared_ptr<CacheReservationManager>
@@ -513,8 +519,6 @@ class ColumnFamilyData {
     return file_metadata_cache_res_mgr_;
   }
 
-  SequenceNumber GetFirstMemtableSequenceNumber() const;
-
   static const uint32_t kDummyColumnFamilyDataId;
 
   // Keep track of whether the mempurge feature was ever used.
@@ -705,6 +709,16 @@ class ColumnFamilySet {
                                        Version* dummy_version,
                                        const ColumnFamilyOptions& options);
 
+  const UnorderedMap<uint32_t, size_t>& GetRunningColumnFamiliesTimestampSize()
+      const {
+    return running_ts_sz_;
+  }
+
+  const UnorderedMap<uint32_t, size_t>&
+  GetColumnFamiliesTimestampSizeForRecord() const {
+    return ts_sz_for_record_;
+  }
+
   iterator begin() { return iterator(dummy_cfd_->next_); }
   iterator end() { return iterator(dummy_cfd_); }
 
@@ -730,6 +744,15 @@ class ColumnFamilySet {
   UnorderedMap<std::string, uint32_t> column_families_;
   UnorderedMap<uint32_t, ColumnFamilyData*> column_family_data_;
 
+  // Mutating / reading `running_ts_sz_` and `ts_sz_for_record_` follow
+  // the same requirements as `column_families_` and `column_family_data_`.
+  // Mapping from column family id to user-defined timestamp size for all
+  // running column families.
+  UnorderedMap<uint32_t, size_t> running_ts_sz_;
+  // Mapping from column family id to user-defined timestamp size for
+  // column families with non-zero user-defined timestamp size.
+  UnorderedMap<uint32_t, size_t> ts_sz_for_record_;
+
   uint32_t max_column_family_;
   const FileOptions file_options_;
 

db/column_family_test.cc

@@ -17,6 +17,7 @@
 #include "options/options_parser.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
+#include "rocksdb/comparator.h"
 #include "rocksdb/convenience.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
@@ -63,6 +64,9 @@ class ColumnFamilyTestBase : public testing::Test {
     db_options_.create_if_missing = true;
     db_options_.fail_if_options_file_error = true;
     db_options_.env = env_;
+  }
+
+  void SetUp() override {
     EXPECT_OK(DestroyDB(dbname_, Options(db_options_, column_family_options_)));
   }
 
@@ -1255,6 +1259,7 @@ TEST_P(ColumnFamilyTest, DifferentCompactionStyles) {
   ColumnFamilyOptions default_cf, one, two;
   db_options_.max_open_files = 20;  // only 10 files in file cache
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
@@ -1272,6 +1277,7 @@ TEST_P(ColumnFamilyTest, DifferentCompactionStyles) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -1326,6 +1332,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
   db_options_.max_open_files = 20;  // only 10 files in file cache
   db_options_.max_background_compactions = 3;
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
@@ -1342,6 +1349,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -1424,13 +1432,14 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
   db_options_.max_open_files = 20;  // only 10 files in file cache
   db_options_.max_background_compactions = 3;
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
   default_cf.target_file_size_base = 30 << 10;
   default_cf.max_compaction_bytes = default_cf.target_file_size_base * 1100;
   BlockBasedTableOptions table_options = GetBlockBasedTableOptions();
-  ;
+
   table_options.no_block_cache = true;
   default_cf.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
@@ -1441,6 +1450,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -1519,13 +1529,14 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   db_options_.max_open_files = 20;  // only 10 files in file cache
   db_options_.max_background_compactions = 3;
 
+  default_cf.level_compaction_dynamic_level_bytes = false;
   default_cf.compaction_style = kCompactionStyleLevel;
   default_cf.num_levels = 3;
   default_cf.write_buffer_size = 64 << 10;  // 64KB
   default_cf.target_file_size_base = 30 << 10;
   default_cf.max_compaction_bytes = default_cf.target_file_size_base * 1100;
   BlockBasedTableOptions table_options = GetBlockBasedTableOptions();
-  ;
+
   table_options.no_block_cache = true;
   default_cf.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
@@ -1536,6 +1547,7 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   one.level0_file_num_compaction_trigger = 4;
   one.write_buffer_size = 120000;
 
+  two.level_compaction_dynamic_level_bytes = false;
   two.compaction_style = kCompactionStyleLevel;
   two.num_levels = 4;
   two.level0_file_num_compaction_trigger = 3;
@@ -3372,6 +3384,205 @@ TEST(ColumnFamilyTest, ValidateMemtableKVChecksumOption) {
   ASSERT_OK(ColumnFamilyData::ValidateOptions(db_options, cf_options));
 }
 
+// Tests the flushing behavior of a column family to retain user-defined
+// timestamp when `persist_user_defined_timestamp` is false.
+class ColumnFamilyRetainUDTTest : public ColumnFamilyTestBase {
+ public:
+  ColumnFamilyRetainUDTTest() : ColumnFamilyTestBase(kLatestFormatVersion) {}
+
+  void SetUp() override {
+    db_options_.allow_concurrent_memtable_write = false;
+    column_family_options_.comparator =
+        test::BytewiseComparatorWithU64TsWrapper();
+    column_family_options_.persist_user_defined_timestamps = false;
+    ColumnFamilyTestBase::SetUp();
+  }
+
+  Status Put(int cf, const std::string& key, const std::string& ts,
+             const std::string& value) {
+    return db_->Put(WriteOptions(), handles_[cf], Slice(key), Slice(ts),
+                    Slice(value));
+  }
+};
+
+class TestTsComparator : public Comparator {
+ public:
+  TestTsComparator() : Comparator(8 /*ts_sz*/) {}
+
+  int Compare(const ROCKSDB_NAMESPACE::Slice& /*a*/,
+              const ROCKSDB_NAMESPACE::Slice& /*b*/) const override {
+    return 0;
+  }
+  const char* Name() const override { return "TestTs"; }
+  void FindShortestSeparator(
+      std::string* /*start*/,
+      const ROCKSDB_NAMESPACE::Slice& /*limit*/) const override {}
+  void FindShortSuccessor(std::string* /*key*/) const override {}
+};
+
+TEST_F(ColumnFamilyRetainUDTTest, SanityCheck) {
+  Open();
+  ColumnFamilyOptions cf_options;
+  cf_options.persist_user_defined_timestamps = false;
+  TestTsComparator test_comparator;
+  cf_options.comparator = &test_comparator;
+  ColumnFamilyHandle* handle;
+  // Not persisting user-defined timestamps feature only supports user-defined
+  // timestamps formatted as uint64_t.
+  ASSERT_TRUE(
+      db_->CreateColumnFamily(cf_options, "pikachu", &handle).IsNotSupported());
+
+  Destroy();
+  // Not persisting user-defined timestamps feature doesn't work in combination
+  // with atomic flush.
+  db_options_.atomic_flush = true;
+  ASSERT_TRUE(TryOpen({"default"}).IsNotSupported());
+
+  // Not persisting user-defined timestamps feature doesn't work in combination
+  // with concurrent memtable write.
+  db_options_.atomic_flush = false;
+  db_options_.allow_concurrent_memtable_write = true;
+  ASSERT_TRUE(TryOpen({"default"}).IsNotSupported());
+  Close();
+}
+
+TEST_F(ColumnFamilyRetainUDTTest, FullHistoryTsLowNotSet) {
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
+        ASSERT_NE(nullptr, arg);
+        auto reschedule_count = *static_cast<int*>(arg);
+        ASSERT_EQ(1, reschedule_count);
+      });
+
+  SyncPoint::GetInstance()->EnableProcessing();
+  Open();
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  // No `full_history_ts_low` explicitly set by user, flush is continued
+  // without checking if its UDTs expired.
+  ASSERT_OK(Flush(0));
+
+  // After flush, `full_history_ts_low` should be automatically advanced to
+  // the effective cutoff timestamp: write_ts + 1
+  std::string cutoff_ts;
+  PutFixed64(&cutoff_ts, 2);
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
+  Close();
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_F(ColumnFamilyRetainUDTTest, AllKeysExpired) {
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
+        ASSERT_NE(nullptr, arg);
+        auto reschedule_count = *static_cast<int*>(arg);
+        ASSERT_EQ(1, reschedule_count);
+      });
+
+  SyncPoint::GetInstance()->EnableProcessing();
+  Open();
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  std::string cutoff_ts;
+  PutFixed64(&cutoff_ts, 3);
+  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
+  // All keys expired w.r.t the configured `full_history_ts_low`, flush continue
+  // without the need for a re-schedule.
+  ASSERT_OK(Flush(0));
+
+  // `full_history_ts_low` stays unchanged after flush.
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
+  Close();
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+TEST_F(ColumnFamilyRetainUDTTest, NotAllKeysExpiredFlushToAvoidWriteStall) {
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
+        ASSERT_NE(nullptr, arg);
+        auto reschedule_count = *static_cast<int*>(arg);
+        ASSERT_EQ(1, reschedule_count);
+      });
+
+  SyncPoint::GetInstance()->EnableProcessing();
+  Open();
+  std::string cutoff_ts;
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  PutFixed64(&cutoff_ts, 1);
+  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
+  ASSERT_OK(db_->SetOptions(handles_[0], {{"max_write_buffer_number", "1"}}));
+  // Not all keys expired, but flush is continued without a re-schedule because
+  // of risk of write stall.
+  ASSERT_OK(Flush(0));
+
+  // After flush, `full_history_ts_low` should be automatically advanced to
+  // the effective cutoff timestamp: write_ts + 1
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+
+  cutoff_ts.clear();
+  PutFixed64(&cutoff_ts, 2);
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
+  Close();
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_F(ColumnFamilyRetainUDTTest, NotAllKeysExpiredFlushRescheduled) {
+  std::string cutoff_ts;
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::AfterRetainUDTReschedule:cb", [&](void* /*arg*/) {
+        // Increasing full_history_ts_low so all keys expired after the initial
+        // FlushRequest is rescheduled
+        cutoff_ts.clear();
+        PutFixed64(&cutoff_ts, 3);
+        ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
+      });
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundFlush:CheckFlushRequest:cb", [&](void* arg) {
+        ASSERT_NE(nullptr, arg);
+        auto reschedule_count = *static_cast<int*>(arg);
+        ASSERT_EQ(2, reschedule_count);
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  Open();
+  std::string write_ts;
+  PutFixed64(&write_ts, 1);
+  ASSERT_OK(Put(0, "foo", write_ts, "v1"));
+  PutFixed64(&cutoff_ts, 1);
+  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], cutoff_ts));
+  // Not all keys expired, and there is no risk of write stall. Flush is
+  // rescheduled. The actual flush happens after `full_history_ts_low` is
+  // increased to mark all keys expired.
+  ASSERT_OK(Flush(0));
+
+  std::string effective_full_history_ts_low;
+  ASSERT_OK(
+      db_->GetFullHistoryTsLow(handles_[0], &effective_full_history_ts_low));
+  // `full_history_ts_low` stays unchanged.
+  ASSERT_EQ(cutoff_ts, effective_full_history_ts_low);
+  Close();
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/compact_files_test.cc

@@ -66,6 +66,7 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
   const int kWriteBufferSize = 10000;
   const int kLevel0Trigger = 2;
   options.create_if_missing = true;
+  options.level_compaction_dynamic_level_bytes = false;
   options.compaction_style = kCompactionStyleLevel;
   // Small slowdown and stop trigger for experimental purpose.
   options.level0_slowdown_writes_trigger = 20;
@@ -344,7 +345,7 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
         return true;
       }
       std::string res;
-      db_->Get(ReadOptions(), "", &res);
+      EXPECT_TRUE(db_->Get(ReadOptions(), "", &res).IsNotFound());
       return true;
     }
 
@@ -359,6 +360,7 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   std::shared_ptr<FilterWithGet> cf(new FilterWithGet());
 
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.create_if_missing = true;
   options.compaction_filter = cf.get();
 
@@ -401,6 +403,7 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
                                 CompactionStyle::kCompactionStyleNone}) {
     ASSERT_OK(DestroyDB(db_name_, Options()));
     Options options;
+    options.level_compaction_dynamic_level_bytes = false;
     options.compaction_style = compaction_style;
     // L0: Snappy, L1: ZSTD, L2: Snappy
     options.compression_per_level = {CompressionType::kSnappyCompression,

db/compaction/compaction.cc

@@ -13,6 +13,7 @@
 #include <vector>
 
 #include "db/column_family.h"
+#include "logging/logging.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/sst_partitioner.h"
 #include "test_util/sync_point.h"
@@ -23,14 +24,13 @@ namespace ROCKSDB_NAMESPACE {
 const uint64_t kRangeTombstoneSentinel =
     PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
 
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b) {
-  auto c = user_cmp->CompareWithoutTimestamp(a.user_key(), b.user_key());
+int sstableKeyCompare(const Comparator* uc, const Slice& a, const Slice& b) {
+  auto c = uc->CompareWithoutTimestamp(ExtractUserKey(a), ExtractUserKey(b));
   if (c != 0) {
     return c;
   }
-  auto a_footer = ExtractInternalKeyFooter(a.Encode());
-  auto b_footer = ExtractInternalKeyFooter(b.Encode());
+  auto a_footer = ExtractInternalKeyFooter(a);
+  auto b_footer = ExtractInternalKeyFooter(b);
   if (a_footer == kRangeTombstoneSentinel) {
     if (b_footer != kRangeTombstoneSentinel) {
       return -1;
@@ -204,6 +204,34 @@ bool Compaction::IsFullCompaction(
   return num_files_in_compaction == total_num_files;
 }
 
+const TablePropertiesCollection& Compaction::GetTableProperties() {
+  if (!input_table_properties_initialized_) {
+    const ReadOptions read_options(Env::IOActivity::kCompaction);
+    for (size_t i = 0; i < num_input_levels(); ++i) {
+      for (const FileMetaData* fmd : *(this->inputs(i))) {
+        std::shared_ptr<const TableProperties> tp;
+        std::string file_name =
+            TableFileName(immutable_options_.cf_paths, fmd->fd.GetNumber(),
+                          fmd->fd.GetPathId());
+        Status s = input_version_->GetTableProperties(read_options, &tp, fmd,
+                                                      &file_name);
+        if (s.ok()) {
+          table_properties_[file_name] = tp;
+        } else {
+          ROCKS_LOG_ERROR(immutable_options_.info_log,
+                          "Unable to load table properties for file %" PRIu64
+                          " --- %s\n",
+                          fmd->fd.GetNumber(), s.ToString().c_str());
+        }
+      }
+    }
+
+    input_table_properties_initialized_ = true;
+  };
+
+  return table_properties_;
+}
+
 Compaction::Compaction(
     VersionStorageInfo* vstorage, const ImmutableOptions& _immutable_options,
     const MutableCFOptions& _mutable_cf_options,
@@ -465,6 +493,11 @@ bool Compaction::IsTrivialMove() const {
     return false;
   }
 
+  if (compaction_reason_ == CompactionReason::kChangeTemperature) {
+    // Changing temperature usually requires rewriting the file.
+    return false;
+  }
+
   // Used in universal compaction, where trivial move can be done if the
   // input files are non overlapping
   if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
@@ -481,26 +514,25 @@ bool Compaction::IsTrivialMove() const {
 
   // assert inputs_.size() == 1
 
-  std::unique_ptr<SstPartitioner> partitioner = CreateSstPartitioner();
-
-  for (const auto& file : inputs_.front().files) {
-    std::vector<FileMetaData*> file_grand_parents;
-    if (output_level_ + 1 >= number_levels_) {
-      continue;
-    }
-    input_vstorage_->GetOverlappingInputs(output_level_ + 1, &file->smallest,
-                                          &file->largest, &file_grand_parents);
-    const auto compaction_size =
-        file->fd.GetFileSize() + TotalFileSize(file_grand_parents);
-    if (compaction_size > max_compaction_bytes_) {
-      return false;
-    }
-
-    if (partitioner.get() != nullptr) {
-      if (!partitioner->CanDoTrivialMove(file->smallest.user_key(),
-                                         file->largest.user_key())) {
+  if (output_level_ + 1 < number_levels_) {
+    std::unique_ptr<SstPartitioner> partitioner = CreateSstPartitioner();
+    for (const auto& file : inputs_.front().files) {
+      std::vector<FileMetaData*> file_grand_parents;
+      input_vstorage_->GetOverlappingInputs(output_level_ + 1, &file->smallest,
+                                            &file->largest,
+                                            &file_grand_parents);
+      const auto compaction_size =
+          file->fd.GetFileSize() + TotalFileSize(file_grand_parents);
+      if (compaction_size > max_compaction_bytes_) {
         return false;
       }
+
+      if (partitioner.get() != nullptr) {
+        if (!partitioner->CanDoTrivialMove(file->smallest.user_key(),
+                                           file->largest.user_key())) {
+          return false;
+        }
+      }
     }
   }
 
@@ -558,6 +590,49 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   return false;
 }
 
+bool Compaction::KeyRangeNotExistsBeyondOutputLevel(
+    const Slice& begin_key, const Slice& end_key,
+    std::vector<size_t>* level_ptrs) const {
+  assert(input_version_ != nullptr);
+  assert(level_ptrs != nullptr);
+  assert(level_ptrs->size() == static_cast<size_t>(number_levels_));
+  assert(cfd_->user_comparator()->CompareWithoutTimestamp(begin_key, end_key) <
+         0);
+  if (bottommost_level_) {
+    return true /* does not overlap */;
+  } else if (output_level_ != 0 &&
+             cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
+    const Comparator* user_cmp = cfd_->user_comparator();
+    for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
+      const std::vector<FileMetaData*>& files =
+          input_vstorage_->LevelFiles(lvl);
+      for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
+        auto* f = files[level_ptrs->at(lvl)];
+        // Advance until the first file with begin_key <= f->largest.user_key()
+        if (user_cmp->CompareWithoutTimestamp(begin_key,
+                                              f->largest.user_key()) > 0) {
+          continue;
+        }
+        // We know that the previous file prev_f, if exists, has
+        // prev_f->largest.user_key() < begin_key.
+        if (user_cmp->CompareWithoutTimestamp(end_key,
+                                              f->smallest.user_key()) <= 0) {
+          // not overlapping with this level
+          break;
+        } else {
+          // We have:
+          // - begin_key < end_key,
+          // - begin_key <= f->largest.user_key(), and
+          // - end_key > f->smallest.user_key()
+          return false /* overlap */;
+        }
+      }
+    }
+    return true /* does not overlap */;
+  }
+  return false /* overlaps */;
+};
+
 // Mark (or clear) each file that is being compacted
 void Compaction::MarkFilesBeingCompacted(bool mark_as_compacted) {
   for (size_t i = 0; i < num_input_levels(); i++) {

db/compaction/compaction.h

@@ -31,8 +31,19 @@ namespace ROCKSDB_NAMESPACE {
 // that key never appears in the database. We don't want adjacent sstables to
 // be considered overlapping if they are separated by the range tombstone
 // sentinel.
-int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
-                      const InternalKey& b);
+int sstableKeyCompare(const Comparator* user_cmp, const Slice&, const Slice&);
+inline int sstableKeyCompare(const Comparator* user_cmp, const Slice& a,
+                             const InternalKey& b) {
+  return sstableKeyCompare(user_cmp, a, b.Encode());
+}
+inline int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                             const Slice& b) {
+  return sstableKeyCompare(user_cmp, a.Encode(), b);
+}
+inline int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                             const InternalKey& b) {
+  return sstableKeyCompare(user_cmp, a.Encode(), b.Encode());
+}
 int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
                       const InternalKey& b);
 int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
@@ -203,10 +214,18 @@ class Compaction {
   void AddInputDeletions(VersionEdit* edit);
 
   // Returns true if the available information we have guarantees that
-  // the input "user_key" does not exist in any level beyond "output_level()".
+  // the input "user_key" does not exist in any level beyond `output_level()`.
   bool KeyNotExistsBeyondOutputLevel(const Slice& user_key,
                                      std::vector<size_t>* level_ptrs) const;
 
+  // Returns true if the user key range [begin_key, end_key) does not exist
+  // in any level beyond `output_level()`.
+  // Used for checking range tombstones, so we assume begin_key < end_key.
+  // begin_key and end_key should include timestamp if enabled.
+  bool KeyRangeNotExistsBeyondOutputLevel(
+      const Slice& begin_key, const Slice& end_key,
+      std::vector<size_t>* level_ptrs) const;
+
   // Clear all files to indicate that they are not being compacted
   // Delete this compaction from the list of running compactions.
   //
@@ -307,12 +326,16 @@ class Compaction {
       int output_level, VersionStorageInfo* vstorage,
       const std::vector<CompactionInputFiles>& inputs);
 
-  TablePropertiesCollection GetOutputTableProperties() const {
-    return output_table_properties_;
-  }
+  // If called before a compaction finishes, will return
+  // table properties of all compaction input files.
+  // If called after a compaction finished, will return
+  // table properties of all compaction input and output files.
+  const TablePropertiesCollection& GetTableProperties();
 
-  void SetOutputTableProperties(TablePropertiesCollection tp) {
-    output_table_properties_ = std::move(tp);
+  void SetOutputTableProperties(
+      const std::string& file_name,
+      const std::shared_ptr<const TableProperties>& tp) {
+    table_properties_[file_name] = tp;
   }
 
   Slice GetSmallestUserKey() const { return smallest_user_key_; }
@@ -499,8 +522,9 @@ class Compaction {
   // Does input compression match the output compression?
   bool InputCompressionMatchesOutput() const;
 
+  bool input_table_properties_initialized_ = false;
   // table properties of output files
-  TablePropertiesCollection output_table_properties_;
+  TablePropertiesCollection table_properties_;
 
   // smallest user keys in compaction
   // includes timestamp if user-defined timestamp is enabled.

db/compaction/compaction_iterator.cc

@@ -31,7 +31,8 @@ CompactionIterator::CompactionIterator(
     BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
     bool enforce_single_del_contracts,
     const std::atomic<bool>& manual_compaction_canceled,
-    const Compaction* compaction, const CompactionFilter* compaction_filter,
+    bool must_count_input_entries, const Compaction* compaction,
+    const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
     const std::shared_ptr<Logger> info_log,
     const std::string* full_history_ts_low,
@@ -45,8 +46,9 @@ CompactionIterator::CompactionIterator(
           manual_compaction_canceled,
           std::unique_ptr<CompactionProxy>(
               compaction ? new RealCompaction(compaction) : nullptr),
-          compaction_filter, shutting_down, info_log, full_history_ts_low,
-          preserve_time_min_seqno, preclude_last_level_min_seqno) {}
+          must_count_input_entries, compaction_filter, shutting_down, info_log,
+          full_history_ts_low, preserve_time_min_seqno,
+          preclude_last_level_min_seqno) {}
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -58,15 +60,14 @@ CompactionIterator::CompactionIterator(
     BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
     bool enforce_single_del_contracts,
     const std::atomic<bool>& manual_compaction_canceled,
-    std::unique_ptr<CompactionProxy> compaction,
+    std::unique_ptr<CompactionProxy> compaction, bool must_count_input_entries,
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
     const std::shared_ptr<Logger> info_log,
     const std::string* full_history_ts_low,
     const SequenceNumber preserve_time_min_seqno,
     const SequenceNumber preclude_last_level_min_seqno)
-    : input_(input, cmp,
-             !compaction || compaction->DoesInputReferenceBlobFiles()),
+    : input_(input, cmp, must_count_input_entries),
       cmp_(cmp),
       merge_helper_(merge_helper),
       snapshots_(snapshots),

db/compaction/compaction_iterator.h

@@ -38,15 +38,18 @@ class SequenceIterWrapper : public InternalIterator {
   bool Valid() const override { return inner_iter_->Valid(); }
   Status status() const override { return inner_iter_->status(); }
   void Next() override {
-    num_itered_++;
+    if (!inner_iter_->IsDeleteRangeSentinelKey()) {
+      num_itered_++;
+    }
     inner_iter_->Next();
   }
   void Seek(const Slice& target) override {
     if (!need_count_entries_) {
+      has_num_itered_ = false;
       inner_iter_->Seek(target);
     } else {
-      // For flush cases, we need to count total number of entries, so we
-      // do Next() rather than Seek().
+      // Need to count total number of entries,
+      // so we do Next() rather than Seek().
       while (inner_iter_->Valid() &&
              icmp_.Compare(inner_iter_->key(), target) < 0) {
         Next();
@@ -62,7 +65,8 @@ class SequenceIterWrapper : public InternalIterator {
   void SeekForPrev(const Slice& /* target */) override { assert(false); }
   void SeekToLast() override { assert(false); }
 
-  uint64_t num_itered() const { return num_itered_; }
+  uint64_t NumItered() const { return num_itered_; }
+  bool HasNumItered() const { return has_num_itered_; }
   bool IsDeleteRangeSentinelKey() const override {
     assert(Valid());
     return inner_iter_->IsDeleteRangeSentinelKey();
@@ -73,6 +77,7 @@ class SequenceIterWrapper : public InternalIterator {
   InternalIterator* inner_iter_;  // not owned
   uint64_t num_itered_ = 0;
   bool need_count_entries_;
+  bool has_num_itered_ = true;
 };
 
 class CompactionIterator {
@@ -189,6 +194,10 @@ class CompactionIterator {
     const Compaction* compaction_;
   };
 
+  // @param must_count_input_entries  if true, `NumInputEntryScanned()` will
+  // return the number of input keys scanned. If false, `NumInputEntryScanned()`
+  // will return this number if no Seek was called on `input`. User should call
+  // `HasNumInputEntryScanned()` first in this case.
   CompactionIterator(
       InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
       SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
@@ -199,7 +208,7 @@ class CompactionIterator {
       BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
       bool enforce_single_del_contracts,
       const std::atomic<bool>& manual_compaction_canceled,
-      const Compaction* compaction = nullptr,
+      bool must_count_input_entries, const Compaction* compaction = nullptr,
       const CompactionFilter* compaction_filter = nullptr,
       const std::atomic<bool>* shutting_down = nullptr,
       const std::shared_ptr<Logger> info_log = nullptr,
@@ -219,6 +228,7 @@ class CompactionIterator {
       bool enforce_single_del_contracts,
       const std::atomic<bool>& manual_compaction_canceled,
       std::unique_ptr<CompactionProxy> compaction,
+      bool must_count_input_entries,
       const CompactionFilter* compaction_filter = nullptr,
       const std::atomic<bool>* shutting_down = nullptr,
       const std::shared_ptr<Logger> info_log = nullptr,
@@ -253,7 +263,8 @@ class CompactionIterator {
     return current_user_key_;
   }
   const CompactionIterationStats& iter_stats() const { return iter_stats_; }
-  uint64_t num_input_entry_scanned() const { return input_.num_itered(); }
+  bool HasNumInputEntryScanned() const { return input_.HasNumItered(); }
+  uint64_t NumInputEntryScanned() const { return input_.NumItered(); }
   // If the current key should be placed on penultimate level, only valid if
   // per_key_placement is supported
   bool output_to_penultimate_level() const {

db/compaction/compaction_iterator_test.cc

@@ -293,8 +293,8 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
         nullptr /* blob_file_builder */, true /*allow_data_in_errors*/,
         true /*enforce_single_del_contracts*/,
         /*manual_compaction_canceled=*/kManualCompactionCanceledFalse_,
-        std::move(compaction), filter, &shutting_down_, /*info_log=*/nullptr,
-        full_history_ts_low));
+        std::move(compaction), /*must_count_input_entries=*/false, filter,
+        &shutting_down_, /*info_log=*/nullptr, full_history_ts_low));
   }
 
   void AddSnapshot(SequenceNumber snapshot,

db/compaction/compaction_job.cc

@@ -260,7 +260,7 @@ void CompactionJob::Prepare() {
     StopWatch sw(db_options_.clock, stats_, SUBCOMPACTION_SETUP_TIME);
     GenSubcompactionBoundaries();
   }
-  if (boundaries_.size() > 1) {
+  if (boundaries_.size() >= 1) {
     for (size_t i = 0; i <= boundaries_.size(); i++) {
       compact_->sub_compact_states.emplace_back(
           c, (i != 0) ? std::optional<Slice>(boundaries_[i - 1]) : std::nullopt,
@@ -504,7 +504,9 @@ void CompactionJob::GenSubcompactionBoundaries() {
         FileMetaData* f = flevel->files[i].file_metadata;
         std::vector<TableReader::Anchor> my_anchors;
         Status s = cfd->table_cache()->ApproximateKeyAnchors(
-            read_options, icomp, *f, my_anchors);
+            read_options, icomp, *f,
+            c->mutable_cf_options()->block_protection_bytes_per_key,
+            my_anchors);
         if (!s.ok() || my_anchors.empty()) {
           my_anchors.emplace_back(f->largest.user_key(), f->fd.GetFileSize());
         }
@@ -735,7 +737,9 @@ Status CompactionJob::Run() {
                 *compact_->compaction->mutable_cf_options()),
             /*smallest_compaction_key=*/nullptr,
             /*largest_compaction_key=*/nullptr,
-            /*allow_unprepared_value=*/false);
+            /*allow_unprepared_value=*/false,
+            compact_->compaction->mutable_cf_options()
+                ->block_protection_bytes_per_key);
         auto s = iter->status();
 
         if (s.ok() && paranoid_file_checks_) {
@@ -792,20 +796,51 @@ Status CompactionJob::Run() {
       auto fn =
           TableFileName(state.compaction->immutable_options()->cf_paths,
                         output.meta.fd.GetNumber(), output.meta.fd.GetPathId());
-      tp[fn] = output.table_properties;
+      compact_->compaction->SetOutputTableProperties(fn,
+                                                     output.table_properties);
     }
   }
-  compact_->compaction->SetOutputTableProperties(std::move(tp));
 
-  // Finish up all book-keeping to unify the subcompaction results
+  // Finish up all bookkeeping to unify the subcompaction results.
   compact_->AggregateCompactionStats(compaction_stats_, *compaction_job_stats_);
-  UpdateCompactionStats();
-
+  uint64_t num_input_range_del = 0;
+  bool ok = UpdateCompactionStats(&num_input_range_del);
+  // (Sub)compactions returned ok, do sanity check on the number of input keys.
+  if (status.ok() && ok && compaction_job_stats_->has_num_input_records) {
+    size_t ts_sz = compact_->compaction->column_family_data()
+                       ->user_comparator()
+                       ->timestamp_size();
+    // When trim_ts_ is non-empty, CompactionIterator takes
+    // HistoryTrimmingIterator as input iterator and sees a trimmed view of
+    // input keys. So the number of keys it processed is not suitable for
+    // verification here.
+    // TODO: support verification when trim_ts_ is non-empty.
+    if (!(ts_sz > 0 && !trim_ts_.empty()) &&
+        db_options_.compaction_verify_record_count) {
+      assert(compaction_stats_.stats.num_input_records > 0);
+      // TODO: verify the number of range deletion entries.
+      uint64_t expected =
+          compaction_stats_.stats.num_input_records - num_input_range_del;
+      uint64_t actual = compaction_job_stats_->num_input_records;
+      if (expected != actual) {
+        std::string msg =
+            "Total number of input records: " + std::to_string(expected) +
+            ", but processed " + std::to_string(actual) + " records.";
+        ROCKS_LOG_WARN(
+            db_options_.info_log, "[%s] [JOB %d] Compaction %s",
+            compact_->compaction->column_family_data()->GetName().c_str(),
+            job_context_->job_id, msg.c_str());
+        status = Status::Corruption(
+            "Compaction number of input keys does not match number of keys "
+            "processed.");
+      }
+    }
+  }
   RecordCompactionIOStats();
   LogFlush(db_options_.info_log);
   TEST_SYNC_POINT("CompactionJob::Run():End");
-
   compact_->status = status;
+  TEST_SYNC_POINT_CALLBACK("CompactionJob::Run():EndStatusSet", &status);
   return status;
 }
 
@@ -1092,17 +1127,17 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // GenSubcompactionBoundaries doesn't strip away the timestamp.
   size_t ts_sz = cfd->user_comparator()->timestamp_size();
   if (start.has_value()) {
-    read_options.iterate_lower_bound = &start.value();
+    read_options.iterate_lower_bound = &(*start);
     if (ts_sz > 0) {
-      start_without_ts = StripTimestampFromUserKey(start.value(), ts_sz);
-      read_options.iterate_lower_bound = &start_without_ts.value();
+      start_without_ts = StripTimestampFromUserKey(*start, ts_sz);
+      read_options.iterate_lower_bound = &(*start_without_ts);
     }
   }
   if (end.has_value()) {
-    read_options.iterate_upper_bound = &end.value();
+    read_options.iterate_upper_bound = &(*end);
     if (ts_sz > 0) {
-      end_without_ts = StripTimestampFromUserKey(end.value(), ts_sz);
-      read_options.iterate_upper_bound = &end_without_ts.value();
+      end_without_ts = StripTimestampFromUserKey(*end, ts_sz);
+      read_options.iterate_upper_bound = &(*end_without_ts);
     }
   }
 
@@ -1134,8 +1169,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   }
 
   if (start.has_value()) {
-    start_ikey.SetInternalKey(start.value(), kMaxSequenceNumber,
-                              kValueTypeForSeek);
+    start_ikey.SetInternalKey(*start, kMaxSequenceNumber, kValueTypeForSeek);
     if (ts_sz > 0) {
       start_ikey.UpdateInternalKey(kMaxSequenceNumber, kValueTypeForSeek,
                                    &ts_slice);
@@ -1144,7 +1178,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     start_user_key = start_ikey.GetUserKey();
   }
   if (end.has_value()) {
-    end_ikey.SetInternalKey(end.value(), kMaxSequenceNumber, kValueTypeForSeek);
+    end_ikey.SetInternalKey(*end, kMaxSequenceNumber, kValueTypeForSeek);
     if (ts_sz > 0) {
       end_ikey.UpdateInternalKey(kMaxSequenceNumber, kValueTypeForSeek,
                                  &ts_slice);
@@ -1249,6 +1283,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       /*expect_valid_internal_key=*/true, range_del_agg.get(),
       blob_file_builder.get(), db_options_.allow_data_in_errors,
       db_options_.enforce_single_del_contracts, manual_compaction_canceled_,
+      sub_compact->compaction
+          ->DoesInputReferenceBlobFiles() /* must_count_input_entries */,
       sub_compact->compaction, compaction_filter, shutting_down_,
       db_options_.info_log, full_history_ts_low, preserve_time_min_seqno_,
       preclude_last_level_min_seqno_);
@@ -1285,8 +1321,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
     // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
     // returns true.
-    assert(!end.has_value() || cfd->user_comparator()->Compare(
-                                   c_iter->user_key(), end.value()) < 0);
+    assert(!end.has_value() ||
+           cfd->user_comparator()->Compare(c_iter->user_key(), *end) < 0);
 
     if (c_iter_stats.num_input_records % kRecordStatsEvery ==
         kRecordStatsEvery - 1) {
@@ -1313,8 +1349,25 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     if (c_iter->status().IsManualCompactionPaused()) {
       break;
     }
+
+#ifndef NDEBUG
+    bool stop = false;
+    TEST_SYNC_POINT_CALLBACK("CompactionJob::ProcessKeyValueCompaction()::stop",
+                             static_cast<void*>(&stop));
+    if (stop) {
+      break;
+    }
+#endif  // NDEBUG
   }
 
