update HISTORY.md and version.h for 9.4.1

Summary:
Make `DestroyDB` slowly delete files if it's configured and enabled via `SstFileManager`.

It's currently not available mainly because of DeleteScheduler's logic related to tracked total_size_ and total_trash_size_. These accounting and logic should not be applied to `DestroyDB`. This PR adds a `DeleteUnaccountedDBFile` util for this purpose which deletes files without accounting it.  This util also supports assigning a file to a specified trash bucket so that user can later wait for a specific trash bucket to be empty. For `DestroyDB`, files with more than 1 hard links will be deleted immediately.

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12891

Test Plan: Added unit tests, existing tests.

Reviewed By: anand1976

Differential Revision: D60300220

Pulled By: jowlyzhang

fbshipit-source-id: 8b18109a177a3a9532f6dc2e40e08310c08ca3c7

.github/workflows/benchmark-linux.yml

@@ -1,13 +1,13 @@
 name: facebook/rocksdb/benchmark-linux
 on: workflow_dispatch
-permissions: {}
-  # FIXME: Disabled temporarily
-  # schedule:
-  # - cron: 7 */2 * * *  # At minute 7 past every 2nd hour
 jobs:
+  # FIXME: when this job is fixed, it should be given a cron schedule like
+  # schedule:
+  # - cron: 0 * * * *
+  # workflow_dispatch:
   benchmark-linux:
     if: ${{ github.repository_owner == 'facebook' }}
-    runs-on: ubuntu-latest # FIXME: change this back to self-hosted when ready
+    runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/build-for-benchmarks"

.github/workflows/nightly-candidate.yml

@@ -1,6 +1,5 @@
 name: facebook/rocksdb/nightly
 on: workflow_dispatch
-permissions: {}
 jobs:
   # These jobs would be in nightly but are failing or otherwise broken for
   # some reason.

.github/workflows/nightly.yml

@@ -3,7 +3,6 @@ on:
   schedule:
   - cron: 0 9 * * *
   workflow_dispatch:
-permissions: {}
 jobs:
   build-format-compatible:
     if: ${{ github.repository_owner == 'facebook' }}
@@ -60,15 +59,12 @@ jobs:
     container:
       image: zjay437/rocksdb:0.6
       options: --shm-size=16gb
-    env:
-      CC: clang-13
-      CXX: clang++-13
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
     - uses: "./.github/actions/setup-folly"
     - uses: "./.github/actions/build-folly"
-    - run: LIB_MODE=static USE_CLANG=1 USE_FOLLY=1 COMPILE_WITH_UBSAN=1 COMPILE_WITH_ASAN=1 make -j32 check
+    - run: CC=clang-13 CXX=clang++-13 LIB_MODE=static USE_CLANG=1 USE_FOLLY=1 COMPILE_WITH_UBSAN=1 COMPILE_WITH_ASAN=1 make -j32 check
     - uses: "./.github/actions/post-steps"
   build-linux-valgrind:
     if: ${{ github.repository_owner == 'facebook' }}
@@ -80,7 +76,7 @@ jobs:
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
-    - run: make V=1 -j32 valgrind_test
+    - run: PORTABLE=1 make V=1 -j32 valgrind_test
     - uses: "./.github/actions/post-steps"
   build-windows-vs2022-avx2:
     if: ${{ github.repository_owner == 'facebook' }}

.github/workflows/pr-jobs-candidate.yml

@@ -1,6 +1,5 @@
 name: facebook/rocksdb/pr-jobs-candidate
 on: workflow_dispatch
-permissions: {}
 jobs:
   # These jobs would be in pr-jobs but are failing or otherwise broken for
   # some reason.

.github/workflows/pr-jobs.yml

@@ -1,6 +1,5 @@
 name: facebook/rocksdb/pr-jobs
 on: [push, pull_request]
-permissions: {}
 jobs:
   # NOTE: multiple workflows would be recommended, but the current GHA UI in
   # PRs doesn't make it clear when there's an overall error with a workflow,

CMakeLists.txt

@@ -32,7 +32,7 @@
 # 3. cmake ..
 # 4. make -j
 
-cmake_minimum_required(VERSION 3.12)
+cmake_minimum_required(VERSION 3.10)
 
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
 include(ReadVersion)

HISTORY.md

@@ -1,111 +1,9 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
-## 9.8.4 (11/18/2024)
-### Behavior Changes
-* When Remote Compaction is enabled, do not purge OPTIONS file immediately by DeleteObsoleteOptionsFiles() after SetOptions(). Rely on PurgeObsoleteFiles() to clean up obsolete OPTIONS file after each compaction.
-
-## 9.8.3 (11/12/2024)
-### Bug Fixes
-* Fix missing cases of corruption retry during DB open and read API processing.
-
-## 9.8.2 (11/06/2024)
-### Public API Changes
-* Added a new API `Transaction::GetAttributeGroupIterator` that can be used to create a multi-column-family attribute group iterator over the specified column families, including the data from both the transaction and the underlying database. This API is currently supported for optimistic and write-committed pessimistic transactions.
-
-### Behavior Changes
-* `BaseDeltaIterator` now honors the read option `allow_unprepared_value`.
-
-### Bug Fixes
-* `BaseDeltaIterator` now calls `PrepareValue` on the base iterator in case it has been created with the `allow_unprepared_value` read option set. Earlier, such base iterators could lead to incorrect values being exposed from `BaseDeltaIterator`.
-* Fix a bug for replaying WALs for WriteCommitted transaction DB when its user-defined timestamps setting is toggled on/off between DB sessions.
-
-## 9.8.1 (10/31/2024)
-### Bug Fixes
-* Fix a leak of obsolete blob files left open until DB::Close(). This bug was introduced in version 9.4.0.
-
-## 9.8.0 (10/25/2024)
-### New Features
-* All non-`block_cache` options in `BlockBasedTableOptions` are now mutable with `DB::SetOptions()`. See also Bug Fixes below.
-* When using iterators with BlobDB, it is now possible to load large values on an on-demand basis, i.e. only if they are actually needed by the application. This can save I/O in use cases where the values associated with certain keys are not needed. For more details, see the new read option `allow_unprepared_value` and the iterator API `PrepareValue`.
-* Add a new file ingestion option `IngestExternalFileOptions::fill_cache` to support not adding blocks from ingested files into block cache during file ingestion.
-* The option `allow_unprepared_value` is now also supported for multi-column-family iterators (i.e. `CoalescingIterator` and `AttributeGroupIterator`).
-* When a file with just one range deletion (standalone range deletion file) is ingested via bulk loading, it will be marked for compaction. During compaction, this type of files can be used to directly filter out some input files that are not protected by any snapshots and completely deleted by the standalone range deletion file.
-
-### Behavior Changes
-* During file ingestion, overlapping files level assignment are done in multiple batches, so that they can potentially be assigned to lower levels other than always land on L0.
-* OPTIONS file to be loaded by remote worker is now preserved so that it does not get purged by the primary host. A similar technique as how we are preserving new SST files from getting purged is used for this. min_options_file_numbers_ is tracked like pending_outputs_ is tracked.
-* Trim readahead_size during scans so data blocks containing keys that are not in the same prefix as the seek key in `Seek()` are not prefetched when `ReadOptions::auto_readahead_size=true` (default value) and `ReadOptions::prefix_same_as_start = true`
-* Assigning levels for external files are done in the same way for universal compaction and leveled compaction. The old behavior tends to assign files to L0 while the new behavior will assign the files to the lowest level possible.
-
-### Bug Fixes
-* Fix a longstanding race condition in SetOptions for `block_based_table_factory` options. The fix has some subtle behavior changes because of copying and replacing the TableFactory on a change with SetOptions, including requiring an Iterator::Refresh() for an existing Iterator to use the latest options.
-* Fix under counting of allocated memory in the compressed secondary cache due to looking at the compressed block size rather than the actual memory allocated, which could be larger due to internal fragmentation.
-* `GetApproximateMemTableStats()` could return disastrously bad estimates 5-25% of the time. The function has been re-engineered to return much better estimates with similar CPU cost.
-* Skip insertion of compressed blocks in the secondary cache if the lowest_used_cache_tier DB option is kVolatileTier.
-* Fix an issue in level compaction where a small CF with small compaction debt can cause the DB to allow parallel compactions. (#13054)
-* Several DB option settings could be lost through `GetOptionsFromString()`, possibly elsewhere as well. Affected options, now fixed:`background_close_inactive_wals`, `write_dbid_to_manifest`, `write_identity_file`, `prefix_seek_opt_in_only`
-
-## 9.7.0 (09/20/2024)
-### New Features
-* Make Cache a customizable class that can be instantiated by the object registry.
-* Add new option `prefix_seek_opt_in_only` that makes iterators generally safer when you might set a `prefix_extractor`. When `prefix_seek_opt_in_only=true`, which is expected to be the future default, prefix seek is only used when `prefix_same_as_start` or `auto_prefix_mode` are set. Also, `prefix_same_as_start` and `auto_prefix_mode` now allow prefix filtering even with `total_order_seek=true`.
-* Add a new table property "rocksdb.key.largest.seqno" which records the largest sequence number of all keys in file. It is verified to be zero during SST file ingestion.
-
-### Behavior Changes
-* Changed the semantics of the BlobDB configuration option `blob_garbage_collection_force_threshold` to define a threshold for the overall garbage ratio of all blob files currently eligible for garbage collection (according to `blob_garbage_collection_age_cutoff`). This can provide better control over space amplification at the cost of slightly higher write amplification.
-* Set `write_dbid_to_manifest=true` by default. This means DB ID will now be preserved through backups, checkpoints, etc. by default. Also add `write_identity_file` option which can be set to false for anticipated future behavior.
-* In FIFO compaction, compactions for changing file temperature (configured by option `file_temperature_age_thresholds`) will compact one file at a time, instead of merging multiple eligible file together (#13018).
-* Support ingesting db generated files using hard link, i.e. IngestExternalFileOptions::move_files/link_files and IngestExternalFileOptions::allow_db_generated_files.
-* Add a new file ingestion option `IngestExternalFileOptions::link_files` to hard link input files and preserve original files links after ingestion.
-* DB::Close now untracks files in SstFileManager, making avaialble any space used
-by them. Prior to this change they would be orphaned until the DB is re-opened.
-
-### Bug Fixes
-* Fix a bug in CompactRange() where result files may not be compacted in any future compaction. This can only happen when users configure CompactRangeOptions::change_level to true and the change level step of manual compaction fails (#13009).
-* Fix handling of dynamic change of `prefix_extractor` with memtable prefix filter. Previously, prefix seek could mix different prefix interpretations between memtable and SST files. Now the latest `prefix_extractor` at the time of iterator creation or refresh is respected.
-* Fix a bug with manual_wal_flush and auto error recovery from WAL failure that may cause CFs to be inconsistent (#12995). The fix will set potential WAL write failure as fatal error when manual_wal_flush is true, and disables auto error recovery from these errors.
-
-## 9.6.0 (08/19/2024)
-### New Features
-* *Best efforts recovery supports recovering to incomplete Version with a clean seqno cut that presents a valid point in time view from the user's perspective, if versioning history doesn't include atomic flush.
-* New option `BlockBasedTableOptions::decouple_partitioned_filters` should improve efficiency in serving read queries because filter and index partitions can consistently target the configured `metadata_block_size`. This option is currently opt-in.
-* Introduce a new mutable CF option `paranoid_memory_checks`. It enables additional validation on data integrity during reads/scanning. Currently, skip list based memtable will validate key ordering during look up and scans.
-
-### Public API Changes
-* Add ticker stats to count file read retries due to checksum mismatch
-* Adds optional installation callback function for remote compaction
-
-### Behavior Changes
-* There may be less intra-L0 compaction triggered by total L0 size being too small. We now use compensated file size (tombstones are assigned some value size) when calculating L0 size and reduce the threshold for L0 size limit. This is to avoid accumulating too much data/tombstones in L0.
-
+## 9.4.1 (08/02/2024)
 ### Bug Fixes
 * *Make DestroyDB supports slow deletion when it's configured in `SstFileManager`. The slow deletion is subject to the configured `rate_bytes_per_sec`, but not subject to the `max_trash_db_ratio`.
-* Fixed a bug where we set unprep_seqs_ even when WriteImpl() fails. This was caught by stress test write fault injection in WriteImpl(). This may have incorrectly caused iteration creation failure for unvalidated writes or returned wrong result for WriteUnpreparedTxn::GetUnpreparedSequenceNumbers().
-* Fixed a bug where successful write right after error recovery for last failed write finishes causes duplicate WAL entries
-* Fixed a data race involving the background error status in `unordered_write` mode.
-* *Fix a bug where file snapshot functions like backup, checkpoint may attempt to copy a non-existing manifest file. #12882
-* Fix a bug where per kv checksum corruption may be ignored in MultiGet().
-* Fix a race condition in pessimistic transactions that could allow multiple transactions with the same name to be registered simultaneously, resulting in a crash or other unpredictable behavior.
-
-## 9.5.0 (07/19/2024)
-### Public API Changes
-* Introduced new C API function rocksdb_writebatch_iterate_cf for column family-aware iteration over the contents of a WriteBatch
-* Add support to ingest SST files generated by a DB instead of SstFileWriter. This can be enabled with experimental option `IngestExternalFileOptions::allow_db_generated_files`.
-
-### Behavior Changes
-* When calculating total log size for the `log_size_for_flush` argument in `CreateCheckpoint` API, the size of the archived log will not be included to avoid unnecessary flush
-
-### Bug Fixes
-* Fix a major bug in which an iterator using prefix filtering and SeekForPrev might miss data when the DB is using `whole_key_filtering=false` and `partition_filters=true`.
-* Fixed a bug where `OnErrorRecoveryBegin()` is not called before auto recovery starts.
-* Fixed a bug where event listener reads ErrorHandler's `bg_error_` member without holding db mutex(#12803).
-* Fixed a bug in handling MANIFEST write error that caused the latest valid MANIFEST file to get deleted, resulting in the DB being unopenable.
-* Fixed a race between error recovery due to manifest sync or write failure and external SST file ingestion. Both attempt to write a new manifest file, which causes an assertion failure.
-
-### Performance Improvements
-* Fix an issue where compactions were opening table files and reading table properties while holding db mutex_.
-* Reduce unnecessary filesystem queries and DB mutex acquires in creating backups and checkpoints.
 
 ## 9.4.0 (06/23/2024)
 ### New Features

Makefile

@@ -630,11 +630,6 @@ VALGRIND_VER := $(join $(VALGRIND_VER),valgrind)
 VALGRIND_OPTS = --error-exitcode=$(VALGRIND_ERROR) --leak-check=full
 # Not yet supported: --show-leak-kinds=definite,possible,reachable --errors-for-leak-kinds=definite,possible,reachable
 
-# Work around valgrind hanging on systems with limited internet access
-ifneq ($(shell which git 2>/dev/null && git config --get https.proxy),)
-  export DEBUGINFOD_URLS=
-endif
-
 TEST_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(TEST_LIB_SOURCES) $(MOCK_LIB_SOURCES)) $(GTEST)
 BENCH_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(BENCH_LIB_SOURCES))
 CACHE_BENCH_OBJECTS = $(patsubst %.cc, $(OBJ_DIR)/%.o, $(CACHE_BENCH_LIB_SOURCES))
@@ -1169,16 +1164,16 @@ ubsan_crash_test_with_best_efforts_recovery: clean
 	$(MAKE) clean
 
 full_valgrind_test:
-	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check
+	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
 full_valgrind_test_some:
-	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check_some
+	ROCKSDB_FULL_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check_some
 
 valgrind_test:
-	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check
+	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
 valgrind_test_some:
-	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 PORTABLE=1 $(MAKE) valgrind_check_some
+	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check_some
 
 valgrind_check: $(TESTS)
 	$(MAKE) DRIVER="$(VALGRIND_VER) $(VALGRIND_OPTS)" gen_parallel_tests
@@ -2144,8 +2139,8 @@ ZLIB_DOWNLOAD_BASE ?= http://zlib.net
 BZIP2_VER ?= 1.0.8
 BZIP2_SHA256 ?= ab5a03176ee106d3f0fa90e381da478ddae405918153cca248e682cd0c4a2269
 BZIP2_DOWNLOAD_BASE ?= http://sourceware.org/pub/bzip2
-SNAPPY_VER ?= 1.2.1
-SNAPPY_SHA256 ?= 736aeb64d86566d2236ddffa2865ee5d7a82d26c9016b36218fcc27ea4f09f86
+SNAPPY_VER ?= 1.1.8
+SNAPPY_SHA256 ?= 16b677f07832a612b0836178db7f374e414f94657c138e6993cbfc5dcc58651f
 SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/archive
 LZ4_VER ?= 1.9.4
 LZ4_SHA256 ?= 0b0e3aa07c8c063ddf40b082bdf7e37a1562bda40a0ff5272957f3e987e0e54b
@@ -2242,7 +2237,7 @@ libsnappy.a: snappy-$(SNAPPY_VER).tar.gz
 	-rm -rf snappy-$(SNAPPY_VER)
 	tar xvzf snappy-$(SNAPPY_VER).tar.gz
 	mkdir snappy-$(SNAPPY_VER)/build
-	cd snappy-$(SNAPPY_VER)/build && CFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CCFLAGS} ${EXTRA_CFLAGS}' CXXFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CXXFLAGS} ${EXTRA_CXXFLAGS}' LDFLAGS='${JAVA_STATIC_DEPS_LDFLAGS} ${EXTRA_LDFLAGS}' cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DSNAPPY_BUILD_BENCHMARKS=OFF -DSNAPPY_BUILD_TESTS=OFF --compile-no-warning-as-error ${PLATFORM_CMAKE_FLAGS} .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
+	cd snappy-$(SNAPPY_VER)/build && CFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CCFLAGS} ${EXTRA_CFLAGS}' CXXFLAGS='$(ARCHFLAG) ${JAVA_STATIC_DEPS_CXXFLAGS} ${EXTRA_CXXFLAGS}' LDFLAGS='${JAVA_STATIC_DEPS_LDFLAGS} ${EXTRA_LDFLAGS}' cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON ${PLATFORM_CMAKE_FLAGS} .. && $(MAKE) ${SNAPPY_MAKE_TARGET}
 	cp snappy-$(SNAPPY_VER)/build/libsnappy.a .
 