+  // This number may not be accurate when CompactionIterator was created
+  // with `must_count_input_entries=false`.
+  assert(!sub_compact->compaction->DoesInputReferenceBlobFiles() ||
+         c_iter->HasNumInputEntryScanned());
+  sub_compact->compaction_job_stats.has_num_input_records =
+      c_iter->HasNumInputEntryScanned();
+  sub_compact->compaction_job_stats.num_input_records =
+      c_iter->NumInputEntryScanned();
   sub_compact->compaction_job_stats.num_blobs_read =
       c_iter_stats.num_blobs_read;
   sub_compact->compaction_job_stats.total_blob_bytes_read =
@@ -1814,10 +1867,10 @@ Status CompactionJob::OpenCompactionOutputFile(SubcompactionState* sub_compact,
   uint64_t current_time = static_cast<uint64_t>(temp_current_time);
   InternalKey tmp_start, tmp_end;
   if (sub_compact->start.has_value()) {
-    tmp_start.SetMinPossibleForUserKey(sub_compact->start.value());
+    tmp_start.SetMinPossibleForUserKey(*(sub_compact->start));
   }
   if (sub_compact->end.has_value()) {
-    tmp_end.SetMinPossibleForUserKey(sub_compact->end.value());
+    tmp_end.SetMinPossibleForUserKey(*(sub_compact->end));
   }
   uint64_t oldest_ancester_time =
       sub_compact->compaction->MinInputFileOldestAncesterTime(
@@ -1900,24 +1953,53 @@ void CopyPrefix(const Slice& src, size_t prefix_length, std::string* dst) {
 }
 }  // namespace
 
-
-void CompactionJob::UpdateCompactionStats() {
+bool CompactionJob::UpdateCompactionStats(uint64_t* num_input_range_del) {
   assert(compact_);
 
   Compaction* compaction = compact_->compaction;
   compaction_stats_.stats.num_input_files_in_non_output_levels = 0;
   compaction_stats_.stats.num_input_files_in_output_level = 0;
+
+  bool has_error = false;
+  const ReadOptions read_options(Env::IOActivity::kCompaction);
+  const auto& input_table_properties = compaction->GetTableProperties();
   for (int input_level = 0;
        input_level < static_cast<int>(compaction->num_input_levels());
        ++input_level) {
+    size_t num_input_files = compaction->num_input_files(input_level);
+    uint64_t* bytes_read;
     if (compaction->level(input_level) != compaction->output_level()) {
-      UpdateCompactionInputStatsHelper(
-          &compaction_stats_.stats.num_input_files_in_non_output_levels,
-          &compaction_stats_.stats.bytes_read_non_output_levels, input_level);
+      compaction_stats_.stats.num_input_files_in_non_output_levels +=
+          static_cast<int>(num_input_files);
+      bytes_read = &compaction_stats_.stats.bytes_read_non_output_levels;
     } else {
-      UpdateCompactionInputStatsHelper(
-          &compaction_stats_.stats.num_input_files_in_output_level,
-          &compaction_stats_.stats.bytes_read_output_level, input_level);
+      compaction_stats_.stats.num_input_files_in_output_level +=
+          static_cast<int>(num_input_files);
+      bytes_read = &compaction_stats_.stats.bytes_read_output_level;
+    }
+    for (size_t i = 0; i < num_input_files; ++i) {
+      const FileMetaData* file_meta = compaction->input(input_level, i);
+      *bytes_read += file_meta->fd.GetFileSize();
+      uint64_t file_input_entries = file_meta->num_entries;
+      uint64_t file_num_range_del = file_meta->num_range_deletions;
+      if (file_input_entries == 0) {
+        uint64_t file_number = file_meta->fd.GetNumber();
+        // Try getting info from table property
+        std::string fn =
+            TableFileName(compaction->immutable_options()->cf_paths,
+                          file_number, file_meta->fd.GetPathId());
+        const auto& tp = input_table_properties.find(fn);
+        if (tp != input_table_properties.end()) {
+          file_input_entries = tp->second->num_entries;
+          file_num_range_del = tp->second->num_range_deletions;
+        } else {
+          has_error = true;
+        }
+      }
+      compaction_stats_.stats.num_input_records += file_input_entries;
+      if (num_input_range_del) {
+        *num_input_range_del += file_num_range_del;
+      }
     }
   }
 
@@ -1927,21 +2009,7 @@ void CompactionJob::UpdateCompactionStats() {
 
   compaction_stats_.stats.num_dropped_records =
       compaction_stats_.DroppedRecords();
-}
-
-void CompactionJob::UpdateCompactionInputStatsHelper(int* num_files,
-                                                     uint64_t* bytes_read,
-                                                     int input_level) {
-  const Compaction* compaction = compact_->compaction;
-  auto num_input_files = compaction->num_input_files(input_level);
-  *num_files += static_cast<int>(num_input_files);
-
-  for (size_t i = 0; i < num_input_files; ++i) {
-    const auto* file_meta = compaction->input(input_level, i);
-    *bytes_read += file_meta->fd.GetFileSize();
-    compaction_stats_.stats.num_input_records +=
-        static_cast<uint64_t>(file_meta->num_entries);
-  }
+  return !has_error;
 }
 
 void CompactionJob::UpdateCompactionJobStats(

db/compaction/compaction_job.h

@@ -192,7 +192,21 @@ class CompactionJob {
   IOStatus io_status() const { return io_status_; }
 
  protected:
-  void UpdateCompactionStats();
+  // Update the following stats in compaction_stats_.stats
+  // - num_input_files_in_non_output_levels
+  // - num_input_files_in_output_level
+  // - bytes_read_non_output_levels
+  // - bytes_read_output_level
+  // - num_input_records
+  // - bytes_read_blob
+  // - num_dropped_records
+  //
+  // @param num_input_range_del if non-null, will be set to the number of range
+  // deletion entries in this compaction input.
+  //
+  // Returns true iff compaction_stats_.stats.num_input_records and
+  // num_input_range_del are calculated successfully.
+  bool UpdateCompactionStats(uint64_t* num_input_range_del = nullptr);
   void LogCompaction();
   virtual void RecordCompactionIOStats();
   void CleanupCompaction();
@@ -267,9 +281,6 @@ class CompactionJob {
   void RecordDroppedKeys(const CompactionIterationStats& c_iter_stats,
                          CompactionJobStats* compaction_job_stats = nullptr);
 
-  void UpdateCompactionInputStatsHelper(int* num_files, uint64_t* bytes_read,
-                                        int input_level);
-
   void NotifyOnSubcompactionBegin(SubcompactionState* sub_compact);
 
   void NotifyOnSubcompactionCompleted(SubcompactionState* sub_compact);

db/compaction/compaction_job_stats_test.cc

@@ -24,7 +24,7 @@
 #include "db/write_batch_internal.h"
 #include "env/mock_env.h"
 #include "file/filename.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "monitoring/thread_status_util.h"
 #include "port/stack_trace.h"
 #include "rocksdb/cache.h"
@@ -54,7 +54,7 @@
 #include "util/compression.h"
 #include "util/hash.h"
 #include "util/mutexlock.h"
-#include "util/rate_limiter.h"
+#include "util/rate_limiter_impl.h"
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
@@ -616,6 +616,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
   // via AddExpectedStats().
   auto* stats_checker = new CompactionJobStatsChecker();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.listeners.emplace_back(stats_checker);
   options.create_if_missing = true;
   // just enough setting to hold off auto-compaction.
@@ -815,6 +816,7 @@ TEST_P(CompactionJobStatsTest, DeletionStatsTest) {
   // what we expect.
   auto* stats_checker = new CompactionJobDeletionStatsChecker();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.listeners.emplace_back(stats_checker);
   options.create_if_missing = true;
   options.level0_file_num_compaction_trigger = kTestScale + 1;

db/compaction/compaction_job_test.cc

@@ -373,7 +373,7 @@ class CompactionJobTestBase : public testing::Test {
     } else if (table_type_ == TableTypeForTest::kMockTable) {
       file_size = 10;
       EXPECT_OK(mock_table_factory_->CreateMockTable(
-          env_, GenerateFileName(file_number), std::move(contents)));
+          env_, GenerateFileName(file_number), contents));
     } else {
       assert(false);
     }
@@ -386,7 +386,8 @@ class CompactionJobTestBase : public testing::Test {
         kUnknownFileCreationTime,
         versions_->GetColumnFamilySet()->GetDefault()->NewEpochNumber(),
         kUnknownFileChecksum, kUnknownFileChecksumFuncName, kNullUniqueId64x2,
-        0);
+        /*compensated_range_deletion_size=*/0, /*tail_size=*/0,
+        /*user_defined_timestamps_persisted=*/true);
 
     mutex_.Lock();
     EXPECT_OK(versions_->LogAndApply(
@@ -454,7 +455,8 @@ class CompactionJobTestBase : public testing::Test {
       Status s = cf_options_.table_factory->NewTableReader(
           read_opts,
           TableReaderOptions(*cfd->ioptions(), nullptr, FileOptions(),
-                             cfd_->internal_comparator()),
+                             cfd_->internal_comparator(),
+                             0 /* block_protection_bytes_per_key */),
           std::move(freader), file_size, &table_reader, false);
       ASSERT_OK(s);
       assert(table_reader);
@@ -653,11 +655,12 @@ class CompactionJobTestBase : public testing::Test {
     ASSERT_TRUE(full_history_ts_low_.empty() ||
                 ucmp_->timestamp_size() == full_history_ts_low_.size());
     const std::atomic<bool> kManualCompactionCanceledFalse{false};
+    JobContext job_context(1, false /* create_superversion */);
     CompactionJob compaction_job(
         0, &compaction, db_options_, mutable_db_options_, env_options_,
         versions_.get(), &shutting_down_, &log_buffer, nullptr, nullptr,
         nullptr, nullptr, &mutex_, &error_handler_, snapshots,
-        earliest_write_conflict_snapshot, snapshot_checker, nullptr,
+        earliest_write_conflict_snapshot, snapshot_checker, &job_context,
         table_cache_, &event_logger, false, false, dbname_,
         &compaction_job_stats_, Env::Priority::USER, nullptr /* IOTracer */,
         /*manual_compaction_canceled=*/kManualCompactionCanceledFalse,

db/compaction/compaction_outputs.cc

@@ -43,7 +43,10 @@ Status CompactionOutputs::Finish(const Status& intput_status,
   const uint64_t current_bytes = builder_->FileSize();
   if (s.ok()) {
     meta->fd.file_size = current_bytes;
+    meta->tail_size = builder_->GetTailSize();
     meta->marked_for_compaction = builder_->NeedCompact();
+    meta->user_defined_timestamps_persisted = static_cast<bool>(
+        builder_->GetTableProperties().user_defined_timestamps_persisted);
   }
   current_output().finished = true;
   stats_.bytes_written += current_bytes;
@@ -124,11 +127,6 @@ size_t CompactionOutputs::UpdateGrandparentBoundaryInfo(
   if (grandparents.empty()) {
     return curr_key_boundary_switched_num;
   }
-  assert(!internal_key.empty());
-  InternalKey ikey;
-  ikey.DecodeFrom(internal_key);
-  assert(ikey.Valid());
-
   const Comparator* ucmp = compaction_->column_family_data()->user_comparator();
 
   // Move the grandparent_index_ to the file containing the current user_key.
@@ -136,7 +134,7 @@ size_t CompactionOutputs::UpdateGrandparentBoundaryInfo(
   // index points to the last file containing the key.
   while (grandparent_index_ < grandparents.size()) {
     if (being_grandparent_gap_) {
-      if (sstableKeyCompare(ucmp, ikey,
+      if (sstableKeyCompare(ucmp, internal_key,
                             grandparents[grandparent_index_]->smallest) < 0) {
         break;
       }
@@ -149,13 +147,13 @@ size_t CompactionOutputs::UpdateGrandparentBoundaryInfo(
       being_grandparent_gap_ = false;
     } else {
       int cmp_result = sstableKeyCompare(
-          ucmp, ikey, grandparents[grandparent_index_]->largest);
+          ucmp, internal_key, grandparents[grandparent_index_]->largest);
       // If it's same key, make sure grandparent_index_ is pointing to the last
       // one.
       if (cmp_result < 0 ||
           (cmp_result == 0 &&
            (grandparent_index_ == grandparents.size() - 1 ||
-            sstableKeyCompare(ucmp, ikey,
+            sstableKeyCompare(ucmp, internal_key,
                               grandparents[grandparent_index_ + 1]->smallest) <
                 0))) {
         break;
@@ -597,10 +595,12 @@ Status CompactionOutputs::AddRangeDels(
     // in any snapshot. trim_ts_ is passed to the constructor for
     // range_del_agg_, and range_del_agg_ internally drops tombstones above
     // trim_ts_.
-    if (bottommost_level && tombstone.seq_ <= earliest_snapshot &&
+    bool consider_drop =
+        tombstone.seq_ <= earliest_snapshot &&
         (ts_sz == 0 ||
          (!full_history_ts_low.empty() &&
-          ucmp->CompareTimestamp(tombstone.ts_, full_history_ts_low) < 0))) {
+          ucmp->CompareTimestamp(tombstone.ts_, full_history_ts_low) < 0));
+    if (consider_drop && bottommost_level) {
       // TODO(andrewkr): tombstones that span multiple output files are
       // counted for each compaction output file, so lots of double
       // counting.
@@ -634,6 +634,20 @@ Status CompactionOutputs::AddRangeDels(
         icmp.Compare(*upper_bound, tombstone_start.Encode()) < 0) {
       break;
     }
+    if (lower_bound &&
+        icmp.Compare(tombstone_start.Encode(), *lower_bound) < 0) {
+      tombstone_start.DecodeFrom(*lower_bound);
+    }
+    if (upper_bound && icmp.Compare(*upper_bound, tombstone_end.Encode()) < 0) {
+      tombstone_end.DecodeFrom(*upper_bound);
+    }
+    if (consider_drop && compaction_->KeyRangeNotExistsBeyondOutputLevel(
+                             tombstone_start.user_key(),
+                             tombstone_end.user_key(), &level_ptrs_)) {
+      range_del_out_stats.num_range_del_drop_obsolete++;
+      range_del_out_stats.num_record_drop_obsolete++;
+      continue;
+    }
     // Here we show that *only* range tombstones that overlap with
     // [lower_bound, upper_bound] are added to the current file, and
     // sanity checking invariants that should hold:
@@ -687,13 +701,6 @@ Status CompactionOutputs::AddRangeDels(
 
     // Range tombstone is not supported by output validator yet.
     builder_->Add(kv.first.Encode(), kv.second);
-    if (lower_bound &&
-        icmp.Compare(tombstone_start.Encode(), *lower_bound) < 0) {
-      tombstone_start.DecodeFrom(*lower_bound);
-    }
-    if (upper_bound && icmp.Compare(*upper_bound, tombstone_end.Encode()) < 0) {
-      tombstone_end.DecodeFrom(*upper_bound);
-    }
     assert(icmp.Compare(tombstone_start, tombstone_end) <= 0);
     meta.UpdateBoundariesForRange(tombstone_start, tombstone_end,
                                   tombstone.seq_, icmp);
@@ -778,6 +785,8 @@ CompactionOutputs::CompactionOutputs(const Compaction* compaction,
   if (compaction->output_level() != 0) {
     FillFilesToCutForTtl();
   }
+
+  level_ptrs_ = std::vector<size_t>(compaction_->number_levels(), 0);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_outputs.h

@@ -206,10 +206,10 @@ class CompactionOutputs {
       // We may only split the output when the cursor is in the range. Split
       if ((!end.has_value() ||
            icmp->user_comparator()->Compare(
-               ExtractUserKey(output_split_key->Encode()), end.value()) < 0) &&
-          (!start.has_value() || icmp->user_comparator()->Compare(
-                                     ExtractUserKey(output_split_key->Encode()),
-                                     start.value()) > 0)) {
+               ExtractUserKey(output_split_key->Encode()), *end) < 0) &&
+          (!start.has_value() ||
+           icmp->user_comparator()->Compare(
+               ExtractUserKey(output_split_key->Encode()), *start) > 0)) {
         local_output_split_key_ = output_split_key;
       }
     }
@@ -356,6 +356,15 @@ class CompactionOutputs {
   // The smallest key of the current output file, this is set when current
   // output file's smallest key is a range tombstone start key.
   InternalKey range_tombstone_lower_bound_;
+
+  // Used for calls to compaction->KeyRangeNotExistsBeyondOutputLevel() in
+  // CompactionOutputs::AddRangeDels().
+  // level_ptrs_[i] holds index of the file that was checked during the last
+  // call to compaction->KeyRangeNotExistsBeyondOutputLevel(). This allows
+  // future calls to the function to pick up where it left off, since each
+  // range tombstone added to output file within each subcompaction is in
+  // increasing key range.
+  std::vector<size_t> level_ptrs_;
 };
 
 // helper struct to concatenate the last level and penultimate level outputs

db/compaction/compaction_picker.cc

@@ -20,7 +20,7 @@
 #include "file/filename.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "test_util/sync_point.h"
 #include "util/random.h"
 #include "util/string_util.h"
@@ -611,23 +611,21 @@ Compaction* CompactionPicker::CompactRange(
     // Universal compaction with more than one level always compacts all the
     // files together to the last level.
     assert(vstorage->num_levels() > 1);
+    int max_output_level =
+        vstorage->MaxOutputLevel(ioptions_.allow_ingest_behind);
     // DBImpl::CompactRange() set output level to be the last level
-    if (ioptions_.allow_ingest_behind) {
-      assert(output_level == vstorage->num_levels() - 2);
-    } else {
-      assert(output_level == vstorage->num_levels() - 1);
-    }
+    assert(output_level == max_output_level);
     // DBImpl::RunManualCompaction will make full range for universal compaction
     assert(begin == nullptr);
     assert(end == nullptr);
     *compaction_end = nullptr;
 
     int start_level = 0;
-    for (; start_level < vstorage->num_levels() &&
+    for (; start_level <= max_output_level &&
            vstorage->NumLevelFiles(start_level) == 0;
          start_level++) {
     }
-    if (start_level == vstorage->num_levels()) {
+    if (start_level > max_output_level) {
       return nullptr;
     }
 
@@ -637,9 +635,9 @@ Compaction* CompactionPicker::CompactRange(
       return nullptr;
     }
 
-    std::vector<CompactionInputFiles> inputs(vstorage->num_levels() -
+    std::vector<CompactionInputFiles> inputs(max_output_level + 1 -
                                              start_level);
-    for (int level = start_level; level < vstorage->num_levels(); level++) {
+    for (int level = start_level; level <= max_output_level; level++) {
       inputs[level - start_level].level = level;
       auto& files = inputs[level - start_level].files;
       for (FileMetaData* f : vstorage->LevelFiles(level)) {
@@ -753,8 +751,10 @@ Compaction* CompactionPicker::CompactRange(
 
   // for BOTTOM LEVEL compaction only, use max_file_num_to_ignore to filter out
   // files that are created during the current compaction.
-  if (compact_range_options.bottommost_level_compaction ==
-          BottommostLevelCompaction::kForceOptimized &&
+  if ((compact_range_options.bottommost_level_compaction ==
+           BottommostLevelCompaction::kForceOptimized ||
+       compact_range_options.bottommost_level_compaction ==
+           BottommostLevelCompaction::kIfHaveCompactionFilter) &&
       max_file_num_to_ignore != std::numeric_limits<uint64_t>::max()) {
     assert(input_level == output_level);
     // inputs_shrunk holds a continuous subset of input files which were all

db/compaction/compaction_picker_fifo.cc

@@ -16,6 +16,7 @@
 #include "db/column_family.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
+#include "options/options_helper.h"
 #include "util/string_util.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -284,31 +285,36 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
   return c;
 }
 
-Compaction* FIFOCompactionPicker::PickCompactionToWarm(
+Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
     LogBuffer* log_buffer) {
-  if (mutable_cf_options.compaction_options_fifo.age_for_warm == 0) {
+  const std::vector<FileTemperatureAge>& ages =
+      mutable_cf_options.compaction_options_fifo
+          .file_temperature_age_thresholds;
+  if (ages.empty()) {
     return nullptr;
   }
 
-  // PickCompactionToWarm is only triggered if there is no non-L0 files.
-  for (int level = 1; level < vstorage->num_levels(); ++level) {
-    if (GetTotalFilesSize(vstorage->LevelFiles(level)) > 0) {
-      return nullptr;
-    }
+  // Does not apply to multi-level FIFO.
+  if (vstorage->num_levels() > 1) {
+    return nullptr;
   }
 
   const int kLevel0 = 0;
   const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  if (level_files.empty()) {
+    return nullptr;
+  }
 
   int64_t _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. "
-                     "Not doing compactions based on warm threshold. ",
-                     cf_name.c_str(), status.ToString().c_str());
+    ROCKS_LOG_BUFFER(
+        log_buffer,
+        "[%s] FIFO compaction: Couldn't get current time: %s. "
+        "Not doing compactions based on file temperature-age threshold. ",
+        cf_name.c_str(), status.ToString().c_str());
     return nullptr;
   }
   const uint64_t current_time = static_cast<uint64_t>(_current_time);
@@ -327,56 +333,77 @@ Compaction* FIFOCompactionPicker::PickCompactionToWarm(
   inputs[0].level = 0;
 
   // avoid underflow
-  if (current_time > mutable_cf_options.compaction_options_fifo.age_for_warm) {
-    uint64_t create_time_threshold =
-        current_time - mutable_cf_options.compaction_options_fifo.age_for_warm;
+  uint64_t min_age = ages[0].age;
+  // kLastTemperature means target temperature is to be determined.
+  Temperature compaction_target_temp = Temperature::kLastTemperature;
+  if (current_time > min_age) {
+    uint64_t create_time_threshold = current_time - min_age;
     uint64_t compaction_size = 0;
-    // We will ideally identify a file qualifying for warm tier by knowing
-    // the timestamp for the youngest entry in the file. However, right now
-    // we don't have the information. We infer it by looking at timestamp
-    // of the next file's (which is just younger) oldest entry's timestamp.
-    FileMetaData* prev_file = nullptr;
-    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-      FileMetaData* f = *ritr;
-      assert(f);
-      if (f->being_compacted) {
-        // Right now this probably won't happen as we never try to schedule
-        // two compactions in parallel, so here we just simply don't schedule
-        // anything.
+    // We will ideally identify a file qualifying for temperature change by
+    // knowing the timestamp for the youngest entry in the file. However, right
+    // now we don't have the information. We infer it by looking at timestamp of
+    // the previous file's (which is just younger) oldest entry's timestamp.
+    Temperature cur_target_temp;
+    // avoid index underflow
+    assert(level_files.size() >= 1);
+    for (size_t index = level_files.size() - 1; index >= 1; --index) {
+      // Try to add cur_file to compaction inputs.
+      FileMetaData* cur_file = level_files[index];
+      // prev_file is just younger than cur_file
+      FileMetaData* prev_file = level_files[index - 1];
+      if (cur_file->being_compacted) {
+        // Should not happen since we check for
+        // `level0_compactions_in_progress_` above. Here we simply just don't
+        // schedule anything.
         return nullptr;
       }
-      uint64_t oldest_ancester_time = f->TryGetOldestAncesterTime();
-      if (oldest_ancester_time == kUnknownOldestAncesterTime) {
+      uint64_t oldest_ancestor_time = prev_file->TryGetOldestAncesterTime();
+      if (oldest_ancestor_time == kUnknownOldestAncesterTime) {
         // Older files might not have enough information. It is possible to
         // handle these files by looking at newer files, but maintaining the
         // logic isn't worth it.
         break;
       }
-      if (oldest_ancester_time > create_time_threshold) {
-        // The previous file (which has slightly older data) doesn't qualify
-        // for warm tier.
+      if (oldest_ancestor_time > create_time_threshold) {
+        // cur_file is too fresh
         break;
       }
-      if (prev_file != nullptr) {
-        compaction_size += prev_file->fd.GetFileSize();
-        if (compaction_size > mutable_cf_options.max_compaction_bytes) {
+      cur_target_temp = ages[0].temperature;
+      for (size_t i = 1; i < ages.size(); ++i) {
+        if (current_time >= ages[i].age &&
+            oldest_ancestor_time <= current_time - ages[i].age) {
+          cur_target_temp = ages[i].temperature;
+        }
+      }
+      if (cur_file->temperature == cur_target_temp) {
+        if (inputs[0].empty()) {
+          continue;
+        } else {
           break;
         }
-        inputs[0].files.push_back(prev_file);
-        ROCKS_LOG_BUFFER(log_buffer,
-                         "[%s] FIFO compaction: picking file %" PRIu64
-                         " with next file's oldest time %" PRIu64 " for warm",
-                         cf_name.c_str(), prev_file->fd.GetNumber(),
-                         oldest_ancester_time);
       }
-      if (f->temperature == Temperature::kUnknown ||
-          f->temperature == Temperature::kHot) {
-        prev_file = f;
-      } else if (!inputs[0].files.empty()) {
-        // A warm file newer than files picked.
+
+      // cur_file needs to change temperature
+      if (compaction_target_temp == Temperature::kLastTemperature) {
+        assert(inputs[0].empty());
+        compaction_target_temp = cur_target_temp;
+      } else if (cur_target_temp != compaction_target_temp) {
+        assert(!inputs[0].empty());
+        break;
+      }
+      if (inputs[0].empty() || compaction_size + cur_file->fd.GetFileSize() <=
+                                   mutable_cf_options.max_compaction_bytes) {
+        inputs[0].files.push_back(cur_file);
+        compaction_size += cur_file->fd.GetFileSize();
+        ROCKS_LOG_BUFFER(
+            log_buffer,
+            "[%s] FIFO compaction: picking file %" PRIu64
+            " with next file's oldest time %" PRIu64 " for temperature %s.",
+            cf_name.c_str(), cur_file->fd.GetNumber(), oldest_ancestor_time,
+            temperature_to_string[cur_target_temp].c_str());
+      }
+      if (compaction_size > mutable_cf_options.max_compaction_bytes) {
         break;
-      } else {
-        assert(prev_file == nullptr);
       }
     }
   }
@@ -390,7 +417,7 @@ Compaction* FIFOCompactionPicker::PickCompactionToWarm(
       std::move(inputs), 0, 0 /* output file size limit */,
       0 /* max compaction bytes, not applicable */, 0 /* output path ID */,
       mutable_cf_options.compression, mutable_cf_options.compression_opts,
-      Temperature::kWarm,
+      compaction_target_temp,
       /* max_subcompactions */ 0, {}, /* is manual */ false, /* trim_ts */ "",
       vstorage->CompactionScore(0),
       /* is deletion compaction */ false, /* l0_files_might_overlap */ true,
@@ -412,8 +439,8 @@ Compaction* FIFOCompactionPicker::PickCompaction(
                            vstorage, log_buffer);
   }
   if (c == nullptr) {
-    c = PickCompactionToWarm(cf_name, mutable_cf_options, mutable_db_options,
-                             vstorage, log_buffer);
+    c = PickTemperatureChangeCompaction(
+        cf_name, mutable_cf_options, mutable_db_options, vstorage, log_buffer);
   }
   RegisterCompaction(c);
   return c;

db/compaction/compaction_picker_fifo.h

@@ -52,10 +52,9 @@ class FIFOCompactionPicker : public CompactionPicker {
                                  VersionStorageInfo* version,
                                  LogBuffer* log_buffer);
 
-  Compaction* PickCompactionToWarm(const std::string& cf_name,
-                                   const MutableCFOptions& mutable_cf_options,
-                                   const MutableDBOptions& mutable_db_options,
-                                   VersionStorageInfo* version,
-                                   LogBuffer* log_buffer);
+  Compaction* PickTemperatureChangeCompaction(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
+      LogBuffer* log_buffer);
 };
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_picker_test.cc

@@ -70,6 +70,11 @@ class CompactionPickerTestBase : public testing::Test {
     mutable_cf_options_.RefreshDerivedOptions(ioptions_);
     ioptions_.cf_paths.emplace_back("dummy",
                                     std::numeric_limits<uint64_t>::max());
+    // When the default value of this option is true, universal compaction
+    // tests can encounter assertion failure since SanitizeOption() is
+    // not run to set this option to false. So we do the sanitization
+    // here. Tests that test this option set this option to true explicitly.
+    ioptions_.level_compaction_dynamic_level_bytes = false;
   }
 
   ~CompactionPickerTestBase() override {}
@@ -79,7 +84,8 @@ class CompactionPickerTestBase : public testing::Test {
     options_.num_levels = num_levels;
     vstorage_.reset(new VersionStorageInfo(
         &icmp_, ucmp_, options_.num_levels, style, nullptr, false,
-        EpochNumberRequirement::kMustPresent));
+        EpochNumberRequirement::kMustPresent, ioptions_.clock,
+        options_.bottommost_file_compaction_delay));
     vstorage_->PrepareForVersionAppend(ioptions_, mutable_cf_options_);
   }
 
@@ -88,7 +94,8 @@ class CompactionPickerTestBase : public testing::Test {
   void AddVersionStorage() {
     temp_vstorage_.reset(new VersionStorageInfo(
         &icmp_, ucmp_, options_.num_levels, ioptions_.compaction_style,
-        vstorage_.get(), false, EpochNumberRequirement::kMustPresent));
+        vstorage_.get(), false, EpochNumberRequirement::kMustPresent,
+        ioptions_.clock, options_.bottommost_file_compaction_delay));
   }
 
   void DeleteVersionStorage() {
@@ -148,7 +155,8 @@ class CompactionPickerTestBase : public testing::Test {
         smallest_seq, largest_seq, marked_for_compact, temperature,
         kInvalidBlobFileNumber, kUnknownOldestAncesterTime,
         kUnknownFileCreationTime, epoch_number, kUnknownFileChecksum,
-        kUnknownFileChecksumFuncName, kNullUniqueId64x2, 0);
+        kUnknownFileChecksumFuncName, kNullUniqueId64x2, 0, 0,
+        true /* user_defined_timestamps_persisted */);
     f->compensated_file_size =
         (compensated_file_size != 0) ? compensated_file_size : file_size;
     f->oldest_ancester_time = oldest_ancestor_time;
@@ -505,7 +513,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
 
 TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
   const uint64_t kFileSize = 100000;
-  NewVersionStorage(1, kCompactionStyleUniversal);
+  NewVersionStorage(3 /* num_levels */, kCompactionStyleUniversal);
   ioptions_.allow_ingest_behind = true;
   ioptions_.num_levels = 3;
   UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
@@ -532,6 +540,14 @@ TEST_F(CompactionPickerTest, CompactionUniversalIngestBehindReservedLevel) {
 
   // output level should be the one above the bottom-most
   ASSERT_EQ(1, compaction->output_level());
+
+  // input should not include the reserved level
+  const std::vector<CompactionInputFiles>* inputs = compaction->inputs();
+  for (const auto& compaction_input : *inputs) {
+    if (!compaction_input.empty()) {
+      ASSERT_LT(compaction_input.level, 2);
+    }
+  }
 }
 // Tests if the files can be trivially moved in multi level
 // universal compaction when allow_trivial_move option is set
@@ -1005,29 +1021,28 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   }
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarm1) {
+TEST_F(CompactionPickerTest, FIFOToCold1) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
   int64_t current_time = 0;
   ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
   uint64_t threshold_time =
-      static_cast<uint64_t>(current_time) - kWarmThreshold;
-  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
-      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
-  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
-      Temperature::kUnknown, threshold_time + 100);
-  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
-      Temperature::kUnknown, threshold_time - 2000);
+      static_cast<uint64_t>(current_time) - kColdThreshold;
+  Add(0 /* level */, 4U /* file_number */, "260", "300", 1 * kFileSize, 0, 2500,
+      2600, 0, true, Temperature::kUnknown,
+      threshold_time - 2000 /* oldest_ancestor_time */);
+  // Qualifies for compaction to kCold.
   Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
       Temperature::kUnknown, threshold_time - 3000);
   UpdateVersionStorageInfo();
@@ -1037,33 +1052,36 @@ TEST_F(CompactionPickerTest, FIFOToWarm1) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(1U, compaction->num_input_files(0));
   ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarm2) {
+TEST_F(CompactionPickerTest, FIFOToCold2) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
   int64_t current_time = 0;
   ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
   uint64_t threshold_time =
-      static_cast<uint64_t>(current_time) - kWarmThreshold;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
       Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
-  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
-      Temperature::kUnknown, threshold_time + 100);
   Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
-      Temperature::kUnknown, threshold_time - 2000);
+      Temperature::kUnknown, threshold_time);
+  // The following two files qualify for compaction to kCold.
   Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
       Temperature::kUnknown, threshold_time - 3000);
   Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
@@ -1075,34 +1093,40 @@ TEST_F(CompactionPickerTest, FIFOToWarm2) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(2U, compaction->num_input_files(0));
   ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
   ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarmMaxSize) {
+TEST_F(CompactionPickerTest, FIFOToColdMaxCompactionSize) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   mutable_cf_options_.max_compaction_bytes = kFileSize * 9;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
   int64_t current_time = 0;
   ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
   uint64_t threshold_time =
-      static_cast<uint64_t>(current_time) - kWarmThreshold;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
       Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
   Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
       Temperature::kUnknown, threshold_time + 100);
   Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
       Temperature::kUnknown, threshold_time - 2000);
+  // The following two files qualify for compaction to kCold.
+  // But only the last two should be included to respect `max_compaction_bytes`.
   Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
       Temperature::kUnknown, threshold_time - 3000);
   Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
@@ -1116,40 +1140,45 @@ TEST_F(CompactionPickerTest, FIFOToWarmMaxSize) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(2U, compaction->num_input_files(0));
   ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
   ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarmWithExistingWarm) {
+TEST_F(CompactionPickerTest, FIFOToColdWithExistingCold) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
   int64_t current_time = 0;
   ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
   uint64_t threshold_time =
-      static_cast<uint64_t>(current_time) - kWarmThreshold;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
       Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
   Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
       Temperature::kUnknown, threshold_time + 100);
   Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
       Temperature::kUnknown, threshold_time - 2000);
+  // The following two files qualify for compaction to kCold.
   Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
       Temperature::kUnknown, threshold_time - 3000);
   Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
       Temperature::kUnknown, threshold_time - 4000);
   Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
-      Temperature::kWarm, threshold_time - 5000);
+      Temperature::kCold, threshold_time - 5000);
   UpdateVersionStorageInfo();
 
   ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
@@ -1157,28 +1186,32 @@ TEST_F(CompactionPickerTest, FIFOToWarmWithExistingWarm) {
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_files(0));
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->num_input_files(0));
   ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, FIFOToWarmWithOngoing) {
+TEST_F(CompactionPickerTest, FIFOToColdWithHotBetweenCold) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const uint64_t kFileSize = 100000;
   const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
+  uint64_t kColdThreshold = 2000;
 
   fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kCold, kColdThreshold}};
   mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
   mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
 
   int64_t current_time = 0;
   ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
   uint64_t threshold_time =
-      static_cast<uint64_t>(current_time) - kWarmThreshold;
+      static_cast<uint64_t>(current_time) - kColdThreshold;
   Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
       Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
   Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
@@ -1186,63 +1219,77 @@ TEST_F(CompactionPickerTest, FIFOToWarmWithOngoing) {
   Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
       Temperature::kUnknown, threshold_time - 2000);
   Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
-      Temperature::kUnknown, threshold_time - 3000);
+      Temperature::kCold, threshold_time - 3000);
+  // Qualifies for compaction to kCold.
   Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
       Temperature::kUnknown, threshold_time - 4000);
   Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
-      Temperature::kWarm, threshold_time - 5000);
-  file_map_[2].first->being_compacted = true;
+      Temperature::kCold, threshold_time - 5000);
   UpdateVersionStorageInfo();
 
   ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
   std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
       cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
       &log_buffer_));
-  // Stop if a file is being compacted
-  ASSERT_TRUE(compaction.get() == nullptr);
-}
-
-TEST_F(CompactionPickerTest, FIFOToWarmWithHotBetweenWarms) {
-  NewVersionStorage(1, kCompactionStyleFIFO);
-  const uint64_t kFileSize = 100000;
-  const uint64_t kMaxSize = kFileSize * 100000;
-  uint64_t kWarmThreshold = 2000;
-
-  fifo_options_.max_table_files_size = kMaxSize;
-  fifo_options_.age_for_warm = kWarmThreshold;
-  mutable_cf_options_.compaction_options_fifo = fifo_options_;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
-  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
-  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
-
-  int64_t current_time = 0;
-  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
-  uint64_t threshold_time =
-      static_cast<uint64_t>(current_time) - kWarmThreshold;
-  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
-      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
-  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
-      Temperature::kUnknown, threshold_time + 100);
-  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
-      Temperature::kUnknown, threshold_time - 2000);
-  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
-      Temperature::kWarm, threshold_time - 3000);
-  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
-      Temperature::kUnknown, threshold_time - 4000);
-  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
-      Temperature::kWarm, threshold_time - 5000);
-  UpdateVersionStorageInfo();
-
-  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
-  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
-      &log_buffer_));
-  // Stop if a file is being compacted
   ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kCold);
   ASSERT_EQ(1U, compaction->num_input_files(0));
   ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
 }
 
+TEST_F(CompactionPickerTest, FIFOToColdAndWarm) {
+  NewVersionStorage(1, kCompactionStyleFIFO);
+  const uint64_t kFileSize = 100000;
+  const uint64_t kMaxSize = kFileSize * 100000;
+  uint64_t kWarmThreshold = 10000;
+  uint64_t kHotThreshold = 2000;
+
+  fifo_options_.max_table_files_size = kMaxSize;
+  // Test that multiple threshold works.
+  fifo_options_.file_temperature_age_thresholds = {
+      {Temperature::kHot, kHotThreshold}, {Temperature::kWarm, kWarmThreshold}};
+  mutable_cf_options_.compaction_options_fifo = fifo_options_;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 100;
+  mutable_cf_options_.max_compaction_bytes = kFileSize * 100;
+  FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
+  int64_t current_time = 0;
+  ASSERT_OK(Env::Default()->GetCurrentTime(&current_time));
+  uint64_t hot_threshold_time =
+      static_cast<uint64_t>(current_time) - kHotThreshold;
+  uint64_t warm_threshold_time =
+      static_cast<uint64_t>(current_time) - kWarmThreshold;
+  Add(0, 6U, "240", "290", 2 * kFileSize, 0, 2900, 3000, 0, true,
+      Temperature::kUnknown, static_cast<uint64_t>(current_time) - 100);
+  Add(0, 5U, "240", "290", 2 * kFileSize, 0, 2700, 2800, 0, true,
+      Temperature::kUnknown, hot_threshold_time + 100);
+  Add(0, 4U, "260", "300", 1 * kFileSize, 0, 2500, 2600, 0, true,
+      Temperature::kUnknown, hot_threshold_time - 200);
+  // Qualifies for Hot
+  Add(0, 3U, "200", "300", 4 * kFileSize, 0, 2300, 2400, 0, true,
+      Temperature::kUnknown, warm_threshold_time - 100);
+  // Qualifies for Warm
+  Add(0, 2U, "200", "300", 4 * kFileSize, 0, 2100, 2200, 0, true,
+      Temperature::kUnknown, warm_threshold_time - 4000);
+  Add(0, 1U, "200", "300", 4 * kFileSize, 0, 2000, 2100, 0, true,
+      Temperature::kUnknown, warm_threshold_time - 5000);
+  UpdateVersionStorageInfo();
+
+  ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), true);
+  std::unique_ptr<Compaction> compaction(fifo_compaction_picker.PickCompaction(
+      cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
+      &log_buffer_));
+  ASSERT_TRUE(compaction.get() != nullptr);
+  ASSERT_EQ(compaction->compaction_reason(),
+            CompactionReason::kChangeTemperature);
+  // Assumes compaction picker picks older files first.
+  ASSERT_EQ(compaction->output_temperature(), Temperature::kWarm);
+  ASSERT_EQ(2U, compaction->num_input_files(0));
+  ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
+}
 
 TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
   NewVersionStorage(6, kCompactionStyleLevel);
@@ -1923,6 +1970,15 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys11) {
   ASSERT_EQ(7U, compaction->input(1, 0)->fd.GetNumber());
 }
 
+TEST_F(CompactionPickerTest, FileTtlBoosterLargeNumLevels) {
+  const uint64_t kCurrentTime = 1000000;
+  FileTtlBooster booster(kCurrentTime, /*ttl=*/2048,
+                         /*num_non_empty_levels=*/100, /*level=*/1);
+  FileMetaData meta;
+  meta.oldest_ancester_time = kCurrentTime - 1023;
+  ASSERT_EQ(1, booster.GetBoostScore(&meta));
+}
+
 TEST_F(CompactionPickerTest, FileTtlBooster) {
   // Set TTL to 2048
   // TTL boosting for all levels starts at 1024,

db/compaction/compaction_picker_universal.cc

@@ -19,7 +19,7 @@
 #include "file/filename.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
-#include "monitoring/statistics.h"
+#include "monitoring/statistics_impl.h"
 #include "test_util/sync_point.h"
 #include "util/random.h"
 #include "util/string_util.h"
@@ -133,8 +133,8 @@ class UniversalCompactionBuilder {
   UniversalCompactionPicker* picker_;
   LogBuffer* log_buffer_;
 
-  static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage);
+  static std::vector<UniversalCompactionBuilder::SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, int last_level);
 
   // Pick a path ID to place a newly generated file, with its estimated file
   // size.
@@ -339,13 +339,13 @@ void UniversalCompactionBuilder::SortedRun::DumpSizeInfo(
 
 std::vector<UniversalCompactionBuilder::SortedRun>
 UniversalCompactionBuilder::CalculateSortedRuns(
-    const VersionStorageInfo& vstorage) {
+    const VersionStorageInfo& vstorage, int last_level) {
   std::vector<UniversalCompactionBuilder::SortedRun> ret;
   for (FileMetaData* f : vstorage.LevelFiles(0)) {
     ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
                      f->being_compacted);
   }
-  for (int level = 1; level < vstorage.num_levels(); level++) {
+  for (int level = 1; level <= last_level; level++) {
     uint64_t total_compensated_size = 0U;
     uint64_t total_size = 0U;
     bool being_compacted = false;
@@ -374,7 +374,9 @@ UniversalCompactionBuilder::CalculateSortedRuns(
 Compaction* UniversalCompactionBuilder::PickCompaction() {
   const int kLevel0 = 0;
   score_ = vstorage_->CompactionScore(kLevel0);
-  sorted_runs_ = CalculateSortedRuns(*vstorage_);
+  int max_output_level =
+      vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
+  sorted_runs_ = CalculateSortedRuns(*vstorage_, max_output_level);
 
   if (sorted_runs_.size() == 0 ||
       (vstorage_->FilesMarkedForPeriodicCompaction().empty() &&
@@ -471,6 +473,8 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
         "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
     return nullptr;
   }
+  assert(c->output_level() <=
+         vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind));
 
   if (mutable_cf_options_.compaction_options_universal.allow_trivial_move ==
           true &&
@@ -698,22 +702,18 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
   int start_level = sorted_runs_[start_index].level;
   int output_level;
+  // last level is reserved for the files ingested behind
+  int max_output_level =
+      vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
   if (first_index_after == sorted_runs_.size()) {
-    output_level = vstorage_->num_levels() - 1;
+    output_level = max_output_level;
   } else if (sorted_runs_[first_index_after].level == 0) {
     output_level = 0;
   } else {
     output_level = sorted_runs_[first_index_after].level - 1;
   }
 
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind &&
-      (output_level == vstorage_->num_levels() - 1)) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  std::vector<CompactionInputFiles> inputs(max_output_level + 1);
   for (size_t i = 0; i < inputs.size(); ++i) {
     inputs[i].level = start_level + static_cast<int>(i);
   }
@@ -1192,8 +1192,10 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
       return nullptr;
     }
 
+    int max_output_level =
+        vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
     // Pick the first non-empty level after the start_level
-    for (output_level = start_level + 1; output_level < vstorage_->num_levels();
+    for (output_level = start_level + 1; output_level <= max_output_level;
          output_level++) {
       if (vstorage_->NumLevelFiles(output_level) != 0) {
         break;
@@ -1201,9 +1203,9 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
     }
 
     // If all higher levels are empty, pick the highest level as output level
-    if (output_level == vstorage_->num_levels()) {
+    if (output_level > max_output_level) {
       if (start_level == 0) {
-        output_level = vstorage_->num_levels() - 1;
+        output_level = max_output_level;
       } else {
         // If start level is non-zero and all higher levels are empty, this
         // compaction will translate into a trivial move. Since the idea is
@@ -1212,11 +1214,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
         return nullptr;
       }
     }
-    if (ioptions_.allow_ingest_behind &&
-        output_level == vstorage_->num_levels() - 1) {
-      assert(output_level > 1);
-      output_level--;
-    }
+    assert(output_level <= max_output_level);
 
     if (output_level != 0) {
       if (start_level == 0) {
@@ -1293,8 +1291,9 @@ Compaction* UniversalCompactionBuilder::PickCompactionWithSortedRunRange(
   uint32_t path_id =
       GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
   int start_level = sorted_runs_[start_index].level;
-
-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  int max_output_level =
+      vstorage_->MaxOutputLevel(ioptions_.allow_ingest_behind);
+  std::vector<CompactionInputFiles> inputs(max_output_level + 1);
   for (size_t i = 0; i < inputs.size(); ++i) {
     inputs[i].level = start_level + static_cast<int>(i);
   }
@@ -1331,13 +1330,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionWithSortedRunRange(
 
   int output_level;
   if (end_index == sorted_runs_.size() - 1) {
-    // output files at the last level, unless it's reserved
-    output_level = vstorage_->num_levels() - 1;
-    // last level is reserved for the files ingested behind
-    if (ioptions_.allow_ingest_behind) {
-      assert(output_level > 1);
-      output_level--;
-    }
+    output_level = max_output_level;
   } else {
     // if it's not including all sorted_runs, it can only output to the level
     // above the `end_index + 1` sorted_run.

db/compaction/compaction_service_test.cc

@@ -928,7 +928,7 @@ TEST_F(CompactionServiceTest, TablePropertiesCollector) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   ASSERT_OK(db_->GetPropertiesOfAllTables(&fname_to_props));
 
@@ -952,4 +952,3 @@ int main(int argc, char** argv) {
   RegisterCustomObjects(argc, argv);
   return RUN_ALL_TESTS();
 }
-

db/compaction/file_pri.h

@@ -53,8 +53,10 @@ class FileTtlBooster {
       enabled_ = true;
       uint64_t all_boost_start_age = ttl / 2;
       uint64_t all_boost_age_range = (ttl / 32) * 31 - all_boost_start_age;
+      // TODO(cbi): more reasonable algorithm that gives different values
+      //   when num_non_empty_levels - level - 1 > 63.
       uint64_t boost_age_range =
-          all_boost_age_range >> (num_non_empty_levels - level - 1);
+          all_boost_age_range >> std::min(63, num_non_empty_levels - level - 1);
       boost_age_start_ = all_boost_start_age + boost_age_range;
       const uint64_t kBoostRatio = 16;
       // prevent 0 value to avoid divide 0 error.

db/compaction/tiered_compaction_test.cc

@@ -209,7 +209,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageUniversal) {
     seq_history.emplace_back(dbfull()->GetLatestSequenceNumber());
     expect_stats[0].Add(kBasicFlushStats);
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // the penultimate level file temperature is not cold, all data are output to
   // the penultimate level.
@@ -374,7 +374,7 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageUniversal) {
     ASSERT_OK(Flush());
     expect_stats[0].Add(kBasicFlushStats);
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,1,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -445,8 +445,8 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageUniversal) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(
-      true));  // make sure the compaction is able to finish
+  // make sure the compaction is able to finish
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,1,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -911,7 +911,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     ASSERT_OK(Flush());
     expect_stats[0].Add(kBasicFlushStats);
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // non last level is hot
   ASSERT_EQ("0,1", FilesPerLevel());
@@ -954,7 +954,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     ASSERT_OK(Flush());
     seq_history.emplace_back(dbfull()->GetLatestSequenceNumber());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,1,0,0,0,0,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -1005,7 +1005,7 @@ TEST_P(TieredCompactionTest, SequenceBasedTieredStorageLevel) {
     ASSERT_OK(Flush());
     seq_history.emplace_back(dbfull()->GetLatestSequenceNumber());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   latest_cold_seq = seq_history[0];
   ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
@@ -1135,7 +1135,7 @@ TEST_P(TieredCompactionTest, RangeBasedTieredStorageLevel) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,1,1", FilesPerLevel());
   ASSERT_GT(GetSstSizeHelper(Temperature::kUnknown), 0);
   ASSERT_GT(GetSstSizeHelper(Temperature::kCold), 0);
@@ -1265,7 +1265,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimeManualCompaction) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1327,7 +1327,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimeAutoCompaction) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1360,7 +1360,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimeAutoCompaction) {
       });
     }
     ASSERT_OK(Flush());
-    ASSERT_OK(dbfull()->WaitForCompact(true));
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
   }
 
   // all data is moved up to the penultimate level
@@ -1403,7 +1403,7 @@ TEST_F(PrecludeLastLevelTest, MigrationFromPreserveTimePartial) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1530,7 +1530,7 @@ TEST_F(PrecludeLastLevelTest, LastLevelOnlyCompactionPartial) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1609,7 +1609,7 @@ TEST_P(PrecludeLastLevelTestWithParms, LastLevelOnlyCompactionNoPreclude) {
     }
     ASSERT_OK(Flush());
   }
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // all data is pushed to the last level
   ASSERT_EQ("0,0,0,0,0,0,1", FilesPerLevel());
@@ -1705,7 +1705,7 @@ TEST_P(PrecludeLastLevelTestWithParms, LastLevelOnlyCompactionNoPreclude) {
 
   manual_compaction_thread.join();
 
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   if (enable_preclude_last_level) {
     ASSERT_NE("0,0,0,0,0,1,1", FilesPerLevel());
@@ -1841,7 +1841,7 @@ TEST_P(PrecludeLastLevelTestWithParms, PeriodicCompactionToPenultimateLevel) {
   }
   ASSERT_OK(Flush());
 
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   stop_token.reset();
 
@@ -1940,7 +1940,7 @@ TEST_F(PrecludeLastLevelTest, PartialPenultimateLevelCompaction) {
     ASSERT_OK(Flush());
   }
 
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   // L5: [0,19] [20,39] [40,299]
   // L6: [0,                299]
@@ -2106,7 +2106,7 @@ TEST_F(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   Slice begin_key(begin_key_buf), end_key(end_key_buf);
   ASSERT_OK(db_->SuggestCompactRange(db_->DefaultColumnFamily(), &begin_key,
                                      &end_key));
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,3,3", FilesPerLevel());
   ASSERT_EQ(1, per_key_comp_num);
   verify_db();
@@ -2116,7 +2116,7 @@ TEST_F(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   db_->ReleaseSnapshot(snap2);
   ASSERT_OK(db_->SuggestCompactRange(db_->DefaultColumnFamily(), &begin_key,
                                      &end_key));
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,3,3", FilesPerLevel());
   ASSERT_EQ(2, per_key_comp_num);
   verify_db();
@@ -2126,7 +2126,7 @@ TEST_F(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   db_->ReleaseSnapshot(snap1);
   ASSERT_OK(db_->SuggestCompactRange(db_->DefaultColumnFamily(), &begin_key,
                                      &end_key));
-  ASSERT_OK(dbfull()->WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,0,0,0,0,2,3", FilesPerLevel());
   ASSERT_EQ(3, per_key_comp_num);
   verify_db();

db/comparator_db_test.cc

@@ -77,7 +77,7 @@ void DoRandomIteraratorTest(DB* db, std::vector<std::string> source_strings,
 
   for (int i = 0; i < num_writes; i++) {
     if (num_trigger_flush > 0 && i != 0 && i % num_trigger_flush == 0) {
-      db->Flush(FlushOptions());
+      ASSERT_OK(db->Flush(FlushOptions()));
     }
 
     int type = rnd->Uniform(2);
@@ -156,6 +156,7 @@ void DoRandomIteraratorTest(DB* db, std::vector<std::string> source_strings,
         if (map.find(key) == map.end()) {
           ASSERT_TRUE(status.IsNotFound());
         } else {
+          ASSERT_OK(status);
           ASSERT_EQ(map[key], result);
         }
         break;

db/convenience.cc

@@ -7,6 +7,7 @@
 
 #include "rocksdb/convenience.h"
 
+#include "db/convenience_impl.h"
 #include "db/db_impl/db_impl.h"
 #include "util/cast_util.h"
 
@@ -39,9 +40,25 @@ Status VerifySstFileChecksum(const Options& options,
 }
 Status VerifySstFileChecksum(const Options& options,
                              const EnvOptions& env_options,
-                             const ReadOptions& read_options,
+                             const ReadOptions& _read_options,
                              const std::string& file_path,
                              const SequenceNumber& largest_seqno) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown) {
+    return Status::InvalidArgument(
+        "Can only call VerifySstFileChecksum with `ReadOptions::io_activity` "
+        "is "
+        "`Env::IOActivity::kUnknown`");
+  }
+  ReadOptions read_options(_read_options);
+  return VerifySstFileChecksumInternal(options, env_options, read_options,
+                                       file_path, largest_seqno);
+}
+
+Status VerifySstFileChecksumInternal(const Options& options,
+                                     const EnvOptions& env_options,
+                                     const ReadOptions& read_options,
+                                     const std::string& file_path,
+                                     const SequenceNumber& largest_seqno) {
   std::unique_ptr<FSRandomAccessFile> file;
   uint64_t file_size;
   InternalKeyComparator internal_comparator(options.comparator);
@@ -64,12 +81,12 @@ Status VerifySstFileChecksum(const Options& options,
   const bool kImmortal = true;
   auto reader_options = TableReaderOptions(
       ioptions, options.prefix_extractor, env_options, internal_comparator,
-      false /* skip_filters */, !kImmortal, false /* force_direct_prefetch */,
-      -1 /* level */);
+      options.block_protection_bytes_per_key, false /* skip_filters */,
+      !kImmortal, false /* force_direct_prefetch */, -1 /* level */);
   reader_options.largest_seqno = largest_seqno;
   s = ioptions.table_factory->NewTableReader(
-      reader_options, std::move(file_reader), file_size, &table_reader,
-      false /* prefetch_index_and_filter_in_cache */);
+      read_options, reader_options, std::move(file_reader), file_size,
+      &table_reader, false /* prefetch_index_and_filter_in_cache */);
   if (!s.ok()) {
     return s;
   }

db/convenience_impl.h

@@ -0,0 +1,15 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+#include "rocksdb/db.h"
+
+namespace ROCKSDB_NAMESPACE {
+Status VerifySstFileChecksumInternal(const Options& options,
+                                     const EnvOptions& env_options,
+                                     const ReadOptions& read_options,
+                                     const std::string& file_path,
+                                     const SequenceNumber& largest_seqno = 0);
+}  // namespace ROCKSDB_NAMESPACE

db/corruption_test.cc

@@ -450,6 +450,7 @@ TEST_F(CorruptionTest, TableFile) {
 
 TEST_F(CorruptionTest, VerifyChecksumReadahead) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   SpecialEnv senv(base_env_);
   options.env = &senv;
   // Disable block cache as we are going to check checksum for
@@ -503,6 +504,7 @@ TEST_F(CorruptionTest, VerifyChecksumReadahead) {
 
 TEST_F(CorruptionTest, TableFileIndexData) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   // very big, we'll trigger flushes manually
   options.write_buffer_size = 100 * 1024 * 1024;
   Reopen(&options);
@@ -659,6 +661,7 @@ TEST_F(CorruptionTest, CorruptedDescriptor) {
 
 TEST_F(CorruptionTest, CompactionInputError) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   Reopen(&options);
   Build(10);
@@ -680,6 +683,7 @@ TEST_F(CorruptionTest, CompactionInputError) {
 
 TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_checks = true;
   options.write_buffer_size = 131072;
@@ -777,6 +781,7 @@ TEST_F(CorruptionTest, RangeDeletionCorrupted) {
 TEST_F(CorruptionTest, FileSystemStateCorrupted) {
   for (int iter = 0; iter < 2; ++iter) {
     Options options;
+    options.level_compaction_dynamic_level_bytes = false;
     options.env = env_.get();
     options.paranoid_checks = true;
     options.create_if_missing = true;
@@ -816,6 +821,7 @@ static const auto& corruption_modes = {
 
 TEST_F(CorruptionTest, ParanoidFileChecksOnFlush) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -844,6 +850,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksOnFlush) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksOnCompact) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_file_checks = true;
   options.create_if_missing = true;
@@ -877,6 +884,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksOnCompact) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeFirst) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -913,6 +921,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeFirst) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRange) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -952,6 +961,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRange) {
 
 TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeLast) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.check_flush_compaction_key_order = false;
   options.paranoid_file_checks = true;
@@ -988,6 +998,7 @@ TEST_F(CorruptionTest, ParanoidFileChecksWithDeleteRangeLast) {
 
 TEST_F(CorruptionTest, LogCorruptionErrorsInCompactionIterator) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.create_if_missing = true;
   options.allow_data_in_errors = true;
@@ -1017,6 +1028,7 @@ TEST_F(CorruptionTest, LogCorruptionErrorsInCompactionIterator) {
 
 TEST_F(CorruptionTest, CompactionKeyOrderCheck) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_file_checks = false;
   options.create_if_missing = true;
@@ -1044,6 +1056,7 @@ TEST_F(CorruptionTest, CompactionKeyOrderCheck) {
 
 TEST_F(CorruptionTest, FlushKeyOrderCheck) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   options.paranoid_file_checks = false;
   options.create_if_missing = true;
@@ -1097,6 +1110,7 @@ TEST_F(CorruptionTest, DisableKeyOrderCheck) {
 TEST_F(CorruptionTest, VerifyWholeTableChecksum) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.env = env_.get();
   ASSERT_OK(DestroyDB(dbname_, options));
   options.create_if_missing = true;
@@ -1182,6 +1196,7 @@ INSTANTIATE_TEST_CASE_P(CorruptionTest, CrashDuringRecoveryWithCorruptionTest,
 TEST_P(CrashDuringRecoveryWithCorruptionTest, CrashDuringRecovery) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.track_and_verify_wals_in_manifest =
       track_and_verify_wals_in_manifest_;
   options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
@@ -1354,6 +1369,7 @@ TEST_P(CrashDuringRecoveryWithCorruptionTest, CrashDuringRecovery) {
 TEST_P(CrashDuringRecoveryWithCorruptionTest, TxnDbCrashDuringRecovery) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
   options.track_and_verify_wals_in_manifest =
       track_and_verify_wals_in_manifest_;
@@ -1551,6 +1567,7 @@ TEST_P(CrashDuringRecoveryWithCorruptionTest, TxnDbCrashDuringRecovery) {
 TEST_P(CrashDuringRecoveryWithCorruptionTest, CrashDuringRecoveryWithFlush) {
   CloseDb();
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
   options.avoid_flush_during_recovery = false;
   options.env = env_.get();

db/cuckoo_table_db_test.cc

@@ -39,6 +39,7 @@ class CuckooTableDBTest : public testing::Test {
 
   Options CurrentOptions() {
     Options options;
+    options.level_compaction_dynamic_level_bytes = false;
     options.table_factory.reset(NewCuckooTableFactory());
     options.memtable_factory.reset(NewHashLinkListRepFactory(4, 0, 3, true));
     options.allow_mmap_reads = true;

db/db_basic_test.cc

@@ -1204,9 +1204,23 @@ TEST_F(DBBasicTest, DBClose) {
   delete db;
   ASSERT_EQ(env->GetCloseCount(), 2);
 
+  // close by WaitForCompact() with close_db option
+  options.create_if_missing = false;
+  s = DB::Open(options, dbname, &db);
+  ASSERT_OK(s);
+  ASSERT_TRUE(db != nullptr);
+  WaitForCompactOptions wait_for_compact_options = WaitForCompactOptions();
+  wait_for_compact_options.close_db = true;
+  s = db->WaitForCompact(wait_for_compact_options);
+  ASSERT_EQ(env->GetCloseCount(), 3);
+  // see TestLogger::CloseHelper()
+  ASSERT_EQ(s, Status::IOError());
+
+  delete db;
+  ASSERT_EQ(env->GetCloseCount(), 3);
+
   // Provide our own logger and ensure DB::Close() does not close it
   options.info_log.reset(new TestEnv::TestLogger(env));
-  options.create_if_missing = false;
   s = DB::Open(options, dbname, &db);
   ASSERT_OK(s);
   ASSERT_TRUE(db != nullptr);
@@ -1214,9 +1228,9 @@ TEST_F(DBBasicTest, DBClose) {
   s = db->Close();
   ASSERT_EQ(s, Status::OK());
   delete db;
-  ASSERT_EQ(env->GetCloseCount(), 2);
-  options.info_log.reset();
   ASSERT_EQ(env->GetCloseCount(), 3);
+  options.info_log.reset();
+  ASSERT_EQ(env->GetCloseCount(), 4);
 }
 
 TEST_F(DBBasicTest, DBCloseAllDirectoryFDs) {

db/db_block_cache_test.cc

@@ -620,9 +620,9 @@ class MockCache : public LRUCache {
   static uint32_t low_pri_insert_count;
 
   MockCache()
-      : LRUCache((size_t)1 << 25 /*capacity*/, 0 /*num_shard_bits*/,
-                 false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/,
-                 0.0 /*low_pri_pool_ratio*/) {}
+      : LRUCache(LRUCacheOptions(
+            size_t{1} << 25 /*capacity*/, 0 /*num_shard_bits*/,
+            false /*strict_capacity_limit*/, 0.0 /*high_pri_pool_ratio*/)) {}
 
   using ShardedCache::Insert;
 
@@ -741,10 +741,15 @@ TEST_F(DBBlockCacheTest, AddRedundantStats) {
   int iterations_tested = 0;
   for (std::shared_ptr<Cache> base_cache :
        {NewLRUCache(capacity, num_shard_bits),
+        // FixedHyperClockCache
         HyperClockCacheOptions(
             capacity,
             BlockBasedTableOptions().block_size /*estimated_value_size*/,
             num_shard_bits)
+            .MakeSharedCache(),
+        // AutoHyperClockCache
+        HyperClockCacheOptions(capacity, 0 /*estimated_value_size*/,
+                               num_shard_bits)
             .MakeSharedCache()}) {
     if (!base_cache) {
       // Skip clock cache when not supported
@@ -979,12 +984,14 @@ TEST_F(DBBlockCacheTest, CacheEntryRoleStats) {
   const size_t capacity = size_t{1} << 25;
   int iterations_tested = 0;
   for (bool partition : {false, true}) {
+    SCOPED_TRACE("Partition? " + std::to_string(partition));
     for (std::shared_ptr<Cache> cache :
          {NewLRUCache(capacity),
           HyperClockCacheOptions(
               capacity,
               BlockBasedTableOptions().block_size /*estimated_value_size*/)
               .MakeSharedCache()}) {
+      SCOPED_TRACE(std::string("Cache: ") + cache->Name());
       ++iterations_tested;
 
       Options options = CurrentOptions();
@@ -1278,6 +1285,7 @@ TEST_F(DBBlockCacheTest, HyperClockCacheReportProblems) {
   HyperClockCacheOptions hcc_opts{capacity, value_size_est};
   hcc_opts.num_shard_bits = 2;  // 4 shards
   hcc_opts.metadata_charge_policy = kDontChargeCacheMetadata;
+  hcc_opts.hash_seed = 0;  // deterministic hashing
   std::shared_ptr<Cache> cache = hcc_opts.MakeSharedCache();
   std::shared_ptr<CountingLogger> logger = std::make_shared<CountingLogger>();
 

db/db_clip_test.cc

@@ -0,0 +1,142 @@
+//  Copyright (c) Meta Platforms, Inc. and affiliates.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/db_test_util.h"
+#include "port/port.h"
+#include "util/random.h"
+
+namespace ROCKSDB_NAMESPACE {
+
+class DBClipTest : public DBTestBase {
+ public:
+  DBClipTest() : DBTestBase("db_clip_test", /*env_do_fsync=*/true) {}
+};
+
+TEST_F(DBClipTest, TestClipRange) {
+  Options options = CurrentOptions();
+  options.write_buffer_size = 10 * 1024 * 1024;
+  options.max_bytes_for_level_multiplier = 2;
+  options.num_levels = 3;
+  options.max_background_compactions = 3;
+  options.disable_auto_compactions = true;
+  options.statistics = CreateDBStatistics();
+
+  DestroyAndReopen(options);
+  int32_t value_size = 10 * 1024;  // 10 KB
+
+  Random rnd(301);
+  std::map<int32_t, std::string> values;
+
+  // file [0 => 100), [100 => 200), ... [900, 1000)
+  for (auto i = 0; i < 10; i++) {
+    for (auto j = 0; j < 100; j++) {
+      auto k = i * 100 + j;
+      values[k] = rnd.RandomString(value_size);
+      ASSERT_OK(Put(Key(k), values[k]));
+    }
+    ASSERT_OK(Flush());
+  }
+  ASSERT_EQ("10", FilesPerLevel(0));
+  auto begin_key = Key(251), end_key = Key(751);
+  ASSERT_OK(
+      db_->ClipColumnFamily(db_->DefaultColumnFamily(), begin_key, end_key));
+
+  for (auto i = 0; i < 251; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+  for (auto i = 251; i < 751; i++) {
+    ASSERT_EQ(Get(Key(i)), values[i]);
+  }
+  for (auto i = 751; i < 1000; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+
+  std::vector<LiveFileMetaData> all_metadata;
+  db_->GetLiveFilesMetaData(&all_metadata);
+  for (auto& md : all_metadata) {
+    // make sure clip_begin_key <= file_smallestkey <= file_largestkey <=
+    // clip_end_key
+    bool in_range = false;
+
+    if (options.comparator->Compare(begin_key, md.smallestkey) <= 0 &&
+        options.comparator->Compare(end_key, md.largestkey) > 0) {
+      in_range = true;
+    }
+    ASSERT_TRUE(in_range);
+  }
+
+  CompactRangeOptions compact_options;
+  compact_options.change_level = true;
+  compact_options.target_level = 2;
+  ASSERT_OK(db_->CompactRange(compact_options, nullptr, nullptr));
+  ASSERT_EQ("0,0,3", FilesPerLevel(0));
+
+  for (auto i = 0; i < 10; i += 2) {
+    for (auto j = 0; j < 100; j++) {
+      auto k = i * 100 + j;
+      ASSERT_OK(Put(Key(k), values[k]));
+    }
+    ASSERT_OK(Flush());
+  }
+  ASSERT_EQ("5,0,3", FilesPerLevel(0));
+  ASSERT_OK(dbfull()->TEST_CompactRange(0, nullptr, nullptr));
+  ASSERT_EQ("0,5,3", FilesPerLevel(0));
+
+  for (auto i = 1; i < 10; i += 2) {
+    for (auto j = 0; j < 100; j++) {
+      auto k = i * 100 + j;
+      ASSERT_OK(Put(Key(k), values[k]));
+    }
+    ASSERT_OK(Flush());
+  }
+  ASSERT_EQ("5,5,3", FilesPerLevel(0));
+
+  auto begin_key_2 = Key(222), end_key_2 = Key(888);
+
+  ASSERT_OK(db_->ClipColumnFamily(db_->DefaultColumnFamily(), begin_key_2,
+                                  end_key_2));
+
+  for (auto i = 0; i < 222; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+  for (auto i = 222; i < 888; i++) {
+    ASSERT_EQ(Get(Key(i)), values[i]);
+  }
+  for (auto i = 888; i < 1000; i++) {
+    ReadOptions ropts;
+    std::string result;
+    auto s = db_->Get(ropts, Key(i), &result);
+    ASSERT_TRUE(s.IsNotFound());
+  }
+
+  std::vector<LiveFileMetaData> all_metadata_2;
+  db_->GetLiveFilesMetaData(&all_metadata_2);
+  for (auto& md : all_metadata_2) {
+    // make sure clip_begin_key <= file_smallestkey <= file_largestkey <=
+    // clip_end_key
+    bool in_range = false;
+    if (begin_key_2.compare(md.smallestkey) <= 0 &&
+        end_key_2.compare(md.largestkey) > 0) {
+      in_range = true;
+    }
+    ASSERT_TRUE(in_range);
+  }
+}
+}  // namespace ROCKSDB_NAMESPACE
+
+int main(int argc, char** argv) {
+  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}

db/db_compaction_test.cc

@@ -153,6 +153,56 @@ class DBCompactionDirectIOTest : public DBCompactionTest,
   DBCompactionDirectIOTest() : DBCompactionTest() {}
 };
 