 lz4-$(LZ4_VER).tar.gz:
@@ -2489,11 +2484,13 @@ checkout_folly:
 	fi
 	@# Pin to a particular version for public CI, so that PR authors don't
 	@# need to worry about folly breaking our integration. Update periodically
-	cd third-party/folly && git reset --hard 03041f014b6e6ebb6119ffae8b7a37308f52e913
+	cd third-party/folly && git reset --hard 17054c85c2dee0e84cbee7ef28d7bae7d0b1630e
 	@# NOTE: this hack is required for clang in some cases
 	perl -pi -e 's/int rv = syscall/int rv = (int)syscall/' third-party/folly/folly/detail/Futex.cpp
 	@# NOTE: this hack is required for gcc in some cases
 	perl -pi -e 's/(__has_include.<experimental.memory_resource>.)/__cpp_rtti && $$1/' third-party/folly/folly/memory/MemoryResource.h
+	@# NOTE: this hack is only needed if building target build_folly in the future
+	perl -pi -e 's,https://github.com/jedisct1/libsodium/releases/download/1.0.17/libsodium-1.0.17.tar.gz,https://download.libsodium.org/libsodium/releases/old/unsupported/libsodium-1.0.17.tar.gz,' third-party/folly/build/fbcode_builder/manifests/libsodium
 	@# NOTE: boost source will be needed for any build including `USE_FOLLY_LITE` builds as those depend on boost headers
 	cd third-party/folly && $(PYTHON) build/fbcode_builder/getdeps.py fetch boost
 

TARGETS

@@ -362,9 +362,9 @@ cpp_library_wrapper(name="rocksdb_lib", srcs=[
         "//folly/experimental/coro:coroutine",
         "//folly/experimental/coro:task",
         "//folly/synchronization:distributed_mutex",
-    ], headers=glob(["**/*.h"]), link_whole=False, extra_test_libs=False)
+    ], headers=None, link_whole=False, extra_test_libs=False)
 
-cpp_library_wrapper(name="rocksdb_whole_archive_lib", srcs=[], deps=[":rocksdb_lib"], headers=[], link_whole=True, extra_test_libs=False)
+cpp_library_wrapper(name="rocksdb_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",
@@ -378,7 +378,7 @@ cpp_library_wrapper(name="rocksdb_test_lib", srcs=[
         "tools/trace_analyzer_tool.cc",
         "utilities/agg_merge/test_agg_merge.cc",
         "utilities/cassandra/test_utils.cc",
-    ], deps=[":rocksdb_lib"], headers=[], link_whole=False, extra_test_libs=True)
+    ], deps=[":rocksdb_lib"], headers=None, link_whole=False, extra_test_libs=True)
 
 cpp_library_wrapper(name="rocksdb_tools_lib", srcs=[
         "test_util/testutil.cc",
@@ -386,9 +386,9 @@ cpp_library_wrapper(name="rocksdb_tools_lib", srcs=[
         "tools/db_bench_tool.cc",
         "tools/simulated_hybrid_file_system.cc",
         "tools/trace_analyzer_tool.cc",
-    ], deps=[":rocksdb_lib"], headers=[], link_whole=False, extra_test_libs=False)
+    ], deps=[":rocksdb_lib"], headers=None, link_whole=False, extra_test_libs=False)
 
-cpp_library_wrapper(name="rocksdb_cache_bench_tools_lib", srcs=["cache/cache_bench_tool.cc"], deps=[":rocksdb_lib"], headers=[], link_whole=False, extra_test_libs=False)
+cpp_library_wrapper(name="rocksdb_cache_bench_tools_lib", srcs=["cache/cache_bench_tool.cc"], deps=[":rocksdb_lib"], headers=None, link_whole=False, extra_test_libs=False)
 
 rocks_cpp_library_wrapper(name="rocksdb_stress_lib", srcs=[
         "db_stress_tool/batched_ops_stress.cc",
@@ -410,15 +410,13 @@ rocks_cpp_library_wrapper(name="rocksdb_stress_lib", srcs=[
         "test_util/testutil.cc",
         "tools/block_cache_analyzer/block_cache_trace_analyzer.cc",
         "tools/trace_analyzer_tool.cc",
-    ], headers=[])
+    ], headers=None)
 
 
 cpp_binary_wrapper(name="ldb", srcs=["tools/ldb.cc"], deps=[":rocksdb_tools_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
 
 cpp_binary_wrapper(name="db_stress", srcs=["db_stress_tool/db_stress.cc"], deps=[":rocksdb_stress_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
 
-cpp_binary_wrapper(name="db_bench", srcs=["tools/db_bench.cc"], deps=[":rocksdb_tools_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
-
 cpp_binary_wrapper(name="cache_bench", srcs=["cache/cache_bench.cc"], deps=[":rocksdb_cache_bench_tools_lib"], extra_preprocessor_flags=[], extra_bench_libs=False)
 
 cpp_binary_wrapper(name="ribbon_bench", srcs=["microbench/ribbon_bench.cc"], deps=[], extra_preprocessor_flags=[], extra_bench_libs=True)
@@ -5026,7 +5024,7 @@ cpp_unittest_wrapper(name="dynamic_bloom_test",
             extra_compiler_flags=[])
 
 
-cpp_library_wrapper(name="env_basic_test_lib", srcs=["env/env_basic_test.cc"], deps=[":rocksdb_test_lib"], headers=[], link_whole=False, extra_test_libs=True)
+cpp_library_wrapper(name="env_basic_test_lib", srcs=["env/env_basic_test.cc"], deps=[":rocksdb_test_lib"], headers=None, link_whole=False, extra_test_libs=True)
 
 cpp_unittest_wrapper(name="env_basic_test",
             srcs=["env/env_basic_test.cc"],

buckifier/buckify_rocksdb.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 try:
     from builtins import str
@@ -10,7 +11,7 @@ import json
 import os
 import sys
 
-from targets_builder import TARGETSBuilder, LiteralValue
+from targets_builder import TARGETSBuilder
 
 from util import ColorString
 
@@ -131,7 +132,7 @@ def generate_targets(repo_path, deps_map):
     if len(sys.argv) >= 2:
         # Heuristically quote and canonicalize whitespace for inclusion
         # in how the file was generated.
-        extra_argv = " '{}'".format(" ".join(sys.argv[1].split()))
+        extra_argv = " '{0}'".format(" ".join(sys.argv[1].split()))
 
     TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path, extra_argv)
 
@@ -149,7 +150,6 @@ def generate_targets(repo_path, deps_map):
             "//folly/experimental/coro:task",
             "//folly/synchronization:distributed_mutex",
         ],
-        headers=LiteralValue("glob([\"**/*.h\"])")
     )
     # rocksdb_whole_archive_lib
     TARGETS.add_library(
@@ -158,6 +158,7 @@ def generate_targets(repo_path, deps_map):
         deps=[
             ":rocksdb_lib",
         ],
+        headers=None,
         extra_external_deps="",
         link_whole=True,
     )
@@ -200,10 +201,6 @@ def generate_targets(repo_path, deps_map):
     TARGETS.add_binary(
         "db_stress", ["db_stress_tool/db_stress.cc"], [":rocksdb_stress_lib"]
     )
-    # db_bench binary
-    TARGETS.add_binary(
-        "db_bench", ["tools/db_bench.cc"], [":rocksdb_tools_lib"]
-    )
     # cache_bench binary
     TARGETS.add_binary(
         "cache_bench", ["cache/cache_bench.cc"], [":rocksdb_cache_bench_tools_lib"]
@@ -212,7 +209,7 @@ def generate_targets(repo_path, deps_map):
     for src in src_mk.get("MICROBENCH_SOURCES", []):
         name = src.rsplit("/", 1)[1].split(".")[0] if "/" in src else src.split(".")[0]
         TARGETS.add_binary(name, [src], [], extra_bench_libs=True)
-    print(f"Extra dependencies:\n{json.dumps(deps_map)}")
+    print("Extra dependencies:\n{0}".format(json.dumps(deps_map)))
 
     # Dictionary test executable name -> relative source file path
     test_source_map = {}

buckifier/targets_builder.py

@@ -1,4 +1,5 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 try:
     from builtins import object, str
@@ -8,28 +9,17 @@ import pprint
 
 import targets_cfg
 
-class LiteralValue:
-    def __init__(self, value):
-        self.value = value
-
-    def __str__(self):
-        return str(self.value)
-
-def smart_quote_value(val):
-    if isinstance(val, LiteralValue):
-        return str(val)
-    return '"%s"' % val
 
 def pretty_list(lst, indent=8):
     if lst is None or len(lst) == 0:
         return ""
 
     if len(lst) == 1:
-        return smart_quote_value(lst[0])
+        return '"%s"' % lst[0]
 
-    separator = ',\n%s' % (" " * indent)
-    res = separator.join(sorted(map(smart_quote_value, lst)))
-    res = "\n" + (" " * indent) + res + ',\n' + (" " * (indent - 4))
+    separator = '",\n%s"' % (" " * indent)
+    res = separator.join(sorted(lst))
+    res = "\n" + (" " * indent) + '"' + res + '",\n' + (" " * (indent - 4))
     return res
 
 
@@ -58,12 +48,7 @@ class TARGETSBuilder:
         extra_test_libs=False,
     ):
         if headers is not None:
-            if isinstance(headers, LiteralValue):
-                headers = str(headers)
-            else:
-                headers = "[" + pretty_list(headers) + "]"
-        else:
-            headers = "[]"
+            headers = "[" + pretty_list(headers) + "]"
         with open(self.path, "ab") as targets_file:
             targets_file.write(
                 targets_cfg.library_template.format(
@@ -80,7 +65,8 @@ class TARGETSBuilder:
         self.total_lib = self.total_lib + 1
 
     def add_rocksdb_library(self, name, srcs, headers=None, external_dependencies=None):
-        headers = "[" + pretty_list(headers) + "]"
+        if headers is not None:
+            headers = "[" + pretty_list(headers) + "]"
         with open(self.path, "ab") as targets_file:
             targets_file.write(
                 targets_cfg.rocksdb_library_template.format(

buckifier/targets_cfg.py

@@ -1,4 +1,5 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 rocksdb_target_header_template = """# This file \100generated by:
 #$ python3 buckifier/buckify_rocksdb.py{extra_argv}

buckifier/util.py

@@ -2,6 +2,7 @@
 """
 This module keeps commonly used components.
 """
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 try:
     from builtins import object

build_tools/amalgamate.py

@@ -25,6 +25,7 @@
 #
 # The solution is to move the include out of the #ifdef.
 
+from __future__ import print_function
 
 import argparse
 import re
@@ -61,7 +62,7 @@ def expand_include(
 
     included.add(include_path)
     with open(include_path) as f:
-        print(f'#line 1 "{include_path}"', file=source_out)
+        print('#line 1 "{}"'.format(include_path), file=source_out)
         process_file(
             f, include_path, source_out, header_out, include_paths, public_include_paths
         )
@@ -117,7 +118,7 @@ def process_file(
                     )
 
             if expanded:
-                print(f'#line {line + 1} "{abs_path}"', file=source_out)
+                print('#line {} "{}"'.format(line + 1, abs_path), file=source_out)
         elif text != "#pragma once\n":
             source_out.write(text)
 
@@ -156,8 +157,8 @@ def main():
     with open(filename) as f, open(args.source_out, "w") as source_out, open(
         args.header_out, "w"
     ) as header_out:
-        print(f'#line 1 "{filename}"', file=source_out)
-        print(f'#include "{header_out.name}"', file=source_out)
+        print('#line 1 "{}"'.format(filename), file=source_out)
+        print('#include "{}"'.format(header_out.name), file=source_out)
         process_file(
             f, abs_path, source_out, header_out, include_paths, public_include_paths
         )

build_tools/benchmark_log_tool.py

@@ -102,7 +102,7 @@ class BenchmarkUtils:
 
 
 class ResultParser:
-    def __init__(self, field=r"(\w|[+-:.%])+", intrafield=r"(\s)+", separator="\t"):
+    def __init__(self, field="(\w|[+-:.%])+", intrafield="(\s)+", separator="\t"):
         self.field = re.compile(field)
         self.intra = re.compile(intrafield)
         self.sep = re.compile(separator)
@@ -159,7 +159,7 @@ class ResultParser:
 
 
 def load_report_from_tsv(filename: str):
-    file = open(filename)
+    file = open(filename, "r")
     contents = file.readlines()
     file.close()
     parser = ResultParser()

build_tools/error_filter.py

@@ -9,6 +9,7 @@
     - Prints those error messages to stdout
 """
 
+from __future__ import absolute_import, division, print_function, unicode_literals
 
 import re
 import sys
@@ -42,7 +43,7 @@ class GTestErrorParser(ErrorParserBase):
             return None
         gtest_fail_match = self._GTEST_FAIL_PATTERN.match(line)
         if gtest_fail_match:
-            return "{} failed: {}".format(self._last_gtest_name, gtest_fail_match.group(1))
+            return "%s failed: %s" % (self._last_gtest_name, gtest_fail_match.group(1))
         return None
 
 
@@ -65,52 +66,52 @@ class CompilerErrorParser(MatchErrorParser):
         # format (link error):
         #   '<filename>:<line #>: error: <error msg>'
         # The below regex catches both
-        super().__init__(r"\S+:\d+: error:")
+        super(CompilerErrorParser, self).__init__(r"\S+:\d+: error:")
 
 
 class ScanBuildErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"scan-build: \d+ bugs found.$")
+        super(ScanBuildErrorParser, self).__init__(r"scan-build: \d+ bugs found.$")
 
 
 class DbCrashErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"\*\*\*.*\^$|TEST FAILED.")
+        super(DbCrashErrorParser, self).__init__(r"\*\*\*.*\^$|TEST FAILED.")
 
 
 class WriteStressErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(
+        super(WriteStressErrorParser, self).__init__(
             r"ERROR: write_stress died with exitcode=\d+"
         )
 
 
 class AsanErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"==\d+==ERROR: AddressSanitizer:")
+        super(AsanErrorParser, self).__init__(r"==\d+==ERROR: AddressSanitizer:")
 
 
 class UbsanErrorParser(MatchErrorParser):
     def __init__(self):
         # format: '<filename>:<line #>:<column #>: runtime error: <error msg>'
-        super().__init__(r"\S+:\d+:\d+: runtime error:")
+        super(UbsanErrorParser, self).__init__(r"\S+:\d+:\d+: runtime error:")
 
 
 class ValgrindErrorParser(MatchErrorParser):
     def __init__(self):
         # just grab the summary, valgrind doesn't clearly distinguish errors
         # from other log messages.
-        super().__init__(r"==\d+== ERROR SUMMARY:")
+        super(ValgrindErrorParser, self).__init__(r"==\d+== ERROR SUMMARY:")
 
 
 class CompatErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"==== .*[Ee]rror.* ====$")
+        super(CompatErrorParser, self).__init__(r"==== .*[Ee]rror.* ====$")
 
 
 class TsanErrorParser(MatchErrorParser):
     def __init__(self):
-        super().__init__(r"WARNING: ThreadSanitizer:")
+        super(TsanErrorParser, self).__init__(r"WARNING: ThreadSanitizer:")
 