+// Params: See WaitForCompactOptions for details
+class DBCompactionWaitForCompactTest
+    : public DBTestBase,
+      public testing::WithParamInterface<
+          std::tuple<bool, bool, bool, std::chrono::microseconds>> {
+ public:
+  DBCompactionWaitForCompactTest()
+      : DBTestBase("db_compaction_test", /*env_do_fsync=*/true) {
+    abort_on_pause_ = std::get<0>(GetParam());
+    flush_ = std::get<1>(GetParam());
+    close_db_ = std::get<2>(GetParam());
+    timeout_ = std::get<3>(GetParam());
+  }
+  bool abort_on_pause_;
+  bool flush_;
+  bool close_db_;
+  std::chrono::microseconds timeout_;
+  Options options_;
+  WaitForCompactOptions wait_for_compact_options_;
+
+  void SetUp() override {
+    // This test sets up a scenario that one more L0 file will trigger a
+    // compaction
+    const int kNumKeysPerFile = 4;
+    const int kNumFiles = 2;
+
+    options_ = CurrentOptions();
+    options_.level0_file_num_compaction_trigger = kNumFiles + 1;
+
+    wait_for_compact_options_ = WaitForCompactOptions();
+    wait_for_compact_options_.abort_on_pause = abort_on_pause_;
+    wait_for_compact_options_.flush = flush_;
+    wait_for_compact_options_.close_db = close_db_;
+    wait_for_compact_options_.timeout = timeout_;
+
+    DestroyAndReopen(options_);
+
+    Random rnd(301);
+    for (int i = 0; i < kNumFiles; ++i) {
+      for (int j = 0; j < kNumKeysPerFile; ++j) {
+        ASSERT_OK(
+            Put(Key(i * kNumKeysPerFile + j), rnd.RandomString(100 /* len */)));
+      }
+      ASSERT_OK(Flush());
+    }
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    ASSERT_EQ("2", FilesPerLevel());
+  }
+};
+
 // Param = true : target level is non-empty
 // Param = false: level between target level and source level
 //  is not empty.
@@ -1105,7 +1155,7 @@ TEST_F(DBCompactionTest, CompactionSstPartitionerNonTrivial) {
   ASSERT_OK(Put("bbbb1", "B"));
   ASSERT_OK(Flush());
   ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
-  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
   std::vector<LiveFileMetaData> files;
   dbfull()->GetLiveFilesMetaData(&files);
@@ -3285,6 +3335,304 @@ TEST_F(DBCompactionTest, SuggestCompactRangeNoTwoLevel0Compactions) {
   TEST_SYNC_POINT(
       "DBCompactionTest::SuggestCompactRangeNoTwoLevel0Compactions:2");
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+}
+
+INSTANTIATE_TEST_CASE_P(
+    DBCompactionWaitForCompactTest, DBCompactionWaitForCompactTest,
+    ::testing::Combine(
+        testing::Bool() /* abort_on_pause */, testing::Bool() /* flush */,
+        testing::Bool() /* close_db */,
+        testing::Values(
+            std::chrono::microseconds::zero(),
+            std::chrono::microseconds{
+                60 * 60 *
+                1000000ULL} /* timeout */)));  // 1 hour (long enough to
+                                               // make sure that tests
+                                               // don't fail unexpectedly
+                                               // when running slow)
+
+TEST_P(DBCompactionWaitForCompactTest,
+       WaitForCompactWaitsOnCompactionToFinish) {
+  // Triggers a compaction. Before the compaction finishes, test
+  // closes the DB Upon reopen, wait for the compaction to finish and checks for
+  // the number of compaction finished
+
+  int compaction_finished = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "CompactionJob::Run():EndStatusSet", [&](void* arg) {
+        auto status = static_cast<Status*>(arg);
+        if (status->ok()) {
+          compaction_finished++;
+        }
+      });
+  // To make sure there's a flush/compaction debt
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::MaybeScheduleFlushOrCompaction:BeforeSchedule", [&](void* arg) {
+        auto unscheduled_flushes = *static_cast<int*>(arg);
+        ASSERT_GT(unscheduled_flushes, 0);
+      });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBCompactionTest::WaitForCompactWaitsOnCompactionToFinish",
+        "DBImpl::MaybeScheduleFlushOrCompaction:BeforeSchedule"}});
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  // create compaction debt by adding one more L0 file then closing
+  Random rnd(123);
+  GenerateNewRandomFile(&rnd, /* nowait */ true);
+  ASSERT_EQ(0, compaction_finished);
+  Close();
+  TEST_SYNC_POINT("DBCompactionTest::WaitForCompactWaitsOnCompactionToFinish");
+  ASSERT_EQ(0, compaction_finished);
+
+  // Reopen the db and we expect the compaction to be triggered.
+  Reopen(options_);
+
+  // Wait for compaction to finish
+  ASSERT_OK(dbfull()->WaitForCompact(wait_for_compact_options_));
+  ASSERT_GT(compaction_finished, 0);
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_P(DBCompactionWaitForCompactTest, WaitForCompactAbortOnPause) {
+  // Triggers a compaction. Before the compaction finishes, test
+  // pauses the compaction. Calling WaitForCompact() with option
+  // abort_on_pause=true should return Status::Aborted Or
+  // ContinueBackgroundWork() must be called
+
+  // Now trigger L0 compaction by adding a file
+  Random rnd(123);
+  GenerateNewRandomFile(&rnd, /* nowait */ true);
+  ASSERT_OK(Flush());
+
+  // Pause the background jobs.
+  ASSERT_OK(dbfull()->PauseBackgroundWork());
+
+  // If not abort_on_pause_ continue the background jobs.
+  if (!abort_on_pause_) {
+    ASSERT_OK(dbfull()->ContinueBackgroundWork());
+  }
+
+  Status s = dbfull()->WaitForCompact(wait_for_compact_options_);
+  if (abort_on_pause_) {
+    ASSERT_NOK(s);
+    ASSERT_TRUE(s.IsAborted());
+  } else {
+    ASSERT_OK(s);
+  }
+}
+
+TEST_P(DBCompactionWaitForCompactTest, WaitForCompactShutdownWhileWaiting) {
+  // Triggers a compaction. Before the compaction finishes, db
+  // shuts down (by calling CancelAllBackgroundWork()). Calling WaitForCompact()
+  // should return Status::IsShutdownInProgress()
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+      {"CompactionJob::Run():Start",
+       "DBCompactionTest::WaitForCompactShutdownWhileWaiting:0"},
+      {"DBImpl::WaitForCompact:StartWaiting",
+       "DBCompactionTest::WaitForCompactShutdownWhileWaiting:1"},
+      {"DBImpl::~DBImpl:WaitJob", "CompactionJob::Run():End"},
+  });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  // Now trigger L0 compaction by adding a file
+  Random rnd(123);
+  GenerateNewRandomFile(&rnd, /* nowait */ true);
+  ASSERT_OK(Flush());
+  // Wait for compaction to start
+  TEST_SYNC_POINT("DBCompactionTest::WaitForCompactShutdownWhileWaiting:0");
+
+  // Wait for Compaction in another thread
+  auto waiting_for_compaction_thread = port::Thread([this]() {
+    Status s = dbfull()->WaitForCompact(wait_for_compact_options_);
+    ASSERT_NOK(s);
+    ASSERT_TRUE(s.IsShutdownInProgress());
+  });
+  TEST_SYNC_POINT("DBCompactionTest::WaitForCompactShutdownWhileWaiting:1");
+  // Shutdown after wait started, but before the compaction finishes
+  auto closing_thread = port::Thread([this]() { ASSERT_OK(db_->Close()); });
+
+  waiting_for_compaction_thread.join();
+  closing_thread.join();
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_P(DBCompactionWaitForCompactTest, WaitForCompactWithOptionToFlush) {
+  // After creating enough L0 files that one more file will trigger the
+  // compaction, write some data in memtable. Calls WaitForCompact with option
+  // to flush. This will flush the memtable to a new L0 file which will trigger
+  // compaction. Lastly check for expected number of files, closing + reopening
+  // DB won't trigger any flush or compaction
+
+  int compaction_finished = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundCompaction:AfterCompaction",
+      [&](void*) { compaction_finished++; });
+
+  int flush_finished = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::End", [&](void*) { flush_finished++; });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  // write to memtable (overlapping key with first L0 file), but no flush is
+  // needed at this point.
+  ASSERT_OK(Put(Key(0), "some random string"));
+  ASSERT_EQ(0, compaction_finished);
+  ASSERT_EQ(0, flush_finished);
+  ASSERT_EQ("2", FilesPerLevel());
+
+  ASSERT_OK(dbfull()->WaitForCompact(wait_for_compact_options_));
+  ASSERT_EQ(flush_, compaction_finished);
+  ASSERT_EQ(flush_, flush_finished);
+
+  if (!close_db_) {
+    std::string expected_files_per_level = flush_ ? "1,2" : "2";
+    ASSERT_EQ(expected_files_per_level, FilesPerLevel());
+  }
+
+  compaction_finished = 0;
+  flush_finished = 0;
+  if (!close_db_) {
+    Close();
+  }
+  Reopen(options_);
+
+  ASSERT_EQ(0, flush_finished);
+  if (flush_) {
+    // if flushed already prior to close and reopen, expect there's no
+    // additional compaction needed
+    ASSERT_EQ(0, compaction_finished);
+  } else {
+    // if not flushed prior to close and reopen, expect L0 file creation from
+    // WAL when reopening which will trigger the compaction.
+    ASSERT_OK(dbfull()->WaitForCompact(wait_for_compact_options_));
+    ASSERT_EQ(1, compaction_finished);
+  }
+
+  if (!close_db_) {
+    ASSERT_EQ("1,2", FilesPerLevel());
+  }
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_P(DBCompactionWaitForCompactTest,
+       WaitForCompactWithOptionToFlushAndCloseDB) {
+  // After creating enough L0 files that one more file will trigger the
+  // compaction, write some data in memtable (WAL disabled). Calls
+  // WaitForCompact. If flush option is true, WaitForCompact will flush the
+  // memtable to a new L0 file which will trigger compaction. We expect the
+  // no-op second flush upon closing because WAL is disabled
+  // (has_unpersisted_data_ true) Check to make sure there's no extra L0 file
+  // created from WAL. Re-opening DB won't trigger any flush or compaction
+
+  int compaction_finished = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::BackgroundCompaction:Finish",
+      [&](void*) { compaction_finished++; });
+
+  int flush_finished = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::End", [&](void*) { flush_finished++; });
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_FALSE(options_.avoid_flush_during_shutdown);
+
+  // write to memtable, but no flush is needed at this point.
+  WriteOptions write_without_wal;
+  write_without_wal.disableWAL = true;
+  ASSERT_OK(Put(Key(0), "some random string", write_without_wal));
+  ASSERT_EQ(0, compaction_finished);
+  ASSERT_EQ(0, flush_finished);
+  ASSERT_EQ("2", FilesPerLevel());
+
+  ASSERT_OK(dbfull()->WaitForCompact(wait_for_compact_options_));
+
+  int expected_flush_count = flush_ || close_db_;
+  ASSERT_EQ(expected_flush_count, flush_finished);
+
+  if (!close_db_) {
+    // During CancelAllBackgroundWork(), a flush can be initiated due to
+    // unpersisted data (data that's still in the memtable when WAL is off).
+    // This results in an additional L0 file which can trigger a compaction.
+    // However, the compaction may not complete if the background thread's
+    // execution is slow enough for the front thread to set the 'shutting_down_'
+    // flag to true before the compaction job even starts.
+    ASSERT_EQ(expected_flush_count, compaction_finished);
+    Close();
+  }
+
+  // Because we had has_unpersisted_data_ = true, flush must have been triggered
+  // upon closing regardless of WaitForCompact. Reopen should have no flush
+  // debt.
+  flush_finished = 0;
+  Reopen(options_);
+  ASSERT_EQ(0, flush_finished);
+
+  // However, if db was closed directly by calling Close(), instead
+  // of WaitForCompact with close_db option or we are in the scenario commented
+  // above, it's possible that the last compaction triggered by flushing
+  // unpersisted data was cancelled. Call WaitForCompact() here again to finish
+  // the compaction
+  if (compaction_finished == 0) {
+    ASSERT_OK(dbfull()->WaitForCompact(wait_for_compact_options_));
+  }
+  ASSERT_EQ(1, compaction_finished);
+  if (!close_db_) {
+    ASSERT_EQ("1,2", FilesPerLevel());
+  }
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+TEST_P(DBCompactionWaitForCompactTest, WaitForCompactToTimeout) {
+  // When timeout is set, this test makes CompactionJob hangs forever
+  // using sync point. This test also sets the timeout to be 1 ms for
+  // WaitForCompact to time out early. WaitForCompact() is expected to return
+  // Status::TimedOut.
+  // When timeout is not set, we expect WaitForCompact() to wait indefinitely.
+  // We don't want the test to hang forever. When timeout = 0, this test is not
+  // much different from WaitForCompactWaitsOnCompactionToFinish
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBCompactionTest::WaitForCompactToTimeout",
+        "CompactionJob::Run():Start"}});
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  // Now trigger L0 compaction by adding a file
+  Random rnd(123);
+  GenerateNewRandomFile(&rnd, /* nowait */ true);
+  ASSERT_OK(Flush());
+
+  if (wait_for_compact_options_.timeout.count()) {
+    // Make timeout shorter to finish test early
+    wait_for_compact_options_.timeout = std::chrono::microseconds{1000};
+  } else {
+    // if timeout is not set, WaitForCompact() will wait forever. We don't
+    // want test to hang forever. Just let compaction go through
+    TEST_SYNC_POINT("DBCompactionTest::WaitForCompactToTimeout");
+  }
+  Status s = dbfull()->WaitForCompact(wait_for_compact_options_);
+  if (wait_for_compact_options_.timeout.count()) {
+    ASSERT_NOK(s);
+    ASSERT_TRUE(s.IsTimedOut());
+  } else {
+    ASSERT_OK(s);
+  }
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
 }
 
 static std::string ShortKey(int i) {
@@ -3830,11 +4178,6 @@ TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
   // files does not need to be preserved in case of a future snapshot.
   ASSERT_OK(Put(Key(0), "val"));
   ASSERT_NE(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
-  // release snapshot and wait for compactions to finish. Single-file
-  // compactions should be triggered, which reduce the size of each bottom-level
-  // file without changing file count.
-  db_->ReleaseSnapshot(snapshot);
-  ASSERT_EQ(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
       "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
         Compaction* compaction = reinterpret_cast<Compaction*>(arg);
@@ -3842,6 +4185,11 @@ TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
                     CompactionReason::kBottommostFiles);
       });
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  // release snapshot and wait for compactions to finish. Single-file
+  // compactions should be triggered, which reduce the size of each bottom-level
+  // file without changing file count.
+  db_->ReleaseSnapshot(snapshot);
+  ASSERT_EQ(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
   db_->GetLiveFilesMetaData(&post_release_metadata);
   ASSERT_EQ(pre_release_metadata.size(), post_release_metadata.size());
@@ -3858,6 +4206,78 @@ TEST_F(DBCompactionTest, CompactBottomLevelFilesWithDeletions) {
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
 }
 
+TEST_F(DBCompactionTest, DelayCompactBottomLevelFilesWithDeletions) {
+  // bottom-level files may contain deletions due to snapshots protecting the
+  // deleted keys. Once the snapshot is released and the files are old enough,
+  // we should see them undergo single-file compactions.
+  Options options = CurrentOptions();
+  env_->SetMockSleep();
+  options.bottommost_file_compaction_delay = 3600;
+  DestroyAndReopen(options);
+  CreateColumnFamilies({"one"}, options);
+  const int kNumKey = 100;
+  const int kValLen = 100;
+
+  Random rnd(301);
+  for (int i = 0; i < kNumKey; ++i) {
+    ASSERT_OK(Put(Key(i), rnd.RandomString(kValLen)));
+  }
+  const Snapshot* snapshot = db_->GetSnapshot();
+  for (int i = 0; i < kNumKey; i += 2) {
+    ASSERT_OK(Delete(Key(i)));
+  }
+  ASSERT_OK(Flush());
+  MoveFilesToLevel(1);
+  ASSERT_EQ(1, NumTableFilesAtLevel(1));
+
+  std::vector<LiveFileMetaData> pre_release_metadata;
+  db_->GetLiveFilesMetaData(&pre_release_metadata);
+  ASSERT_EQ(1, pre_release_metadata.size());
+  std::atomic_int compaction_count = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
+        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
+        ASSERT_TRUE(compaction->compaction_reason() ==
+                    CompactionReason::kBottommostFiles);
+        compaction_count++;
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  // just need to bump seqnum so ReleaseSnapshot knows the newest key in the SST
+  // files does not need to be preserved in case of a future snapshot.
+  ASSERT_OK(Put(Key(0), "val"));
+  ASSERT_NE(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
+  // release snapshot will not trigger compaction.
+  db_->ReleaseSnapshot(snapshot);
+  ASSERT_EQ(kMaxSequenceNumber, dbfull()->bottommost_files_mark_threshold_);
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  ASSERT_EQ(0, compaction_count);
+  // Now the file is old enough for compaction.
+  env_->MockSleepForSeconds(3600);
+  // Another flush will trigger re-computation of the compaction score
+  // to find out that the file is qualified for compaction.
+  ASSERT_OK(Flush());
+  ASSERT_EQ(1, NumTableFilesAtLevel(0));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  ASSERT_EQ(1, compaction_count);
+
+  std::vector<LiveFileMetaData> post_release_metadata;
+  db_->GetLiveFilesMetaData(&post_release_metadata);
+  ASSERT_EQ(2, post_release_metadata.size());
+
+  const auto& pre_file = pre_release_metadata[0];
+  // Get the L1 (bottommost level) file.
+  const auto& post_file = post_release_metadata[0].level == 0
+                              ? post_release_metadata[1]
+                              : post_release_metadata[0];
+
+  ASSERT_EQ(1, pre_file.level);
+  ASSERT_EQ(1, post_file.level);
+  // the file is smaller than it was before as it was rewritten without
+  // deletion markers/deleted keys.
+  ASSERT_LT(post_file.size, pre_file.size);
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+}
+
 TEST_F(DBCompactionTest, NoCompactBottomLevelFilesWithDeletions) {
   // bottom-level files may contain deletions due to snapshots protecting the
   // deleted keys. Once the snapshot is released, we should see files with many
@@ -4378,6 +4798,7 @@ TEST_F(DBCompactionTest, LevelTtlCascadingCompactions) {
               PutVarint64(encoded_fieled, 0);
             }
           });
+      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
       options.env = env_;
 
@@ -4394,7 +4815,6 @@ TEST_F(DBCompactionTest, LevelTtlCascadingCompactions) {
               ttl_compactions++;
             }
           });
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
       // Add two L6 files with key ranges: [1 .. 100], [101 .. 200].
       Random rnd(301);
@@ -4526,6 +4946,7 @@ TEST_F(DBCompactionTest, LevelPeriodicCompaction) {
               PutVarint64(encoded_fieled, 0);
             }
           });
+      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
       options.env = env_;
 
@@ -4542,7 +4963,6 @@ TEST_F(DBCompactionTest, LevelPeriodicCompaction) {
               periodic_compactions++;
             }
           });
-      ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
       Random rnd(301);
       for (int i = 0; i < kNumLevelFiles; ++i) {
@@ -5009,6 +5429,12 @@ TEST_F(DBCompactionTest, CompactRangeDelayedByImmMemTableCount) {
     }
 
     auto manual_compaction_thread = port::Thread([this]() {
+      // Write something to make the current Memtable non-empty, so an extra
+      // immutable Memtable will be created upon manual flush requested by
+      // CompactRange, triggering a write stall mode to be entered because of
+      // accumulation of write buffers due to manual flush.
+      Random compact_rnd(301);
+      ASSERT_OK(Put(Key(0), compact_rnd.RandomString(1024)));
       CompactRangeOptions cro;
       cro.allow_write_stall = false;
       ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
@@ -5075,7 +5501,11 @@ TEST_F(DBCompactionTest, CompactRangeShutdownWhileDelayed) {
     manual_compaction_thread.join();
     TEST_SYNC_POINT(
         "DBCompactionTest::CompactRangeShutdownWhileDelayed:PostManual");
-    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    if (i == 0) {
+      ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    } else {
+      ASSERT_NOK(dbfull()->TEST_WaitForCompact());
+    }
     ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
   }
 }
@@ -5595,23 +6025,18 @@ TEST_P(DBCompactionDirectIOTest, DirectIO) {
   options.use_direct_io_for_flush_and_compaction = GetParam();
   options.env = MockEnv::Create(Env::Default());
   Reopen(options);
-  bool readahead = false;
   SyncPoint::GetInstance()->SetCallBack(
       "CompactionJob::OpenCompactionOutputFile", [&](void* arg) {
         bool* use_direct_writes = static_cast<bool*>(arg);
         ASSERT_EQ(*use_direct_writes,
                   options.use_direct_io_for_flush_and_compaction);
       });
-  if (options.use_direct_io_for_flush_and_compaction) {
-    SyncPoint::GetInstance()->SetCallBack(
-        "SanitizeOptions:direct_io", [&](void* /*arg*/) { readahead = true; });
-  }
   SyncPoint::GetInstance()->EnableProcessing();
   CreateAndReopenWithCF({"pikachu"}, options);
   MakeTables(3, "p", "q", 1);
   ASSERT_EQ("1,1,1", FilesPerLevel(1));
   Compact(1, "p", "q");
-  ASSERT_EQ(readahead, options.use_direct_reads);
+  ASSERT_EQ(false, options.use_direct_reads);
   ASSERT_EQ("0,0,1", FilesPerLevel(1));
   Destroy(options);
   delete options.env;
@@ -5818,7 +6243,7 @@ TEST_P(RoundRobinSubcompactionsAgainstPressureToken, PressureTokenTest) {
   }
   TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstPressureToken:2");
 
-  ASSERT_OK(dbfull()->WaitForCompact());
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_TRUE(num_planned_subcompactions_verified);
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -5893,7 +6318,7 @@ TEST_P(RoundRobinSubcompactionsAgainstResources, SubcompactionsUsingResources) {
         "CompactionJob::ReleaseSubcompactionResources:1"}});
   SyncPoint::GetInstance()->EnableProcessing();
 
-  ASSERT_OK(dbfull()->WaitForCompact());
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_OK(dbfull()->EnableAutoCompaction({dbfull()->DefaultColumnFamily()}));
   TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:0");
   TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:1");
@@ -5909,7 +6334,7 @@ TEST_P(RoundRobinSubcompactionsAgainstResources, SubcompactionsUsingResources) {
       total_low_pri_threads_ - 1,
       env_->ReleaseThreads(total_low_pri_threads_ - 1, Env::Priority::LOW));
   TEST_SYNC_POINT("RoundRobinSubcompactionsAgainstResources:4");
-  ASSERT_OK(dbfull()->WaitForCompact());
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_TRUE(num_planned_subcompactions_verified);
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -5981,11 +6406,11 @@ TEST_P(DBCompactionTestWithParam, RoundRobinWithoutAdditionalResources) {
         "BackgroundCallCompaction:0"}});
   SyncPoint::GetInstance()->EnableProcessing();
 
-  ASSERT_OK(dbfull()->WaitForCompact());
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_OK(dbfull()->EnableAutoCompaction({dbfull()->DefaultColumnFamily()}));
   TEST_SYNC_POINT("DBCompactionTest::RoundRobinWithoutAdditionalResources:0");
 
-  ASSERT_OK(dbfull()->WaitForCompact());
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_TRUE(num_planned_subcompactions_verified);
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
@@ -6740,10 +7165,8 @@ class DBCompactionTestL0FilesMisorderCorruption : public DBCompactionTest {
       if (compaction_path_to_test == "FindIntraL0Compaction" ||
           compaction_path_to_test == "CompactRange") {
         fifo_options.allow_compaction = true;
-        fifo_options.age_for_warm = 0;
       } else if (compaction_path_to_test == "CompactFile") {
         fifo_options.allow_compaction = false;
-        fifo_options.age_for_warm = 0;
       }
       options_.compaction_options_fifo = fifo_options;
     }
@@ -7742,26 +8165,14 @@ TEST_F(DBCompactionTest, ChangeLevelErrorPathTest) {
   auto start_idx = key_idx;
   GenerateNewFile(&rnd, &key_idx);
   GenerateNewFile(&rnd, &key_idx);
-  auto end_idx = key_idx - 1;
   ASSERT_EQ("1,1,2", FilesPerLevel(0));
 
-  // Next two CompactRange() calls are used to test exercise error paths within
+  MoveFilesToLevel(1);
+  ASSERT_EQ("0,2,2", FilesPerLevel(0));
+
+  // The next CompactRange() call is used to test exercise error paths within
   // RefitLevel() before triggering a valid RefitLevel() call
-
-  // Trigger a refit to L1 first
-  {
-    std::string begin_string = Key(start_idx);
-    std::string end_string = Key(end_idx);
-    Slice begin(begin_string);
-    Slice end(end_string);
-
-    CompactRangeOptions cro;
-    cro.change_level = true;
-    cro.target_level = 1;
-    ASSERT_OK(dbfull()->CompactRange(cro, &begin, &end));
-  }
-  ASSERT_EQ("0,3,2", FilesPerLevel(0));
-
+  //
   // Try a refit from L2->L1 - this should fail and exercise error paths in
   // RefitLevel()
   {
@@ -7776,7 +8187,7 @@ TEST_F(DBCompactionTest, ChangeLevelErrorPathTest) {
     cro.target_level = 1;
     ASSERT_NOK(dbfull()->CompactRange(cro, &begin, &end));
   }
-  ASSERT_EQ("0,3,2", FilesPerLevel(0));
+  ASSERT_EQ("0,2,2", FilesPerLevel(0));
 
   // Try a valid Refit request to ensure, the path is still working
   {
@@ -7789,10 +8200,8 @@ TEST_F(DBCompactionTest, ChangeLevelErrorPathTest) {
 }
 
 TEST_F(DBCompactionTest, CompactionWithBlob) {
-  Options options;
-  options.env = env_;
+  Options options = CurrentOptions();
   options.disable_auto_compactions = true;
-
   Reopen(options);
 
   constexpr char first_key[] = "first_key";
@@ -7884,10 +8293,8 @@ INSTANTIATE_TEST_CASE_P(DBCompactionTestBlobError, DBCompactionTestBlobError,
                             "BlobFileBuilder::WriteBlobToFile:AppendFooter"}));
 
 TEST_P(DBCompactionTestBlobError, CompactionError) {
-  Options options;
+  Options options = CurrentOptions();
   options.disable_auto_compactions = true;
-  options.env = env_;
-
   Reopen(options);
 
   constexpr char first_key[] = "first_key";
@@ -8053,8 +8460,7 @@ TEST_P(DBCompactionTestBlobGC, CompactionWithBlobGCOverrides) {
 }
 
 TEST_P(DBCompactionTestBlobGC, CompactionWithBlobGC) {
-  Options options;
-  options.env = env_;
+  Options options = CurrentOptions();
   options.disable_auto_compactions = true;
   options.enable_blob_files = true;
   options.blob_file_size = 32;  // one blob per file
@@ -8593,7 +8999,7 @@ TEST_F(DBCompactionTest, CompactionWithChecksumHandoffManifest2) {
   Destroy(options);
 }
 
-TEST_F(DBCompactionTest, FIFOWarm) {
+TEST_F(DBCompactionTest, FIFOChangeTemperature) {
   Options options = CurrentOptions();
   options.compaction_style = kCompactionStyleFIFO;
   options.num_levels = 1;
@@ -8601,18 +9007,18 @@ TEST_F(DBCompactionTest, FIFOWarm) {
   options.level0_file_num_compaction_trigger = 2;
   options.create_if_missing = true;
   CompactionOptionsFIFO fifo_options;
-  fifo_options.age_for_warm = 1000;
+  fifo_options.file_temperature_age_thresholds = {{Temperature::kCold, 1000}};
   fifo_options.max_table_files_size = 100000000;
   options.compaction_options_fifo = fifo_options;
   env_->SetMockSleep();
   Reopen(options);
 
-  int total_warm = 0;
+  int total_cold = 0;
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
       "NewWritableFile::FileOptions.temperature", [&](void* arg) {
         Temperature temperature = *(static_cast<Temperature*>(arg));
-        if (temperature == Temperature::kWarm) {
-          total_warm++;
+        if (temperature == Temperature::kCold) {
+          total_cold++;
         }
       });
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
@@ -8649,9 +9055,9 @@ TEST_F(DBCompactionTest, FIFOWarm) {
   ASSERT_EQ(4, metadata.file_count);
   ASSERT_EQ(Temperature::kUnknown, metadata.levels[0].files[0].temperature);
   ASSERT_EQ(Temperature::kUnknown, metadata.levels[0].files[1].temperature);
-  ASSERT_EQ(Temperature::kWarm, metadata.levels[0].files[2].temperature);
-  ASSERT_EQ(Temperature::kWarm, metadata.levels[0].files[3].temperature);
-  ASSERT_EQ(2, total_warm);
+  ASSERT_EQ(Temperature::kCold, metadata.levels[0].files[2].temperature);
+  ASSERT_EQ(Temperature::kCold, metadata.levels[0].files[3].temperature);
+  ASSERT_EQ(2, total_cold);
 
   Destroy(options);
 }
@@ -8716,7 +9122,7 @@ TEST_F(DBCompactionTest, DisableMultiManualCompaction) {
 
   sleeping_task_low.WakeUp();
   sleeping_task_low.WaitUntilDone();
-  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
 }
 
 TEST_F(DBCompactionTest, DisableJustStartedManualCompaction) {
@@ -8848,7 +9254,7 @@ TEST_F(DBCompactionTest, DisableManualCompactionThreadQueueFull) {
 
   sleeping_task_low.WakeUp();
   sleeping_task_low.WaitUntilDone();
-  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ("0,1", FilesPerLevel(0));
 }
 
@@ -9413,6 +9819,224 @@ TEST_F(DBCompactionTest, DrainUnnecessaryLevelsAfterDBBecomesSmall) {
   ASSERT_GT(after_delete_range_nonempty, final_num_nonempty);
 }
 
+TEST_F(DBCompactionTest, ManualCompactionCompactAllKeysInRange) {
+  // CompactRange() used to pre-compute target level to compact to
+  // before running compactions. However, the files at target level
+  // could be trivially moved down by some background compaction. This means
+  // some keys in the manual compaction key range may not be compacted
+  // during the manual compaction. This unit test tests this scenario.
+  // A fix has been applied for this scenario to always compact
+  // to the bottommost level.
+  const int kBaseLevelBytes = 8 << 20;  // 8MB
+  const int kMultiplier = 2;
+  Options options = CurrentOptions();
+  options.num_levels = 7;
+  options.level_compaction_dynamic_level_bytes = false;
+  options.compaction_style = kCompactionStyleLevel;
+  options.max_bytes_for_level_base = kBaseLevelBytes;
+  options.max_bytes_for_level_multiplier = kMultiplier;
+  options.compression = kNoCompression;
+  options.target_file_size_base = 2 * kBaseLevelBytes;
+
+  DestroyAndReopen(options);
+  Random rnd(301);
+  // Populate L2 so that manual compaction will compact to at least L2.
+  // Otherwise, there is still a possibility of race condition where
+  // the manual compaction thread believes that max non-empty level is L1
+  // while there is some auto compaction that moves some files from L1 to L2.
+  ASSERT_OK(db_->Put(WriteOptions(), Key(1000), rnd.RandomString(100)));
+  ASSERT_OK(Flush());
+  MoveFilesToLevel(2);
+  ASSERT_EQ(1, NumTableFilesAtLevel(2));
+
+  // one file in L1: [Key(5), Key(6)]
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(5), rnd.RandomString(kBaseLevelBytes / 3)));
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(6), rnd.RandomString(kBaseLevelBytes / 3)));
+  ASSERT_OK(Flush());
+  MoveFilesToLevel(1);
+  ASSERT_EQ(1, NumTableFilesAtLevel(1));
+
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(1), rnd.RandomString(kBaseLevelBytes / 2)));
+  // We now do manual compaction for key range [Key(1), Key(6)].
+  // First it compacts file [Key(1)] to L1.
+  // L1 will have two files [Key(1)], and [Key(5), Key(6)].
+  // After L0 -> L1 manual compaction, an automatic compaction will trivially
+  // move both files from L1 to L2. Here the dependency makes manual compaction
+  // wait for auto-compaction to pick a compaction before proceeding. Manual
+  // compaction should not stop at L1 and keep compacting L2. With kForce
+  // specified, expected output is that manual compaction compacts to L2 and L2
+  // will contain 2 files: one for Key(1000) and one for Key(1), Key(5) and
+  // Key(6).
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::BackgroundCompaction():AfterPickCompaction",
+        "DBImpl::RunManualCompaction()::1"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+  std::string begin_str = Key(1);
+  std::string end_str = Key(6);
+  Slice begin_slice = begin_str;
+  Slice end_slice = end_str;
+  CompactRangeOptions cro;
+  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
+  ASSERT_OK(db_->CompactRange(cro, &begin_slice, &end_slice));
+
+  ASSERT_EQ(NumTableFilesAtLevel(2), 2);
+}
+
+TEST_F(DBCompactionTest,
+       ManualCompactionCompactAllKeysInRangeDynamicLevelBytes) {
+  // Similar to the test above (ManualCompactionCompactAllKeysInRange), but with
+  // level_compaction_dynamic_level_bytes = true.
+  const int kBaseLevelBytes = 8 << 20;  // 8MB
+  const int kMultiplier = 2;
+  Options options = CurrentOptions();
+  options.num_levels = 7;
+  options.level_compaction_dynamic_level_bytes = true;
+  options.compaction_style = kCompactionStyleLevel;
+  options.max_bytes_for_level_base = kBaseLevelBytes;
+  options.max_bytes_for_level_multiplier = kMultiplier;
+  options.compression = kNoCompression;
+  options.target_file_size_base = 2 * kBaseLevelBytes;
+  DestroyAndReopen(options);
+
+  Random rnd(301);
+  ASSERT_OK(db_->Put(WriteOptions(), Key(5),
+                     rnd.RandomString(3 * kBaseLevelBytes / 2)));
+  ASSERT_OK(Flush());
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  ASSERT_EQ(1, NumTableFilesAtLevel(6));
+  // L6 now has one file with size ~ 3/2 * kBaseLevelBytes.
+  // L5 is the new base level, with target size ~ 3/4 * kBaseLevelBytes.
+
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(3), rnd.RandomString(kBaseLevelBytes / 3)));
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(4), rnd.RandomString(kBaseLevelBytes / 3)));
+  ASSERT_OK(Flush());
+
+  MoveFilesToLevel(5);
+  ASSERT_EQ(1, NumTableFilesAtLevel(5));
+  // L5 now has one file with size ~ 2/3 * kBaseLevelBytes, which is below its
+  // target size.
+
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(1), rnd.RandomString(kBaseLevelBytes / 3)));
+  ASSERT_OK(
+      db_->Put(WriteOptions(), Key(2), rnd.RandomString(kBaseLevelBytes / 3)));
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::BackgroundCompaction():AfterPickCompaction",
+        "DBImpl::RunManualCompaction()::1"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+  // After compacting the file with [Key(1), Key(2)] to L5,
+  // L5 has size ~ 4/3 * kBaseLevelBytes > its target size.
+  // We let manual compaction wait for an auto-compaction to pick
+  // a compaction before proceeding. The auto-compaction would
+  // trivially move both files in L5 down to L6. If manual compaction
+  // works correctly with kForce specified, it should rewrite the two files in
+  // L6 into a single file.
+  CompactRangeOptions cro;
+  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
+  std::string begin_str = Key(1);
+  std::string end_str = Key(4);
+  Slice begin_slice = begin_str;
+  Slice end_slice = end_str;
+  ASSERT_OK(db_->CompactRange(cro, &begin_slice, &end_slice));
+  ASSERT_EQ(2, NumTableFilesAtLevel(6));
+  ASSERT_EQ(0, NumTableFilesAtLevel(5));
+}
+
+TEST_F(DBCompactionTest, NumberOfSubcompactions) {
+  // Tests that expected number of subcompactions are created.
+  class SubCompactionEventListener : public EventListener {
+   public:
+    void OnSubcompactionCompleted(const SubcompactionJobInfo&) override {
+      sub_compaction_finished_++;
+    }
+    void OnCompactionCompleted(DB*, const CompactionJobInfo&) override {
+      compaction_finished_++;
+    }
+    std::atomic<int> sub_compaction_finished_{0};
+    std::atomic<int> compaction_finished_{0};
+  };
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleLevel;
+  options.compression = kNoCompression;
+  const int kFileSize = 100 << 10;  // 100KB
+  options.target_file_size_base = kFileSize;
+  const int kLevel0CompactTrigger = 2;
+  options.level0_file_num_compaction_trigger = kLevel0CompactTrigger;
+  Destroy(options);
+  Random rnd(301);
+
+  // Exposing internal implementation detail here where the
+  // number of subcompactions depends on the size of data
+  // being compacted. In particular, to enable x subcompactions,
+  // we need to compact at least x * target file size amount
+  // of data.
+  //
+  // Will write two files below to avoid trivial move.
+  // Size written in total: 500 * 1000 * 2 ~ 10MB ~ 100 * target file size.
+  const int kValueSize = 500;
+  const int kNumKeyPerFile = 1000;
+  for (int i = 1; i <= 8; ++i) {
+    options.max_subcompactions = i;
+    SubCompactionEventListener* listener = new SubCompactionEventListener();
+    options.listeners.clear();
+    options.listeners.emplace_back(listener);
+    ASSERT_OK(TryReopen(options));
+
+    for (int file = 0; file < kLevel0CompactTrigger; ++file) {
+      for (int key = file; key < 2 * kNumKeyPerFile; key += 2) {
+        ASSERT_OK(Put(Key(key), rnd.RandomString(kValueSize)));
+      }
+      ASSERT_OK(Flush());
+    }
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    ASSERT_EQ(listener->compaction_finished_, 1);
+    EXPECT_EQ(listener->sub_compaction_finished_, i);
+    Destroy(options);
+  }
+}
+
+TEST_F(DBCompactionTest, VerifyRecordCount) {
+  Options options = CurrentOptions();
+  options.compaction_style = kCompactionStyleLevel;
+  options.level0_file_num_compaction_trigger = 3;
+  options.compaction_verify_record_count = true;
+  DestroyAndReopen(options);
+  Random rnd(301);
+
+  // Create 2 overlapping L0 files
+  for (int i = 1; i < 20; i += 2) {
+    ASSERT_OK(Put(Key(i), rnd.RandomString(100)));
+  }
+  ASSERT_OK(Flush());
+
+  for (int i = 0; i < 20; i += 2) {
+    ASSERT_OK(Put(Key(i), rnd.RandomString(100)));
+  }
+  ASSERT_OK(Flush());
+
+  // Only iterator through 10 keys and force compaction to finish.
+  int num_iter = 0;
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "CompactionJob::ProcessKeyValueCompaction()::stop", [&](void* stop_ptr) {
+        num_iter++;
+        if (num_iter == 10) {
+          *(bool*)stop_ptr = true;
+        }
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  Status s = db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
+  ASSERT_TRUE(s.IsCorruption());
+  const char* expect =
+      "Compaction number of input keys does not match number of keys "
+      "processed.";
+  ASSERT_TRUE(std::strstr(s.getState(), expect));
+}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_filesnapshot.cc

@@ -29,35 +29,8 @@
 namespace ROCKSDB_NAMESPACE {
 
 Status DBImpl::FlushForGetLiveFiles() {
-  mutex_.AssertHeld();
-
-  // flush all dirty data to disk.
-  Status status;
-  if (immutable_db_options_.atomic_flush) {
-    mutex_.Unlock();
-    status = AtomicFlushMemTables(FlushOptions(), FlushReason::kGetLiveFiles);
-    if (status.IsColumnFamilyDropped()) {
-      status = Status::OK();
-    }
-    mutex_.Lock();
-  } else {
-    for (auto cfd : versions_->GetRefedColumnFamilySet()) {
-      if (cfd->IsDropped()) {
-        continue;
-      }
-      mutex_.Unlock();
-      status = FlushMemTable(cfd, FlushOptions(), FlushReason::kGetLiveFiles);
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
-      mutex_.Lock();
-      if (!status.ok() && !status.IsColumnFamilyDropped()) {
-        break;
-      } else if (status.IsColumnFamilyDropped()) {
-        status = Status::OK();
-      }
-    }
-  }
-  return status;
+  return DBImpl::FlushAllColumnFamilies(FlushOptions(),
+                                        FlushReason::kGetLiveFiles);
 }
 
 Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,

db/db_flush_test.cc

@@ -222,7 +222,7 @@ TEST_F(DBFlushTest, CloseDBWhenFlushInLowPri) {
   sleeping_task_low.WaitUntilDone();
   ASSERT_EQ(0, num_flushes);
 
-  TryReopenWithColumnFamilies({"default", "cf1", "cf2"}, options);
+  ASSERT_OK(TryReopenWithColumnFamilies({"default", "cf1", "cf2"}, options));
   ASSERT_OK(Put(0, "key3", DummyString(8192)));
   ASSERT_OK(Flush(0));
   ASSERT_EQ(1, num_flushes);
@@ -3193,6 +3193,279 @@ INSTANTIATE_TEST_CASE_P(DBFlushDirectIOTest, DBFlushDirectIOTest,
 
 INSTANTIATE_TEST_CASE_P(DBAtomicFlushTest, DBAtomicFlushTest, testing::Bool());
 
+TEST_F(DBFlushTest, NonAtomicFlushRollbackPendingFlushes) {
+  // Fix a bug in when atomic_flush=false.
+  // The bug can happen as follows:
+  // Start Flush0 for memtable M0 to SST0
+  // Start Flush1 for memtable M1 to SST1
+  // Flush1 returns OK, but don't install to MANIFEST and let whoever flushes
+  // M0 to take care of it
+  // Flush0 finishes with a retryable IOError
+  //   - It rollbacks M0, (incorrectly) not M1
+  //   - Deletes SST1 and SST2
+  //
+  // Auto-recovery will start Flush2 for M0, it does not pick up M1 since it
+  // thinks that M1 is flushed
+  // Flush2 writes SST3 and finishes OK, tries to install SST3 and SST2
+  // Error opening SST2 since it's already deleted
+  //
+  // The fix is to let Flush0 also rollback M1.
+  Options opts = CurrentOptions();
+  opts.atomic_flush = false;
+  opts.memtable_factory.reset(test::NewSpecialSkipListFactory(1));
+  opts.max_write_buffer_number = 64;
+  opts.max_background_flushes = 4;
+  env_->SetBackgroundThreads(4, Env::HIGH);
+  DestroyAndReopen(opts);
+  std::atomic_int flush_count = 0;
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::WriteLevel0Table:s", [&](void* s_ptr) {
+        int c = flush_count.fetch_add(1);
+        if (c == 0) {
+          Status* s = (Status*)(s_ptr);
+          IOStatus io_error = IOStatus::IOError("injected foobar");
+          io_error.SetRetryable(true);
+          *s = io_error;
+          TEST_SYNC_POINT("Let mem1 flush start");
+          TEST_SYNC_POINT("Wait for mem1 flush to finish");
+        }
+      });
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"Let mem1 flush start", "Mem1 flush starts"},
+       {"DBImpl::BGWorkFlush:done", "Wait for mem1 flush to finish"},
+       {"RecoverFromRetryableBGIOError:RecoverSuccess",
+        "Wait for error recover"}});
+  // Need first flush to wait for the second flush to finish
+  SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "val1"));
+  // trigger bg flush mem0
+  ASSERT_OK(Put(Key(2), "val2"));
+  TEST_SYNC_POINT("Mem1 flush starts");
+  // trigger bg flush mem1
+  ASSERT_OK(Put(Key(3), "val3"));
+
+  TEST_SYNC_POINT("Wait for error recover");
+  ASSERT_EQ(1, NumTableFilesAtLevel(0));
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_F(DBFlushTest, AbortNonAtomicFlushWhenBGError) {
+  // Fix a bug in when atomic_flush=false.
+  // The bug can happen as follows:
+  // Start Flush0 for memtable M0 to SST0
+  // Start Flush1 for memtable M1 to SST1
+  // Flush1 returns OK, but doesn't install output MANIFEST and let whoever
+  // flushes M0 to take care of it
+  // Start Flush2 for memtable M2 to SST2
+  // Flush0 finishes with a retryable IOError
+  //   - It rollbacks M0 AND M1
+  //   - Deletes SST1 and SST2
+  // Flush2 finishes, does not rollback M2,
+  //  - releases the pending file number that keeps SST2 alive
+  //  - deletes SST2
+  //
+  // Then auto-recovery starts, error opening SST2 when try to install
+  // flush result
+  //
+  // The fix is to let Flush2 rollback M2 if it finds that
+  // there is a background error.
+  Options opts = CurrentOptions();
+  opts.atomic_flush = false;
+  opts.memtable_factory.reset(test::NewSpecialSkipListFactory(1));
+  opts.max_write_buffer_number = 64;
+  opts.max_background_flushes = 4;
+  env_->SetBackgroundThreads(4, Env::HIGH);
+  DestroyAndReopen(opts);
+  std::atomic_int flush_count = 0;
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::WriteLevel0Table:s", [&](void* s_ptr) {
+        int c = flush_count.fetch_add(1);
+        if (c == 0) {
+          Status* s = (Status*)(s_ptr);
+          IOStatus io_error = IOStatus::IOError("injected foobar");
+          io_error.SetRetryable(true);
+          *s = io_error;
+          TEST_SYNC_POINT("Let mem1 flush start");
+          TEST_SYNC_POINT("Wait for mem1 flush to finish");
+
+          TEST_SYNC_POINT("Let mem2 flush start");
+          TEST_SYNC_POINT("Wait for mem2 to start writing table");
+        }
+      });
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::WriteLevel0Table", [&](void* mems) {
+        autovector<MemTable*>* mems_ptr = (autovector<MemTable*>*)mems;
+        if ((*mems_ptr)[0]->GetID() == 3) {
+          TEST_SYNC_POINT("Mem2 flush starts writing table");
+          TEST_SYNC_POINT("Mem2 flush waits until rollback");
+        }
+      });
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"Let mem1 flush start", "Mem1 flush starts"},
+       {"DBImpl::BGWorkFlush:done", "Wait for mem1 flush to finish"},
+       {"Let mem2 flush start", "Mem2 flush starts"},
+       {"Mem2 flush starts writing table",
+        "Wait for mem2 to start writing table"},
+       {"RollbackMemtableFlush", "Mem2 flush waits until rollback"},
+       {"RecoverFromRetryableBGIOError:RecoverSuccess",
+        "Wait for error recover"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_OK(Put(Key(1), "val1"));
+  // trigger bg flush mem0
+  ASSERT_OK(Put(Key(2), "val2"));
+  TEST_SYNC_POINT("Mem1 flush starts");
+  // trigger bg flush mem1
+  ASSERT_OK(Put(Key(3), "val3"));
+
+  TEST_SYNC_POINT("Mem2 flush starts");
+  ASSERT_OK(Put(Key(4), "val4"));
+
+  TEST_SYNC_POINT("Wait for error recover");
+  // Recovery flush writes 3 memtables together into 1 file.
+  ASSERT_EQ(1, NumTableFilesAtLevel(0));
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_F(DBFlushTest, NonAtomicNormalFlushAbortWhenBGError) {
+  Options opts = CurrentOptions();
+  opts.atomic_flush = false;
+  opts.memtable_factory.reset(test::NewSpecialSkipListFactory(1));
+  opts.max_write_buffer_number = 64;
+  opts.max_background_flushes = 1;
+  env_->SetBackgroundThreads(2, Env::HIGH);
+  DestroyAndReopen(opts);
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+  std::atomic_int flush_write_table_count = 0;
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::WriteLevel0Table:s", [&](void* s_ptr) {
+        int c = flush_write_table_count.fetch_add(1);
+        if (c == 0) {
+          Status* s = (Status*)(s_ptr);
+          IOStatus io_error = IOStatus::IOError("injected foobar");
+          io_error.SetRetryable(true);
+          *s = io_error;
+        }
+      });
+
+  SyncPoint::GetInstance()->EnableProcessing();
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"Let error recovery start",
+        "RecoverFromRetryableBGIOError:BeforeStart"},
+       {"RecoverFromRetryableBGIOError:RecoverSuccess",
+        "Wait for error recover"}});
+
+  ASSERT_OK(Put(Key(1), "val1"));
+  // trigger bg flush0 for mem0
+  ASSERT_OK(Put(Key(2), "val2"));
+  // Not checking status since this wait can finish before flush starts.
+  dbfull()->TEST_WaitForFlushMemTable().PermitUncheckedError();
+
+  // trigger bg flush1 for mem1, should see bg error and abort
+  // before picking a memtable to flush
+  ASSERT_OK(Put(Key(3), "val3"));
+  ASSERT_NOK(dbfull()->TEST_WaitForFlushMemTable());
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+
+  TEST_SYNC_POINT("Let error recovery start");
+  TEST_SYNC_POINT("Wait for error recover");
+  // Recovery flush writes 2 memtables together into 1 file.
+  ASSERT_EQ(1, NumTableFilesAtLevel(0));
+  // 1 for flush 0 and 1 for recovery flush
+  ASSERT_EQ(2, flush_write_table_count);
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_F(DBFlushTest, DBStuckAfterAtomicFlushError) {
+  // Test for a bug with atomic flush where DB can become stuck
+  // after a flush error. A repro timeline:
+  //
+  // Start Flush0 for mem0
+  // Start Flush1 for mem1
+  // Now Flush1 will wait for Flush0 to install mem0
+  // Flush0 finishes with retryable IOError, rollbacks mem0
+  // Resume starts and waits for background job to finish, i.e., Flush1
+  // Fill memtable again, trigger Flush2 for mem0
+  // Flush2 will get error status, and not rollback mem0, see code in
+  // https://github.com/facebook/rocksdb/blob/b927ba5936216861c2c35ab68f50ba4a78e65747/db/db_impl/db_impl_compaction_flush.cc#L725
+  //
+  // DB is stuck since mem0 can never be picked now
+  //
+  // The fix is to rollback mem0 in Flush2, and let Flush1 also abort upon
+  // background error besides waiting for older memtables to be installed.
+  // The recovery flush in this case should pick up all memtables
+  // and write them to a single L0 file.
+  Options opts = CurrentOptions();
+  opts.atomic_flush = true;
+  opts.memtable_factory.reset(test::NewSpecialSkipListFactory(1));
+  opts.max_write_buffer_number = 64;
+  opts.max_background_flushes = 4;
+  env_->SetBackgroundThreads(4, Env::HIGH);
+  DestroyAndReopen(opts);
+
+  std::atomic_int flush_count = 0;
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::WriteLevel0Table:s", [&](void* s_ptr) {
+        int c = flush_count.fetch_add(1);
+        if (c == 0) {
+          Status* s = (Status*)(s_ptr);
+          IOStatus io_error = IOStatus::IOError("injected foobar");
+          io_error.SetRetryable(true);
+          *s = io_error;
+          TEST_SYNC_POINT("Let flush for mem1 start");
+          // Wait for Flush1 to start waiting to install flush result
+          TEST_SYNC_POINT("Wait for flush for mem1");
+        }
+      });
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"Let flush for mem1 start", "Flush for mem1"},
+       {"DBImpl::AtomicFlushMemTablesToOutputFiles:WaitCV",
+        "Wait for flush for mem1"},
+       {"RecoverFromRetryableBGIOError:BeforeStart",
+        "Wait for resume to start"},
+       {"Recovery should continue here",
+        "RecoverFromRetryableBGIOError:BeforeStart2"},
+       {"RecoverFromRetryableBGIOError:RecoverSuccess",
+        "Wait for error recover"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_OK(Put(Key(1), "val1"));
+  // trigger Flush0 for mem0
+  ASSERT_OK(Put(Key(2), "val2"));
+
+  // trigger Flush1 for mem1
+  TEST_SYNC_POINT("Flush for mem1");
+  ASSERT_OK(Put(Key(3), "val3"));
+
+  // Wait until resume started to schedule another flush
+  TEST_SYNC_POINT("Wait for resume to start");
+  // This flush should not be scheduled due to bg error
+  ASSERT_OK(Put(Key(4), "val4"));
+
+  // TEST_WaitForBackgroundWork() returns background error
+  // after all background work is done.
+  ASSERT_NOK(dbfull()->TEST_WaitForBackgroundWork());
+  // Flush should abort and not writing any table
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+
+  // Wait until this flush is done.
+  TEST_SYNC_POINT("Recovery should continue here");
+  TEST_SYNC_POINT("Wait for error recover");
+  // error recovery can schedule new flushes, but should not
+  // encounter error
+  ASSERT_OK(dbfull()->TEST_WaitForBackgroundWork());
+  ASSERT_EQ(1, NumTableFilesAtLevel(0));
+}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_impl/compacted_db_impl.cc

@@ -43,18 +43,25 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
              /*timestamp*/ nullptr);
 }
 
-Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
-                            const Slice& key, PinnableSlice* value,
-                            std::string* timestamp) {
-  if (options.io_activity != Env::IOActivity::kUnknown) {
+Status CompactedDBImpl::Get(const ReadOptions& _read_options,
+                            ColumnFamilyHandle*, const Slice& key,
+                            PinnableSlice* value, std::string* timestamp) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kGet) {
     return Status::InvalidArgument(
-        "Cannot call Get with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
+        "Can only call Get with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kGet`");
   }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kGet;
+  }
+
   assert(user_comparator_);
-  if (options.timestamp) {
-    const Status s = FailIfTsMismatchCf(
-        DefaultColumnFamily(), *(options.timestamp), /*ts_for_read=*/true);
+  if (read_options.timestamp) {
+    const Status s =
+        FailIfTsMismatchCf(DefaultColumnFamily(), *(read_options.timestamp),
+                           /*ts_for_read=*/true);
     if (!s.ok()) {
       return s;
     }
@@ -74,7 +81,7 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
   GetWithTimestampReadCallback read_cb(kMaxSequenceNumber);
   std::string* ts =
       user_comparator_->timestamp_size() > 0 ? timestamp : nullptr;
-  LookupKey lkey(key, kMaxSequenceNumber, options.timestamp);
+  LookupKey lkey(key, kMaxSequenceNumber, read_options.timestamp);
   GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                          GetContext::kNotFound, lkey.user_key(), value,
                          /*columns=*/nullptr, ts, nullptr, nullptr, true,
@@ -88,8 +95,8 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
           /*b_has_ts=*/false) < 0) {
     return Status::NotFound();
   }
-  Status s = f.fd.table_reader->Get(options, lkey.internal_key(), &get_context,
-                                    nullptr);
+  Status s = f.fd.table_reader->Get(read_options, lkey.internal_key(),
+                                    &get_context, nullptr);
   if (!s.ok() && !s.IsNotFound()) {
     return s;
   }
@@ -106,15 +113,28 @@ std::vector<Status> CompactedDBImpl::MultiGet(
 }
 
 std::vector<Status> CompactedDBImpl::MultiGet(
-    const ReadOptions& options, const std::vector<ColumnFamilyHandle*>&,
+    const ReadOptions& _read_options, const std::vector<ColumnFamilyHandle*>&,
     const std::vector<Slice>& keys, std::vector<std::string>* values,
     std::vector<std::string>* timestamps) {
   assert(user_comparator_);
   size_t num_keys = keys.size();
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kMultiGet) {
+    Status s = Status::InvalidArgument(
+        "Can only call MultiGet with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kMultiGet`");
+    return std::vector<Status>(num_keys, s);
+  }
 
-  if (options.timestamp) {
-    Status s = FailIfTsMismatchCf(DefaultColumnFamily(), *(options.timestamp),
-                                  /*ts_for_read=*/true);
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kMultiGet;
+  }
+
+  if (read_options.timestamp) {
+    Status s =
+        FailIfTsMismatchCf(DefaultColumnFamily(), *(read_options.timestamp),
+                           /*ts_for_read=*/true);
     if (!s.ok()) {
       return std::vector<Status>(num_keys, s);
     }
@@ -136,7 +156,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(
   GetWithTimestampReadCallback read_cb(kMaxSequenceNumber);
   autovector<TableReader*, 16> reader_list;
   for (const auto& key : keys) {
-    LookupKey lkey(key, kMaxSequenceNumber, options.timestamp);
+    LookupKey lkey(key, kMaxSequenceNumber, read_options.timestamp);
     const FdWithKeyRange& f = files_.files[FindFile(lkey.user_key())];
     if (user_comparator_->CompareWithoutTimestamp(
             key, /*a_has_ts=*/false,
@@ -159,14 +179,15 @@ std::vector<Status> CompactedDBImpl::MultiGet(
     if (r != nullptr) {
       PinnableSlice pinnable_val;
       std::string& value = (*values)[idx];
-      LookupKey lkey(keys[idx], kMaxSequenceNumber, options.timestamp);
+      LookupKey lkey(keys[idx], kMaxSequenceNumber, read_options.timestamp);
       std::string* timestamp = timestamps ? &(*timestamps)[idx] : nullptr;
       GetContext get_context(
           user_comparator_, nullptr, nullptr, nullptr, GetContext::kNotFound,
           lkey.user_key(), &pinnable_val, /*columns=*/nullptr,
           user_comparator_->timestamp_size() > 0 ? timestamp : nullptr, nullptr,
           nullptr, true, nullptr, nullptr, nullptr, nullptr, &read_cb);
-      Status s = r->Get(options, lkey.internal_key(), &get_context, nullptr);
+      Status s =
+          r->Get(read_options, lkey.internal_key(), &get_context, nullptr);
       assert(static_cast<size_t>(idx) < statuses.size());
       if (!s.ok() && !s.IsNotFound()) {
         statuses[idx] = s;

db/db_impl/compacted_db_impl.h

@@ -30,9 +30,9 @@ class CompactedDBImpl : public DBImpl {
                      ColumnFamilyHandle* column_family, const Slice& key,
                      PinnableSlice* value) override;
 
-  Status Get(const ReadOptions& options, ColumnFamilyHandle* column_family,
-             const Slice& key, PinnableSlice* value,
-             std::string* timestamp) override;
+  Status Get(const ReadOptions& _read_options,
+             ColumnFamilyHandle* column_family, const Slice& key,
+             PinnableSlice* value, std::string* timestamp) override;
 
   using DB::MultiGet;
   // Note that CompactedDBImpl::MultiGet is not the optimized version of
@@ -43,7 +43,7 @@ class CompactedDBImpl : public DBImpl {
       const std::vector<Slice>& keys,
       std::vector<std::string>* values) override;
 
-  std::vector<Status> MultiGet(const ReadOptions& options,
+  std::vector<Status> MultiGet(const ReadOptions& _read_options,
                                const std::vector<ColumnFamilyHandle*>&,
                                const std::vector<Slice>& keys,
                                std::vector<std::string>* values,
@@ -118,16 +118,24 @@ class CompactedDBImpl : public DBImpl {
       const IngestExternalFileOptions& /*ingestion_options*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
+
   using DB::CreateColumnFamilyWithImport;
   virtual Status CreateColumnFamilyWithImport(
       const ColumnFamilyOptions& /*options*/,
       const std::string& /*column_family_name*/,
       const ImportColumnFamilyOptions& /*import_options*/,
-      const ExportImportFilesMetaData& /*metadata*/,
+      const std::vector<const ExportImportFilesMetaData*>& /*metadatas*/,
       ColumnFamilyHandle** /*handle*/) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
 
+  using DB::ClipColumnFamily;
+  virtual Status ClipColumnFamily(ColumnFamilyHandle* /*column_family*/,
+                                  const Slice& /*begin*/,
+                                  const Slice& /*end*/) override {
+    return Status::NotSupported("Not supported in compacted db mode.");
+  }
+
   // FIXME: some missing overrides for more "write" functions
   // Share with DBImplReadOnly?
 

db/db_impl/db_impl.cc

@@ -28,6 +28,7 @@
 #include "db/arena_wrapped_db_iter.h"
 #include "db/builder.h"
 #include "db/compaction/compaction_job.h"
+#include "db/convenience_impl.h"
 #include "db/db_info_dumper.h"
 #include "db/db_iter.h"
 #include "db/dbformat.h"
@@ -74,7 +75,6 @@
 #include "port/port.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/compaction_filter.h"
-#include "rocksdb/convenience.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/merge_operator.h"
@@ -149,6 +149,24 @@ void DumpSupportInfo(Logger* logger) {
 
   ROCKS_LOG_HEADER(logger, "DMutex implementation: %s", DMutex::kName());
 }
+
+// `start` is the inclusive lower user key bound without user-defined timestamp
+// `limit` is the exclusive upper user key bound without user-defined timestamp
+std::tuple<Slice, Slice> MaybeAddTimestampsToRange(const Slice& start,
+                                                   const Slice& limit,
+                                                   size_t ts_sz,
+                                                   std::string* start_with_ts,
+                                                   std::string* limit_with_ts) {
+  if (ts_sz == 0) {
+    return std::make_tuple(start, limit);
+  }
+  // Maximum timestamp means including all key with any timestamp
+  AppendKeyWithMaxTimestamp(start_with_ts, start, ts_sz);
+  // Append a maximum timestamp as the range limit is exclusive:
+  // [start, limit)
+  AppendKeyWithMaxTimestamp(limit_with_ts, limit, ts_sz);
+  return std::make_tuple(Slice(*start_with_ts), Slice(*limit_with_ts));
+}
 }  // namespace
 
 DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
@@ -183,6 +201,7 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
       batch_per_txn_(batch_per_txn),
       next_job_id_(1),
       shutting_down_(false),
+      reject_new_background_jobs_(false),
       db_lock_(nullptr),
       manual_compaction_paused_(false),
       bg_cv_(&mutex_),
@@ -258,6 +277,9 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
   co.capacity = table_cache_size;
   co.num_shard_bits = immutable_db_options_.table_cache_numshardbits;
   co.metadata_charge_policy = kDontChargeCacheMetadata;
+  // TODO: Consider a non-fixed seed once test fallout (prefetch_test) is
+  // dealt with
+  co.hash_seed = 0;
   table_cache_ = NewLRUCache(co);
   SetDbSessionId();
   assert(!db_session_id_.empty());
@@ -389,22 +411,7 @@ Status DBImpl::ResumeImpl(DBRecoverContext context) {
     FlushOptions flush_opts;
     // We allow flush to stall write since we are trying to resume from error.
     flush_opts.allow_write_stall = true;
-    if (immutable_db_options_.atomic_flush) {
-      mutex_.Unlock();
-      s = AtomicFlushMemTables(flush_opts, context.flush_reason);
-      mutex_.Lock();
-    } else {
-      for (auto cfd : versions_->GetRefedColumnFamilySet()) {
-        if (cfd->IsDropped()) {
-          continue;
-        }
-        InstrumentedMutexUnlock u(&mutex_);
-        s = FlushMemTable(cfd, flush_opts, context.flush_reason);
-        if (!s.ok()) {
-          break;
-        }
-      }
-    }
+    s = FlushAllColumnFamilies(flush_opts, context.flush_reason);
     if (!s.ok()) {
       ROCKS_LOG_INFO(immutable_db_options_.info_log,
                      "DB resume requested but failed due to Flush failure [%s]",
@@ -464,6 +471,28 @@ Status DBImpl::ResumeImpl(DBRecoverContext context) {
   if (shutdown_initiated_) {
     s = Status::ShutdownInProgress();
   }
+  if (s.ok() && context.flush_after_recovery) {
+    // Since we drop all non-recovery flush requests during recovery,
+    // and new memtable may fill up during recovery,
+    // schedule one more round of flush.
+    FlushOptions flush_opts;
+    flush_opts.allow_write_stall = false;
+    flush_opts.wait = false;
+    Status status = FlushAllColumnFamilies(
+        flush_opts, FlushReason::kCatchUpAfterErrorRecovery);
+    if (!status.ok()) {
+      // FlushAllColumnFamilies internally should take care of setting
+      // background error if needed.
+      ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                     "The catch up flush after successful recovery failed [%s]",
+                     s.ToString().c_str());
+    }
+    // FlushAllColumnFamilies releases and re-acquires mutex.
+    if (shutdown_initiated_) {
+      s = Status::ShutdownInProgress();
+    }
+  }
+
   if (s.ok()) {
     for (auto cfd : *versions_->GetColumnFamilySet()) {
       SchedulePendingCompaction(cfd);
@@ -491,36 +520,15 @@ void DBImpl::WaitForBackgroundWork() {
 void DBImpl::CancelAllBackgroundWork(bool wait) {
   ROCKS_LOG_INFO(immutable_db_options_.info_log,
                  "Shutdown: canceling all background work");
-
-  for (uint8_t task_type = 0;
-       task_type < static_cast<uint8_t>(PeriodicTaskType::kMax); task_type++) {
-    Status s = periodic_task_scheduler_.Unregister(
-        static_cast<PeriodicTaskType>(task_type));
-    if (!s.ok()) {
-      ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                     "Failed to unregister periodic task %d, status: %s",
-                     task_type, s.ToString().c_str());
-    }
-  }
+  Status s = CancelPeriodicTaskScheduler();
+  s.PermitUncheckedError();
 
   InstrumentedMutexLock l(&mutex_);
   if (!shutting_down_.load(std::memory_order_acquire) &&
       has_unpersisted_data_.load(std::memory_order_relaxed) &&
       !mutable_db_options_.avoid_flush_during_shutdown) {
-    if (immutable_db_options_.atomic_flush) {
-      mutex_.Unlock();
-      Status s = AtomicFlushMemTables(FlushOptions(), FlushReason::kShutDown);
-      s.PermitUncheckedError();  //**TODO: What to do on error?
-      mutex_.Lock();
-    } else {
-      for (auto cfd : versions_->GetRefedColumnFamilySet()) {
-        if (!cfd->IsDropped() && cfd->initialized() && !cfd->mem()->IsEmpty()) {
-          InstrumentedMutexUnlock u(&mutex_);
-          Status s = FlushMemTable(cfd, FlushOptions(), FlushReason::kShutDown);
-          s.PermitUncheckedError();  //**TODO: What to do on error?
-        }
-      }
-    }
+    s = DBImpl::FlushAllColumnFamilies(FlushOptions(), FlushReason::kShutDown);
+    s.PermitUncheckedError();  //**TODO: What to do on error?
   }
 
   shutting_down_.store(true, std::memory_order_release);
@@ -869,6 +877,21 @@ Status DBImpl::RegisterRecordSeqnoTimeWorker() {
   return s;
 }
 
+Status DBImpl::CancelPeriodicTaskScheduler() {
+  Status s = Status::OK();
+  for (uint8_t task_type = 0;
+       task_type < static_cast<uint8_t>(PeriodicTaskType::kMax); task_type++) {
+    s = periodic_task_scheduler_.Unregister(
+        static_cast<PeriodicTaskType>(task_type));
+    if (!s.ok()) {
+      ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                     "Failed to unregister periodic task %d, status: %s",
+                     task_type, s.ToString().c_str());
+    }
+  }
+  return s;
+}
+
 // esitmate the total size of stats_history_
 size_t DBImpl::EstimateInMemoryStatsHistorySize() const {
   size_t size_total =
@@ -967,7 +990,7 @@ void DBImpl::PersistStats() {
                      "Storing %" ROCKSDB_PRIszt " stats with timestamp %" PRIu64
                      " to in-memory stats history",
                      stats_slice_.size(), now_seconds);
-      stats_history_[now_seconds] = stats_delta;
+      stats_history_[now_seconds] = std::move(stats_delta);
     }
     stats_slice_initialized_ = true;
     std::swap(stats_slice_, stats_map);
@@ -1919,15 +1942,43 @@ Status DBImpl::Get(const ReadOptions& read_options,
   return Get(read_options, column_family, key, value, /*timestamp=*/nullptr);
 }
 
-Status DBImpl::Get(const ReadOptions& read_options,
+Status DBImpl::GetImpl(const ReadOptions& read_options,
+                       ColumnFamilyHandle* column_family, const Slice& key,
+                       PinnableSlice* value) {
+  return GetImpl(read_options, column_family, key, value,
+                 /*timestamp=*/nullptr);
+}
+
+Status DBImpl::Get(const ReadOptions& _read_options,
                    ColumnFamilyHandle* column_family, const Slice& key,
                    PinnableSlice* value, std::string* timestamp) {
   assert(value != nullptr);
   value->Reset();
+
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kGet) {
+    return Status::InvalidArgument(
+        "Can only call Get with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kGet`");
+  }
+
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kGet;
+  }
+
+  Status s = GetImpl(read_options, column_family, key, value, timestamp);
+  return s;
+}
+
+Status DBImpl::GetImpl(const ReadOptions& read_options,
+                       ColumnFamilyHandle* column_family, const Slice& key,
+                       PinnableSlice* value, std::string* timestamp) {
   GetImplOptions get_impl_options;
   get_impl_options.column_family = column_family;
   get_impl_options.value = value;
   get_impl_options.timestamp = timestamp;
+
   Status s = GetImpl(read_options, key, get_impl_options);
   return s;
 }
@@ -1996,11 +2047,6 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
 
   assert(get_impl_options.column_family);
 
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return Status::InvalidArgument(
-        "Cannot call Get with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-  }
 
   if (read_options.timestamp) {
     const Status s = FailIfTsMismatchCf(get_impl_options.column_family,
@@ -2294,7 +2340,7 @@ std::vector<Status> DBImpl::MultiGet(
 }
 
 std::vector<Status> DBImpl::MultiGet(
-    const ReadOptions& read_options,
+    const ReadOptions& _read_options,
     const std::vector<ColumnFamilyHandle*>& column_family,
     const std::vector<Slice>& keys, std::vector<std::string>* values,
     std::vector<std::string>* timestamps) {
@@ -2306,12 +2352,30 @@ std::vector<Status> DBImpl::MultiGet(
   assert(column_family.size() == num_keys);
   std::vector<Status> stat_list(num_keys);
 
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kMultiGet) {
+    Status s = Status::InvalidArgument(
+        "Can only call MultiGet with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kMultiGet`");
+
+    for (size_t i = 0; i < num_keys; ++i) {
+      stat_list[i] = s;
+    }
+    return stat_list;
+  }
+
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kMultiGet;
+  }
+
   bool should_fail = false;
   for (size_t i = 0; i < num_keys; ++i) {
     assert(column_family[i]);
     if (read_options.timestamp) {
-      stat_list[i] = FailIfTsMismatchCf(
-          column_family[i], *(read_options.timestamp), /*ts_for_read=*/true);
+      stat_list[i] =
+          FailIfTsMismatchCf(column_family[i], *(read_options.timestamp),
+                             /*ts_for_read=*/true);
       if (!stat_list[i].ok()) {
         should_fail = true;
       }
@@ -2475,7 +2539,6 @@ std::vector<Status> DBImpl::MultiGet(
 
   // Post processing (decrement reference counts and record statistics)
   PERF_TIMER_GUARD(get_post_process_time);
-  autovector<SuperVersion*> superversions_to_delete;
 
   for (auto mgd_iter : multiget_cf_data) {
     auto mgd = mgd_iter.second;
@@ -2625,10 +2688,26 @@ void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
            /* timestamps */ nullptr, statuses, sorted_input);
 }
 
-void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
+void DBImpl::MultiGet(const ReadOptions& _read_options, const size_t num_keys,
                       ColumnFamilyHandle** column_families, const Slice* keys,
                       PinnableSlice* values, std::string* timestamps,
                       Status* statuses, const bool sorted_input) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kMultiGet) {
+    Status s = Status::InvalidArgument(
+        "Can only call MultiGet with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kMultiGet`");
+    for (size_t i = 0; i < num_keys; ++i) {
+      if (statuses[i].ok()) {
+        statuses[i] = s;
+      }
+    }
+    return;
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kMultiGet;
+  }
   MultiGetCommon(read_options, num_keys, column_families, keys, values,
                  /* columns */ nullptr, timestamps, statuses, sorted_input);
 }
@@ -2643,7 +2722,6 @@ void DBImpl::MultiGetCommon(const ReadOptions& read_options,
   if (num_keys == 0) {
     return;
   }
-
   bool should_fail = false;
   for (size_t i = 0; i < num_keys; ++i) {
     ColumnFamilyHandle* cfh = column_families[i];
@@ -2826,11 +2904,28 @@ void DBImpl::MultiGet(const ReadOptions& read_options,
            /* timestamps */ nullptr, statuses, sorted_input);
 }
 
-void DBImpl::MultiGet(const ReadOptions& read_options,
+void DBImpl::MultiGet(const ReadOptions& _read_options,
                       ColumnFamilyHandle* column_family, const size_t num_keys,
                       const Slice* keys, PinnableSlice* values,
                       std::string* timestamps, Status* statuses,
                       const bool sorted_input) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kMultiGet) {
+    Status s = Status::InvalidArgument(
+        "Can only call MultiGet with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kMultiGet`");
+    for (size_t i = 0; i < num_keys; ++i) {
+      if (statuses[i].ok()) {
+        statuses[i] = s;
+      }
+    }
+    return;
+  }
+
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kMultiGet;
+  }
   MultiGetCommon(read_options, column_family, num_keys, keys, values,
                  /* columns */ nullptr, timestamps, statuses, sorted_input);
 }
@@ -2879,9 +2974,20 @@ void DBImpl::MultiGetCommon(const ReadOptions& read_options,
 }
 
 void DBImpl::MultiGetWithCallback(
-    const ReadOptions& read_options, ColumnFamilyHandle* column_family,
+    const ReadOptions& _read_options, ColumnFamilyHandle* column_family,
     ReadCallback* callback,
     autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kMultiGet) {
+    assert(false);
+    return;
+  }
+
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kMultiGet;
+  }
+
   std::array<MultiGetColumnFamilyData, 1> multiget_cf_data;
   multiget_cf_data[0] = MultiGetColumnFamilyData(column_family, nullptr);
   std::function<MultiGetColumnFamilyData*(
@@ -2952,11 +3058,6 @@ Status DBImpl::MultiGetImpl(
     autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys,
     SuperVersion* super_version, SequenceNumber snapshot,
     ReadCallback* callback) {
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return Status::InvalidArgument(
-        "Cannot call MultiGet with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-  }
   PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
   StopWatch sw(immutable_db_options_.clock, stats_, DB_MULTIGET);
 