 
 _TEST_NAME_TO_PARSERS = {

cache/cache.cc

@@ -133,25 +133,19 @@ Status Cache::CreateFromString(const ConfigOptions& config_options,
                                std::shared_ptr<Cache>* result) {
   Status status;
   std::shared_ptr<Cache> cache;
-  if (StartsWith(value, "null")) {
-    cache = nullptr;
-  } else if (value.find("://") == std::string::npos) {
-    if (value.find('=') == std::string::npos) {
-      cache = NewLRUCache(ParseSizeT(value));
-    } else {
-      LRUCacheOptions cache_opts;
-      status = OptionTypeInfo::ParseStruct(config_options, "",
-                                           &lru_cache_options_type_info, "",
-                                           value, &cache_opts);
-      if (status.ok()) {
-        cache = NewLRUCache(cache_opts);
-      }
-    }
-    if (status.ok()) {
-      result->swap(cache);
-    }
+  if (value.find('=') == std::string::npos) {
+    cache = NewLRUCache(ParseSizeT(value));
   } else {
-    status = LoadSharedObject<Cache>(config_options, value, result);
+    LRUCacheOptions cache_opts;
+    status = OptionTypeInfo::ParseStruct(config_options, "",
+                                         &lru_cache_options_type_info, "",
+                                         value, &cache_opts);
+    if (status.ok()) {
+      cache = NewLRUCache(cache_opts);
+    }
+  }
+  if (status.ok()) {
+    result->swap(cache);
   }
   return status;
 }

cache/cache_test.cc

@@ -886,32 +886,6 @@ TEST_P(CacheTest, ApplyToAllEntriesDuringResize) {
   ASSERT_EQ(special_count, kSpecialCount);
 }
 
-TEST_P(CacheTest, ApplyToHandleTest) {
-  std::string callback_state;
-  const auto callback = [&](const Slice& key, Cache::ObjectPtr value,
-                            size_t charge,
-                            const Cache::CacheItemHelper* helper) {
-    callback_state = std::to_string(DecodeKey(key)) + "," +
-                     std::to_string(DecodeValue(value)) + "," +
-                     std::to_string(charge);
-    assert(helper == &CacheTest::kHelper);
-  };
-
-  std::vector<std::string> inserted;
-
-  for (int i = 0; i < 10; ++i) {
-    Insert(i, i * 2, i + 1);
-    inserted.push_back(std::to_string(i) + "," + std::to_string(i * 2) + "," +
-                       std::to_string(i + 1));
-  }
-  for (int i = 0; i < 10; ++i) {
-    Cache::Handle* handle = cache_->Lookup(EncodeKey(i));
-    cache_->ApplyToHandle(cache_.get(), handle, callback);
-    EXPECT_EQ(inserted[i], callback_state);
-    cache_->Release(handle);
-  }
-}
-
 TEST_P(CacheTest, DefaultShardBits) {
   // Prevent excessive allocation (to save time & space)
   estimated_value_size_ = 100000;

cache/clock_cache.cc

@@ -1444,22 +1444,6 @@ const Cache::CacheItemHelper* BaseHyperClockCache<Table>::GetCacheItemHelper(
   return h->helper;
 }
 
-template <class Table>
-void BaseHyperClockCache<Table>::ApplyToHandle(
-    Cache* cache, Handle* handle,
-    const std::function<void(const Slice& key, Cache::ObjectPtr value,
-                             size_t charge, const CacheItemHelper* helper)>&
-        callback) {
-  BaseHyperClockCache<Table>* cache_ptr =
-      static_cast<BaseHyperClockCache<Table>*>(cache);
-  auto h = static_cast<const typename Table::HandleImpl*>(handle);
-  UniqueId64x2 unhashed;
-  auto hash_seed = cache_ptr->GetShard(h->GetHash()).GetTable().GetHashSeed();
-  callback(
-      ClockCacheShard<Table>::ReverseHash(h->hashed_key, &unhashed, hash_seed),
-      h->value, h->GetTotalCharge(), h->helper);
-}
-
 namespace {
 
 // For each cache shard, estimate what the table load factor would be if

cache/clock_cache.h

@@ -1128,12 +1128,6 @@ class BaseHyperClockCache : public ShardedCache<ClockCacheShard<Table>> {
 
   const CacheItemHelper* GetCacheItemHelper(Handle* handle) const override;
 
-  void ApplyToHandle(
-      Cache* cache, Handle* handle,
-      const std::function<void(const Slice& key, Cache::ObjectPtr obj,
-                               size_t charge, const CacheItemHelper* helper)>&
-          callback) override;
-
   void ReportProblems(
       const std::shared_ptr<Logger>& /*info_log*/) const override;
 };

cache/compressed_secondary_cache.cc

@@ -79,11 +79,7 @@ std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
     data_ptr = GetVarint32Ptr(data_ptr, data_ptr + 1,
                               static_cast<uint32_t*>(&source_32));
     source = static_cast<CacheTier>(source_32);
-    uint64_t data_size = 0;
-    data_ptr = GetVarint64Ptr(data_ptr, ptr->get() + handle_value_charge,
-                              static_cast<uint64_t*>(&data_size));
-    assert(handle_value_charge > data_size);
-    handle_value_charge = data_size;
+    handle_value_charge -= (data_ptr - ptr->get());
   }
   MemoryAllocator* allocator = cache_options_.memory_allocator.get();
 
@@ -173,15 +169,13 @@ Status CompressedSecondaryCache::InsertInternal(
   }
 
   auto internal_helper = GetHelper(cache_options_.enable_custom_split_merge);
-  char header[20];
+  char header[10];
   char* payload = header;
   payload = EncodeVarint32(payload, static_cast<uint32_t>(type));
   payload = EncodeVarint32(payload, static_cast<uint32_t>(source));
-  size_t data_size = (*helper->size_cb)(value);
-  char* data_size_ptr = payload;
-  payload = EncodeVarint64(payload, data_size);
 
   size_t header_size = payload - header;
+  size_t data_size = (*helper->size_cb)(value);
   size_t total_size = data_size + header_size;
   CacheAllocationPtr ptr =
       AllocateBlock(total_size, cache_options_.memory_allocator.get());
@@ -216,8 +210,6 @@ Status CompressedSecondaryCache::InsertInternal(
 
     val = Slice(compressed_val);
     data_size = compressed_val.size();
-    payload = EncodeVarint64(data_size_ptr, data_size);
-    header_size = payload - header;
     total_size = header_size + data_size;
     PERF_COUNTER_ADD(compressed_sec_cache_compressed_bytes, data_size);
 
@@ -230,21 +222,14 @@ Status CompressedSecondaryCache::InsertInternal(
 
   PERF_COUNTER_ADD(compressed_sec_cache_insert_real_count, 1);
   if (cache_options_.enable_custom_split_merge) {
-    size_t split_charge{0};
-    CacheValueChunk* value_chunks_head = SplitValueIntoChunks(
-        val, cache_options_.compression_type, split_charge);
-    return cache_->Insert(key, value_chunks_head, internal_helper,
-                          split_charge);
+    size_t charge{0};
+    CacheValueChunk* value_chunks_head =
+        SplitValueIntoChunks(val, cache_options_.compression_type, charge);
+    return cache_->Insert(key, value_chunks_head, internal_helper, charge);
   } else {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-    size_t charge = malloc_usable_size(ptr.get());
-#else
-    size_t charge = total_size;
-#endif
     std::memcpy(ptr.get(), header, header_size);
     CacheAllocationPtr* buf = new CacheAllocationPtr(std::move(ptr));
-    charge += sizeof(CacheAllocationPtr);
-    return cache_->Insert(key, buf, internal_helper, charge);
+    return cache_->Insert(key, buf, internal_helper, total_size);
   }
 }
 
@@ -413,21 +398,6 @@ const Cache::CacheItemHelper* CompressedSecondaryCache::GetHelper(
   }
 }
 
-size_t CompressedSecondaryCache::TEST_GetCharge(const Slice& key) {
-  Cache::Handle* lru_handle = cache_->Lookup(key);
-  if (lru_handle == nullptr) {
-    return 0;
-  }
-
-  size_t charge = cache_->GetCharge(lru_handle);
-  if (cache_->Value(lru_handle) != nullptr &&
-      !cache_options_.enable_custom_split_merge) {
-    charge -= 10;
-  }
-  cache_->Release(lru_handle, /*erase_if_last_ref=*/false);
-  return charge;
-}
-
 std::shared_ptr<SecondaryCache>
 CompressedSecondaryCacheOptions::MakeSharedSecondaryCache() const {
   return std::make_shared<CompressedSecondaryCache>(*this);

cache/compressed_secondary_cache.h

@@ -139,8 +139,6 @@ class CompressedSecondaryCache : public SecondaryCache {
                         const Cache::CacheItemHelper* helper,
                         CompressionType type, CacheTier source);
 
-  size_t TEST_GetCharge(const Slice& key);
-
   // TODO: clean up to use cleaner interfaces in typed_cache.h
   const Cache::CacheItemHelper* GetHelper(bool enable_custom_split_merge) const;
   std::shared_ptr<Cache> cache_;

cache/compressed_secondary_cache_test.cc

@@ -39,8 +39,6 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
  protected:
   void BasicTestHelper(std::shared_ptr<SecondaryCache> sec_cache,
                        bool sec_cache_is_compressed) {
-    CompressedSecondaryCache* comp_sec_cache =
-        static_cast<CompressedSecondaryCache*>(sec_cache.get());
     get_perf_context()->Reset();
     bool kept_in_sec_cache{true};
     // Lookup an non-existent key.
@@ -68,8 +66,6 @@ class CompressedSecondaryCacheTestBase : public testing::Test,
     ASSERT_OK(sec_cache->Insert(key1, &item1, GetHelper(), false));
     ASSERT_EQ(get_perf_context()->compressed_sec_cache_insert_real_count, 1);
 
-    ASSERT_GT(comp_sec_cache->TEST_GetCharge(key1), 1000);
-
     std::unique_ptr<SecondaryCacheResultHandle> handle1_2 =
         sec_cache->Lookup(key1, GetHelper(), this, true, /*advise_erase=*/true,
                           /*stats=*/nullptr, kept_in_sec_cache);

cache/lru_cache.cc

@@ -677,17 +677,6 @@ const Cache::CacheItemHelper* LRUCache::GetCacheItemHelper(
   return h->helper;
 }
 
-void LRUCache::ApplyToHandle(
-    Cache* cache, Handle* handle,
-    const std::function<void(const Slice& key, ObjectPtr value, size_t charge,
-                             const CacheItemHelper* helper)>& callback) {
-  auto cache_ptr = static_cast<LRUCache*>(cache);
-  auto h = static_cast<const LRUHandle*>(handle);
-  callback(h->key(), h->value,
-           h->GetCharge(cache_ptr->GetShard(0).metadata_charge_policy_),
-           h->helper);
-}
-
 size_t LRUCache::TEST_GetLRUSize() {
   return SumOverShards([](LRUCacheShard& cs) { return cs.TEST_GetLRUSize(); });
 }

cache/lru_cache.h

@@ -452,12 +452,6 @@ class LRUCache
   size_t GetCharge(Handle* handle) const override;
   const CacheItemHelper* GetCacheItemHelper(Handle* handle) const override;
 
-  void ApplyToHandle(
-      Cache* cache, Handle* handle,
-      const std::function<void(const Slice& key, ObjectPtr obj, size_t charge,
-                               const CacheItemHelper* helper)>& callback)
-      override;
-
   // Retrieves number of elements in LRU, for unit test purpose only.
   size_t TEST_GetLRUSize();
   // Retrieves high pri pool ratio.

cache/secondary_cache_adapter.cc

@@ -271,8 +271,7 @@ Status CacheWithSecondaryAdapter::Insert(const Slice& key, ObjectPtr value,
   // Warm up the secondary cache with the compressed block. The secondary
   // cache may choose to ignore it based on the admission policy.
   if (value != nullptr && !compressed_value.empty() &&
-      adm_policy_ == TieredAdmissionPolicy::kAdmPolicyThreeQueue &&
-      helper->IsSecondaryCacheCompatible()) {
+      adm_policy_ == TieredAdmissionPolicy::kAdmPolicyThreeQueue) {
     Status status = secondary_cache_->InsertSaved(key, compressed_value, type);
     assert(status.ok() || status.IsNotSupported());
   }

cache/tiered_secondary_cache_test.cc

@@ -253,7 +253,6 @@ TEST_F(DBTieredSecondaryCacheTest, BasicTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   // Disable paranoid_file_checks so that flush will not read back the newly
@@ -365,7 +364,6 @@ TEST_F(DBTieredSecondaryCacheTest, BasicMultiGetTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   options.paranoid_file_checks = false;
@@ -508,7 +506,6 @@ TEST_F(DBTieredSecondaryCacheTest, WaitAllTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   options.paranoid_file_checks = false;
@@ -609,7 +606,6 @@ TEST_F(DBTieredSecondaryCacheTest, ReadyBeforeWaitAllTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   options.statistics = CreateDBStatistics();
 
@@ -721,7 +717,6 @@ TEST_F(DBTieredSecondaryCacheTest, IterateTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   options.paranoid_file_checks = false;
@@ -765,54 +760,6 @@ TEST_F(DBTieredSecondaryCacheTest, IterateTest) {
   Destroy(options);
 }
 
-TEST_F(DBTieredSecondaryCacheTest, VolatileTierTest) {
-  if (!LZ4_Supported()) {
-    ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-    return;
-  }
-
-  BlockBasedTableOptions table_options;
-  // We want a block cache of size 5KB, and a compressed secondary cache of
-  // size 5KB. However, we specify a block cache size of 256KB here in order
-  // to take into account the cache reservation in the block cache on
-  // behalf of the compressed cache. The unit of cache reservation is 256KB.
-  // The effective block cache capacity will be calculated as 256 + 5 = 261KB,
-  // and 256KB will be reserved for the compressed cache, leaving 5KB for
-  // the primary block cache. We only have to worry about this here because
-  // the cache size is so small.
-  table_options.block_cache = NewCache(256 * 1024, 5 * 1024, 256 * 1024);
-  table_options.block_size = 4 * 1024;
-  table_options.cache_index_and_filter_blocks = false;
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.compression = kLZ4Compression;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-
-  // Disable paranoid_file_checks so that flush will not read back the newly
-  // written file
-  options.paranoid_file_checks = false;
-  options.lowest_used_cache_tier = CacheTier::kVolatileTier;
-  DestroyAndReopen(options);
-  Random rnd(301);
-  const int N = 256;
-  for (int i = 0; i < N; i++) {
-    std::string p_v;
-    test::CompressibleString(&rnd, 0.5, 1007, &p_v);
-    ASSERT_OK(Put(Key(i), p_v));
-  }
-
-  ASSERT_OK(Flush());
-
-  // Since lowest_used_cache_tier is the volatile tier, nothing should be
-  // inserted in the secondary cache.
-  std::string v = Get(Key(0));
-  ASSERT_EQ(1007, v.size());
-  ASSERT_EQ(nvm_sec_cache()->num_insert_saved(), 0u);
-  ASSERT_EQ(nvm_sec_cache()->num_misses(), 0u);
-
-  Destroy(options);
-}
-
 class DBTieredAdmPolicyTest
     : public DBTieredSecondaryCacheTest,
       public testing::WithParamInterface<TieredAdmissionPolicy> {};
@@ -837,7 +784,6 @@ TEST_P(DBTieredAdmPolicyTest, CompressedOnlyTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   size_t comp_cache_usage = compressed_secondary_cache()->TEST_GetUsage();
@@ -890,7 +836,6 @@ TEST_P(DBTieredAdmPolicyTest, CompressedCacheAdmission) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
   size_t comp_cache_usage = compressed_secondary_cache()->TEST_GetUsage();
@@ -992,7 +937,6 @@ TEST_F(DBTieredSecondaryCacheTest, FSBufferTest) {
   table_options.cache_index_and_filter_blocks = false;
   Options options = GetDefaultOptions();
   options.create_if_missing = true;
-  options.compression = kLZ4Compression;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   options.statistics = CreateDBStatistics();
   options.env = wrap_env.get();

coverage/parse_gcov_output.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
+from __future__ import print_function
 
 import optparse
 import re
@@ -108,11 +109,11 @@ def report_coverage():
 
     # Check if we need to display coverage info for interested files.
     if len(interested_files):
-        per_file_coverage = {
-            fname: per_file_coverage[fname]
+        per_file_coverage = dict(
+            (fname, per_file_coverage[fname])
             for fname in interested_files
             if fname in per_file_coverage
-        }
+        )
         # If we only interested in several files, it makes no sense to report
         # the total_coverage
         total_coverage = None

db/arena_wrapped_db_iter.cc

@@ -45,23 +45,20 @@ void ArenaWrappedDBIter::Init(
     const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iteration,
     uint64_t version_number, ReadCallback* read_callback,
     ColumnFamilyHandleImpl* cfh, bool expose_blob_index, bool allow_refresh) {
+  auto mem = arena_.AllocateAligned(sizeof(DBIter));
+  db_iter_ = new (mem) DBIter(
+      env, read_options, ioptions, mutable_cf_options, ioptions.user_comparator,
+      /* iter */ nullptr, version, sequence, true,
+      max_sequential_skip_in_iteration, read_callback, cfh, expose_blob_index);
+  sv_number_ = version_number;
   read_options_ = read_options;
+  allow_refresh_ = allow_refresh;
+  memtable_range_tombstone_iter_ = nullptr;
+
   if (!CheckFSFeatureSupport(env->GetFileSystem().get(),
                              FSSupportedOps::kAsyncIO)) {
     read_options_.async_io = false;
   }
-  read_options_.total_order_seek |= ioptions.prefix_seek_opt_in_only;
-
-  auto mem = arena_.AllocateAligned(sizeof(DBIter));
-  db_iter_ = new (mem) DBIter(env, read_options_, ioptions, mutable_cf_options,
-                              ioptions.user_comparator,
-                              /* iter */ nullptr, version, sequence, true,
-                              max_sequential_skip_in_iteration, read_callback,
-                              cfh, expose_blob_index);
-
-  sv_number_ = version_number;
-  allow_refresh_ = allow_refresh;
-  memtable_range_tombstone_iter_ = nullptr;
 }
 