@@ -3189,6 +3290,8 @@ Status DBImpl::CreateColumnFamilyImpl(const ColumnFamilyOptions& cf_options,
     edit.SetColumnFamily(new_id);
     edit.SetLogNumber(logfile_number_);
     edit.SetComparatorName(cf_options.comparator->Name());
+    edit.SetPersistUserDefinedTimestamps(
+        cf_options.persist_user_defined_timestamps);
 
     // LogAndApply will both write the creation in MANIFEST and create
     // ColumnFamilyData object
@@ -3379,8 +3482,19 @@ bool DBImpl::KeyMayExist(const ReadOptions& read_options,
   return s.ok() || s.IsIncomplete();
 }
 
-Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
+Iterator* DBImpl::NewIterator(const ReadOptions& _read_options,
                               ColumnFamilyHandle* column_family) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kDBIterator) {
+    return NewErrorIterator(Status::InvalidArgument(
+        "Can only call NewIterator with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kDBIterator`"));
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kDBIterator;
+  }
+
   if (read_options.managed) {
     return NewErrorIterator(
         Status::NotSupported("Managed iterator is not supported anymore."));
@@ -3390,17 +3504,12 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
     return NewErrorIterator(Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators."));
   }
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return NewErrorIterator(Status::InvalidArgument(
-        "Cannot call NewIterator with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`"));
-  }
-
   assert(column_family);
 
   if (read_options.timestamp) {
-    const Status s = FailIfTsMismatchCf(
-        column_family, *(read_options.timestamp), /*ts_for_read=*/true);
+    const Status s =
+        FailIfTsMismatchCf(column_family, *(read_options.timestamp),
+                           /*ts_for_read=*/true);
     if (!s.ok()) {
       return NewErrorIterator(s);
     }
@@ -3520,9 +3629,19 @@ ArenaWrappedDBIter* DBImpl::NewIteratorImpl(const ReadOptions& read_options,
 }
 
 Status DBImpl::NewIterators(
-    const ReadOptions& read_options,
+    const ReadOptions& _read_options,
     const std::vector<ColumnFamilyHandle*>& column_families,
     std::vector<Iterator*>* iterators) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kDBIterator) {
+    return Status::InvalidArgument(
+        "Can only call NewIterators with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kDBIterator`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kDBIterator;
+  }
   if (read_options.managed) {
     return Status::NotSupported("Managed iterator is not supported anymore.");
   }
@@ -3530,11 +3649,6 @@ Status DBImpl::NewIterators(
     return Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators.");
   }
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return Status::InvalidArgument(
-        "Cannot call NewIterators with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-  }
 
   if (read_options.timestamp) {
     for (auto* cf : column_families) {
@@ -4181,9 +4295,17 @@ void DBImpl::GetApproximateMemTableStats(ColumnFamilyHandle* column_family,
   ColumnFamilyData* cfd = cfh->cfd();
   SuperVersion* sv = GetAndRefSuperVersion(cfd);
 
+  const Comparator* const ucmp = column_family->GetComparator();
+  assert(ucmp);
+  size_t ts_sz = ucmp->timestamp_size();
+
+  // Add timestamp if needed
+  std::string start_with_ts, limit_with_ts;
+  auto [start, limit] = MaybeAddTimestampsToRange(
+      range.start, range.limit, ts_sz, &start_with_ts, &limit_with_ts);
   // Convert user_key into a corresponding internal key.
-  InternalKey k1(range.start, kMaxSequenceNumber, kValueTypeForSeek);
-  InternalKey k2(range.limit, kMaxSequenceNumber, kValueTypeForSeek);
+  InternalKey k1(start, kMaxSequenceNumber, kValueTypeForSeek);
+  InternalKey k2(limit, kMaxSequenceNumber, kValueTypeForSeek);
   MemTable::MemTableStats memStats =
       sv->mem->ApproximateStats(k1.Encode(), k2.Encode());
   MemTable::MemTableStats immStats =
@@ -4214,20 +4336,10 @@ Status DBImpl::GetApproximateSizes(const SizeApproximationOptions& options,
   // TODO: plumb Env::IOActivity
   const ReadOptions read_options;
   for (int i = 0; i < n; i++) {
-    Slice start = range[i].start;
-    Slice limit = range[i].limit;
-
     // Add timestamp if needed
     std::string start_with_ts, limit_with_ts;
-    if (ts_sz > 0) {
-      // Maximum timestamp means including all key with any timestamp
-      AppendKeyWithMaxTimestamp(&start_with_ts, start, ts_sz);
-      // Append a maximum timestamp as the range limit is exclusive:
-      // [start, limit)
-      AppendKeyWithMaxTimestamp(&limit_with_ts, limit, ts_sz);
-      start = start_with_ts;
-      limit = limit_with_ts;
-    }
+    auto [start, limit] = MaybeAddTimestampsToRange(
+        range[i].start, range[i].limit, ts_sz, &start_with_ts, &limit_with_ts);
     // Convert user_key into a corresponding internal key.
     InternalKey k1(start, kMaxSequenceNumber, kValueTypeForSeek);
     InternalKey k2(limit, kMaxSequenceNumber, kValueTypeForSeek);
@@ -4443,10 +4555,12 @@ Status DBImpl::DeleteFilesInRanges(ColumnFamilyHandle* column_family,
           deleted_files.insert(level_file);
           level_file->being_compacted = true;
         }
-        vstorage->ComputeCompactionScore(*cfd->ioptions(),
-                                         *cfd->GetLatestMutableCFOptions());
       }
     }
+    if (!deleted_files.empty()) {
+      vstorage->ComputeCompactionScore(*cfd->ioptions(),
+                                       *cfd->GetLatestMutableCFOptions());
+    }
     if (edit.GetDeletedFiles().empty()) {
       job_context.Clean();
       return status;
@@ -4520,7 +4634,6 @@ void DBImpl::GetAllColumnFamilyMetaData(
   }
 }
 
-
 Status DBImpl::CheckConsistency() {
   mutex_.AssertHeld();
   std::vector<LiveFileMetaData> metadata;
@@ -4911,6 +5024,15 @@ Status DBImpl::WriteOptionsFile(bool need_mutex_lock,
   if (s.ok()) {
     s = RenameTempFileToOptionsFile(file_name);
   }
+
+  if (!s.ok() && GetEnv()->FileExists(file_name).ok()) {
+    if (!GetEnv()->DeleteFile(file_name).ok()) {
+      ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                     "Unable to delete temp options file %s",
+                     file_name.c_str());
+    }
+  }
+
   // restore lock
   if (!need_mutex_lock) {
     mutex_.Lock();
@@ -5565,14 +5687,24 @@ Status DBImpl::IngestExternalFiles(
 Status DBImpl::CreateColumnFamilyWithImport(
     const ColumnFamilyOptions& options, const std::string& column_family_name,
     const ImportColumnFamilyOptions& import_options,
-    const ExportImportFilesMetaData& metadata, ColumnFamilyHandle** handle) {
+    const std::vector<const ExportImportFilesMetaData*>& metadatas,
+    ColumnFamilyHandle** handle) {
   assert(handle != nullptr);
   assert(*handle == nullptr);
   // TODO: plumb Env::IOActivity
   const ReadOptions read_options;
   std::string cf_comparator_name = options.comparator->Name();
-  if (cf_comparator_name != metadata.db_comparator_name) {
-    return Status::InvalidArgument("Comparator name mismatch");
+
+  size_t total_file_num = 0;
+  std::vector<std::vector<LiveFileMetaData*>> metadata_files(metadatas.size());
+  for (size_t i = 0; i < metadatas.size(); i++) {
+    if (cf_comparator_name != metadatas[i]->db_comparator_name) {
+      return Status::InvalidArgument("Comparator name mismatch");
+    }
+    for (auto& file : metadatas[i]->files) {
+      metadata_files[i].push_back((LiveFileMetaData*)&file);
+    }
+    total_file_num += metadatas[i]->files.size();
   }
 
   // Create column family.
@@ -5586,7 +5718,7 @@ Status DBImpl::CreateColumnFamilyWithImport(
   auto cfd = cfh->cfd();
   ImportColumnFamilyJob import_job(versions_.get(), cfd, immutable_db_options_,
                                    file_options_, import_options,
-                                   metadata.files, io_tracer_);
+                                   metadata_files, io_tracer_);
 
   SuperVersionContext dummy_sv_ctx(/* create_superversion */ true);
   VersionEdit dummy_edit;
@@ -5609,7 +5741,7 @@ Status DBImpl::CreateColumnFamilyWithImport(
       // reuse the file number that has already assigned to the internal file,
       // and this will overwrite the external file. To protect the external
       // file, we have to make sure the file number will never being reused.
-      next_file_number = versions_->FetchAddFileNumber(metadata.files.size());
+      next_file_number = versions_->FetchAddFileNumber(total_file_num);
       auto cf_options = cfd->GetLatestMutableCFOptions();
       status =
           versions_->LogAndApply(cfd, *cf_options, read_options, &dummy_edit,
@@ -5694,12 +5826,110 @@ Status DBImpl::CreateColumnFamilyWithImport(
   return status;
 }
 
-Status DBImpl::VerifyFileChecksums(const ReadOptions& read_options) {
-  return VerifyChecksumInternal(read_options, /*use_file_checksum=*/true);
+Status DBImpl::ClipColumnFamily(ColumnFamilyHandle* column_family,
+                                const Slice& begin_key, const Slice& end_key) {
+  assert(column_family);
+  Status status;
+  // Flush memtable
+  FlushOptions flush_opts;
+  flush_opts.allow_write_stall = true;
+  auto* cfd =
+      static_cast_with_check<ColumnFamilyHandleImpl>(column_family)->cfd();
+  if (immutable_db_options_.atomic_flush) {
+    status = AtomicFlushMemTables(flush_opts, FlushReason::kDeleteFiles,
+                                  {} /* provided_candidate_cfds */,
+                                  false /* entered_write_thread */);
+  } else {
+    status = FlushMemTable(cfd, flush_opts, FlushReason::kDeleteFiles,
+                           false /* entered_write_thread */);
+  }
+
+  if (status.ok()) {
+    // DeleteFilesInRanges non-overlap files except L0
+    std::vector<RangePtr> ranges;
+    ranges.push_back(RangePtr(nullptr, &begin_key));
+    ranges.push_back(RangePtr(&end_key, nullptr));
+    status = DeleteFilesInRanges(column_family, ranges.data(), ranges.size());
+  }
+
+  // DeleteRange the remaining overlapping keys
+  bool empty_after_delete = false;
+  if (status.ok()) {
+    Slice smallest_user_key, largest_user_key;
+    {
+      // Lock db mutex
+      InstrumentedMutexLock l(&mutex_);
+      cfd->current()->GetSstFilesBoundaryKeys(&smallest_user_key,
+                                              &largest_user_key);
+    }
+    // all the files has been deleted after DeleteFilesInRanges;
+    if (smallest_user_key.empty() && largest_user_key.empty()) {
+      empty_after_delete = true;
+    } else {
+      const Comparator* const ucmp = column_family->GetComparator();
+      WriteOptions wo;
+      // Delete [smallest_user_key, clip_begin_key)
+      if (ucmp->Compare(smallest_user_key, begin_key) < 0) {
+        status = DeleteRange(wo, column_family, smallest_user_key, begin_key);
+      }
+
+      if (status.ok()) {
+        // Delete [clip_end_key, largest_use_key]
+        if (ucmp->Compare(end_key, largest_user_key) < 0) {
+          status = DeleteRange(wo, column_family, end_key, largest_user_key);
+          if (status.ok()) {
+            status = Delete(wo, column_family, largest_user_key);
+          }
+        }
+      }
+    }
+  }
+
+  if (status.ok() && !empty_after_delete) {
+    // CompactRange delete all the tombstones
+    CompactRangeOptions compact_options;
+    compact_options.exclusive_manual_compaction = true;
+    compact_options.bottommost_level_compaction =
+        BottommostLevelCompaction::kForceOptimized;
+    // We could just compact the ranges [null, clip_begin_key] and
+    // [clip_end_key, null]. But due to how manual compaction calculates the
+    // last level to compact to and that range tombstones are not dropped
+    // during non-bottommost compactions, calling CompactRange() on these two
+    // ranges may not clear all range tombstones.
+    status = CompactRange(compact_options, nullptr, nullptr);
+  }
+  return status;
 }
 
-Status DBImpl::VerifyChecksum(const ReadOptions& read_options) {
-  return VerifyChecksumInternal(read_options, /*use_file_checksum=*/false);
+Status DBImpl::VerifyFileChecksums(const ReadOptions& _read_options) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kVerifyFileChecksums) {
+    return Status::InvalidArgument(
+        "Can only call VerifyFileChecksums with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or "
+        "`Env::IOActivity::kVerifyFileChecksums`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kVerifyFileChecksums;
+  }
+  return VerifyChecksumInternal(read_options,
+                                /*use_file_checksum=*/true);
+}
+
+Status DBImpl::VerifyChecksum(const ReadOptions& _read_options) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kVerifyDBChecksum) {
+    return Status::InvalidArgument(
+        "Can only call VerifyChecksum with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kVerifyDBChecksum`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kVerifyDBChecksum;
+  }
+  return VerifyChecksumInternal(read_options,
+                                /*use_file_checksum=*/false);
 }
 
 Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
@@ -5711,12 +5941,6 @@ Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
 
   Status s;
 
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    s = Status::InvalidArgument(
-        "Cannot verify file checksum with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-    return s;
-  }
   if (use_file_checksum) {
     FileChecksumGenFactory* const file_checksum_gen_factory =
         immutable_db_options_.file_checksum_gen_factory.get();
@@ -5727,6 +5951,7 @@ Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
       return s;
     }
   }
+  // FIXME? What does it mean if read_options.verify_checksums == false?
 
   // TODO: simplify using GetRefedColumnFamilySet?
   std::vector<ColumnFamilyData*> cfd_list;
@@ -5767,7 +5992,7 @@ Status DBImpl::VerifyChecksumInternal(const ReadOptions& read_options,
                                      fmeta->file_checksum_func_name, fname,
                                      read_options);
         } else {
-          s = ROCKSDB_NAMESPACE::VerifySstFileChecksum(
+          s = ROCKSDB_NAMESPACE::VerifySstFileChecksumInternal(
               opts, file_options_, read_options, fname, fd.largest_seqno);
         }
         RecordTick(stats_, VERIFY_CHECKSUM_READ_BYTES,
@@ -5830,12 +6055,6 @@ Status DBImpl::VerifyFullFileChecksum(const std::string& file_checksum_expected,
                                       const std::string& func_name_expected,
                                       const std::string& fname,
                                       const ReadOptions& read_options) {
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return Status::InvalidArgument(
-        "Cannot call VerifyChecksum with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-  }
-
   Status s;
   if (file_checksum_expected == kUnknownFileChecksum) {
     return s;
@@ -5846,8 +6065,8 @@ Status DBImpl::VerifyFullFileChecksum(const std::string& file_checksum_expected,
       fs_.get(), fname, immutable_db_options_.file_checksum_gen_factory.get(),
       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(),
-      read_options.rate_limiter_priority);
+      io_tracer_, immutable_db_options_.rate_limiter.get(), read_options,
+      immutable_db_options_.stats, immutable_db_options_.clock);
   if (s.ok()) {
     assert(func_name_expected == func_name);
     if (file_checksum != file_checksum_expected) {

db/db_impl/db_impl.h

@@ -234,7 +234,7 @@ class DBImpl : public DB {
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
                      PinnableSlice* value) override;
-  virtual Status Get(const ReadOptions& options,
+  virtual Status Get(const ReadOptions& _read_options,
                      ColumnFamilyHandle* column_family, const Slice& key,
                      PinnableSlice* value, std::string* timestamp) override;
 
@@ -265,7 +265,7 @@ class DBImpl : public DB {
       const std::vector<Slice>& keys,
       std::vector<std::string>* values) override;
   virtual std::vector<Status> MultiGet(
-      const ReadOptions& options,
+      const ReadOptions& _read_options,
       const std::vector<ColumnFamilyHandle*>& column_family,
       const std::vector<Slice>& keys, std::vector<std::string>* values,
       std::vector<std::string>* timestamps) override;
@@ -280,8 +280,9 @@ class DBImpl : public DB {
   void MultiGet(const ReadOptions& options, ColumnFamilyHandle* column_family,
                 const size_t num_keys, const Slice* keys, PinnableSlice* values,
                 Status* statuses, const bool sorted_input = false) override;
-  void MultiGet(const ReadOptions& options, ColumnFamilyHandle* column_family,
-                const size_t num_keys, const Slice* keys, PinnableSlice* values,
+  void MultiGet(const ReadOptions& _read_options,
+                ColumnFamilyHandle* column_family, const size_t num_keys,
+                const Slice* keys, PinnableSlice* values,
                 std::string* timestamps, Status* statuses,
                 const bool sorted_input = false) override;
 
@@ -289,13 +290,13 @@ class DBImpl : public DB {
                 ColumnFamilyHandle** column_families, const Slice* keys,
                 PinnableSlice* values, Status* statuses,
                 const bool sorted_input = false) override;
-  void MultiGet(const ReadOptions& options, const size_t num_keys,
+  void MultiGet(const ReadOptions& _read_options, const size_t num_keys,
                 ColumnFamilyHandle** column_families, const Slice* keys,
                 PinnableSlice* values, std::string* timestamps,
                 Status* statuses, const bool sorted_input = false) override;
 
   void MultiGetWithCallback(
-      const ReadOptions& options, ColumnFamilyHandle* column_family,
+      const ReadOptions& _read_options, ColumnFamilyHandle* column_family,
       ReadCallback* callback,
       autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys);
 
@@ -336,10 +337,10 @@ class DBImpl : public DB {
                            bool* value_found = nullptr) override;
 
   using DB::NewIterator;
-  virtual Iterator* NewIterator(const ReadOptions& options,
+  virtual Iterator* NewIterator(const ReadOptions& _read_options,
                                 ColumnFamilyHandle* column_family) override;
   virtual Status NewIterators(
-      const ReadOptions& options,
+      const ReadOptions& _read_options,
       const std::vector<ColumnFamilyHandle*>& column_families,
       std::vector<Iterator*>* iterators) override;
 
@@ -531,9 +532,14 @@ class DBImpl : public DB {
   virtual Status CreateColumnFamilyWithImport(
       const ColumnFamilyOptions& options, const std::string& column_family_name,
       const ImportColumnFamilyOptions& import_options,
-      const ExportImportFilesMetaData& metadata,
+      const std::vector<const ExportImportFilesMetaData*>& metadatas,
       ColumnFamilyHandle** handle) override;
 
+  using DB::ClipColumnFamily;
+  virtual Status ClipColumnFamily(ColumnFamilyHandle* column_family,
+                                  const Slice& begin_key,
+                                  const Slice& end_key) override;
+
   using DB::VerifyFileChecksums;
   Status VerifyFileChecksums(const ReadOptions& read_options) override;
 
@@ -622,6 +628,14 @@ class DBImpl : public DB {
     int* number_of_operands = nullptr;
   };
 
+  Status GetImpl(const ReadOptions& read_options,
+                 ColumnFamilyHandle* column_family, const Slice& key,
+                 PinnableSlice* value);
+
+  Status GetImpl(const ReadOptions& read_options,
+                 ColumnFamilyHandle* column_family, const Slice& key,
+                 PinnableSlice* value, std::string* timestamp);
+
   // Function that Get and KeyMayExist call with no_io true or false
   // Note: 'value_found' from KeyMayExist propagates here
   // This function is also called by GetMergeOperands
@@ -806,6 +820,8 @@ class DBImpl : public DB {
   // being deleted.
   uint64_t MinObsoleteSstNumberToKeep();
 
+  uint64_t GetObsoleteSstFilesSize();
+
   // Returns the list of live files in 'live' and the list
   // of all files in the filesystem in 'candidate_files'.
   // If force == false and the last call was less than
@@ -1053,10 +1069,8 @@ class DBImpl : public DB {
 
   VersionSet* GetVersionSet() const { return versions_.get(); }
 
-  // Wait for any compaction
-  // We add a bool parameter to wait for unscheduledCompactions_ == 0, but this
-  // is only for the special test of CancelledCompactions
-  Status WaitForCompact(bool waitUnscheduled = false);
+  Status WaitForCompact(
+      const WaitForCompactOptions& wait_for_compact_options) override;
 
 #ifndef NDEBUG
   // Compact any files in the named level that overlap [*begin, *end]
@@ -1095,10 +1109,9 @@ class DBImpl : public DB {
   // Wait for memtable compaction
   Status TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family = nullptr);
 
-  // Wait for any compaction
-  // We add a bool parameter to wait for unscheduledCompactions_ == 0, but this
-  // is only for the special test of CancelledCompactions
-  Status TEST_WaitForCompact(bool waitUnscheduled = false);
+  Status TEST_WaitForCompact();
+  Status TEST_WaitForCompact(
+      const WaitForCompactOptions& wait_for_compact_options);
 
   // Wait for any background purge
   Status TEST_WaitForPurge();
@@ -1336,6 +1349,11 @@ class DBImpl : public DB {
 
   std::atomic<bool> shutting_down_;
 
+  // No new background jobs can be queued if true. This is used to prevent new
+  // background jobs from being queued after WaitForCompact() completes waiting
+  // all background jobs then attempts to close when close_db_ option is true.
+  bool reject_new_background_jobs_;
+
   // RecoveryContext struct stores the context about version edits along
   // with corresponding column_family_data and column_family_options.
   class RecoveryContext {
@@ -1408,6 +1426,9 @@ class DBImpl : public DB {
   void NotifyOnExternalFileIngested(
       ColumnFamilyData* cfd, const ExternalSstFileIngestionJob& ingestion_job);
 
+  Status FlushAllColumnFamilies(const FlushOptions& flush_options,
+                                FlushReason flush_reason);
+
   virtual Status FlushForGetLiveFiles();
 
   void NewThreadStatusCfInfo(ColumnFamilyData* cfd) const;
@@ -1559,12 +1580,14 @@ class DBImpl : public DB {
   friend class ForwardIterator;
   friend struct SuperVersion;
   friend class CompactedDBImpl;
+#ifndef NDEBUG
   friend class DBTest_ConcurrentFlushWAL_Test;
   friend class DBTest_MixedSlowdownOptionsStop_Test;
   friend class DBCompactionTest_CompactBottomLevelFilesWithDeletions_Test;
   friend class DBCompactionTest_CompactionDuringShutdown_Test;
+  friend class DBCompactionTest_DelayCompactBottomLevelFilesWithDeletions_Test;
+  friend class DBCompactionTest_DisableCompactBottomLevelFiles_Test;
   friend class StatsHistoryTest_PersistentStatsCreateColumnFamilies_Test;
-#ifndef NDEBUG
   friend class DBTest2_ReadCallbackTest_Test;
   friend class WriteCallbackPTest_WriteWithCallbackTest_Test;
   friend class XFTransactionWriteHandler;
@@ -2056,6 +2079,10 @@ class DBImpl : public DB {
     // flush is considered complete.
     std::unordered_map<ColumnFamilyData*, uint64_t>
         cfd_to_max_mem_id_to_persist;
+
+#ifndef NDEBUG
+    int reschedule_count = 1;
+#endif /* !NDEBUG */
   };
 
   void GenerateFlushRequest(const autovector<ColumnFamilyData*>& cfds,
@@ -2084,6 +2111,7 @@ class DBImpl : public DB {
                               Env::Priority thread_pri);
   Status BackgroundFlush(bool* madeProgress, JobContext* job_context,
                          LogBuffer* log_buffer, FlushReason* reason,
+                         bool* flush_rescheduled_to_retain_udt,
                          Env::Priority thread_pri);
 
   bool EnoughRoomForCompaction(ColumnFamilyData* cfd,
@@ -2096,9 +2124,18 @@ class DBImpl : public DB {
                               std::unique_ptr<TaskLimiterToken>* token,
                               LogBuffer* log_buffer);
 
+  // Return true if the `FlushRequest` can be rescheduled to retain the UDT.
+  // Only true if there are user-defined timestamps in the involved MemTables
+  // with newer than cutoff timestamp `full_history_ts_low` and not flushing
+  // immediately will not cause entering write stall mode.
+  bool ShouldRescheduleFlushRequestToRetainUDT(const FlushRequest& flush_req);
+
   // Schedule background tasks
   Status StartPeriodicTaskScheduler();
 
+  // Cancel scheduled periodic tasks
+  Status CancelPeriodicTaskScheduler();
+
   Status RegisterRecordSeqnoTimeWorker();
 
   void PrintStatistics();
@@ -2182,7 +2219,7 @@ class DBImpl : public DB {
   void BuildCompactionJobInfo(const ColumnFamilyData* cfd, Compaction* c,
                               const Status& st,
                               const CompactionJobStats& compaction_job_stats,
-                              const int job_id, const Version* current,
+                              const int job_id,
                               CompactionJobInfo* compaction_job_info) const;
   // Reserve the next 'num' file numbers for to-be-ingested external SST files,
   // and return the current file_number in 'next_file_number'.
@@ -2310,7 +2347,7 @@ class DBImpl : public DB {
   // logfile_number_. With two_write_queues it also protects alive_log_files_,
   // and log_empty_. Refer to the definition of each variable below for more
   // details.
-  // Note: to avoid dealock, if needed to acquire both log_write_mutex_ and
+  // Note: to avoid deadlock, if needed to acquire both log_write_mutex_ and
   // mutex_, the order should be first mutex_ and then log_write_mutex_.
   InstrumentedMutex log_write_mutex_;
 

db/db_impl/db_impl_compaction_flush.cc

@@ -21,6 +21,7 @@
 #include "monitoring/thread_status_util.h"
 #include "test_util/sync_point.h"
 #include "util/cast_util.h"
+#include "util/coding.h"
 #include "util/concurrent_task_limiter_impl.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -76,6 +77,40 @@ bool DBImpl::RequestCompactionToken(ColumnFamilyData* cfd, bool force,
   return false;
 }
 
+bool DBImpl::ShouldRescheduleFlushRequestToRetainUDT(
+    const FlushRequest& flush_req) {
+  mutex_.AssertHeld();
+  assert(flush_req.cfd_to_max_mem_id_to_persist.size() == 1);
+  ColumnFamilyData* cfd = flush_req.cfd_to_max_mem_id_to_persist.begin()->first;
+  uint64_t max_memtable_id =
+      flush_req.cfd_to_max_mem_id_to_persist.begin()->second;
+  if (cfd->IsDropped() ||
+      !cfd->ShouldPostponeFlushToRetainUDT(max_memtable_id)) {
+    return false;
+  }
+  // Check if holding on the flush will cause entering write stall mode.
+  // Write stall entered because of the accumulation of write buffers can be
+  // alleviated if we continue with the flush instead of postponing it.
+  const auto& mutable_cf_options = *cfd->GetLatestMutableCFOptions();
+
+  // Taking the status of the active Memtable into consideration so that we are
+  // not just checking if DB is currently already in write stall mode.
+  int mem_to_flush = cfd->mem()->ApproximateMemoryUsageFast() >=
+                             cfd->mem()->write_buffer_size() / 2
+                         ? 1
+                         : 0;
+  WriteStallCondition write_stall =
+      ColumnFamilyData::GetWriteStallConditionAndCause(
+          cfd->imm()->NumNotFlushed() + mem_to_flush, /*num_l0_files=*/0,
+          /*num_compaction_needed_bytes=*/0, mutable_cf_options,
+          *cfd->ioptions())
+          .first;
+  if (write_stall != WriteStallCondition::kNormal) {
+    return false;
+  }
+  return true;
+}
+
 IOStatus DBImpl::SyncClosedLogs(JobContext* job_context,
                                 VersionEdit* synced_wals) {
   TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Start");
@@ -248,6 +283,24 @@ Status DBImpl::FlushMemTableToOutputFile(
   // 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");
+  // Exit a flush due to bg error should not set bg error again.
+  bool skip_set_bg_error = false;
+  if (s.ok() && !error_handler_.GetBGError().ok() &&
+      error_handler_.IsBGWorkStopped() &&
+      flush_reason != FlushReason::kErrorRecovery &&
+      flush_reason != FlushReason::kErrorRecoveryRetryFlush) {
+    // Error recovery in progress, should not pick memtable which excludes
+    // them from being picked up by recovery flush.
+    // This ensures that when bg error is set, no new flush can pick
+    // memtables.
+    skip_set_bg_error = true;
+    s = error_handler_.GetBGError();
+    assert(!s.ok());
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[JOB %d] Skip flush due to background error %s",
+                     job_context->job_id, s.ToString().c_str());
+  }
+
   if (s.ok()) {
     flush_job.PickMemTable();
     need_cancel = true;
@@ -268,7 +321,8 @@ Status DBImpl::FlushMemTableToOutputFile(
   // is unlocked by the current thread.
   if (s.ok()) {
     s = flush_job.Run(&logs_with_prep_tracker_, &file_meta,
-                      &switched_to_mempurge);
+                      &switched_to_mempurge, &skip_set_bg_error,
+                      &error_handler_);
     need_cancel = false;
   }
 
@@ -309,7 +363,8 @@ Status DBImpl::FlushMemTableToOutputFile(
     }
   }
 
-  if (!s.ok() && !s.IsShutdownInProgress() && !s.IsColumnFamilyDropped()) {
+  if (!s.ok() && !s.IsShutdownInProgress() && !s.IsColumnFamilyDropped() &&
+      !skip_set_bg_error) {
     if (log_io_s.ok()) {
       // Error while writing to MANIFEST.
       // In fact, versions_->io_status() can also be the result of renaming
@@ -521,6 +576,21 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     pick_status.push_back(false);
   }
 
+  bool flush_for_recovery =
+      bg_flush_args[0].flush_reason_ == FlushReason::kErrorRecovery ||
+      bg_flush_args[0].flush_reason_ == FlushReason::kErrorRecoveryRetryFlush;
+  bool skip_set_bg_error = false;
+
+  if (s.ok() && !error_handler_.GetBGError().ok() &&
+      error_handler_.IsBGWorkStopped() && !flush_for_recovery) {
+    s = error_handler_.GetBGError();
+    skip_set_bg_error = true;
+    assert(!s.ok());
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[JOB %d] Skip flush due to background error %s",
+                     job_context->job_id, s.ToString().c_str());
+  }
+
   if (s.ok()) {
     for (int i = 0; i != num_cfs; ++i) {
       jobs[i]->PickMemTable();
@@ -585,7 +655,10 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
         }
       }
     }
-  } else {
+  } else if (!skip_set_bg_error) {
+    // When `skip_set_bg_error` is true, no memtable is picked so
+    // there is no need to call Cancel() or RollbackMemtableFlush().
+    //
     // Need to undo atomic flush if something went wrong, i.e. s is not OK and
     // it is not because of CF drop.
     // Have to cancel the flush jobs that have NOT executed because we need to
@@ -598,8 +671,8 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     for (int i = 0; i != num_cfs; ++i) {
       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());
+        cfds[i]->imm()->RollbackMemtableFlush(
+            mems, /*rollback_succeeding_memtables=*/false);
       }
     }
   }
@@ -641,10 +714,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
     };
 
     bool resuming_from_bg_err =
-        error_handler_.IsDBStopped() ||
-        (bg_flush_args[0].flush_reason_ == FlushReason::kErrorRecovery ||
-         bg_flush_args[0].flush_reason_ ==
-             FlushReason::kErrorRecoveryRetryFlush);
+        error_handler_.IsDBStopped() || flush_for_recovery;
     while ((!resuming_from_bg_err || error_handler_.GetRecoveryError().ok())) {
       std::pair<Status, bool> res = wait_to_install_func();
 
@@ -655,15 +725,27 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
         s = res.first;
         break;
       } else if (!res.second) {
+        // we are the oldest immutable memtable
+        break;
+      }
+      // We are not the oldest immutable memtable
+      TEST_SYNC_POINT_CALLBACK(
+          "DBImpl::AtomicFlushMemTablesToOutputFiles:WaitCV", &res);
+      //
+      // If bg work is stopped, recovery thread first calls
+      // WaitForBackgroundWork() before proceeding to flush for recovery. This
+      // flush can block WaitForBackgroundWork() while waiting for recovery
+      // flush to install result. To avoid this deadlock, we should abort here
+      // if there is background error.
+      if (!flush_for_recovery && error_handler_.IsBGWorkStopped() &&
+          !error_handler_.GetBGError().ok()) {
+        s = error_handler_.GetBGError();
+        assert(!s.ok());
         break;
       }
       atomic_flush_install_cv_.Wait();
 
-      resuming_from_bg_err =
-          error_handler_.IsDBStopped() ||
-          (bg_flush_args[0].flush_reason_ == FlushReason::kErrorRecovery ||
-           bg_flush_args[0].flush_reason_ ==
-               FlushReason::kErrorRecoveryRetryFlush);
+      resuming_from_bg_err = error_handler_.IsDBStopped() || flush_for_recovery;
     }
 
     if (!resuming_from_bg_err) {
@@ -679,6 +761,17 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
       // installation.
       s = error_handler_.GetRecoveryError();
     }
+    // Since we are not installing these memtables, need to rollback
+    // to allow future flush job to pick up these memtables.
+    if (!s.ok()) {
+      for (int i = 0; i != num_cfs; ++i) {
+        assert(exec_status[i].first);
+        assert(exec_status[i].second.ok());
+        auto& mems = jobs[i]->GetMemTables();
+        cfds[i]->imm()->RollbackMemtableFlush(
+            mems, /*rollback_succeeding_memtables=*/false);
+      }
+    }
   }
 
   if (s.ok()) {
@@ -782,7 +875,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
 
   // Need to undo atomic flush if something went wrong, i.e. s is not OK and
   // it is not because of CF drop.
-  if (!s.ok() && !s.IsColumnFamilyDropped()) {
+  if (!s.ok() && !s.IsColumnFamilyDropped() && !skip_set_bg_error) {
     if (log_io_s.ok()) {
       // Error while writing to MANIFEST.
       // In fact, versions_->io_status() can also be the result of renaming
@@ -852,8 +945,8 @@ void DBImpl::NotifyOnFlushBegin(ColumnFamilyData* cfd, FileMetaData* file_meta,
     }
   }
   mutex_.Lock();
-// no need to signal bg_cv_ as it will be signaled at the end of the
-// flush process.
+  // no need to signal bg_cv_ as it will be signaled at the end of the
+  // flush process.
 }
 
 void DBImpl::NotifyOnFlushCompleted(
@@ -1066,7 +1159,6 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
                             std::numeric_limits<uint64_t>::max(), trim_ts);
   } else {
     int first_overlapped_level = kInvalidLevel;
-    int max_overlapped_level = kInvalidLevel;
     {
       SuperVersion* super_version = cfd->GetReferencedSuperVersion(this);
       Version* current_version = super_version->current;
@@ -1142,10 +1234,8 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
                                                                     begin, end);
         }
         if (overlap) {
-          if (first_overlapped_level == kInvalidLevel) {
-            first_overlapped_level = level;
-          }
-          max_overlapped_level = level;
+          first_overlapped_level = level;
+          break;
         }
       }
       CleanupSuperVersion(super_version);
@@ -1159,7 +1249,7 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
             end, exclusive, true /* disallow_trivial_move */,
             std::numeric_limits<uint64_t>::max() /* max_file_num_to_ignore */,
             trim_ts);
-        final_output_level = max_overlapped_level;
+        final_output_level = first_overlapped_level;
       } else {
         assert(cfd->ioptions()->compaction_style == kCompactionStyleLevel);
         uint64_t next_file_number = versions_->current_next_file_number();
@@ -1170,8 +1260,30 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
         // at L1 (or LBase), if applicable.
         int level = first_overlapped_level;
         final_output_level = level;
-        int output_level, base_level;
-        while (level < max_overlapped_level || level == 0) {
+        int output_level = 0, base_level = 0;
+        for (;;) {
+          // Always allow L0 -> L1 compaction
+          if (level > 0) {
+            if (cfd->ioptions()->level_compaction_dynamic_level_bytes) {
+              assert(final_output_level < cfd->ioptions()->num_levels);
+              if (final_output_level + 1 == cfd->ioptions()->num_levels) {
+                break;
+              }
+            } else {
+              // TODO(cbi): there is still a race condition here where
+              //  if a background compaction compacts some file beyond
+              //  current()->storage_info()->num_non_empty_levels() right after
+              //  the check here.This should happen very infrequently and should
+              //  not happen once a user populates the last level of the LSM.
+              InstrumentedMutexLock l(&mutex_);
+              // num_non_empty_levels may be lower after a compaction, so
+              // we check for >= here.
+              if (final_output_level + 1 >=
+                  cfd->current()->storage_info()->num_non_empty_levels()) {
+                break;
+              }
+            }
+          }
           output_level = level + 1;
           if (cfd->ioptions()->level_compaction_dynamic_level_bytes &&
               level == 0) {
@@ -1203,17 +1315,8 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
         if (s.ok()) {
           assert(final_output_level > 0);
           // bottommost level intra-level compaction
-          // TODO(cbi): this preserves earlier behavior where if
-          //  max_overlapped_level = 0 and bottommost_level_compaction is
-          //  kIfHaveCompactionFilter, we only do a L0 -> LBase compaction
-          //  and do not do intra-LBase compaction even when user configures
-          //  compaction filter. We may want to still do a LBase -> LBase
-          //  compaction in case there is some file in LBase that did not go
-          //  through L0 -> LBase compaction, and hence did not go through
-          //  compaction filter.
           if ((options.bottommost_level_compaction ==
                    BottommostLevelCompaction::kIfHaveCompactionFilter &&
-               max_overlapped_level != 0 &&
                (cfd->ioptions()->compaction_filter != nullptr ||
                 cfd->ioptions()->compaction_filter_factory != nullptr)) ||
               options.bottommost_level_compaction ==
@@ -1221,10 +1324,11 @@ Status DBImpl::CompactRangeInternal(const CompactRangeOptions& options,
               options.bottommost_level_compaction ==
                   BottommostLevelCompaction::kForce) {
             // Use `next_file_number` as `max_file_num_to_ignore` to avoid
-            // rewriting newly compacted files when it is kForceOptimized.
+            // rewriting newly compacted files when it is kForceOptimized
+            // or kIfHaveCompactionFilter with compaction filter set.
             s = RunManualCompaction(
                 cfd, final_output_level, final_output_level, options, begin,
-                end, exclusive, !trim_ts.empty() /* disallow_trivial_move */,
+                end, exclusive, true /* disallow_trivial_move */,
                 next_file_number /* max_file_num_to_ignore */, trim_ts);
           }
         }
@@ -1375,6 +1479,14 @@ Status DBImpl::CompactFilesImpl(
     }
   }
 
+  if (cfd->ioptions()->allow_ingest_behind &&
+      output_level >= cfd->ioptions()->num_levels - 1) {
+    return Status::InvalidArgument(
+        "Exceed the maximum output level defined by "
+        "the current compaction algorithm with ingest_behind --- " +
+        std::to_string(cfd->ioptions()->num_levels - 1));
+  }
+
   Status s = cfd->compaction_picker()->SanitizeCompactionInputFiles(
       &input_set, cf_meta, output_level);
   TEST_SYNC_POINT("DBImpl::CompactFilesImpl::PostSanitizeCompactionInputFiles");
@@ -1492,7 +1604,7 @@ Status DBImpl::CompactFilesImpl(
 
   if (compaction_job_info != nullptr) {
     BuildCompactionJobInfo(cfd, c.get(), s, compaction_job_stats,
-                           job_context->job_id, version, compaction_job_info);
+                           job_context->job_id, compaction_job_info);
   }
 
   if (status.ok()) {
@@ -1589,21 +1701,18 @@ void DBImpl::NotifyOnCompactionBegin(ColumnFamilyData* cfd, Compaction* c,
   }
 
   c->SetNotifyOnCompactionCompleted();
-  Version* current = cfd->current();
-  current->Ref();
   // release lock while notifying events
   mutex_.Unlock();
   TEST_SYNC_POINT("DBImpl::NotifyOnCompactionBegin::UnlockMutex");
   {
     CompactionJobInfo info{};
-    BuildCompactionJobInfo(cfd, c, st, job_stats, job_id, current, &info);
+    BuildCompactionJobInfo(cfd, c, st, job_stats, job_id, &info);
     for (auto listener : immutable_db_options_.listeners) {
       listener->OnCompactionBegin(this, info);
     }
     info.status.PermitUncheckedError();
   }
   mutex_.Lock();
-  current->Unref();
 }
 
 void DBImpl::NotifyOnCompactionCompleted(
@@ -1621,21 +1730,17 @@ void DBImpl::NotifyOnCompactionCompleted(
     return;
   }
 
-  Version* current = cfd->current();
-  current->Ref();
   // release lock while notifying events
   mutex_.Unlock();
   TEST_SYNC_POINT("DBImpl::NotifyOnCompactionCompleted::UnlockMutex");
   {
     CompactionJobInfo info{};
-    BuildCompactionJobInfo(cfd, c, st, compaction_job_stats, job_id, current,
-                           &info);
+    BuildCompactionJobInfo(cfd, c, st, compaction_job_stats, job_id, &info);
     for (auto listener : immutable_db_options_.listeners) {
       listener->OnCompactionCompleted(this, info);
     }
   }
   mutex_.Lock();
-  current->Unref();
   // no need to signal bg_cv_ as it will be signaled at the end of the
   // flush process.
 }
@@ -1758,7 +1863,8 @@ Status DBImpl::ReFitLevel(ColumnFamilyData* cfd, int level, int target_level) {
           f->marked_for_compaction, f->temperature, f->oldest_blob_file_number,
           f->oldest_ancester_time, f->file_creation_time, f->epoch_number,
           f->file_checksum, f->file_checksum_func_name, f->unique_id,
-          f->compensated_range_deletion_size);
+          f->compensated_range_deletion_size, f->tail_size,
+          f->user_defined_timestamps_persisted);
     }
     ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
                     "[%s] Apply version edit:\n%s", cfd->GetName().c_str(),
@@ -1808,6 +1914,37 @@ int DBImpl::Level0StopWriteTrigger(ColumnFamilyHandle* column_family) {
       ->mutable_cf_options.level0_stop_writes_trigger;
 }
 
+Status DBImpl::FlushAllColumnFamilies(const FlushOptions& flush_options,
+                                      FlushReason flush_reason) {
+  mutex_.AssertHeld();
+  Status status;
+  if (immutable_db_options_.atomic_flush) {
+    mutex_.Unlock();
+    status = AtomicFlushMemTables(flush_options, flush_reason);
+    if (status.IsColumnFamilyDropped()) {
+      status = Status::OK();
+    }
+    mutex_.Lock();
+  } else {
+    for (auto cfd : versions_->GetRefedColumnFamilySet()) {
+      if (cfd->IsDropped()) {
+        continue;
+      }
+      mutex_.Unlock();
+      status = FlushMemTable(cfd, flush_options, flush_reason);
+      TEST_SYNC_POINT("DBImpl::FlushAllColumnFamilies:1");
+      TEST_SYNC_POINT("DBImpl::FlushAllColumnFamilies:2");
+      mutex_.Lock();
+      if (!status.ok() && !status.IsColumnFamilyDropped()) {
+        break;
+      } else if (status.IsColumnFamilyDropped()) {
+        status = Status::OK();
+      }
+    }
+  }
+  return status;
+}
+
 Status DBImpl::Flush(const FlushOptions& flush_options,
                      ColumnFamilyHandle* column_family) {
   auto cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
@@ -2144,9 +2281,13 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
     WaitForPendingWrites();
 
     if (flush_reason != FlushReason::kErrorRecoveryRetryFlush &&
+        flush_reason != FlushReason::kCatchUpAfterErrorRecovery &&
         (!cfd->mem()->IsEmpty() || !cached_recoverable_state_empty_.load())) {
       // Note that, when flush reason is kErrorRecoveryRetryFlush, during the
       // auto retry resume, we want to avoid creating new small memtables.
+      // If flush reason is kCatchUpAfterErrorRecovery, we try to flush any new
+      // memtable that filled up during recovery, and we also want to avoid
+      // switching memtable to create small memtables.
       // Therefore, SwitchMemtable will not be called. Also, since ResumeImpl
       // will iterate through all the CFs and call FlushMemtable during auto
       // retry resume, it is possible that in some CFs,
@@ -2337,7 +2478,8 @@ Status DBImpl::AtomicFlushMemTables(
 
     for (auto cfd : cfds) {
       if ((cfd->mem()->IsEmpty() && cached_recoverable_state_empty_.load()) ||
-          flush_reason == FlushReason::kErrorRecoveryRetryFlush) {
+          flush_reason == FlushReason::kErrorRecoveryRetryFlush ||
+          flush_reason == FlushReason::kCatchUpAfterErrorRecovery) {
         continue;
       }
       cfd->Ref();
@@ -2455,8 +2597,11 @@ 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
+      // No extra immutable Memtable will be created if the current Memtable is
+      // empty.
+      int mem_to_flush = cfd->mem()->IsEmpty() ? 0 : 1;
       write_stall_condition = ColumnFamilyData::GetWriteStallConditionAndCause(
-                                  cfd->imm()->NumNotFlushed() + 1,
+                                  cfd->imm()->NumNotFlushed() + mem_to_flush,
                                   vstorage->l0_delay_trigger_count() + 1,
                                   vstorage->estimated_compaction_needed_bytes(),
                                   mutable_cf_options, *cfd->ioptions())
@@ -2602,6 +2747,11 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
     // There has been a hard error and this call is not part of the recovery
     // sequence. Bail out here so we don't get into an endless loop of
     // scheduling BG work which will again call this function
+    //
+    // Note that a non-recovery flush can still be scheduled if
+    // error_handler_.IsRecoveryInProgress() returns true. We rely on
+    // BackgroundCallFlush() to check flush reason and drop non-recovery
+    // flushes.
     return;
   } else if (shutting_down_.load(std::memory_order_acquire)) {
     // DB is being deleted; no more background compactions
@@ -2612,6 +2762,9 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
       env_->GetBackgroundThreads(Env::Priority::HIGH) == 0;
   while (!is_flush_pool_empty && unscheduled_flushes_ > 0 &&
          bg_flush_scheduled_ < bg_job_limits.max_flushes) {
+    TEST_SYNC_POINT_CALLBACK(
+        "DBImpl::MaybeScheduleFlushOrCompaction:BeforeSchedule",
+        &unscheduled_flushes_);
     bg_flush_scheduled_++;
     FlushThreadArg* fta = new FlushThreadArg;
     fta->db_ = this;
@@ -2721,7 +2874,7 @@ ColumnFamilyData* DBImpl::PopFirstFromCompactionQueue() {
 
 DBImpl::FlushRequest DBImpl::PopFirstFromFlushQueue() {
   assert(!flush_queue_.empty());
-  FlushRequest flush_req = flush_queue_.front();
+  FlushRequest flush_req = std::move(flush_queue_.front());
   flush_queue_.pop_front();
   if (!immutable_db_options_.atomic_flush) {
     assert(flush_req.cfd_to_max_mem_id_to_persist.size() == 1);
@@ -2765,6 +2918,9 @@ ColumnFamilyData* DBImpl::PickCompactionFromQueue(
 
 void DBImpl::SchedulePendingFlush(const FlushRequest& flush_req) {
   mutex_.AssertHeld();
+  if (reject_new_background_jobs_) {
+    return;
+  }
   if (flush_req.cfd_to_max_mem_id_to_persist.empty()) {
     return;
   }
@@ -2794,6 +2950,9 @@ void DBImpl::SchedulePendingFlush(const FlushRequest& flush_req) {
 
 void DBImpl::SchedulePendingCompaction(ColumnFamilyData* cfd) {
   mutex_.AssertHeld();
+  if (reject_new_background_jobs_) {
+    return;
+  }
   if (!cfd->queued_for_compaction() && cfd->NeedsCompaction()) {
     AddToCompactionQueue(cfd);
     ++unscheduled_compactions_;
@@ -2803,6 +2962,9 @@ void DBImpl::SchedulePendingCompaction(ColumnFamilyData* cfd) {
 void DBImpl::SchedulePendingPurge(std::string fname, std::string dir_to_sync,
                                   FileType type, uint64_t number, int job_id) {
   mutex_.AssertHeld();
+  if (reject_new_background_jobs_) {
+    return;
+  }
   PurgeFileInfo file_info(fname, dir_to_sync, type, number, job_id);
   purge_files_.insert({{number, std::move(file_info)}});
 }
@@ -2891,6 +3053,7 @@ void DBImpl::UnscheduleFlushCallback(void* arg) {
 
 Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
                                LogBuffer* log_buffer, FlushReason* reason,
+                               bool* flush_rescheduled_to_retain_udt,
                                Env::Priority thread_pri) {
   mutex_.AssertHeld();
 
@@ -2916,14 +3079,61 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
   autovector<ColumnFamilyData*> column_families_not_to_flush;
   while (!flush_queue_.empty()) {
     // This cfd is already referenced
-    const FlushRequest& flush_req = PopFirstFromFlushQueue();
+    FlushRequest flush_req = PopFirstFromFlushQueue();
     FlushReason flush_reason = flush_req.flush_reason;
+    if (!error_handler_.GetBGError().ok() && error_handler_.IsBGWorkStopped() &&
+        flush_reason != FlushReason::kErrorRecovery &&
+        flush_reason != FlushReason::kErrorRecoveryRetryFlush) {
+      // Stop non-recovery flush when bg work is stopped
+      // Note that we drop the flush request here.
+      // Recovery thread should schedule further flushes after bg error
+      // is cleared.
+      status = error_handler_.GetBGError();
+      assert(!status.ok());
+      ROCKS_LOG_BUFFER(log_buffer,
+                       "[JOB %d] Abort flush due to background error %s",
+                       job_context->job_id, status.ToString().c_str());
+      *reason = flush_reason;
+      for (auto item : flush_req.cfd_to_max_mem_id_to_persist) {
+        item.first->UnrefAndTryDelete();
+      }
+      return status;
+    }
+    if (!immutable_db_options_.atomic_flush &&
+        ShouldRescheduleFlushRequestToRetainUDT(flush_req)) {
+      assert(flush_req.cfd_to_max_mem_id_to_persist.size() == 1);
+      ColumnFamilyData* cfd =
+          flush_req.cfd_to_max_mem_id_to_persist.begin()->first;
+      if (cfd->UnrefAndTryDelete()) {
+        return Status::OK();
+      }
+      ROCKS_LOG_BUFFER(log_buffer,
+                       "FlushRequest for column family %s is re-scheduled to "
+                       "retain user-defined timestamps.",
+                       cfd->GetName().c_str());
+      // Reschedule the `FlushRequest` as is without checking dropped column
+      // family etc. The follow-up job will do the check anyways, so save the
+      // duplication. Column family is deduplicated by `SchdulePendingFlush` and
+      // `PopFirstFromFlushQueue` contains at flush request enqueueing and
+      // dequeueing time.
+      // This flush request is rescheduled right after it's popped from the
+      // queue while the db mutex is held, so there should be no other
+      // FlushRequest for the same column family with higher `max_memtable_id`
+      // in the queue to block the reschedule from succeeding.
+#ifndef NDEBUG
+      flush_req.reschedule_count += 1;
+#endif /* !NDEBUG */
+      SchedulePendingFlush(flush_req);
+      *reason = flush_reason;
+      *flush_rescheduled_to_retain_udt = true;
+      return Status::TryAgain();
+    }
     superversion_contexts.clear();
     superversion_contexts.reserve(
         flush_req.cfd_to_max_mem_id_to_persist.size());
 
-    for (const auto& iter : flush_req.cfd_to_max_mem_id_to_persist) {
-      ColumnFamilyData* cfd = iter.first;
+    for (const auto& [cfd, max_memtable_id] :
+         flush_req.cfd_to_max_mem_id_to_persist) {
       if (cfd->GetMempurgeUsed()) {
         // If imm() contains silent memtables (e.g.: because
         // MemPurge was activated), requesting a flush will
@@ -2937,10 +3147,16 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
         continue;
       }
       superversion_contexts.emplace_back(SuperVersionContext(true));
-      bg_flush_args.emplace_back(cfd, iter.second,
+      bg_flush_args.emplace_back(cfd, max_memtable_id,
                                  &(superversion_contexts.back()), flush_reason);
     }
-    if (!bg_flush_args.empty()) {
+    // `MaybeScheduleFlushOrCompaction` schedules as many `BackgroundCallFlush`
+    // jobs as the number of `FlushRequest` in the `flush_queue_`, a.k.a
+    // `unscheduled_flushes_`. So it's sufficient to make each `BackgroundFlush`
+    // handle one `FlushRequest` and each have a Status returned.
+    if (!bg_flush_args.empty() || !column_families_not_to_flush.empty()) {
+      TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundFlush:CheckFlushRequest:cb",
+                               const_cast<int*>(&flush_req.reschedule_count));
       break;
     }
   }
@@ -3002,11 +3218,20 @@ void DBImpl::BackgroundCallFlush(Env::Priority thread_pri) {
         pending_outputs_inserted_elem(new std::list<uint64_t>::iterator(
             CaptureCurrentFileNumberInPendingOutputs()));
     FlushReason reason;
-
-    Status s = BackgroundFlush(&made_progress, &job_context, &log_buffer,
-                               &reason, thread_pri);
-    if (!s.ok() && !s.IsShutdownInProgress() && !s.IsColumnFamilyDropped() &&
-        reason != FlushReason::kErrorRecovery) {
+    bool flush_rescheduled_to_retain_udt = false;
+    Status s =
+        BackgroundFlush(&made_progress, &job_context, &log_buffer, &reason,
+                        &flush_rescheduled_to_retain_udt, thread_pri);
+    if (s.IsTryAgain() && flush_rescheduled_to_retain_udt) {
+      bg_cv_.SignalAll();  // In case a waiter can proceed despite the error
+      mutex_.Unlock();
+      TEST_SYNC_POINT_CALLBACK("DBImpl::AfterRetainUDTReschedule:cb", nullptr);
+      immutable_db_options_.clock->SleepForMicroseconds(
+          100000);  // prevent hot loop
+      mutex_.Lock();
+    } else if (!s.ok() && !s.IsShutdownInProgress() &&
+               !s.IsColumnFamilyDropped() &&
+               reason != FlushReason::kErrorRecovery) {
       // Wait a little bit before retrying background flush in
       // case this is an environmental problem and we do not want to
       // chew up resources for failed flushes for the duration of
@@ -3016,9 +3241,9 @@ void DBImpl::BackgroundCallFlush(Env::Priority thread_pri) {
       bg_cv_.SignalAll();  // In case a waiter can proceed despite the error
       mutex_.Unlock();
       ROCKS_LOG_ERROR(immutable_db_options_.info_log,
-                      "Waiting after background flush error: %s"
+                      "[JOB %d] Waiting after background flush error: %s"
                       "Accumulated background error counts: %" PRIu64,
-                      s.ToString().c_str(), error_cnt);
+                      job_context.job_id, s.ToString().c_str(), error_cnt);
       log_buffer.FlushBufferToLog();
       LogFlush(immutable_db_options_.info_log);
       immutable_db_options_.clock->SleepForMicroseconds(1000000);
@@ -3027,29 +3252,33 @@ void DBImpl::BackgroundCallFlush(Env::Priority thread_pri) {
 
     TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:FlushFinish:0");
     ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
-
-    // If flush failed, we want to delete all temporary files that we might have
-    // created. Thus, we force full scan in FindObsoleteFiles()
-    FindObsoleteFiles(&job_context, !s.ok() && !s.IsShutdownInProgress() &&
-                                        !s.IsColumnFamilyDropped());
-    // delete unnecessary files if any, this is done outside the mutex
-    if (job_context.HaveSomethingToClean() ||
-        job_context.HaveSomethingToDelete() || !log_buffer.IsEmpty()) {
-      mutex_.Unlock();
-      TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:FilesFound");
-      // Have to flush the info logs before bg_flush_scheduled_--
-      // because if bg_flush_scheduled_ becomes 0 and the lock is
-      // released, the deconstructor of DB can kick in and destroy all the
-      // states of DB so info_log might not be available after that point.
-      // It also applies to access other states that DB owns.
-      log_buffer.FlushBufferToLog();
-      if (job_context.HaveSomethingToDelete()) {
-        PurgeObsoleteFiles(job_context);
+    // There is no need to do these clean up if the flush job is rescheduled
+    // to retain user-defined timestamps because the job doesn't get to the
+    // stage of actually flushing the MemTables.
+    if (!flush_rescheduled_to_retain_udt) {
+      // If flush failed, we want to delete all temporary files that we might
+      // have created. Thus, we force full scan in FindObsoleteFiles()
+      FindObsoleteFiles(&job_context, !s.ok() && !s.IsShutdownInProgress() &&
+                                          !s.IsColumnFamilyDropped());
+      // delete unnecessary files if any, this is done outside the mutex
+      if (job_context.HaveSomethingToClean() ||
+          job_context.HaveSomethingToDelete() || !log_buffer.IsEmpty()) {
+        mutex_.Unlock();
+        TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:FilesFound");
+        // Have to flush the info logs before bg_flush_scheduled_--
+        // because if bg_flush_scheduled_ becomes 0 and the lock is
+        // released, the deconstructor of DB can kick in and destroy all the
+        // states of DB so info_log might not be available after that point.
+        // It also applies to access other states that DB owns.
+        log_buffer.FlushBufferToLog();
+        if (job_context.HaveSomethingToDelete()) {
+          PurgeObsoleteFiles(job_context);
+        }
+        job_context.Clean();
+        mutex_.Lock();
       }
-      job_context.Clean();
-      mutex_.Lock();
+      TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:ContextCleanedUp");
     }
-    TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:ContextCleanedUp");
 
     assert(num_running_flushes_ > 0);
     num_running_flushes_--;
@@ -3457,7 +3686,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
             f->oldest_blob_file_number, f->oldest_ancester_time,
             f->file_creation_time, f->epoch_number, f->file_checksum,
             f->file_checksum_func_name, f->unique_id,
-            f->compensated_range_deletion_size);
+            f->compensated_range_deletion_size, f->tail_size,
+            f->user_defined_timestamps_persisted);
 
         ROCKS_LOG_BUFFER(
             log_buffer,
@@ -3569,7 +3799,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     mutex_.Unlock();
     TEST_SYNC_POINT_CALLBACK(
         "DBImpl::BackgroundCompaction:NonTrivial:BeforeRun", nullptr);
-    // Should handle erorr?
+    // Should handle error?
     compaction_job.Run().PermitUncheckedError();
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
     mutex_.Lock();
@@ -3781,7 +4011,7 @@ bool DBImpl::MCOverlap(ManualCompactionState* m, ManualCompactionState* m1) {
 void DBImpl::BuildCompactionJobInfo(
     const ColumnFamilyData* cfd, Compaction* c, const Status& st,
     const CompactionJobStats& compaction_job_stats, const int job_id,
-    const Version* current, CompactionJobInfo* compaction_job_info) const {
+    CompactionJobInfo* compaction_job_info) const {
   assert(compaction_job_info != nullptr);
   compaction_job_info->cf_id = cfd->GetID();
   compaction_job_info->cf_name = cfd->GetName();
@@ -3791,7 +4021,7 @@ void DBImpl::BuildCompactionJobInfo(
   compaction_job_info->base_input_level = c->start_level();
   compaction_job_info->output_level = c->output_level();
   compaction_job_info->stats = compaction_job_stats;
-  compaction_job_info->table_properties = c->GetOutputTableProperties();
+  compaction_job_info->table_properties = c->GetTableProperties();
   compaction_job_info->compaction_reason = c->compaction_reason();
   compaction_job_info->compression = c->output_compression();
 
@@ -3805,15 +4035,9 @@ void DBImpl::BuildCompactionJobInfo(
       compaction_job_info->input_files.push_back(fn);
       compaction_job_info->input_file_infos.push_back(CompactionFileInfo{
           static_cast<int>(i), file_number, fmd->oldest_blob_file_number});
-      if (compaction_job_info->table_properties.count(fn) == 0) {
-        std::shared_ptr<const TableProperties> tp;
-        auto s = current->GetTableProperties(read_options, &tp, fmd, &fn);
-        if (s.ok()) {
-          compaction_job_info->table_properties[fn] = tp;
-        }
-      }
     }
   }
+
   for (const auto& newf : c->edit()->GetNewFiles()) {
     const FileMetaData& meta = newf.second;
     const FileDescriptor& desc = meta.fd;
@@ -3957,16 +4181,58 @@ void DBImpl::GetSnapshotContext(
   *snapshot_seqs = snapshots_.GetAll(earliest_write_conflict_snapshot);
 }
 
-Status DBImpl::WaitForCompact(bool wait_unscheduled) {
-  // Wait until the compaction completes
+Status DBImpl::WaitForCompact(
+    const WaitForCompactOptions& wait_for_compact_options) {
   InstrumentedMutexLock l(&mutex_);
-  while ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
-          bg_flush_scheduled_ ||
-          (wait_unscheduled && unscheduled_compactions_)) &&
-         (error_handler_.GetBGError().ok())) {
-    bg_cv_.Wait();
+  if (wait_for_compact_options.flush) {
+    Status s = DBImpl::FlushAllColumnFamilies(FlushOptions(),
+                                              FlushReason::kManualFlush);
+    if (!s.ok()) {
+      return s;
+    }
+  } else if (wait_for_compact_options.close_db &&
+             has_unpersisted_data_.load(std::memory_order_relaxed) &&
+             !mutable_db_options_.avoid_flush_during_shutdown) {
+    Status s =
+        DBImpl::FlushAllColumnFamilies(FlushOptions(), FlushReason::kShutDown);
+    if (!s.ok()) {
+      return s;
+    }
+  }
+  TEST_SYNC_POINT("DBImpl::WaitForCompact:StartWaiting");
+  const auto deadline = immutable_db_options_.clock->NowMicros() +
+                        wait_for_compact_options.timeout.count();
+  for (;;) {
+    if (shutting_down_.load(std::memory_order_acquire)) {
+      return Status::ShutdownInProgress();
+    }
+    if (bg_work_paused_ && wait_for_compact_options.abort_on_pause) {
+      return Status::Aborted();
+    }
+    if ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
+         bg_flush_scheduled_ || unscheduled_compactions_ ||
+         unscheduled_flushes_ || error_handler_.IsRecoveryInProgress()) &&
+        (error_handler_.GetBGError().ok())) {
+      if (wait_for_compact_options.timeout.count()) {
+        if (bg_cv_.TimedWait(deadline)) {
+          return Status::TimedOut();
+        }
+      } else {
+        bg_cv_.Wait();
+      }
+    } else if (wait_for_compact_options.close_db) {
+      reject_new_background_jobs_ = true;
+      mutex_.Unlock();
+      Status s = Close();
+      mutex_.Lock();
+      if (!s.ok()) {
+        reject_new_background_jobs_ = false;
+      }
+      return s;
+    } else {
+      return error_handler_.GetBGError();
+    }
   }
-  return error_handler_.GetBGError();
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db/db_impl/db_impl_debug.cc

@@ -178,9 +178,12 @@ Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
   return WaitForFlushMemTable(cfd, nullptr, false);
 }
 
-Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
-  // Wait until the compaction completes
-  return WaitForCompact(wait_unscheduled);
+Status DBImpl::TEST_WaitForCompact() {
+  return WaitForCompact(WaitForCompactOptions());
+}
+Status DBImpl::TEST_WaitForCompact(
+    const WaitForCompactOptions& wait_for_compact_options) {
+  return WaitForCompact(wait_for_compact_options);
 }
 
 Status DBImpl::TEST_WaitForPurge() {

db/db_impl/db_impl_experimental.cc

@@ -138,7 +138,8 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
                    f->oldest_blob_file_number, f->oldest_ancester_time,
                    f->file_creation_time, f->epoch_number, f->file_checksum,
                    f->file_checksum_func_name, f->unique_id,
-                   f->compensated_range_deletion_size);
+                   f->compensated_range_deletion_size, f->tail_size,
+                   f->user_defined_timestamps_persisted);
     }
 
     status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),

db/db_impl/db_impl_files.cc

@@ -35,6 +35,11 @@ uint64_t DBImpl::MinObsoleteSstNumberToKeep() {
   return std::numeric_limits<uint64_t>::max();
 }
 
+uint64_t DBImpl::GetObsoleteSstFilesSize() {
+  mutex_.AssertHeld();
+  return versions_->GetObsoleteSstFilesSize();
+}
+
 Status DBImpl::DisableFileDeletions() {
   Status s;
   int my_disable_delete_obsolete_files;
@@ -286,6 +291,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     return;
   }
 
+  bool mutex_unlocked = false;
   if (!alive_log_files_.empty() && !logs_.empty()) {
     uint64_t min_log_number = job_context->log_number;
     size_t num_alive_log_files = alive_log_files_.size();
@@ -315,6 +321,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
     }
     log_write_mutex_.Unlock();
     mutex_.Unlock();
+    mutex_unlocked = true;
     TEST_SYNC_POINT_CALLBACK("FindObsoleteFiles::PostMutexUnlock", nullptr);
     log_write_mutex_.Lock();
     while (!logs_.empty() && logs_.front().number < min_log_number) {
@@ -337,7 +344,9 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
 
   logs_to_free_.clear();
   log_write_mutex_.Unlock();
-  mutex_.Lock();
+  if (mutex_unlocked) {
+    mutex_.Lock();
+  }
   job_context->log_recycle_files.assign(log_recycle_files_.begin(),
                                         log_recycle_files_.end());
 }

db/db_impl/db_impl_open.cc

@@ -24,7 +24,8 @@
 #include "rocksdb/table.h"
 #include "rocksdb/wal_filter.h"
 #include "test_util/sync_point.h"
-#include "util/rate_limiter.h"
+#include "util/rate_limiter_impl.h"
+#include "util/udt_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 Options SanitizeOptions(const std::string& dbname, const Options& src,
@@ -142,11 +143,6 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src,
     result.wal_dir = result.wal_dir.substr(0, result.wal_dir.size() - 1);
   }
 
-  if (result.use_direct_reads && result.compaction_readahead_size == 0) {
-    TEST_SYNC_POINT_CALLBACK("SanitizeOptions:direct_io", nullptr);
-    result.compaction_readahead_size = 1024 * 1024 * 2;
-  }
-
   // Force flush on DB open if 2PC is enabled, since with 2PC we have no
   // guarantee that consecutive log files have consecutive sequence id, which
   // make recovery complicated.
@@ -616,7 +612,8 @@ Status DBImpl::Recover(
                            f->oldest_blob_file_number, f->oldest_ancester_time,
                            f->file_creation_time, f->epoch_number,
                            f->file_checksum, f->file_checksum_func_name,
-                           f->unique_id, f->compensated_range_deletion_size);
+                           f->unique_id, f->compensated_range_deletion_size,
+                           f->tail_size, f->user_defined_timestamps_persisted);
               ROCKS_LOG_WARN(immutable_db_options_.info_log,
                              "[%s] Moving #%" PRIu64
                              " from from_level-%d to from_level-%d %" PRIu64
@@ -1185,6 +1182,9 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
     std::string scratch;
     Slice record;
 
+    const UnorderedMap<uint32_t, size_t>& running_ts_sz =
+        versions_->GetRunningColumnFamiliesTimestampSize();
+
     TEST_SYNC_POINT_CALLBACK("DBImpl::RecoverLogFiles:BeforeReadWal",
                              /*arg=*/nullptr);
     uint64_t record_checksum;
@@ -1198,27 +1198,41 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
                             Status::Corruption("log record too small"));
         continue;
       }
-
       // We create a new batch and initialize with a valid prot_info_ to store
       // the data checksums
       WriteBatch batch;
+      std::unique_ptr<WriteBatch> new_batch;
 
       status = WriteBatchInternal::SetContents(&batch, record);
       if (!status.ok()) {
         return status;
       }
-      TEST_SYNC_POINT_CALLBACK(
-          "DBImpl::RecoverLogFiles:BeforeUpdateProtectionInfo:batch", &batch);
-      TEST_SYNC_POINT_CALLBACK(
-          "DBImpl::RecoverLogFiles:BeforeUpdateProtectionInfo:checksum",
-          &record_checksum);
-      status = WriteBatchInternal::UpdateProtectionInfo(
-          &batch, 8 /* bytes_per_key */, &record_checksum);
+
+      const UnorderedMap<uint32_t, size_t>& record_ts_sz =
+          reader.GetRecordedTimestampSize();
+      status = HandleWriteBatchTimestampSizeDifference(
+          &batch, running_ts_sz, record_ts_sz,
+          TimestampSizeConsistencyMode::kReconcileInconsistency, &new_batch);
       if (!status.ok()) {
         return status;
       }
 
-      SequenceNumber sequence = WriteBatchInternal::Sequence(&batch);
+      bool batch_updated = new_batch != nullptr;
+      WriteBatch* batch_to_use = batch_updated ? new_batch.get() : &batch;
+      TEST_SYNC_POINT_CALLBACK(
+          "DBImpl::RecoverLogFiles:BeforeUpdateProtectionInfo:batch",
+          batch_to_use);
+      TEST_SYNC_POINT_CALLBACK(
+          "DBImpl::RecoverLogFiles:BeforeUpdateProtectionInfo:checksum",
+          &record_checksum);
+      status = WriteBatchInternal::UpdateProtectionInfo(
+          batch_to_use, 8 /* bytes_per_key */,
+          batch_updated ? nullptr : &record_checksum);
+      if (!status.ok()) {
+        return status;
+      }
+
+      SequenceNumber sequence = WriteBatchInternal::Sequence(batch_to_use);
 
       if (immutable_db_options_.wal_recovery_mode ==
           WALRecoveryMode::kPointInTimeRecovery) {
@@ -1239,7 +1253,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
       // and returns true.
       if (!InvokeWalFilterIfNeededOnWalRecord(wal_number, fname, reporter,
                                               status, stop_replay_by_wal_filter,
-                                              batch)) {
+                                              *batch_to_use)) {
         continue;
       }
 
@@ -1250,7 +1264,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
       // That's why we set ignore missing column families to true
       bool has_valid_writes = false;
       status = WriteBatchInternal::InsertInto(
-          &batch, column_family_memtables_.get(), &flush_scheduler_,
+          batch_to_use, column_family_memtables_.get(), &flush_scheduler_,
           &trim_history_scheduler_, true, wal_number, this,
           false /* concurrent_memtable_writes */, next_sequence,
           &has_valid_writes, seq_per_batch_, batch_per_txn_);
@@ -1453,7 +1467,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
         recovery_ctx->UpdateVersionEdits(cfd, iter->second);
       }
 