 Status ArenaWrappedDBIter::Refresh() { return Refresh(nullptr); }
@@ -141,10 +138,10 @@ Status ArenaWrappedDBIter::Refresh(const Snapshot* snapshot) {
             reinit_internal_iter();
             break;
           } else {
-            *memtable_range_tombstone_iter_ =
-                std::make_unique<TruncatedRangeDelIterator>(
-                    std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
-                    &cfd->internal_comparator(), nullptr, nullptr);
+            delete *memtable_range_tombstone_iter_;
+            *memtable_range_tombstone_iter_ = new TruncatedRangeDelIterator(
+                std::unique_ptr<FragmentedRangeTombstoneIterator>(t),
+                &cfd->internal_comparator(), nullptr, nullptr);
           }
         }
         db_impl->ReturnAndCleanupSuperVersion(cfd, sv);

db/arena_wrapped_db_iter.h

@@ -55,8 +55,7 @@ class ArenaWrappedDBIter : public Iterator {
     db_iter_->SetIter(iter);
   }
 
-  void SetMemtableRangetombstoneIter(
-      std::unique_ptr<TruncatedRangeDelIterator>* iter) {
+  void SetMemtableRangetombstoneIter(TruncatedRangeDelIterator** iter) {
     memtable_range_tombstone_iter_ = iter;
   }
 
@@ -83,8 +82,6 @@ class ArenaWrappedDBIter : public Iterator {
   Status Refresh() override;
   Status Refresh(const Snapshot*) override;
 
-  bool PrepareValue() override { return db_iter_->PrepareValue(); }
-
   void Init(Env* env, const ReadOptions& read_options,
             const ImmutableOptions& ioptions,
             const MutableCFOptions& mutable_cf_options, const Version* version,
@@ -113,8 +110,7 @@ class ArenaWrappedDBIter : public Iterator {
   bool allow_refresh_ = true;
   // If this is nullptr, it means the mutable memtable does not contain range
   // tombstone when added under this DBIter.
-  std::unique_ptr<TruncatedRangeDelIterator>* memtable_range_tombstone_iter_ =
-      nullptr;
+  TruncatedRangeDelIterator** memtable_range_tombstone_iter_ = nullptr;
 };
 
 // Generate the arena wrapped iterator class.

db/attribute_group_iterator_impl.h

@@ -13,11 +13,14 @@ namespace ROCKSDB_NAMESPACE {
 class AttributeGroupIteratorImpl : public AttributeGroupIterator {
  public:
   AttributeGroupIteratorImpl(
-      const ReadOptions& read_options, const Comparator* comparator,
-      std::vector<std::pair<ColumnFamilyHandle*, std::unique_ptr<Iterator>>>&&
-          cfh_iter_pairs)
-      : impl_(read_options, comparator, std::move(cfh_iter_pairs),
-              ResetFunc(this), PopulateFunc(this)) {}
+      const Comparator* comparator,
+      const std::vector<ColumnFamilyHandle*>& column_families,
+      const std::vector<Iterator*>& child_iterators)
+      : impl_(
+            comparator, column_families, child_iterators, [this]() { Reset(); },
+            [this](const autovector<MultiCfIteratorInfo>& items) {
+              AddToAttributeGroups(items);
+            }) {}
   ~AttributeGroupIteratorImpl() override {}
 
   // No copy allowed
@@ -42,36 +45,8 @@ class AttributeGroupIteratorImpl : public AttributeGroupIterator {
 
   void Reset() { attribute_groups_.clear(); }
 
-  bool PrepareValue() override { return impl_.PrepareValue(); }
-
  private:
-  class ResetFunc {
-   public:
-    explicit ResetFunc(AttributeGroupIteratorImpl* iter) : iter_(iter) {}
-
-    void operator()() const {
-      assert(iter_);
-      iter_->Reset();
-    }
-
-   private:
-    AttributeGroupIteratorImpl* iter_;
-  };
-
-  class PopulateFunc {
-   public:
-    explicit PopulateFunc(AttributeGroupIteratorImpl* iter) : iter_(iter) {}
-
-    void operator()(const autovector<MultiCfIteratorInfo>& items) const {
-      assert(iter_);
-      iter_->AddToAttributeGroups(items);
-    }
-
-   private:
-    AttributeGroupIteratorImpl* iter_;
-  };
-
-  MultiCfIteratorImpl<ResetFunc, PopulateFunc> impl_;
+  MultiCfIteratorImpl impl_;
   IteratorAttributeGroups attribute_groups_;
   void AddToAttributeGroups(const autovector<MultiCfIteratorInfo>& items);
 };

db/blob/blob_file_cache.cc

@@ -42,7 +42,6 @@ Status BlobFileCache::GetBlobFileReader(
   assert(blob_file_reader);
   assert(blob_file_reader->IsEmpty());
 
-  // NOTE: sharing same Cache with table_cache
   const Slice key = GetSliceForKey(&blob_file_number);
 
   assert(cache_);
@@ -99,13 +98,4 @@ Status BlobFileCache::GetBlobFileReader(
   return Status::OK();
 }
 
-void BlobFileCache::Evict(uint64_t blob_file_number) {
-  // NOTE: sharing same Cache with table_cache
-  const Slice key = GetSliceForKey(&blob_file_number);
-
-  assert(cache_);
-
-  cache_.get()->Erase(key);
-}
-
 }  // namespace ROCKSDB_NAMESPACE

db/blob/blob_file_cache.h

@@ -36,15 +36,6 @@ class BlobFileCache {
                            uint64_t blob_file_number,
                            CacheHandleGuard<BlobFileReader>* blob_file_reader);
 
-  // Called when a blob file is obsolete to ensure it is removed from the cache
-  // to avoid effectively leaking the open file and assicated memory
-  void Evict(uint64_t blob_file_number);
-
-  // Used to identify cache entries for blob files (not normally useful)
-  static const Cache::CacheItemHelper* GetHelper() {
-    return CacheInterface::GetBasicHelper();
-  }
-
  private:
   using CacheInterface =
       BasicTypedCacheInterface<BlobFileReader, CacheEntryRole::kMisc>;

db/blob/blob_source.cc

@@ -20,24 +20,23 @@
 
 namespace ROCKSDB_NAMESPACE {
 
-BlobSource::BlobSource(const ImmutableOptions& immutable_options,
-                       const MutableCFOptions& mutable_cf_options,
+BlobSource::BlobSource(const ImmutableOptions* immutable_options,
                        const std::string& db_id,
                        const std::string& db_session_id,
                        BlobFileCache* blob_file_cache)
     : db_id_(db_id),
       db_session_id_(db_session_id),
-      statistics_(immutable_options.statistics.get()),
+      statistics_(immutable_options->statistics.get()),
       blob_file_cache_(blob_file_cache),
-      blob_cache_(immutable_options.blob_cache),
-      lowest_used_cache_tier_(immutable_options.lowest_used_cache_tier) {
+      blob_cache_(immutable_options->blob_cache),
+      lowest_used_cache_tier_(immutable_options->lowest_used_cache_tier) {
   auto bbto =
-      mutable_cf_options.table_factory->GetOptions<BlockBasedTableOptions>();
+      immutable_options->table_factory->GetOptions<BlockBasedTableOptions>();
   if (bbto &&
       bbto->cache_usage_options.options_overrides.at(CacheEntryRole::kBlobCache)
               .charged == CacheEntryRoleOptions::Decision::kEnabled) {
     blob_cache_ = SharedCacheInterface{std::make_shared<ChargedCache>(
-        immutable_options.blob_cache, bbto->block_cache)};
+        immutable_options->blob_cache, bbto->block_cache)};
   }
 }
 

db/blob/blob_source.h

@@ -21,7 +21,6 @@
 namespace ROCKSDB_NAMESPACE {
 
 struct ImmutableOptions;
-struct MutableCFOptions;
 class Status;
 class FilePrefetchBuffer;
 class Slice;
@@ -32,10 +31,7 @@ class Slice;
 // storage with minimal cost.
 class BlobSource {
  public:
-  // NOTE: db_id, db_session_id, and blob_file_cache are saved by reference or
-  // pointer.
-  BlobSource(const ImmutableOptions& immutable_options,
-             const MutableCFOptions& mutable_cf_options,
+  BlobSource(const ImmutableOptions* immutable_options,
              const std::string& db_id, const std::string& db_session_id,
              BlobFileCache* blob_file_cache);
 

db/blob/blob_source_test.cc

@@ -148,7 +148,6 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -194,8 +193,8 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -465,7 +464,6 @@ TEST_F(BlobSourceTest, GetCompressedBlobs) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -500,8 +498,8 @@ TEST_F(BlobSourceTest, GetCompressedBlobs) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, nullptr /*HistogramImpl*/, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -591,7 +589,6 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -647,8 +644,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -785,7 +782,6 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromCache) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -831,8 +827,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromCache) {
           backing_cache.get(), &immutable_options, &file_options,
           column_family_id, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ReadOptions read_options;
   read_options.verify_checksums = true;
@@ -1109,7 +1105,6 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr uint32_t column_family_id = 1;
   constexpr bool has_ttl = false;
@@ -1142,8 +1137,8 @@ TEST_F(BlobSecondaryCacheTest, GetBlobsFromSecondaryCache) {
       backing_cache.get(), &immutable_options, &file_options, column_family_id,
       blob_file_read_hist, nullptr /*IOTracer*/));
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   CacheHandleGuard<BlobFileReader> file_reader;
   ReadOptions read_options;
@@ -1410,7 +1405,6 @@ TEST_F(BlobSourceCacheReservationTest, SimpleCacheReservation) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
 
   constexpr ExpirationRange expiration_range;
 
@@ -1432,8 +1426,8 @@ TEST_F(BlobSourceCacheReservationTest, SimpleCacheReservation) {
           backing_cache.get(), &immutable_options, &file_options,
           kColumnFamilyId, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ConcurrentCacheReservationManager* cache_res_mgr =
       static_cast<ChargedCache*>(blob_source.GetBlobCache())
@@ -1525,8 +1519,6 @@ TEST_F(BlobSourceCacheReservationTest, IncreaseCacheReservation) {
   DestroyAndReopen(options_);
 
   ImmutableOptions immutable_options(options_);
-  MutableCFOptions mutable_cf_options(options_);
-
   constexpr size_t blob_size = 24 << 10;  // 24KB
   for (size_t i = 0; i < kNumBlobs; ++i) {
     blob_file_size_ -= blobs_[i].size();  // old blob size
@@ -1554,8 +1546,8 @@ TEST_F(BlobSourceCacheReservationTest, IncreaseCacheReservation) {
           backing_cache.get(), &immutable_options, &file_options,
           kColumnFamilyId, blob_file_read_hist, nullptr /*IOTracer*/);
 
-  BlobSource blob_source(immutable_options, mutable_cf_options, db_id_,
-                         db_session_id_, blob_file_cache.get());
+  BlobSource blob_source(&immutable_options, db_id_, db_session_id_,
+                         blob_file_cache.get());
 
   ConcurrentCacheReservationManager* cache_res_mgr =
       static_cast<ChargedCache*>(blob_source.GetBlobCache())

db/blob/db_blob_basic_test.cc

@@ -374,115 +374,6 @@ TEST_F(DBBlobBasicTest, IterateBlobsFromCachePinning) {
   }
 }
 
-TEST_F(DBBlobBasicTest, IterateBlobsAllowUnpreparedValue) {
-  Options options = GetDefaultOptions();
-  options.enable_blob_files = true;
-
-  Reopen(options);
-
-  constexpr size_t num_blobs = 5;
-  std::vector<std::string> keys;
-  std::vector<std::string> blobs;
-
-  for (size_t i = 0; i < num_blobs; ++i) {
-    keys.emplace_back("key" + std::to_string(i));
-    blobs.emplace_back("blob" + std::to_string(i));
-    ASSERT_OK(Put(keys[i], blobs[i]));
-  }
-
-  ASSERT_OK(Flush());
-
-  ReadOptions read_options;
-  read_options.allow_unprepared_value = true;
-
-  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-
-  {
-    size_t i = 0;
-
-    for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_EQ(iter->value(), blobs[i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-
-  {
-    size_t i = 0;
-
-    for (iter->SeekToLast(); iter->Valid(); iter->Prev()) {
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_EQ(iter->value(), blobs[num_blobs - 1 - i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-
-  {
-    size_t i = 1;
-
-    for (iter->Seek(keys[i]); iter->Valid(); iter->Next()) {
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[i]);
-      ASSERT_EQ(iter->value(), blobs[i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-
-  {
-    size_t i = 1;
-
-    for (iter->SeekForPrev(keys[num_blobs - 1 - i]); iter->Valid();
-         iter->Prev()) {
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_TRUE(iter->value().empty());
-      ASSERT_OK(iter->status());
-
-      ASSERT_TRUE(iter->PrepareValue());
-
-      ASSERT_EQ(iter->key(), keys[num_blobs - 1 - i]);
-      ASSERT_EQ(iter->value(), blobs[num_blobs - 1 - i]);
-      ASSERT_OK(iter->status());
-
-      ++i;
-    }
-
-    ASSERT_OK(iter->status());
-    ASSERT_EQ(i, num_blobs);
-  }
-}
-
 TEST_F(DBBlobBasicTest, MultiGetBlobs) {
   constexpr size_t min_blob_size = 6;
 
@@ -1764,46 +1655,6 @@ TEST_P(DBBlobBasicIOErrorTest, CompactionFilterReadBlob_IOError) {
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
-TEST_P(DBBlobBasicIOErrorTest, IterateBlobsAllowUnpreparedValue_IOError) {
-  Options options;
-  options.env = fault_injection_env_.get();
-  options.enable_blob_files = true;
-
-  Reopen(options);
-
-  constexpr char key[] = "key";
-  constexpr char blob_value[] = "blob_value";
-
-  ASSERT_OK(Put(key, blob_value));
-
-  ASSERT_OK(Flush());
-
-  SyncPoint::GetInstance()->SetCallBack(sync_point_, [this](void* /* arg */) {
-    fault_injection_env_->SetFilesystemActive(false,
-                                              Status::IOError(sync_point_));
-  });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ReadOptions read_options;
-  read_options.allow_unprepared_value = true;
-
-  std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-  iter->SeekToFirst();
-
-  ASSERT_TRUE(iter->Valid());
-  ASSERT_EQ(iter->key(), key);
-  ASSERT_TRUE(iter->value().empty());
-  ASSERT_OK(iter->status());
-
-  ASSERT_FALSE(iter->PrepareValue());
-
-  ASSERT_FALSE(iter->Valid());
-  ASSERT_TRUE(iter->status().IsIOError());
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 TEST_F(DBBlobBasicTest, WarmCacheWithBlobsDuringFlush) {
   Options options = GetDefaultOptions();
 

db/builder.cc

@@ -53,7 +53,7 @@ TableBuilder* NewTableBuilder(const TableBuilderOptions& tboptions,
   assert((tboptions.column_family_id ==
           TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
          tboptions.column_family_name.empty());
-  return tboptions.moptions.table_factory->NewTableBuilder(tboptions, file);
+  return tboptions.ioptions.table_factory->NewTableBuilder(tboptions, file);
 }
 
 Status BuildTable(
@@ -206,6 +206,10 @@ Status BuildTable(
         /*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 logical_strip_timestamp =
+        ts_sz > 0 && !ioptions.persist_user_defined_timestamps;
+
     SequenceNumber smallest_preferred_seqno = kMaxSequenceNumber;
     std::string key_after_flush_buf;
     std::string value_buf;
@@ -218,6 +222,16 @@ Status BuildTable(
       Slice key_after_flush = key_after_flush_buf;
       Slice value_after_flush = value;
 
+      // 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 (logical_strip_timestamp) {
+        key_after_flush_buf.clear();
+        ReplaceInternalKeyWithMinTimestamp(&key_after_flush_buf, key, ts_sz);
+        key_after_flush = key_after_flush_buf;
+      }
+
       if (ikey.type == kTypeValuePreferredSeqno) {
         auto [unpacked_value, unix_write_time] =
             ParsePackedValueWithWriteTime(value);
@@ -277,7 +291,11 @@ Status BuildTable(
       Slice last_tombstone_start_user_key{};
       for (range_del_it->SeekToFirst(); range_del_it->Valid();
            range_del_it->Next()) {
-        auto tombstone = range_del_it->Tombstone();
+        // When user timestamp should not be persisted, we logically strip a
+        // range tombstone's start and end key's timestamp (replace it with min
+        // timestamp) before passing them along to table builder and to update
+        // file boundaries.
+        auto tombstone = range_del_it->Tombstone(logical_strip_timestamp);
         std::pair<InternalKey, Slice> kv = tombstone.Serialize();
         builder->Add(kv.first.Encode(), kv.second);
         InternalKey tombstone_end = tombstone.SerializeEndKey();
@@ -420,7 +438,8 @@ Status BuildTable(
       // the goal is to cache it here for further user reads.
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
           tboptions.read_options, file_options, tboptions.internal_comparator,
-          *meta, nullptr /* range_del_agg */, mutable_cf_options, nullptr,
+          *meta, nullptr /* range_del_agg */,
+          mutable_cf_options.prefix_extractor, nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : internal_stats->GetFileReadHist(0),
           TableReaderCaller::kFlush, /*arena=*/nullptr,
@@ -428,7 +447,8 @@ 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

@@ -532,42 +532,6 @@ struct rocksdb_universal_compaction_options_t {
   ROCKSDB_NAMESPACE::CompactionOptionsUniversal* rep;
 };
 
-struct rocksdb_callback_logger_t : public Logger {
-  static const ssize_t STACK_BUFSZ = 512;
-  rocksdb_callback_logger_t(InfoLogLevel log_level,
-                            void (*logv_cb)(void*, unsigned, char*, size_t),
-                            void* priv)
-      : Logger(log_level), logv_cb_(logv_cb), priv_(priv) {}
-
-  using Logger::Logv;
-  void Logv(const InfoLogLevel level, const char* fmt, va_list ap0) override {
-    char stack_buf[STACK_BUFSZ];
-    char* alloc_buf = nullptr;
-    char* buf = stack_buf;
-    int len = 0;
-    va_list ap1;
-    if (!logv_cb_) return;
-    va_copy(ap1, ap0);
-    len = vsnprintf(buf, STACK_BUFSZ, fmt, ap0);
-    if (len <= 0)
-      goto cleanup;
-    else if (len >= STACK_BUFSZ) {
-      buf = alloc_buf = reinterpret_cast<char*>(malloc(len + 1));
-      if (!buf) goto cleanup;
-      len = vsnprintf(buf, len + 1, fmt, ap1);
-      if (len <= 0) goto cleanup;
-    }
-    logv_cb_(priv_, unsigned(level), buf, size_t(len));
-  cleanup:
-    va_end(ap1);
-    free(alloc_buf);
-  }
-
- private:
-  void (*logv_cb_)(void*, unsigned, char*, size_t) = nullptr;
-  void* priv_ = nullptr;
-};
-
 static bool SaveError(char** errptr, const Status& s) {
   assert(errptr != nullptr);
   if (s.ok()) {
@@ -1838,26 +1802,6 @@ void rocksdb_approximate_sizes_cf(
   delete[] ranges;
 }
 
-extern ROCKSDB_LIBRARY_API void rocksdb_approximate_sizes_cf_with_flags(
-    rocksdb_t* db, rocksdb_column_family_handle_t* column_family,
-    int num_ranges, const char* const* range_start_key,
-    const size_t* range_start_key_len, const char* const* range_limit_key,
-    const size_t* range_limit_key_len, uint8_t include_flags, uint64_t* sizes,
-    char** errptr) {
-  Range* ranges = new Range[num_ranges];
-  for (int i = 0; i < num_ranges; i++) {
-    ranges[i].start = Slice(range_start_key[i], range_start_key_len[i]);
-    ranges[i].limit = Slice(range_limit_key[i], range_limit_key_len[i]);
-  }
-  Status s = db->rep->GetApproximateSizes(
-      column_family->rep, ranges, num_ranges, sizes,
-      static_cast<DB::SizeApproximationFlags>(include_flags));
-  if (!s.ok()) {
-    SaveError(errptr, s);
-  }
-  delete[] ranges;
-}
-
 void rocksdb_delete_file(rocksdb_t* db, const char* name) {
   db->rep->DeleteFile(name);
 }
@@ -2286,32 +2230,6 @@ class H : public WriteBatch::Handler {
   }
 };
 
-class HCF : public WriteBatch::Handler {
- public:
-  void* state_;
-  void (*put_cf_)(void*, uint32_t cfid, const char* k, size_t klen,
-                  const char* v, size_t vlen);
-  void (*deleted_cf_)(void*, uint32_t cfid, const char* k, size_t klen);
-  void (*merge_cf_)(void*, uint32_t cfid, const char* k, size_t klen,
-                    const char* v, size_t vlen);
-  Status PutCF(uint32_t column_family_id, const Slice& key,
-               const Slice& value) override {
-    (*put_cf_)(state_, column_family_id, key.data(), key.size(), value.data(),
-               value.size());
-    return Status::OK();
-  }
-  Status DeleteCF(uint32_t column_family_id, const Slice& key) override {
-    (*deleted_cf_)(state_, column_family_id, key.data(), key.size());
-    return Status::OK();
-  }
-  Status MergeCF(uint32_t column_family_id, const Slice& key,
-                 const Slice& value) override {
-    (*merge_cf_)(state_, column_family_id, key.data(), key.size(), value.data(),
-                 value.size());
-    return Status::OK();
-  }
-};
-
 void rocksdb_writebatch_iterate(rocksdb_writebatch_t* b, void* state,
                                 void (*put)(void*, const char* k, size_t klen,
                                             const char* v, size_t vlen),
@@ -2324,21 +2242,6 @@ void rocksdb_writebatch_iterate(rocksdb_writebatch_t* b, void* state,
   b->rep.Iterate(&handler);
 }
 
-void rocksdb_writebatch_iterate_cf(
-    rocksdb_writebatch_t* b, void* state,
-    void (*put_cf)(void*, uint32_t cfid, const char* k, size_t klen,
-                   const char* v, size_t vlen),
-    void (*deleted_cf)(void*, uint32_t cfid, const char* k, size_t klen),
-    void (*merge_cf)(void*, uint32_t cfid, const char* k, size_t klen,
-                     const char* v, size_t vlen)) {
-  HCF handler;
-  handler.state_ = state;
-  handler.put_cf_ = put_cf;
-  handler.deleted_cf_ = deleted_cf;
-  handler.merge_cf_ = merge_cf;
-  b->rep.Iterate(&handler);
-}
-
 const char* rocksdb_writebatch_data(rocksdb_writebatch_t* b, size_t* size) {
   *size = b->rep.GetDataSize();
   return b->rep.Data().c_str();
@@ -3134,15 +3037,6 @@ rocksdb_logger_t* rocksdb_logger_create_stderr_logger(int log_level,
   return logger;
 }
 
-rocksdb_logger_t* rocksdb_logger_create_callback_logger(
-    int log_level, void (*callback)(void*, unsigned, char*, size_t),
-    void* priv) {
-  rocksdb_logger_t* logger = new rocksdb_logger_t;
-  logger->rep = std::make_shared<rocksdb_callback_logger_t>(
-      static_cast<InfoLogLevel>(log_level), callback, priv);
-  return logger;
-}
-
 void rocksdb_logger_destroy(rocksdb_logger_t* logger) { delete logger; }
 
 void rocksdb_options_set_env(rocksdb_options_t* opt, rocksdb_env_t* env) {
@@ -4075,15 +3969,6 @@ void rocksdb_options_set_write_dbid_to_manifest(
   opt->rep.write_dbid_to_manifest = write_dbid_to_manifest;
 }
 
-unsigned char rocksdb_options_get_write_identity_file(rocksdb_options_t* opt) {
-  return opt->rep.write_identity_file;
-}
-
-void rocksdb_options_set_write_identity_file(
-    rocksdb_options_t* opt, unsigned char write_identity_file) {
-  opt->rep.write_identity_file = write_identity_file;
-}
-
 unsigned char rocksdb_options_get_track_and_verify_wals_in_manifest(
     rocksdb_options_t* opt) {
   return opt->rep.track_and_verify_wals_in_manifest;

db/c_test.c

@@ -199,79 +199,6 @@ static void CheckDel(void* ptr, const char* k, size_t klen) {
   (*state)++;
 }
 
-// Callback from rocksdb_writebatch_iterate_cf()
-static void CheckPutCF(void* ptr, uint32_t cfid, const char* k, size_t klen,
-                       const char* v, size_t vlen) {
-  int* state = (int*)ptr;
-  switch (*state) {
-    case 0:
-      CheckEqual("bar", k, klen);
-      CheckEqual("b", v, vlen);
-      CheckCondition(cfid == 1);
-      break;
-    case 1:
-      CheckEqual("box", k, klen);
-      CheckEqual("c", v, vlen);
-      CheckCondition(cfid == 1);
-      break;
-    case 4:
-      CheckEqual("foo", k, klen);
-      CheckEqual("f", v, vlen);
-      CheckCondition(cfid == 0);
-      break;
-    case 6:
-      CheckEqual("baz", k, klen);
-      CheckEqual("a", v, vlen);
-      CheckCondition(cfid == 0);
-      break;
-    default:
-      CheckCondition(false);
-      break;
-  }
-  (*state)++;
-}
-
-// Callback from rocksdb_writebatch_iterate_cf()
-static void CheckDelCF(void* ptr, uint32_t cfid, const char* k, size_t klen) {
-  int* state = (int*)ptr;
-  switch (*state) {
-    case 2:
-      CheckEqual("bar", k, klen);
-      CheckCondition(cfid == 1);
-      break;
-    case 5:
-      CheckEqual("foo", k, klen);
-      CheckCondition(cfid == 0);
-      break;
-    default:
-      CheckCondition(false);
-      break;
-  }
-  (*state)++;
-}
-
-// Callback from rocksdb_writebatch_iterate_cf()
-static void CheckMergeCF(void* ptr, uint32_t cfid, const char* k, size_t klen,
-                         const char* v, size_t vlen) {
-  int* state = (int*)ptr;
-  switch (*state) {
-    case 3:
-      CheckEqual("box", k, klen);
-      CheckEqual("cc", v, vlen);
-      CheckCondition(cfid == 1);
-      break;
-    case 7:
-      CheckEqual("baz", k, klen);
-      CheckEqual("aa", v, vlen);
-      CheckCondition(cfid == 0);
-      break;
-    default:
-      CheckCondition(false);
-      break;
-  }
-  (*state)++;
-}
-
 static void CmpDestroy(void* arg) { (void)arg; }
 
 static int CmpCompare(void* arg, const char* a, size_t alen, const char* b,
@@ -772,8 +699,6 @@ int main(int argc, char** argv) {
   rocksdb_options_set_write_buffer_size(options, 100000);
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
-  /* Compatibility with how test was written */
-  rocksdb_options_set_write_dbid_to_manifest(options, 0);
 
   table_options = rocksdb_block_based_options_create();
   rocksdb_block_based_options_set_block_cache(table_options, cache);
@@ -964,24 +889,15 @@ int main(int argc, char** argv) {
     rocksdb_options_t* options_dbid_in_manifest = rocksdb_options_create();
     rocksdb_options_set_create_if_missing(options_dbid_in_manifest, 1);
 
-    rocksdb_options_set_write_dbid_to_manifest(options_dbid_in_manifest, false);
     unsigned char write_to_manifest =
         rocksdb_options_get_write_dbid_to_manifest(options_dbid_in_manifest);
     CheckCondition(!write_to_manifest);
     rocksdb_options_set_write_dbid_to_manifest(options_dbid_in_manifest, true);
+    CheckCondition(!write_to_manifest);
     write_to_manifest =
         rocksdb_options_get_write_dbid_to_manifest(options_dbid_in_manifest);
     CheckCondition(write_to_manifest);
 
-    rocksdb_options_set_write_identity_file(options_dbid_in_manifest, true);
-    unsigned char write_identity_file =
-        rocksdb_options_get_write_identity_file(options_dbid_in_manifest);
-    CheckCondition(write_identity_file);
-    rocksdb_options_set_write_identity_file(options_dbid_in_manifest, false);
-    write_identity_file =
-        rocksdb_options_get_write_identity_file(options_dbid_in_manifest);
-    CheckCondition(!write_identity_file);
-
     db = rocksdb_open(options_dbid_in_manifest, dbbackupname, &err);
     CheckNoError(err);
 
@@ -1772,21 +1688,6 @@ int main(int argc, char** argv) {
     CheckPinGetCF(db, roptions, handles[1], "bar", NULL);
     CheckPinGetCF(db, roptions, handles[1], "box", "c");
     CheckPinGetCF(db, roptions, handles[1], "buff", "rocksdb");
-    rocksdb_writebatch_clear(wb);
-    // Test WriteBatch iteration with Column Family
-    int pos = 0;
-    rocksdb_writebatch_put_cf(wb, handles[1], "bar", 3, "b", 1);
-    rocksdb_writebatch_put_cf(wb, handles[1], "box", 3, "c", 1);
-    rocksdb_writebatch_delete_cf(wb, handles[1], "bar", 3);
-    rocksdb_writebatch_merge_cf(wb, handles[1], "box", 3, "cc", 2);
-    rocksdb_writebatch_put(wb, "foo", 3, "f", 1);
-    rocksdb_writebatch_delete(wb, "foo", 3);
-    rocksdb_writebatch_put(wb, "baz", 3, "a", 1);
-    rocksdb_writebatch_merge(wb, "baz", 3, "aa", 2);
-    rocksdb_writebatch_iterate_cf(wb, &pos, CheckPutCF, CheckDelCF,
-                                  CheckMergeCF);
-    CheckCondition(pos == 8);
-    rocksdb_writebatch_clear(wb);
     rocksdb_writebatch_destroy(wb);
 
     rocksdb_flush_wal(db, 1, &err);

db/coalescing_iterator.h

@@ -12,12 +12,14 @@ namespace ROCKSDB_NAMESPACE {
 // EXPERIMENTAL
 class CoalescingIterator : public Iterator {
  public:
-  CoalescingIterator(
-      const ReadOptions& read_options, const Comparator* comparator,
-      std::vector<std::pair<ColumnFamilyHandle*, std::unique_ptr<Iterator>>>&&
-          cfh_iter_pairs)
-      : impl_(read_options, comparator, std::move(cfh_iter_pairs),
-              ResetFunc(this), PopulateFunc(this)) {}
+  CoalescingIterator(const Comparator* comparator,
+                     const std::vector<ColumnFamilyHandle*>& column_families,
+                     const std::vector<Iterator*>& child_iterators)
+      : impl_(
+            comparator, column_families, child_iterators, [this]() { Reset(); },
+            [this](const autovector<MultiCfIteratorInfo>& items) {
+              Coalesce(items);
+            }) {}
   ~CoalescingIterator() override {}
 
   // No copy allowed
@@ -48,36 +50,8 @@ class CoalescingIterator : public Iterator {
     wide_columns_.clear();
   }
 
-  bool PrepareValue() override { return impl_.PrepareValue(); }
-
  private:
-  class ResetFunc {
-   public:
-    explicit ResetFunc(CoalescingIterator* iter) : iter_(iter) {}
-
-    void operator()() const {
-      assert(iter_);
-      iter_->Reset();
-    }
-
-   private:
-    CoalescingIterator* iter_;
-  };
-
-  class PopulateFunc {
-   public:
-    explicit PopulateFunc(CoalescingIterator* iter) : iter_(iter) {}
-
-    void operator()(const autovector<MultiCfIteratorInfo>& items) const {
-      assert(iter_);
-      iter_->Coalesce(items);
-    }
-
-   private:
-    CoalescingIterator* iter_;
-  };
-
-  MultiCfIteratorImpl<ResetFunc, PopulateFunc> impl_;
+  MultiCfIteratorImpl impl_;
   Slice value_;
   WideColumns wide_columns_;
 

db/column_family.cc

@@ -595,8 +595,8 @@ ColumnFamilyData::ColumnFamilyData(
     blob_file_cache_.reset(
         new BlobFileCache(_table_cache, ioptions(), soptions(), id_,
                           internal_stats_->GetBlobFileReadHist(), io_tracer));
-    blob_source_.reset(new BlobSource(ioptions_, mutable_cf_options_, db_id,
-                                      db_session_id, blob_file_cache_.get()));
+    blob_source_.reset(new BlobSource(ioptions(), db_id, db_session_id,
+                                      blob_file_cache_.get()));
 
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
@@ -901,11 +901,7 @@ uint64_t GetPendingCompactionBytesForCompactionSpeedup(
     return slowdown_threshold;
   }
 
-  // Prevent a small CF from triggering parallel compactions for other CFs.
-  // Require compaction debt to be more than a full L0 to Lbase compaction.
-  const uint64_t kMinDebtSize = 2 * mutable_cf_options.max_bytes_for_level_base;
-  uint64_t size_threshold =
-      std::max(bottommost_files_size / kBottommostSizeDivisor, kMinDebtSize);
+  uint64_t size_threshold = bottommost_files_size / kBottommostSizeDivisor;
   return std::min(size_threshold, slowdown_threshold);
 }
 
@@ -1176,12 +1172,10 @@ bool ColumnFamilyData::NeedsCompaction() const {
 
 Compaction* ColumnFamilyData::PickCompaction(
     const MutableCFOptions& mutable_options,
-    const MutableDBOptions& mutable_db_options,
-    const std::vector<SequenceNumber>& existing_snapshots,
-    const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer) {
+    const MutableDBOptions& mutable_db_options, LogBuffer* log_buffer) {
   auto* result = compaction_picker_->PickCompaction(
-      GetName(), mutable_options, mutable_db_options, existing_snapshots,
-      snapshot_checker, current_->storage_info(), log_buffer);
+      GetName(), mutable_options, mutable_db_options, current_->storage_info(),
+      log_buffer);
   if (result != nullptr) {
     result->FinalizeInputInfo(current_);
   }
@@ -1207,10 +1201,8 @@ Status ColumnFamilyData::RangesOverlapWithMemtables(
   read_opts.total_order_seek = true;
   MergeIteratorBuilder merge_iter_builder(&internal_comparator_, &arena);
   merge_iter_builder.AddIterator(super_version->mem->NewIterator(
-      read_opts, /*seqno_to_time_mapping=*/nullptr, &arena,
-      /*prefix_extractor=*/nullptr));
+      read_opts, /*seqno_to_time_mapping=*/nullptr, &arena));
   super_version->imm->AddIterators(read_opts, /*seqno_to_time_mapping=*/nullptr,
-                                   /*prefix_extractor=*/nullptr,
                                    &merge_iter_builder,
                                    false /* add_range_tombstone_iter */);
   ScopedArenaPtr<InternalIterator> memtable_iter(merge_iter_builder.Finish());
@@ -1573,6 +1565,28 @@ Status ColumnFamilyData::SetOptions(
   return s;
 }
 
+// REQUIRES: DB mutex held
+Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
+  if (initial_cf_options_.compaction_style != kCompactionStyleLevel) {
+    return Env::WLTH_NOT_SET;
+  }
+  if (level == 0) {
+    return Env::WLTH_MEDIUM;
+  }
+  int base_level = current_->storage_info()->base_level();
+
+  // L1: medium, L2: long, ...
+  if (level - base_level >= 2) {
+    return Env::WLTH_EXTREME;
+  } else if (level < base_level) {
+    // There is no restriction which prevents level passed in to be smaller
+    // than base_level.
+    return Env::WLTH_MEDIUM;
+  }
+  return static_cast<Env::WriteLifeTimeHint>(
+      level - base_level + static_cast<int>(Env::WLTH_MEDIUM));
+}
+
 Status ColumnFamilyData::AddDirectories(
     std::map<std::string, std::shared_ptr<FSDirectory>>* created_dirs) {
   Status s;
@@ -1638,9 +1652,6 @@ bool ColumnFamilyData::ShouldPostponeFlushToRetainUDT(
   }
   for (const Slice& table_newest_udt :
        imm()->GetTablesNewestUDT(max_memtable_id)) {
-    if (table_newest_udt.empty()) {
-      continue;
-    }
     assert(table_newest_udt.size() == full_history_ts_low.size());
     // Checking the newest UDT contained in MemTable with ascending ID up to
     // `max_memtable_id`. Return immediately on finding the first MemTable that

db/column_family.h

@@ -16,7 +16,6 @@
 
 #include "cache/cache_reservation_manager.h"
 #include "db/memtable_list.h"
-#include "db/snapshot_checker.h"
 #include "db/table_cache.h"
 #include "db/table_properties_collector.h"
 #include "db/write_batch_internal.h"
@@ -386,9 +385,9 @@ class ColumnFamilyData {
   uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
   uint64_t GetLiveSstFilesSize() const;   // REQUIRE: DB mutex held
   uint64_t GetTotalBlobFileSize() const;  // REQUIRE: DB mutex held
-  // REQUIRE: DB mutex held
   void SetMemtable(MemTable* new_mem) {
-    new_mem->SetID(++last_memtable_id_);
+    uint64_t memtable_id = last_memtable_id_.fetch_add(1) + 1;
+    new_mem->SetID(memtable_id);
     mem_ = new_mem;
   }
 
@@ -402,18 +401,15 @@ class ColumnFamilyData {
                          SequenceNumber earliest_seq);
 
   TableCache* table_cache() const { return table_cache_.get(); }
-  BlobFileCache* blob_file_cache() const { return blob_file_cache_.get(); }
   BlobSource* blob_source() const { return blob_source_.get(); }
 
   // See documentation in compaction_picker.h
   // REQUIRES: DB mutex held
   bool NeedsCompaction() const;
   // REQUIRES: DB mutex held
-  Compaction* PickCompaction(
-      const MutableCFOptions& mutable_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& existing_snapshots,
-      const SnapshotChecker* snapshot_checker, LogBuffer* log_buffer);
+  Compaction* PickCompaction(const MutableCFOptions& mutable_options,
+                             const MutableDBOptions& mutable_db_options,
+                             LogBuffer* log_buffer);
 
   // Check if the passed range overlap with any running compactions.
   // REQUIRES: DB mutex held
@@ -515,6 +511,8 @@ class ColumnFamilyData {
     return initial_cf_options_;
   }
 
+  Env::WriteLifeTimeHint CalculateSSTWriteHint(int level);
+
   // created_dirs remembers directory created, so that we don't need to call
   // the same data creation operation again.
   Status AddDirectories(
@@ -673,7 +671,7 @@ class ColumnFamilyData {
   bool allow_2pc_;
 
   // Memtable id to track flush.
-  uint64_t last_memtable_id_;
+  std::atomic<uint64_t> last_memtable_id_;
 
   // Directories corresponding to cf_paths.
   std::vector<std::shared_ptr<FSDirectory>> data_dirs_;

db/column_family_test.cc

@@ -3012,25 +3012,19 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupForCompactionDebt) {
   ASSERT_OK(db_->Flush(FlushOptions()));
 
   {
+    // 1MB debt is way bigger than bottommost data so definitely triggers
+    // speedup.
     VersionStorageInfo* vstorage = cfd->current()->storage_info();
+    vstorage->TEST_set_estimated_compaction_needed_bytes(1048576 /* 1MB */,
+                                                         dbmu);
+    RecalculateWriteStallConditions(cfd, mutable_cf_options);
+    ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
+
     // Eight bytes is way smaller than bottommost data so definitely does not
     // trigger speedup.
     vstorage->TEST_set_estimated_compaction_needed_bytes(8, dbmu);
     RecalculateWriteStallConditions(cfd, mutable_cf_options);
     ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-
-    // 1MB is much larger than bottommost level size. However, since it's too
-    // small in terms of absolute size, it does not trigger parallel compaction
-    // in this case (see GetPendingCompactionBytesForCompactionSpeedup()).
-    vstorage->TEST_set_estimated_compaction_needed_bytes(1048576 /* 1MB */,
-                                                         dbmu);
-    RecalculateWriteStallConditions(cfd, mutable_cf_options);
-    ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-
-    vstorage->TEST_set_estimated_compaction_needed_bytes(
-        2 * mutable_cf_options.max_bytes_for_level_base, dbmu);
-    RecalculateWriteStallConditions(cfd, mutable_cf_options);
-    ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
   }
 }
 
@@ -3073,20 +3067,12 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupForMarkedFiles) {
   WaitForCompaction();
   AssertFilesPerLevel("0,1", 0 /* cf */);
 
-  // We should calculate the limit by obtaining the number of env background
-  // threads, because the current test case will share the same env
-  // with another case that may have already increased the number of
-  // background threads which is larger than kParallelismLimit
-  const auto limit = env_->GetBackgroundThreads(Env::Priority::LOW);
-
   // Block the compaction thread pool so marked files accumulate in L0.
-  std::vector<std::shared_ptr<test::SleepingBackgroundTask>> sleeping_tasks;
-  for (int i = 0; i < limit; i++) {
-    sleeping_tasks.emplace_back(
-        std::make_shared<test::SleepingBackgroundTask>());
+  test::SleepingBackgroundTask sleeping_tasks[kParallelismLimit];
+  for (int i = 0; i < kParallelismLimit; i++) {
     env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask,
-                   sleeping_tasks[i].get(), Env::Priority::LOW);
-    sleeping_tasks[i]->WaitUntilSleeping();
+                   &sleeping_tasks[i], Env::Priority::LOW);
+    sleeping_tasks[i].WaitUntilSleeping();
   }
 
   // Zero marked upper-level files. No speedup.
@@ -3105,9 +3091,9 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupForMarkedFiles) {
   ASSERT_EQ(kParallelismLimit, dbfull()->TEST_BGCompactionsAllowed());
   AssertFilesPerLevel("2,1", 0 /* cf */);
 
-  for (int i = 0; i < limit; i++) {
-    sleeping_tasks[i]->WakeUp();
-    sleeping_tasks[i]->WaitUntilDone();
+  for (int i = 0; i < kParallelismLimit; i++) {
+    sleeping_tasks[i].WakeUp();
+    sleeping_tasks[i].WaitUntilDone();
   }
 }
 
@@ -3876,91 +3862,6 @@ TEST_F(ManualFlushSkipRetainUDTTest, ManualFlush) {
   Close();
 }
 
-TEST_F(ManualFlushSkipRetainUDTTest, FlushRemovesStaleEntries) {
-  column_family_options_.max_write_buffer_number = 4;
-  Open();
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));
-
-  ColumnFamilyHandle* cfh = db_->DefaultColumnFamily();
-  ColumnFamilyData* cfd =
-      static_cast_with_check<ColumnFamilyHandleImpl>(cfh)->cfd();
-  for (int version = 0; version < 100; version++) {
-    if (version == 50) {
-      ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable(cfd));
-    }
-    ASSERT_OK(
-        Put(0, "foo", EncodeAsUint64(version), "v" + std::to_string(version)));
-  }
-
-  ASSERT_OK(Flush(0));
-  TablePropertiesCollection tables_properties;
-  ASSERT_OK(db_->GetPropertiesOfAllTables(&tables_properties));
-  ASSERT_EQ(1, tables_properties.size());
-  std::shared_ptr<const TableProperties> table_properties =
-      tables_properties.begin()->second;
-  ASSERT_EQ(1, table_properties->num_entries);
-  ASSERT_EQ(0, table_properties->num_deletions);
-  ASSERT_EQ(0, table_properties->num_range_deletions);
-  CheckEffectiveCutoffTime(100);
-  CheckAutomaticFlushRetainUDT(101);
-
-  Close();
-}
-
-TEST_F(ManualFlushSkipRetainUDTTest, RangeDeletionFlushRemovesStaleEntries) {
-  column_family_options_.max_write_buffer_number = 4;
-  Open();
-  // TODO(yuzhangyu): a non 0 full history ts low is needed for this garbage
-  // collection to kick in. This doesn't work well for the very first flush of
-  // the column family. Not a big issue, but would be nice to improve this.
-  ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(9)));
-
-  for (int i = 10; i < 100; i++) {
-    ASSERT_OK(Put(0, "foo" + std::to_string(i), EncodeAsUint64(i),
-                  "val" + std::to_string(i)));
-    if (i % 2 == 1) {
-      ASSERT_OK(db_->DeleteRange(WriteOptions(), "foo" + std::to_string(i - 1),
-                                 "foo" + std::to_string(i), EncodeAsUint64(i)));
-    }
-  }
-
-  ASSERT_OK(Flush(0));
-  CheckEffectiveCutoffTime(100);
-  std::string read_ts = EncodeAsUint64(100);
-  std::string min_ts = EncodeAsUint64(0);
-  ReadOptions ropts;
-  Slice read_ts_slice = read_ts;
-  std::string value;
-  ropts.timestamp = &read_ts_slice;
-  {
-    Iterator* iter = db_->NewIterator(ropts);
-    iter->SeekToFirst();
-    int i = 11;
-    while (iter->Valid()) {
-      ASSERT_TRUE(iter->Valid());
-      ASSERT_EQ("foo" + std::to_string(i), iter->key());
-      ASSERT_EQ("val" + std::to_string(i), iter->value());
-      ASSERT_EQ(min_ts, iter->timestamp());
-      iter->Next();
-      i += 2;
-    }
-    ASSERT_OK(iter->status());
-    delete iter;
-  }
-  TablePropertiesCollection tables_properties;
-  ASSERT_OK(db_->GetPropertiesOfAllTables(&tables_properties));
-  ASSERT_EQ(1, tables_properties.size());
-  std::shared_ptr<const TableProperties> table_properties =
-      tables_properties.begin()->second;
-  // 45 point data + 45 range deletions. 45 obsolete point data are garbage
-  // collected.
-  ASSERT_EQ(90, table_properties->num_entries);
-  ASSERT_EQ(45, table_properties->num_deletions);
-  ASSERT_EQ(45, table_properties->num_range_deletions);
-
-  Close();
-}
-
 TEST_F(ManualFlushSkipRetainUDTTest, ManualCompaction) {
   Open();
   ASSERT_OK(db_->IncreaseFullHistoryTsLow(handles_[0], EncodeAsUint64(0)));

db/compaction/compaction.cc

@@ -63,9 +63,7 @@ uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
   return sum;
 }
 
-// TODO(hx235): consider making this function part of the construction so we
-// don't forget to call it
-void Compaction::FinalizeInputInfo(Version* _input_version) {
+void Compaction::SetInputVersion(Version* _input_version) {
   input_version_ = _input_version;
   cfd_ = input_version_->cfd();
 
@@ -283,10 +281,9 @@ Compaction::Compaction(
     uint32_t _output_path_id, CompressionType _compression,
     CompressionOptions _compression_opts, Temperature _output_temperature,
     uint32_t _max_subcompactions, std::vector<FileMetaData*> _grandparents,
-    std::optional<SequenceNumber> _earliest_snapshot,
-    const SnapshotChecker* _snapshot_checker, bool _manual_compaction,
-    const std::string& _trim_ts, double _score, bool _deletion_compaction,
-    bool l0_files_might_overlap, CompactionReason _compaction_reason,
+    bool _manual_compaction, const std::string& _trim_ts, double _score,
+    bool _deletion_compaction, bool l0_files_might_overlap,
+    CompactionReason _compaction_reason,
     BlobGarbageCollectionPolicy _blob_garbage_collection_policy,
     double _blob_garbage_collection_age_cutoff)
     : input_vstorage_(vstorage),
@@ -308,8 +305,6 @@ Compaction::Compaction(
       l0_files_might_overlap_(l0_files_might_overlap),
       inputs_(PopulateWithAtomicBoundaries(vstorage, std::move(_inputs))),
       grandparents_(std::move(_grandparents)),
-      earliest_snapshot_(_earliest_snapshot),
-      snapshot_checker_(_snapshot_checker),
       score_(_score),
       bottommost_level_(
           // For simplicity, we don't support the concept of "bottommost level"
@@ -370,13 +365,9 @@ Compaction::Compaction(
   // setup input_levels_
   {
     input_levels_.resize(num_input_levels());
-    if (earliest_snapshot_.has_value()) {
-      FilterInputsForCompactionIterator();
-    } else {
-      for (size_t which = 0; which < num_input_levels(); which++) {
-        DoGenerateLevelFilesBrief(&input_levels_[which], inputs_[which].files,
-                                  &arena_);
-      }
+    for (size_t which = 0; which < num_input_levels(); which++) {
+      DoGenerateLevelFilesBrief(&input_levels_[which], inputs_[which].files,
+                                &arena_);
     }
   }
 
@@ -693,11 +684,12 @@ bool Compaction::KeyRangeNotExistsBeyondOutputLevel(
 };
 
 // Mark (or clear) each file that is being compacted
-void Compaction::MarkFilesBeingCompacted(bool being_compacted) const {
+void Compaction::MarkFilesBeingCompacted(bool mark_as_compacted) {
   for (size_t i = 0; i < num_input_levels(); i++) {
     for (size_t j = 0; j < inputs_[i].size(); j++) {
-      assert(being_compacted != inputs_[i][j]->being_compacted);
-      inputs_[i][j]->being_compacted = being_compacted;
+      assert(mark_as_compacted ? !inputs_[i][j]->being_compacted
+                               : inputs_[i][j]->being_compacted);
+      inputs_[i][j]->being_compacted = mark_as_compacted;
     }
   }
 }
@@ -741,7 +733,7 @@ uint64_t Compaction::CalculateTotalInputSize() const {
   return size;
 }
 
-void Compaction::ReleaseCompactionFiles(const Status& status) {
+void Compaction::ReleaseCompactionFiles(Status status) {
   MarkFilesBeingCompacted(false);
   cfd_->compaction_picker()->ReleaseCompactionFiles(this, status);
 }
@@ -752,10 +744,8 @@ void Compaction::ResetNextCompactionIndex() {
 }
 
 namespace {
-int InputSummary(const std::vector<FileMetaData*>& files,
-                 const std::vector<bool>& files_filtered, char* output,
+int InputSummary(const std::vector<FileMetaData*>& files, char* output,
                  int len) {
-  assert(files_filtered.empty() || (files.size() == files_filtered.size()));
   *output = '\0';
   int write = 0;
   for (size_t i = 0; i < files.size(); i++) {
@@ -763,14 +753,8 @@ int InputSummary(const std::vector<FileMetaData*>& files,
     int ret;
     char sztxt[16];
     AppendHumanBytes(files.at(i)->fd.GetFileSize(), sztxt, 16);
-    if (files_filtered.empty()) {
-      ret = snprintf(output + write, sz, "%" PRIu64 "(%s) ",
-                     files.at(i)->fd.GetNumber(), sztxt);
-    } else {
-      ret = snprintf(output + write, sz, "%" PRIu64 "(%s filtered:%s) ",
-                     files.at(i)->fd.GetNumber(), sztxt,
-                     files_filtered.at(i) ? "true" : "false");
-    }
+    ret = snprintf(output + write, sz, "%" PRIu64 "(%s) ",
+                   files.at(i)->fd.GetNumber(), sztxt);
     if (ret < 0 || ret >= sz) {
       break;
     }
@@ -796,15 +780,8 @@ void Compaction::Summary(char* output, int len) {
         return;
       }
     }
-
-    assert(non_start_level_input_files_filtered_.empty() ||
-           non_start_level_input_files_filtered_.size() == inputs_.size() - 1);
-    write += InputSummary(
-        inputs_[level_iter].files,
-        (level_iter == 0 || non_start_level_input_files_filtered_.empty())
-            ? std::vector<bool>{}
-            : non_start_level_input_files_filtered_[level_iter - 1],
-        output + write, len - write);
+    write +=
+        InputSummary(inputs_[level_iter].files, output + write, len - write);
     if (write < 0 || write >= len) {
       return;
     }
@@ -887,11 +864,6 @@ bool Compaction::ShouldFormSubcompactions() const {
     return false;
   }
 
-  if (mutable_cf_options_.table_factory->Name() ==
-      TableFactory::kPlainTableName()) {
-    return false;
-  }
-
   // Round-Robin pri under leveled compaction allows subcompactions by default
   // and the number of subcompactions can be larger than max_subcompactions_
   if (cfd_->ioptions()->compaction_pri == kRoundRobin &&
@@ -1013,69 +985,4 @@ int Compaction::EvaluatePenultimateLevel(
   return penultimate_level;
 }
 
-void Compaction::FilterInputsForCompactionIterator() {
-  assert(earliest_snapshot_.has_value());
-  // cfd_ is not populated at Compaction construction time, get it from
-  // VersionStorageInfo instead.
-  assert(input_vstorage_);
-  const auto* ucmp = input_vstorage_->user_comparator();
-  assert(ucmp);
-  // Simply comparing file boundaries when user-defined timestamp is defined
-  // is not as safe because we need to also compare timestamp to know for
-  // sure. Although entries with higher timestamp is also supposed to have
-  // higher sequence number for the same user key (without timestamp).
-  assert(ucmp->timestamp_size() == 0);
-  size_t num_input_levels = inputs_.size();
-  // TODO(yuzhangyu): filtering of older L0 file by new L0 file is not
-  // supported yet.
-  FileMetaData* rangedel_candidate = inputs_[0].level == 0
-                                         ? inputs_[0].files.back()
-                                         : inputs_[0].files.front();
-  assert(rangedel_candidate);
-  if (!rangedel_candidate->FileIsStandAloneRangeTombstone() ||
-      !DataIsDefinitelyInSnapshot(rangedel_candidate->fd.smallest_seqno,
-                                  earliest_snapshot_.value(),
-                                  snapshot_checker_)) {
-    for (size_t level = 0; level < num_input_levels; level++) {
-      DoGenerateLevelFilesBrief(&input_levels_[level], inputs_[level].files,
-                                &arena_);
-    }
-    return;
-  }
-
-  Slice rangedel_start_ukey = rangedel_candidate->smallest.user_key();
-  Slice rangedel_end_ukey = rangedel_candidate->largest.user_key();
-  SequenceNumber rangedel_seqno = rangedel_candidate->fd.smallest_seqno;
-
-  std::vector<std::vector<FileMetaData*>> non_start_level_input_files;
-  non_start_level_input_files.reserve(num_input_levels - 1);
-  non_start_level_input_files_filtered_.reserve(num_input_levels - 1);
-  for (size_t level = 1; level < num_input_levels; level++) {
-    non_start_level_input_files.emplace_back();
-    non_start_level_input_files_filtered_.emplace_back();
-    for (FileMetaData* file : inputs_[level].files) {
-      non_start_level_input_files_filtered_.back().push_back(false);
-      // When range data and point data has the same sequence number, point
-      // data wins. Range deletion end key is exclusive, so check it's bigger
-      // than file right boundary user key.
-      if (rangedel_seqno > file->fd.largest_seqno &&
-          ucmp->CompareWithoutTimestamp(rangedel_start_ukey,
-                                        file->smallest.user_key()) <= 0 &&
-          ucmp->CompareWithoutTimestamp(rangedel_end_ukey,
-                                        file->largest.user_key()) > 0) {
-        non_start_level_input_files_filtered_.back().back() = true;
-      } else {
-        non_start_level_input_files.back().push_back(file);
-      }
-    }
-  }
-
-  DoGenerateLevelFilesBrief(&input_levels_[0], inputs_[0].files, &arena_);
-  assert(non_start_level_input_files.size() == num_input_levels - 1);
-  for (size_t level = 1; level < num_input_levels; level++) {
-    DoGenerateLevelFilesBrief(&input_levels_[level],
-                              non_start_level_input_files[level - 1], &arena_);
-  }
-}
-
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction.h

@@ -8,8 +8,6 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
 #pragma once
-
-#include "db/snapshot_checker.h"
 #include "db/version_set.h"
 #include "memory/arena.h"
 #include "options/cf_options.h"
@@ -92,8 +90,6 @@ class Compaction {
              CompressionOptions compression_opts,
              Temperature output_temperature, uint32_t max_subcompactions,
              std::vector<FileMetaData*> grandparents,
-             std::optional<SequenceNumber> earliest_snapshot,
-             const SnapshotChecker* snapshot_checker,
              bool manual_compaction = false, const std::string& trim_ts = "",
              double score = -1, bool deletion_compaction = false,
              bool l0_files_might_overlap = true,
@@ -234,7 +230,7 @@ class Compaction {
   // Delete this compaction from the list of running compactions.
   //
   // Requirement: DB mutex held
-  void ReleaseCompactionFiles(const Status& status);
+  void ReleaseCompactionFiles(Status status);
 
   // Returns the summary of the compaction in "output" with maximum "len"
   // in bytes.  The caller is responsible for the memory management of
@@ -293,7 +289,14 @@ class Compaction {
   // is the sum of all input file sizes.
   uint64_t OutputFilePreallocationSize() const;
 
-  void FinalizeInputInfo(Version* input_version);
+  // TODO(hx235): eventually we should consider `InitInputTableProperties()`'s
+  // status and fail the compaction if needed
+  // TODO(hx235): consider making this function part of the construction so we
+  // don't forget to call it
+  void FinalizeInputInfo(Version* input_version) {
+    SetInputVersion(input_version);
+    InitInputTableProperties().PermitUncheckedError();
+  }
 
   struct InputLevelSummaryBuffer {
     char buffer[128];
@@ -330,16 +333,6 @@ class Compaction {
       int output_level, VersionStorageInfo* vstorage,
       const std::vector<CompactionInputFiles>& inputs);
 
-  // TODO(hx235): eventually we should consider `InitInputTableProperties()`'s
-  // status and fail the compaction if needed
-  //
-  // May open and read table files for table property.
-  // Should not be called while holding mutex_.
-  const TablePropertiesCollection& GetOrInitInputTableProperties() {
-    InitInputTableProperties().PermitUncheckedError();
-    return input_table_properties_;
-  }
-
   const TablePropertiesCollection& GetInputTableProperties() const {
     return input_table_properties_;
   }
@@ -439,13 +432,14 @@ class Compaction {
                                       const int start_level,
                                       const int output_level);
 
-  // mark (or clear) all files that are being compacted
-  void MarkFilesBeingCompacted(bool being_compacted) const;
-
  private:
+  void SetInputVersion(Version* input_version);
 
   Status InitInputTableProperties();
 
+  // mark (or clear) all files that are being compacted
+  void MarkFilesBeingCompacted(bool mark_as_compacted);
+
   // get the smallest and largest key present in files to be compacted
   static void GetBoundaryKeys(VersionStorageInfo* vstorage,
                               const std::vector<CompactionInputFiles>& inputs,
@@ -464,13 +458,6 @@ class Compaction {
   // `Compaction::WithinPenultimateLevelOutputRange()`.
   void PopulatePenultimateLevelOutputRange();
 
-  // If oldest snapshot is specified at Compaction construction time, we have
-  // an opportunity to optimize inputs for compaction iterator for this case:
-  // When a standalone range deletion file on the start level is recognized and
-  // can be determined to completely shadow some input files on non-start level.
-  // These files will be filtered out and later not feed to compaction iterator.
-  void FilterInputsForCompactionIterator();
-
   // Get the atomic file boundaries for all files in the compaction. Necessary
   // in order to avoid the scenario described in
   // https://github.com/facebook/rocksdb/pull/4432#discussion_r221072219 and
@@ -521,27 +508,12 @@ class Compaction {
   // Compaction input files organized by level. Constant after construction
   const std::vector<CompactionInputFiles> inputs_;
 
-  // All files from inputs_ that are not filtered and will be fed to compaction
-  // iterator, organized more closely in memory.
+  // A copy of inputs_, organized more closely in memory
   autovector<LevelFilesBrief, 2> input_levels_;
 
   // State used to check for number of overlapping grandparent files
   // (grandparent == "output_level_ + 1")
   std::vector<FileMetaData*> grandparents_;
-
-  // The earliest snapshot and snapshot checker at compaction picking time.
-  // These fields are only set for deletion triggered compactions picked in
-  // universal compaction. And when user-defined timestamp is not enabled.
-  // It will be used to possibly filter out some non start level input files.
-  std::optional<SequenceNumber> earliest_snapshot_;
-  const SnapshotChecker* snapshot_checker_;
-
-  // Markers for which non start level input files are filtered out if
-  // applicable. Only applicable if earliest_snapshot_ is provided and input
-  // start level has a standalone range deletion file.
-  std::vector<std::vector<bool>> non_start_level_input_files_filtered_;
-
-  //  bool standalone_range_tombstones_used_for_filtering_inputs_;
   const double score_;  // score that was used to pick this compaction.
 
   // Is this compaction creating a file in the bottom most level?

db/compaction/compaction_iterator.h

@@ -540,12 +540,18 @@ class CompactionIterator {
 
 inline bool CompactionIterator::DefinitelyInSnapshot(SequenceNumber seq,
                                                      SequenceNumber snapshot) {
-  return DataIsDefinitelyInSnapshot(seq, snapshot, snapshot_checker_);
+  return ((seq) <= (snapshot) &&
+          (snapshot_checker_ == nullptr ||
+           LIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                  SnapshotCheckerResult::kInSnapshot)));
 }
 
 inline bool CompactionIterator::DefinitelyNotInSnapshot(
     SequenceNumber seq, SequenceNumber snapshot) {
-  return DataIsDefinitelyNotInSnapshot(seq, snapshot, snapshot_checker_);
+  return ((seq) > (snapshot) ||
+          (snapshot_checker_ != nullptr &&
+           UNLIKELY(snapshot_checker_->CheckInSnapshot((seq), (snapshot)) ==
+                    SnapshotCheckerResult::kNotInSnapshot)));
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_job.cc

@@ -251,13 +251,12 @@ void CompactionJob::Prepare() {
 
   // Generate file_levels_ for compaction before making Iterator
   auto* c = compact_->compaction;
-  [[maybe_unused]] ColumnFamilyData* cfd = c->column_family_data();
+  ColumnFamilyData* cfd = c->column_family_data();
   assert(cfd != nullptr);
-  const VersionStorageInfo* storage_info = c->input_version()->storage_info();
-  assert(storage_info);
-  assert(storage_info->NumLevelFiles(compact_->compaction->level()) > 0);
+  assert(cfd->current()->storage_info()->NumLevelFiles(
+             compact_->compaction->level()) > 0);
 
-  write_hint_ = storage_info->CalculateSSTWriteHint(c->output_level());
+  write_hint_ = cfd->CalculateSSTWriteHint(c->output_level());
   bottommost_level_ = c->bottommost_level();
 
   if (c->ShouldFormSubcompactions()) {
@@ -298,8 +297,8 @@ void CompactionJob::Prepare() {
     for (const auto& each_level : *c->inputs()) {
       for (const auto& fmd : each_level.files) {
         std::shared_ptr<const TableProperties> tp;
-        Status s = c->input_version()->GetTableProperties(read_options, &tp,
-                                                          fmd, nullptr);
+        Status s =
+            cfd->current()->GetTableProperties(read_options, &tp, fmd, nullptr);
         if (s.ok()) {
           s = seqno_to_time_mapping_.DecodeFrom(tp->seqno_to_time_mapping);
         }
@@ -469,11 +468,6 @@ void CompactionJob::GenSubcompactionBoundaries() {
   ReadOptions read_options(Env::IOActivity::kCompaction);
   read_options.rate_limiter_priority = GetRateLimiterPriority();
   auto* c = compact_->compaction;
-  if (c->mutable_cf_options()->table_factory->Name() ==
-      TableFactory::kPlainTableName()) {
-    return;
-  }
-
   if (c->max_subcompactions() <= 1 &&
       !(c->immutable_options()->compaction_pri == kRoundRobin &&
         c->immutable_options()->compaction_style == kCompactionStyleLevel)) {
@@ -506,7 +500,9 @@ 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, *c->mutable_cf_options(), 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());
         }
@@ -625,7 +621,6 @@ Status CompactionJob::Run() {
   const size_t num_threads = compact_->sub_compact_states.size();
   assert(num_threads > 0);
   const uint64_t start_micros = db_options_.clock->NowMicros();
-  compact_->compaction->GetOrInitInputTableProperties();
 
   // Launch a thread for each of subcompactions 1...num_threads-1
   std::vector<port::Thread> thread_pool;
@@ -709,6 +704,8 @@ Status CompactionJob::Run() {
       }
     }
     ColumnFamilyData* cfd = compact_->compaction->column_family_data();
+    auto& prefix_extractor =
+        compact_->compaction->mutable_cf_options()->prefix_extractor;
     std::atomic<size_t> next_file_idx(0);
     auto verify_table = [&](Status& output_status) {
       while (true) {
@@ -729,8 +726,7 @@ Status CompactionJob::Run() {
         InternalIterator* iter = cfd->table_cache()->NewIterator(
             verify_table_read_options, file_options_,
             cfd->internal_comparator(), files_output[file_idx]->meta,
-            /*range_del_agg=*/nullptr,
-            *compact_->compaction->mutable_cf_options(),
+            /*range_del_agg=*/nullptr, prefix_extractor,
             /*table_reader_ptr=*/nullptr,
             cfd->internal_stats()->GetFileReadHist(
                 compact_->compaction->output_level()),
@@ -740,7 +736,9 @@ 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_) {
@@ -801,12 +799,6 @@ Status CompactionJob::Run() {
     }
   }
 
-  // Before the compaction starts, is_remote_compaction was set to true if
-  // compaction_service is set. We now know whether each sub_compaction was
-  // done remotely or not. Reset is_remote_compaction back to false and allow
-  // AggregateCompactionStats() to set the right value.
-  compaction_job_stats_->is_remote_compaction = false;
-
   // Finish up all bookkeeping to unify the subcompaction results.
   compact_->AggregateCompactionStats(compaction_stats_, *compaction_job_stats_);
   uint64_t num_input_range_del = 0;
@@ -1085,7 +1077,6 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     }
     // fallback to local compaction
     assert(comp_status == CompactionServiceJobStatus::kUseLocal);
-    sub_compact->compaction_job_stats.is_remote_compaction = false;
   }
 
   uint64_t prev_cpu_micros = db_options_.clock->CPUMicros();
@@ -2003,12 +1994,10 @@ bool CompactionJob::UpdateCompactionStats(uint64_t* num_input_range_del) {
   bool has_error = false;
   const ReadOptions read_options(Env::IOActivity::kCompaction);
   const auto& input_table_properties = compaction->GetInputTableProperties();
-  // TODO(yuzhangyu): add dedicated stats for filtered files.
   for (int input_level = 0;
        input_level < static_cast<int>(compaction->num_input_levels());
        ++input_level) {
-    const LevelFilesBrief* flevel = compaction->input_levels(input_level);
-    size_t num_input_files = flevel->num_files;
+    size_t num_input_files = compaction->num_input_files(input_level);
     uint64_t* bytes_read;
     if (compaction->level(input_level) != compaction->output_level()) {
       compaction_stats_.stats.num_input_files_in_non_output_levels +=
@@ -2020,7 +2009,7 @@ bool CompactionJob::UpdateCompactionStats(uint64_t* num_input_range_del) {
       bytes_read = &compaction_stats_.stats.bytes_read_output_level;
     }
     for (size_t i = 0; i < num_input_files; ++i) {
-      const FileMetaData* file_meta = flevel->files[i].file_metadata;
+      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;

db/compaction/compaction_job.h

@@ -209,8 +209,6 @@ class CompactionJob {
   // 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);
-  virtual void UpdateCompactionJobStats(
-      const InternalStats::CompactionStats& stats) const;
   void LogCompaction();
   virtual void RecordCompactionIOStats();
   void CleanupCompaction();
@@ -281,7 +279,8 @@ class CompactionJob {
                                   bool* compaction_released);
   Status OpenCompactionOutputFile(SubcompactionState* sub_compact,
                                   CompactionOutputs& outputs);
-
+  void UpdateCompactionJobStats(
+      const InternalStats::CompactionStats& stats) const;
   void RecordDroppedKeys(const CompactionIterationStats& c_iter_stats,
                          CompactionJobStats* compaction_job_stats = nullptr);
 
@@ -378,7 +377,9 @@ class CompactionJob {
 // doesn't contain the LSM tree information, which is passed though MANIFEST
 // file.
 struct CompactionServiceInput {
-  std::string cf_name;
+  ColumnFamilyDescriptor column_family;
+
+  DBOptions db_options;
 
   std::vector<SequenceNumber> snapshots;
 
@@ -386,7 +387,7 @@ struct CompactionServiceInput {
   // files needed for this compaction, for both input level files and output
   // level files.
   std::vector<std::string> input_files;
-  int output_level = 0;
+  int output_level;
 
   // db_id is used to generate unique id of sst on the remote compactor
   std::string db_id;
@@ -397,12 +398,13 @@ struct CompactionServiceInput {
   bool has_end = false;
   std::string end;
 
-  uint64_t options_file_number = 0;
-
   // serialization interface to read and write the object
   static Status Read(const std::string& data_str, CompactionServiceInput* obj);
   Status Write(std::string* output);
 
+  // Initialize a dummy ColumnFamilyDescriptor
+  CompactionServiceInput() : column_family("", ColumnFamilyOptions()) {}
+
 #ifndef NDEBUG
   bool TEST_Equals(CompactionServiceInput* other);
   bool TEST_Equals(CompactionServiceInput* other, std::string* mismatch);
@@ -416,25 +418,20 @@ struct CompactionServiceOutputFile {
   SequenceNumber largest_seqno;
   std::string smallest_internal_key;
   std::string largest_internal_key;
-  uint64_t oldest_ancester_time = kUnknownOldestAncesterTime;
-  uint64_t file_creation_time = kUnknownFileCreationTime;
-  uint64_t epoch_number = kUnknownEpochNumber;
-  std::string file_checksum = kUnknownFileChecksum;
-  std::string file_checksum_func_name = kUnknownFileChecksumFuncName;
+  uint64_t oldest_ancester_time;
+  uint64_t file_creation_time;
+  uint64_t epoch_number;
   uint64_t paranoid_hash;
   bool marked_for_compaction;
-  UniqueId64x2 unique_id{};
-  TableProperties table_properties;
+  UniqueId64x2 unique_id;
 
   CompactionServiceOutputFile() = default;
   CompactionServiceOutputFile(
       const std::string& name, SequenceNumber smallest, SequenceNumber largest,
       std::string _smallest_internal_key, std::string _largest_internal_key,
       uint64_t _oldest_ancester_time, uint64_t _file_creation_time,
-      uint64_t _epoch_number, const std::string& _file_checksum,
-      const std::string& _file_checksum_func_name, uint64_t _paranoid_hash,
-      bool _marked_for_compaction, UniqueId64x2 _unique_id,
-      const std::shared_ptr<const TableProperties>& _table_properties)
+      uint64_t _epoch_number, uint64_t _paranoid_hash,
+      bool _marked_for_compaction, UniqueId64x2 _unique_id)
       : file_name(name),
         smallest_seqno(smallest),
         largest_seqno(largest),
@@ -443,12 +440,9 @@ struct CompactionServiceOutputFile {
         oldest_ancester_time(_oldest_ancester_time),
         file_creation_time(_file_creation_time),
         epoch_number(_epoch_number),
-        file_checksum(_file_checksum),
-        file_checksum_func_name(_file_checksum_func_name),
         paranoid_hash(_paranoid_hash),
         marked_for_compaction(_marked_for_compaction),
-        unique_id(std::move(_unique_id)),
-        table_properties(*_table_properties.get()) {}
+        unique_id(std::move(_unique_id)) {}
 };
 
 // CompactionServiceResult contains the compaction result from a different db
@@ -457,11 +451,14 @@ struct CompactionServiceOutputFile {
 struct CompactionServiceResult {
   Status status;
   std::vector<CompactionServiceOutputFile> output_files;
-  int output_level = 0;
+  int output_level;
 
   // location of the output files
   std::string output_path;
 
+  // some statistics about the compaction
+  uint64_t num_output_records = 0;
+  uint64_t total_bytes = 0;
   uint64_t bytes_read = 0;
   uint64_t bytes_written = 0;
   CompactionJobStats stats;
@@ -507,9 +504,6 @@ class CompactionServiceCompactionJob : private CompactionJob {
  protected:
   void RecordCompactionIOStats() override;
 
-  void UpdateCompactionJobStats(
-      const InternalStats::CompactionStats& stats) const override;
-
  private:
   // Get table file name in output_path
   std::string GetTableFileName(uint64_t file_number) override;

db/compaction/compaction_job_test.cc

@@ -50,8 +50,7 @@ void VerifyInitializationOfCompactionJobStats(
   ASSERT_EQ(compaction_job_stats.num_output_records, 0U);
   ASSERT_EQ(compaction_job_stats.num_output_files, 0U);
 
-  ASSERT_TRUE(compaction_job_stats.is_manual_compaction);
-  ASSERT_FALSE(compaction_job_stats.is_remote_compaction);
+  ASSERT_EQ(compaction_job_stats.is_manual_compaction, true);
 
   ASSERT_EQ(compaction_job_stats.total_input_bytes, 0U);
   ASSERT_EQ(compaction_job_stats.total_output_bytes, 0U);
@@ -250,7 +249,6 @@ class CompactionJobTestBase : public testing::Test {
     } else {
       assert(false);
     }
-    mutable_cf_options_.table_factory = cf_options_.table_factory;
   }
 
   std::string GenerateFileName(uint64_t file_number) {
@@ -547,14 +545,14 @@ class CompactionJobTestBase : public testing::Test {
     ASSERT_OK(s);
     db_options_.info_log = info_log;
 
-    versions_.reset(
-        new VersionSet(dbname_, &db_options_, env_options_, table_cache_.get(),
-                       &write_buffer_manager_, &write_controller_,
-                       /*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr,
-                       test::kUnitTestDbId, /*db_session_id=*/"",
-                       /*daily_offpeak_time_utc=*/"",
-                       /*error_handler=*/nullptr, /*read_only=*/false));
+    versions_.reset(new VersionSet(
+        dbname_, &db_options_, env_options_, table_cache_.get(),
+        &write_buffer_manager_, &write_controller_,
+        /*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr,
+        /*db_id=*/"", /*db_session_id=*/"", /*daily_offpeak_time_utc=*/"",
+        /*error_handler=*/nullptr, /*read_only=*/false));
     compaction_job_stats_.Reset();
+    ASSERT_OK(SetIdentityFile(WriteOptions(), env_, dbname_));
 
     VersionEdit new_db;
     new_db.SetLogNumber(0);
@@ -577,8 +575,7 @@ class CompactionJobTestBase : public testing::Test {
     }
     ASSERT_OK(s);
     // Make "CURRENT" file that points to the new manifest file.
-    s = SetCurrentFile(WriteOptions(), fs_.get(), dbname_, 1,
-                       Temperature::kUnknown, nullptr);
+    s = SetCurrentFile(WriteOptions(), fs_.get(), dbname_, 1, nullptr);
 
     ASSERT_OK(s);
 
@@ -652,8 +649,7 @@ class CompactionJobTestBase : public testing::Test {
         mutable_cf_options_.target_file_size_base,
         mutable_cf_options_.max_compaction_bytes, 0, kNoCompression,
         cfd->GetLatestMutableCFOptions()->compression_opts,
-        Temperature::kUnknown, max_subcompactions, grandparents,
-        /*earliest_snapshot*/ std::nullopt, /*snapshot_checker*/ nullptr, true);
+        Temperature::kUnknown, max_subcompactions, grandparents, true);
     compaction.FinalizeInputInfo(cfd->current());
 
     assert(db_options_.info_log);
@@ -1571,7 +1567,17 @@ TEST_F(CompactionJobTest, InputSerialization) {
   const int kStrMaxLen = 1000;
   Random rnd(static_cast<uint32_t>(time(nullptr)));
   Random64 rnd64(time(nullptr));
-  input.cf_name = rnd.RandomString(rnd.Uniform(kStrMaxLen));
+  input.column_family.name = rnd.RandomString(rnd.Uniform(kStrMaxLen));
+  input.column_family.options.comparator = ReverseBytewiseComparator();
+  input.column_family.options.max_bytes_for_level_base =
+      rnd64.Uniform(UINT64_MAX);
+  input.column_family.options.disable_auto_compactions = rnd.OneIn(2);
+  input.column_family.options.compression = kZSTD;
+  input.column_family.options.compression_opts.level = 4;
+  input.db_options.max_background_flushes = 10;
+  input.db_options.paranoid_checks = rnd.OneIn(2);
+  input.db_options.statistics = CreateDBStatistics();
+  input.db_options.env = env_;
   while (!rnd.OneIn(10)) {
     input.snapshots.emplace_back(rnd64.Uniform(UINT64_MAX));
   }
@@ -1599,10 +1605,10 @@ TEST_F(CompactionJobTest, InputSerialization) {
   ASSERT_TRUE(deserialized1.TEST_Equals(&input));
 
   // Test mismatch
-  deserialized1.output_level += 10;
+  deserialized1.db_options.max_background_flushes += 10;
   std::string mismatch;
   ASSERT_FALSE(deserialized1.TEST_Equals(&input, &mismatch));
-  ASSERT_EQ(mismatch, "output_level");
+  ASSERT_EQ(mismatch, "db_options.max_background_flushes");
 
   // Test unknown field
   CompactionServiceInput deserialized2;
@@ -1658,44 +1664,20 @@ TEST_F(CompactionJobTest, ResultSerialization) {
   };
   result.status =
       status_list.at(rnd.Uniform(static_cast<int>(status_list.size())));
-
-  std::string file_checksum = rnd.RandomBinaryString(rnd.Uniform(kStrMaxLen));
-  std::string file_checksum_func_name = "MyAwesomeChecksumGenerator";
   while (!rnd.OneIn(10)) {
-    TableProperties tp;
-    tp.user_collected_properties.emplace(
-        "UCP_Key1", rnd.RandomString(rnd.Uniform(kStrMaxLen)));
-    tp.user_collected_properties.emplace(
-        "UCP_Key2", rnd.RandomString(rnd.Uniform(kStrMaxLen)));
-    tp.readable_properties.emplace("RP_Key1",
-                                   rnd.RandomString(rnd.Uniform(kStrMaxLen)));
-    tp.readable_properties.emplace("RP_K2y2",
-                                   rnd.RandomString(rnd.Uniform(kStrMaxLen)));
-
-    std::shared_ptr<const TableProperties> table_properties =
-        std::make_shared<const TableProperties>(tp);
-
     UniqueId64x2 id{rnd64.Uniform(UINT64_MAX), rnd64.Uniform(UINT64_MAX)};
     result.output_files.emplace_back(
-        rnd.RandomString(rnd.Uniform(kStrMaxLen)) /* file_name */,
-        rnd64.Uniform(UINT64_MAX) /* smallest_seqno */,
-        rnd64.Uniform(UINT64_MAX) /* largest_seqno */,
-        rnd.RandomBinaryString(
-            rnd.Uniform(kStrMaxLen)) /* smallest_internal_key */,
-        rnd.RandomBinaryString(
-            rnd.Uniform(kStrMaxLen)) /* largest_internal_key */,
-        rnd64.Uniform(UINT64_MAX) /* oldest_ancester_time */,
-        rnd64.Uniform(UINT64_MAX) /* file_creation_time */,
-        rnd64.Uniform(UINT64_MAX) /* epoch_number */,
-        file_checksum /* file_checksum */,
-        file_checksum_func_name /* file_checksum_func_name */,
-        rnd64.Uniform(UINT64_MAX) /* paranoid_hash */,
-        rnd.OneIn(2) /* marked_for_compaction */, id /* unique_id */,
-        table_properties);
+        rnd.RandomString(rnd.Uniform(kStrMaxLen)), rnd64.Uniform(UINT64_MAX),
+        rnd64.Uniform(UINT64_MAX),
+        rnd.RandomBinaryString(rnd.Uniform(kStrMaxLen)),
+        rnd.RandomBinaryString(rnd.Uniform(kStrMaxLen)),
+        rnd64.Uniform(UINT64_MAX), rnd64.Uniform(UINT64_MAX),
+        rnd64.Uniform(UINT64_MAX), rnd64.Uniform(UINT64_MAX), rnd.OneIn(2), id);
   }
   result.output_level = rnd.Uniform(10);
   result.output_path = rnd.RandomString(rnd.Uniform(kStrMaxLen));
-  result.stats.num_output_records = rnd64.Uniform(UINT64_MAX);
+  result.num_output_records = rnd64.Uniform(UINT64_MAX);
+  result.total_bytes = rnd64.Uniform(UINT64_MAX);
   result.bytes_read = 123;
   result.bytes_written = rnd64.Uniform(UINT64_MAX);
   result.stats.elapsed_micros = rnd64.Uniform(UINT64_MAX);
@@ -1712,21 +1694,6 @@ TEST_F(CompactionJobTest, ResultSerialization) {
   ASSERT_OK(CompactionServiceResult::Read(output, &deserialized1));
   ASSERT_TRUE(deserialized1.TEST_Equals(&result));
 
-  for (size_t i = 0; i < result.output_files.size(); i++) {
-    for (const auto& prop :
-         result.output_files[i].table_properties.user_collected_properties) {
-      ASSERT_EQ(deserialized1.output_files[i]
-                    .table_properties.user_collected_properties[prop.first],
-                prop.second);
-    }
-    for (const auto& prop :
-         result.output_files[i].table_properties.readable_properties) {
-      ASSERT_EQ(deserialized1.output_files[i]
-                    .table_properties.readable_properties[prop.first],
-                prop.second);
-    }
-  }
-
   // Test mismatch
   deserialized1.stats.num_input_files += 10;
   std::string mismatch;
@@ -1741,10 +1708,6 @@ TEST_F(CompactionJobTest, ResultSerialization) {
     ASSERT_FALSE(deserialized_tmp.TEST_Equals(&result, &mismatch));
     ASSERT_EQ(mismatch, "output_files.unique_id");
     deserialized_tmp.status.PermitUncheckedError();
-
-    ASSERT_EQ(deserialized_tmp.output_files[0].file_checksum, file_checksum);
-    ASSERT_EQ(deserialized_tmp.output_files[0].file_checksum_func_name,
-              file_checksum_func_name);
   }
 
   // Test unknown field

db/compaction/compaction_outputs.h

@@ -62,9 +62,8 @@ class CompactionOutputs {
   }
 
   // TODO: Remove it when remote compaction support tiered compaction
-  void AddBytesWritten(uint64_t bytes) { stats_.bytes_written += bytes; }
+  void SetTotalBytes(uint64_t bytes) { stats_.bytes_written += bytes; }
   void SetNumOutputRecords(uint64_t num) { stats_.num_output_records = num; }
-  void SetNumOutputFiles(uint64_t num) { stats_.num_output_files = num; }
 
   // TODO: Move the BlobDB builder into CompactionOutputs
   const std::vector<BlobFileAddition>& GetBlobFileAdditions() const {
@@ -108,12 +107,6 @@ class CompactionOutputs {
   Status Finish(const Status& intput_status,
                 const SeqnoToTimeMapping& seqno_to_time_mapping);
 
-  // Update output table properties from already populated TableProperties.
-  // Used for remote compaction
-  void UpdateTableProperties(const TableProperties& table_properties) {
-    current_output().table_properties =
-        std::make_shared<TableProperties>(table_properties);
-  }
   // Update output table properties from table builder
   void UpdateTableProperties() {
     current_output().table_