-      if (flushed) {
+      if (flushed || !data_seen) {
         VersionEdit wal_deletion;
         if (immutable_db_options_.track_and_verify_wals_in_manifest) {
           wal_deletion.DeleteWalsBefore(max_wal_number + 1);
@@ -1639,6 +1653,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       Version* version = cfd->current();
       version->Ref();
       const ReadOptions read_option(Env::IOActivity::kDBOpen);
+      uint64_t num_input_entries = 0;
       s = BuildTable(
           dbname_, versions_.get(), immutable_db_options_, tboptions,
           file_options_for_compaction_, read_option, cfd->table_cache(),
@@ -1648,7 +1663,8 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
           io_tracer_, BlobFileCreationReason::kRecovery,
           empty_seqno_time_mapping, &event_logger_, job_id, Env::IO_HIGH,
           nullptr /* table_properties */, write_hint,
-          nullptr /*full_history_ts_low*/, &blob_callback_, version);
+          nullptr /*full_history_ts_low*/, &blob_callback_, version,
+          &num_input_entries);
       version->Unref();
       LogFlush(immutable_db_options_.info_log);
       ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
@@ -1662,6 +1678,19 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       if (!io_s.ok() && s.ok()) {
         s = io_s;
       }
+
+      uint64_t total_num_entries = mem->num_entries();
+      if (s.ok() && total_num_entries != num_input_entries) {
+        std::string msg = "Expected " + std::to_string(total_num_entries) +
+                          " entries in memtable, but read " +
+                          std::to_string(num_input_entries);
+        ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                       "[%s] [JOB %d] Level-0 flush during recover: %s",
+                       cfd->GetName().c_str(), job_id, msg.c_str());
+        if (immutable_db_options_.flush_verify_memtable_count) {
+          s = Status::Corruption(msg);
+        }
+      }
     }
   }
   ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
@@ -1680,7 +1709,8 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                   meta.oldest_blob_file_number, meta.oldest_ancester_time,
                   meta.file_creation_time, meta.epoch_number,
                   meta.file_checksum, meta.file_checksum_func_name,
-                  meta.unique_id, meta.compensated_range_deletion_size);
+                  meta.unique_id, meta.compensated_range_deletion_size,
+                  meta.tail_size, meta.user_defined_timestamps_persisted);
 
     for (const auto& blob : blob_file_additions) {
       edit->AddBlobFile(blob);

db/db_impl/db_impl_readonly.cc

@@ -36,23 +36,30 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
              /*timestamp*/ nullptr);
 }
 
-Status DBImplReadOnly::Get(const ReadOptions& read_options,
+Status DBImplReadOnly::Get(const ReadOptions& _read_options,
                            ColumnFamilyHandle* column_family, const Slice& key,
                            PinnableSlice* pinnable_val,
                            std::string* timestamp) {
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kGet) {
     return Status::InvalidArgument(
-        "Cannot call Get with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
+        "Can only call Get with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kGet`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kGet;
   }
   assert(pinnable_val != nullptr);
-  // TODO: stopwatch DB_GET needed?, perf timer needed?
+  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);
 
   assert(column_family);
   if (read_options.timestamp) {
-    const Status s = FailIfTsMismatchCf(
-        column_family, *(read_options.timestamp), /*ts_for_read=*/true);
+    const Status s =
+        FailIfTsMismatchCf(column_family, *(read_options.timestamp),
+                           /*ts_for_read=*/true);
     if (!s.ok()) {
       return s;
     }
@@ -115,17 +122,23 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
   return s;
 }
 
-Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
+Iterator* DBImplReadOnly::NewIterator(const ReadOptions& _read_options,
                                       ColumnFamilyHandle* column_family) {
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kDBIterator) {
     return NewErrorIterator(Status::InvalidArgument(
-        "Cannot call NewIterator with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`"));
+        "Can only call NewIterator with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kDBIterator`"));
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kDBIterator;
   }
   assert(column_family);
   if (read_options.timestamp) {
-    const Status s = FailIfTsMismatchCf(
-        column_family, *(read_options.timestamp), /*ts_for_read=*/true);
+    const Status s =
+        FailIfTsMismatchCf(column_family, *(read_options.timestamp),
+                           /*ts_for_read=*/true);
     if (!s.ok()) {
       return NewErrorIterator(s);
     }

db/db_impl/db_impl_readonly.h

@@ -28,14 +28,14 @@ class DBImplReadOnly : public DBImpl {
   virtual Status Get(const ReadOptions& options,
                      ColumnFamilyHandle* column_family, const Slice& key,
                      PinnableSlice* value) override;
-  Status Get(const ReadOptions& options, ColumnFamilyHandle* column_family,
-             const Slice& key, PinnableSlice* value,
-             std::string* timestamp) override;
+  Status Get(const ReadOptions& _read_options,
+             ColumnFamilyHandle* column_family, const Slice& key,
+             PinnableSlice* value, std::string* timestamp) override;
 
   // TODO: Implement ReadOnly MultiGet?
 
   using DBImpl::NewIterator;
-  virtual Iterator* NewIterator(const ReadOptions&,
+  virtual Iterator* NewIterator(const ReadOptions& _read_options,
                                 ColumnFamilyHandle* column_family) override;
 
   virtual Status NewIterators(
@@ -142,6 +142,22 @@ class DBImplReadOnly : public DBImpl {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
 
+  virtual Status CreateColumnFamilyWithImport(
+      const ColumnFamilyOptions& /*options*/,
+      const std::string& /*column_family_name*/,
+      const ImportColumnFamilyOptions& /*import_options*/,
+      const std::vector<const ExportImportFilesMetaData*>& /*metadatas*/,
+      ColumnFamilyHandle** /*handle*/) override {
+    return Status::NotSupported("Not supported operation in read only mode.");
+  }
+
+  using DB::ClipColumnFamily;
+  virtual Status ClipColumnFamily(ColumnFamilyHandle* /*column_family*/,
+                                  const Slice& /*begin*/,
+                                  const Slice& /*end*/) override {
+    return Status::NotSupported("Not supported operation in read only mode.");
+  }
+
   // FIXME: some missing overrides for more "write" functions
 
  protected:
@@ -163,4 +179,3 @@ class DBImplReadOnly : public DBImpl {
   friend class DB;
 };
 }  // namespace ROCKSDB_NAMESPACE
-

db/db_impl/db_impl_secondary.cc

@@ -14,6 +14,7 @@
 #include "monitoring/perf_context_imp.h"
 #include "rocksdb/configurable.h"
 #include "util/cast_util.h"
+#include "util/write_batch_util.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -197,6 +198,9 @@ Status DBImplSecondary::RecoverLogFiles(
     }
     assert(reader != nullptr);
   }
+
+  const UnorderedMap<uint32_t, size_t>& running_ts_sz =
+      versions_->GetRunningColumnFamiliesTimestampSize();
   for (auto log_number : log_numbers) {
     auto it = log_readers_.find(log_number);
     assert(it != log_readers_.end());
@@ -224,6 +228,14 @@ Status DBImplSecondary::RecoverLogFiles(
       if (!status.ok()) {
         break;
       }
+      const UnorderedMap<uint32_t, size_t>& record_ts_sz =
+          reader->GetRecordedTimestampSize();
+      status = HandleWriteBatchTimestampSizeDifference(
+          &batch, running_ts_sz, record_ts_sz,
+          TimestampSizeConsistencyMode::kVerifyConsistency);
+      if (!status.ok()) {
+        break;
+      }
       SequenceNumber seq_of_batch = WriteBatchInternal::Sequence(&batch);
       std::vector<uint32_t> column_family_ids;
       status = CollectColumnFamilyIdsFromWriteBatch(batch, &column_family_ids);
@@ -328,16 +340,36 @@ Status DBImplSecondary::RecoverLogFiles(
 }
 
 // Implementation of the DB interface
-Status DBImplSecondary::Get(const ReadOptions& read_options,
+Status DBImplSecondary::Get(const ReadOptions& _read_options,
                             ColumnFamilyHandle* column_family, const Slice& key,
                             PinnableSlice* value) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kGet) {
+    return Status::InvalidArgument(
+        "Can only call Get with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kGet`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kGet;
+  }
   return GetImpl(read_options, column_family, key, value,
                  /*timestamp*/ nullptr);
 }
 
-Status DBImplSecondary::Get(const ReadOptions& read_options,
+Status DBImplSecondary::Get(const ReadOptions& _read_options,
                             ColumnFamilyHandle* column_family, const Slice& key,
                             PinnableSlice* value, std::string* timestamp) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kGet) {
+    return Status::InvalidArgument(
+        "Can only call Get with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kGet`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kGet;
+  }
   return GetImpl(read_options, column_family, key, value, timestamp);
 }
 
@@ -345,11 +377,6 @@ Status DBImplSecondary::GetImpl(const ReadOptions& read_options,
                                 ColumnFamilyHandle* column_family,
                                 const Slice& key, PinnableSlice* pinnable_val,
                                 std::string* timestamp) {
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return Status::InvalidArgument(
-        "Cannot call Get with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-  }
   assert(pinnable_val != nullptr);
   PERF_CPU_TIMER_GUARD(get_cpu_nanos, immutable_db_options_.clock);
   StopWatch sw(immutable_db_options_.clock, stats_, DB_GET);
@@ -440,8 +467,18 @@ Status DBImplSecondary::GetImpl(const ReadOptions& read_options,
   return s;
 }
 
-Iterator* DBImplSecondary::NewIterator(const ReadOptions& read_options,
+Iterator* DBImplSecondary::NewIterator(const ReadOptions& _read_options,
                                        ColumnFamilyHandle* column_family) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kDBIterator) {
+    return NewErrorIterator(Status::InvalidArgument(
+        "Can only call NewIterator with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kDBIterator`"));
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kDBIterator;
+  }
   if (read_options.managed) {
     return NewErrorIterator(
         Status::NotSupported("Managed iterator is not supported anymore."));
@@ -450,16 +487,12 @@ Iterator* DBImplSecondary::NewIterator(const ReadOptions& read_options,
     return NewErrorIterator(Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators."));
   }
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return NewErrorIterator(Status::InvalidArgument(
-        "Cannot call NewIterator with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`"));
-  }
 
   assert(column_family);
   if (read_options.timestamp) {
-    const Status s = FailIfTsMismatchCf(
-        column_family, *(read_options.timestamp), /*ts_for_read=*/true);
+    const Status s =
+        FailIfTsMismatchCf(column_family, *(read_options.timestamp),
+                           /*ts_for_read=*/true);
     if (!s.ok()) {
       return NewErrorIterator(s);
     }
@@ -511,9 +544,19 @@ ArenaWrappedDBIter* DBImplSecondary::NewIteratorImpl(
 }
 
 Status DBImplSecondary::NewIterators(
-    const ReadOptions& read_options,
+    const ReadOptions& _read_options,
     const std::vector<ColumnFamilyHandle*>& column_families,
     std::vector<Iterator*>* iterators) {
+  if (_read_options.io_activity != Env::IOActivity::kUnknown &&
+      _read_options.io_activity != Env::IOActivity::kDBIterator) {
+    return Status::InvalidArgument(
+        "Can only call NewIterators with `ReadOptions::io_activity` is "
+        "`Env::IOActivity::kUnknown` or `Env::IOActivity::kDBIterator`");
+  }
+  ReadOptions read_options(_read_options);
+  if (read_options.io_activity == Env::IOActivity::kUnknown) {
+    read_options.io_activity = Env::IOActivity::kDBIterator;
+  }
   if (read_options.managed) {
     return Status::NotSupported("Managed iterator is not supported anymore.");
   }
@@ -521,11 +564,6 @@ Status DBImplSecondary::NewIterators(
     return Status::NotSupported(
         "ReadTier::kPersistedData is not yet supported in iterators.");
   }
-  if (read_options.io_activity != Env::IOActivity::kUnknown) {
-    return Status::InvalidArgument(
-        "Cannot call NewIterators with `ReadOptions::io_activity` != "
-        "`Env::IOActivity::kUnknown`");
-  }
   ReadCallback* read_callback = nullptr;  // No read callback provided.
   if (iterators == nullptr) {
     return Status::InvalidArgument("iterators not allowed to be nullptr");
@@ -948,6 +986,8 @@ Status DB::OpenAndCompact(
   delete db;
   if (s.ok()) {
     return serialization_status;
+  } else {
+    serialization_status.PermitUncheckedError();
   }
   return s;
 }

db/db_impl/db_impl_secondary.h

@@ -96,12 +96,13 @@ class DBImplSecondary : public DBImpl {
   // workaround, the secondaries can be opened with `max_open_files=-1` so that
   // it eagerly keeps all talbe files open and is able to access the contents of
   // deleted files via prior open fd.
-  Status Get(const ReadOptions& options, ColumnFamilyHandle* column_family,
-             const Slice& key, PinnableSlice* value) override;
+  Status Get(const ReadOptions& _read_options,
+             ColumnFamilyHandle* column_family, const Slice& key,
+             PinnableSlice* value) override;
 
-  Status Get(const ReadOptions& options, ColumnFamilyHandle* column_family,
-             const Slice& key, PinnableSlice* value,
-             std::string* timestamp) override;
+  Status Get(const ReadOptions& _read_options,
+             ColumnFamilyHandle* column_family, const Slice& key,
+             PinnableSlice* value, std::string* timestamp) override;
 
   Status GetImpl(const ReadOptions& options, ColumnFamilyHandle* column_family,
                  const Slice& key, PinnableSlice* value,
@@ -117,7 +118,7 @@ class DBImplSecondary : public DBImpl {
   // deleted. As a partial hacky workaround, the secondaries can be opened with
   // `max_open_files=-1` so that it eagerly keeps all talbe files open and is
   // able to access the contents of deleted files via prior open fd.
-  Iterator* NewIterator(const ReadOptions&,
+  Iterator* NewIterator(const ReadOptions& _read_options,
                         ColumnFamilyHandle* column_family) override;
 
   ArenaWrappedDBIter* NewIteratorImpl(const ReadOptions& read_options,
@@ -127,7 +128,7 @@ class DBImplSecondary : public DBImpl {
                                       bool expose_blob_index = false,
                                       bool allow_refresh = true);
 
-  Status NewIterators(const ReadOptions& options,
+  Status NewIterators(const ReadOptions& _read_options,
                       const std::vector<ColumnFamilyHandle*>& column_families,
                       std::vector<Iterator*>* iterators) override;
 
@@ -273,85 +274,6 @@ class DBImplSecondary : public DBImpl {
     return Status::OK();
   }
 
-  // ColumnFamilyCollector is a write batch handler which does nothing
-  // except recording unique column family IDs
-  class ColumnFamilyCollector : public WriteBatch::Handler {
-    std::unordered_set<uint32_t> column_family_ids_;
-
-    Status AddColumnFamilyId(uint32_t column_family_id) {
-      if (column_family_ids_.find(column_family_id) ==
-          column_family_ids_.end()) {
-        column_family_ids_.insert(column_family_id);
-      }
-      return Status::OK();
-    }
-
-   public:
-    explicit ColumnFamilyCollector() {}
-
-    ~ColumnFamilyCollector() override {}
-
-    Status PutCF(uint32_t column_family_id, const Slice&,
-                 const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status DeleteCF(uint32_t column_family_id, const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status SingleDeleteCF(uint32_t column_family_id, const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status DeleteRangeCF(uint32_t column_family_id, const Slice&,
-                         const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status MergeCF(uint32_t column_family_id, const Slice&,
-                   const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status PutBlobIndexCF(uint32_t column_family_id, const Slice&,
-                          const Slice&) override {
-      return AddColumnFamilyId(column_family_id);
-    }
-
-    Status MarkBeginPrepare(bool) override { return Status::OK(); }
-
-    Status MarkEndPrepare(const Slice&) override { return Status::OK(); }
-
-    Status MarkRollback(const Slice&) override { return Status::OK(); }
-
-    Status MarkCommit(const Slice&) override { return Status::OK(); }
-
-    Status MarkCommitWithTimestamp(const Slice&, const Slice&) override {
-      return Status::OK();
-    }
-
-    Status MarkNoop(bool) override { return Status::OK(); }
-
-    const std::unordered_set<uint32_t>& column_families() const {
-      return column_family_ids_;
-    }
-  };
-
-  Status CollectColumnFamilyIdsFromWriteBatch(
-      const WriteBatch& batch, std::vector<uint32_t>* column_family_ids) {
-    assert(column_family_ids != nullptr);
-    column_family_ids->clear();
-    ColumnFamilyCollector handler;
-    Status s = batch.Iterate(&handler);
-    if (s.ok()) {
-      for (const auto& cf : handler.column_families()) {
-        column_family_ids->push_back(cf);
-      }
-    }
-    return s;
-  }
-
   bool OwnTablesAndLogs() const override {
     // Currently, the secondary instance does not own the database files. It
     // simply opens the files of the primary instance and tracks their file
@@ -403,4 +325,3 @@ class DBImplSecondary : public DBImpl {
 };
 
 }  // namespace ROCKSDB_NAMESPACE
-

db/db_impl/db_impl_write.cc

@@ -1328,7 +1328,13 @@ IOStatus DBImpl::WriteToWAL(const WriteBatch& merged_batch,
   if (UNLIKELY(needs_locking)) {
     log_write_mutex_.Lock();
   }
-  IOStatus io_s = log_writer->AddRecord(log_entry, rate_limiter_priority);
+  IOStatus io_s = log_writer->MaybeAddUserDefinedTimestampSizeRecord(
+      versions_->GetColumnFamiliesTimestampSizeForRecord(),
+      rate_limiter_priority);
+  if (!io_s.ok()) {
+    return io_s;
+  }
+  io_s = log_writer->AddRecord(log_entry, rate_limiter_priority);
 
   if (UNLIKELY(needs_locking)) {
     log_write_mutex_.Unlock();

db/db_iter.cc

@@ -77,6 +77,7 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
       expose_blob_index_(expose_blob_index),
       is_blob_(false),
       arena_mode_(arena_mode),
+      io_activity_(read_options.io_activity),
       db_impl_(db_impl),
       cfd_(cfd),
       timestamp_ub_(read_options.timestamp),
@@ -196,12 +197,11 @@ bool DBIter::SetBlobValueIfNeeded(const Slice& user_key,
 
   // TODO: consider moving ReadOptions from ArenaWrappedDBIter to DBIter to
   // avoid having to copy options back and forth.
-  // TODO: plumb Env::IOActivity
   ReadOptions read_options;
   read_options.read_tier = read_tier_;
   read_options.fill_cache = fill_cache_;
   read_options.verify_checksums = verify_checksums_;
-
+  read_options.io_activity = io_activity_;
   constexpr FilePrefetchBuffer* prefetch_buffer = nullptr;
   constexpr uint64_t* bytes_read = nullptr;
 
@@ -964,9 +964,6 @@ bool DBIter::FindValueForCurrentKey() {
     assert(last_key_entry_type == ikey_.type);
   }
 
-  Status s;
-  s.PermitUncheckedError();
-
   switch (last_key_entry_type) {
     case kTypeDeletion:
     case kTypeDeletionWithTimestamp:
@@ -1043,11 +1040,6 @@ bool DBIter::FindValueForCurrentKey() {
           std::to_string(static_cast<unsigned int>(last_key_entry_type)));
       return false;
   }
-  if (!s.ok()) {
-    valid_ = false;
-    status_ = s;
-    return false;
-  }
   valid_ = true;
   return true;
 }

db/db_iter.h

@@ -384,6 +384,7 @@ class DBIter final : public Iterator {
   bool expose_blob_index_;
   bool is_blob_;
   bool arena_mode_;
+  const Env::IOActivity io_activity_;
   // List of operands for merge operator.
   MergeContext merge_context_;
   LocalStatistics local_stats_;

db/db_iterator_test.cc

@@ -16,7 +16,7 @@
 #include "port/stack_trace.h"
 #include "rocksdb/iostats_context.h"
 #include "rocksdb/perf_context.h"
-#include "table/block_based/flush_block_policy.h"
+#include "table/block_based/flush_block_policy_impl.h"
 #include "util/random.h"
 #include "utilities/merge_operators/string_append/stringappend2.h"
 

db/db_merge_operand_test.cc

@@ -49,10 +49,8 @@ TEST_F(DBMergeOperandTest, CacheEvictedMergeOperandReadAfterFreeBug) {
   // There was a bug of reading merge operands after they are mistakely freed
   // in DB::GetMergeOperands, which is surfaced by cache full.
   // See PR#9507 for more.
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   options.merge_operator = MergeOperators::CreateStringAppendOperator();
-  options.env = env_;
   BlockBasedTableOptions table_options;
 
   // Small cache to simulate cache full
@@ -121,11 +119,9 @@ TEST_F(DBMergeOperandTest, FlushedMergeOperandReadAfterFreeBug) {
 }
 
 TEST_F(DBMergeOperandTest, GetMergeOperandsBasic) {
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   // Use only the latest two merge operands.
   options.merge_operator = std::make_shared<LimitedStringAppendMergeOp>(2, ',');
-  options.env = env_;
   Reopen(options);
   int num_records = 4;
   int number_of_operands = 0;
@@ -309,13 +305,11 @@ TEST_F(DBMergeOperandTest, GetMergeOperandsBasic) {
 }
 
 TEST_F(DBMergeOperandTest, BlobDBGetMergeOperandsBasic) {
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   options.enable_blob_files = true;
   options.min_blob_size = 0;
   // Use only the latest two merge operands.
   options.merge_operator = std::make_shared<LimitedStringAppendMergeOp>(2, ',');
-  options.env = env_;
   Reopen(options);
   int num_records = 4;
   int number_of_operands = 0;
@@ -401,8 +395,7 @@ TEST_F(DBMergeOperandTest, GetMergeOperandsLargeResultOptimization) {
   const int kNumOperands = 1024;
   const int kOperandLen = 1024;
 
-  Options options;
-  options.create_if_missing = true;
+  Options options = CurrentOptions();
   options.merge_operator = MergeOperators::CreateStringAppendOperator();
   DestroyAndReopen(options);
 

db/db_merge_operator_test.cc

@@ -81,7 +81,7 @@ TEST_F(DBMergeOperatorTest, LimitMergeOperands) {
     size_t limit_ = 0;
   };
 
-  Options options;
+  Options options = CurrentOptions();
   options.create_if_missing = true;
   // Use only the latest two merge operands.
   options.merge_operator = std::make_shared<LimitedStringAppendMergeOp>(2, ',');
@@ -134,7 +134,7 @@ TEST_F(DBMergeOperatorTest, LimitMergeOperands) {
 }
 
 TEST_F(DBMergeOperatorTest, MergeErrorOnRead) {
-  Options options;
+  Options options = CurrentOptions();
   options.create_if_missing = true;
   options.merge_operator.reset(new TestPutOperator());
   options.env = env_;
@@ -147,7 +147,7 @@ TEST_F(DBMergeOperatorTest, MergeErrorOnRead) {
 }
 
 TEST_F(DBMergeOperatorTest, MergeErrorOnWrite) {
-  Options options;
+  Options options = CurrentOptions();
   options.create_if_missing = true;
   options.merge_operator.reset(new TestPutOperator());
   options.max_successive_merges = 3;
@@ -163,7 +163,7 @@ TEST_F(DBMergeOperatorTest, MergeErrorOnWrite) {
 }
 
 TEST_F(DBMergeOperatorTest, MergeErrorOnIteration) {
-  Options options;
+  Options options = CurrentOptions();
   options.create_if_missing = true;
   options.merge_operator.reset(new TestPutOperator());
   options.env = env_;
@@ -221,7 +221,7 @@ TEST_F(DBMergeOperatorTest, MergeOperatorFailsWithMustMerge) {
   // expect "k0" and "k2" to always be readable. "k1" is expected to be readable
   // only by APIs that do not require merging, such as `GetMergeOperands()`.
   const int kNumOperands = 3;
-  Options options;
+  Options options = CurrentOptions();
   options.merge_operator.reset(new TestPutOperator());
   options.env = env_;
   Reopen(options);
@@ -361,7 +361,7 @@ TEST_F(DBMergeOperatorTest, MergeOperatorFailsWithMustMerge) {
 TEST_F(DBMergeOperatorTest, DataBlockBinaryAndHash) {
   // Basic test to check that merge operator works with data block index type
   // DataBlockBinaryAndHash.
-  Options options;
+  Options options = CurrentOptions();
   options.create_if_missing = true;
   options.merge_operator.reset(new TestPutOperator());
   options.env = env_;

db/db_options_test.cc

@@ -22,6 +22,7 @@
 #include "test_util/sync_point.h"
 #include "test_util/testutil.h"
 #include "util/random.h"
+#include "utilities/fault_injection_fs.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -581,6 +582,7 @@ TEST_F(DBOptionsTest, EnableAutoCompactionAndTriggerStall) {
 
 TEST_F(DBOptionsTest, SetOptionsMayTriggerCompaction) {
   Options options;
+  options.level_compaction_dynamic_level_bytes = false;
   options.create_if_missing = true;
   options.level0_file_num_compaction_trigger = 1000;
   options.env = env_;
@@ -878,9 +880,13 @@ TEST_F(DBOptionsTest, SanitizeFIFOPeriodicCompaction) {
   Options options;
   options.compaction_style = kCompactionStyleFIFO;
   options.env = CurrentOptions().env;
+  // Default value allows RocksDB to set ttl to 30 days.
+  ASSERT_EQ(30 * 24 * 60 * 60, dbfull()->GetOptions().ttl);
+
+  // Disable
   options.ttl = 0;
   Reopen(options);
-  ASSERT_EQ(30 * 24 * 60 * 60, dbfull()->GetOptions().ttl);
+  ASSERT_EQ(0, dbfull()->GetOptions().ttl);
 
   options.ttl = 100;
   Reopen(options);
@@ -890,15 +896,12 @@ TEST_F(DBOptionsTest, SanitizeFIFOPeriodicCompaction) {
   Reopen(options);
   ASSERT_EQ(100 * 24 * 60 * 60, dbfull()->GetOptions().ttl);
 
-  options.ttl = 200;
-  options.periodic_compaction_seconds = 300;
-  Reopen(options);
-  ASSERT_EQ(200, dbfull()->GetOptions().ttl);
-
+  // periodic_compaction_seconds should have no effect
+  // on FIFO compaction.
   options.ttl = 500;
   options.periodic_compaction_seconds = 300;
   Reopen(options);
-  ASSERT_EQ(300, dbfull()->GetOptions().ttl);
+  ASSERT_EQ(500, dbfull()->GetOptions().ttl);
 }
 
 TEST_F(DBOptionsTest, SetFIFOCompactionOptions) {
@@ -910,6 +913,7 @@ TEST_F(DBOptionsTest, SetFIFOCompactionOptions) {
   options.compression = kNoCompression;
   options.create_if_missing = true;
   options.compaction_options_fifo.allow_compaction = false;
+  options.num_levels = 1;
   env_->SetMockSleep();
   options.env = env_;
 
@@ -1009,32 +1013,58 @@ TEST_F(DBOptionsTest, SetFIFOCompactionOptions) {
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_GE(NumTableFilesAtLevel(0), 1);
   ASSERT_LE(NumTableFilesAtLevel(0), 5);
+
+  // Test dynamically setting `file_temperature_age_thresholds`
+  ASSERT_TRUE(
+      dbfull()
+          ->GetOptions()
+          .compaction_options_fifo.file_temperature_age_thresholds.empty());
+  ASSERT_OK(dbfull()->SetOptions({{"compaction_options_fifo",
+                                   "{file_temperature_age_thresholds={{age=10;"
+                                   "temperature=kWarm}:{age=30000;"
+                                   "temperature=kCold}}}"}}));
+  auto opts = dbfull()->GetOptions();
+  const auto& fifo_temp_opt =
+      opts.compaction_options_fifo.file_temperature_age_thresholds;
+  ASSERT_EQ(fifo_temp_opt.size(), 2);
+  ASSERT_EQ(fifo_temp_opt[0].temperature, Temperature::kWarm);
+  ASSERT_EQ(fifo_temp_opt[0].age, 10);
+  ASSERT_EQ(fifo_temp_opt[1].temperature, Temperature::kCold);
+  ASSERT_EQ(fifo_temp_opt[1].age, 30000);
 }
 
 TEST_F(DBOptionsTest, CompactionReadaheadSizeChange) {
-  SpecialEnv env(env_);
-  Options options;
-  options.env = &env;
+  for (bool use_direct_reads : {true, false}) {
+    SpecialEnv env(env_);
+    Options options;
+    options.env = &env;
 
-  options.compaction_readahead_size = 0;
-  options.level0_file_num_compaction_trigger = 2;
-  const std::string kValue(1024, 'v');
-  Reopen(options);
+    options.use_direct_reads = use_direct_reads;
+    options.level0_file_num_compaction_trigger = 2;
+    const std::string kValue(1024, 'v');
+    Status s = TryReopen(options);
+    if (use_direct_reads && (s.IsNotSupported() || s.IsInvalidArgument())) {
+      continue;
+    } else {
+      ASSERT_OK(s);
+    }
 
-  ASSERT_EQ(0, dbfull()->GetDBOptions().compaction_readahead_size);
-  ASSERT_OK(dbfull()->SetDBOptions({{"compaction_readahead_size", "256"}}));
-  ASSERT_EQ(256, dbfull()->GetDBOptions().compaction_readahead_size);
-  for (int i = 0; i < 1024; i++) {
-    ASSERT_OK(Put(Key(i), kValue));
+    ASSERT_EQ(1024 * 1024 * 2,
+              dbfull()->GetDBOptions().compaction_readahead_size);
+    ASSERT_OK(dbfull()->SetDBOptions({{"compaction_readahead_size", "256"}}));
+    ASSERT_EQ(256, dbfull()->GetDBOptions().compaction_readahead_size);
+    for (int i = 0; i < 1024; i++) {
+      ASSERT_OK(Put(Key(i), kValue));
+    }
+    ASSERT_OK(Flush());
+    for (int i = 0; i < 1024 * 2; i++) {
+      ASSERT_OK(Put(Key(i), kValue));
+    }
+    ASSERT_OK(Flush());
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
+    ASSERT_EQ(256, env_->compaction_readahead_size_);
+    Close();
   }
-  ASSERT_OK(Flush());
-  for (int i = 0; i < 1024 * 2; i++) {
-    ASSERT_OK(Put(Key(i), kValue));
-  }
-  ASSERT_OK(Flush());
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  ASSERT_EQ(256, env_->compaction_readahead_size_);
-  Close();
 }
 
 TEST_F(DBOptionsTest, FIFOTtlBackwardCompatible) {
@@ -1043,6 +1073,7 @@ TEST_F(DBOptionsTest, FIFOTtlBackwardCompatible) {
   options.write_buffer_size = 10 << 10;  // 10KB
   options.create_if_missing = true;
   options.env = CurrentOptions().env;
+  options.num_levels = 1;
 
   ASSERT_OK(TryReopen(options));
 
@@ -1063,12 +1094,19 @@ TEST_F(DBOptionsTest, FIFOTtlBackwardCompatible) {
   // ttl under compaction_options_fifo.
   ASSERT_OK(dbfull()->SetOptions(
       {{"compaction_options_fifo",
-        "{allow_compaction=true;max_table_files_size=1024;ttl=731;}"},
+        "{allow_compaction=true;max_table_files_size=1024;ttl=731;file_"
+        "temperature_age_thresholds={temperature=kCold;age=12345}}"},
        {"ttl", "60"}}));
   ASSERT_EQ(dbfull()->GetOptions().compaction_options_fifo.allow_compaction,
             true);
   ASSERT_EQ(dbfull()->GetOptions().compaction_options_fifo.max_table_files_size,
             1024);
+  auto opts = dbfull()->GetOptions();
+  const auto& file_temp_age =
+      opts.compaction_options_fifo.file_temperature_age_thresholds;
+  ASSERT_EQ(file_temp_age.size(), 1);
+  ASSERT_EQ(file_temp_age[0].temperature, Temperature::kCold);
+  ASSERT_EQ(file_temp_age[0].age, 12345);
   ASSERT_EQ(dbfull()->GetOptions().ttl, 60);
 
   // Put ttl as the first option inside compaction_options_fifo. That works as
@@ -1081,6 +1119,9 @@ TEST_F(DBOptionsTest, FIFOTtlBackwardCompatible) {
             true);
   ASSERT_EQ(dbfull()->GetOptions().compaction_options_fifo.max_table_files_size,
             1024);
+  ASSERT_EQ(file_temp_age.size(), 1);
+  ASSERT_EQ(file_temp_age[0].temperature, Temperature::kCold);
+  ASSERT_EQ(file_temp_age[0].age, 12345);
   ASSERT_EQ(dbfull()->GetOptions().ttl, 191);
 }
 
@@ -1206,6 +1247,90 @@ TEST_F(DBOptionsTest, BottommostCompressionOptsWithFallbackType) {
   ASSERT_EQ(kBottommostCompressionLevel, compression_opt_used.level);
 }
 
+TEST_F(DBOptionsTest, FIFOTemperatureAgeThresholdValidation) {
+  Options options = CurrentOptions();
+  Destroy(options);
+
+  options.num_levels = 1;
+  options.compaction_style = kCompactionStyleFIFO;
+  options.max_open_files = -1;
+  // elements are not sorted
+  // During DB open
+  options.compaction_options_fifo.file_temperature_age_thresholds.push_back(
+      {Temperature::kCold, 1000});
+  options.compaction_options_fifo.file_temperature_age_thresholds.push_back(
+      {Temperature::kWarm, 500});
+  Status s = TryReopen(options);
+  ASSERT_TRUE(s.IsNotSupported());
+  ASSERT_TRUE(std::strstr(
+      s.getState(),
+      "Option file_temperature_age_thresholds requires elements to be sorted "
+      "in increasing order with respect to `age` field."));
+  // Dynamically set option
+  options.compaction_options_fifo.file_temperature_age_thresholds.pop_back();
+  ASSERT_OK(TryReopen(options));
+  s = db_->SetOptions({{"compaction_options_fifo",
+                        "{file_temperature_age_thresholds={{temperature=kCold;"
+                        "age=1000000}:{temperature=kWarm;age=1}}}"}});
+  ASSERT_TRUE(s.IsNotSupported());
+  ASSERT_TRUE(std::strstr(
+      s.getState(),
+      "Option file_temperature_age_thresholds requires elements to be sorted "
+      "in increasing order with respect to `age` field."));
+
+  // not single level
+  // During DB open
+  options.num_levels = 2;
+  s = TryReopen(options);
+  ASSERT_TRUE(s.IsNotSupported());
+  ASSERT_TRUE(std::strstr(s.getState(),
+                          "Option file_temperature_age_thresholds is only "
+                          "supported when num_levels = 1."));
+  // Dynamically set option
+  options.compaction_options_fifo.file_temperature_age_thresholds.clear();
+  DestroyAndReopen(options);
+  s = db_->SetOptions(
+      {{"compaction_options_fifo",
+        "{file_temperature_age_thresholds={temperature=kCold;age=1000}}"}});
+  ASSERT_TRUE(s.IsNotSupported());
+  ASSERT_TRUE(std::strstr(s.getState(),
+                          "Option file_temperature_age_thresholds is only "
+                          "supported when num_levels = 1."));
+}
+
+TEST_F(DBOptionsTest, TempOptionsFailTest) {
+  std::shared_ptr<FaultInjectionTestFS> fs;
+  std::unique_ptr<Env> env;
+
+  fs.reset(new FaultInjectionTestFS(env_->GetFileSystem()));
+  env = NewCompositeEnv(fs);
+  Options options = CurrentOptions();
+  options.env = env.get();
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "PersistRocksDBOptions:create",
+      [&](void* /*arg*/) { fs->SetFilesystemActive(false); });
+  SyncPoint::GetInstance()->SetCallBack(
+      "PersistRocksDBOptions:written",
+      [&](void* /*arg*/) { fs->SetFilesystemActive(true); });
+
+  SyncPoint::GetInstance()->EnableProcessing();
+  ASSERT_NOK(TryReopen(options));
+  SyncPoint::GetInstance()->DisableProcessing();
+
+  std::vector<std::string> filenames;
+  ASSERT_OK(env_->GetChildren(dbname_, &filenames));
+  uint64_t number;
+  FileType type;
+  bool found_temp_file = false;
+  for (size_t i = 0; i < filenames.size(); i++) {
+    if (ParseFileName(filenames[i], &number, &type) && type == kTempFile) {
+      found_temp_file = true;
+    }
+  }
+  ASSERT_FALSE(found_temp_file);
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {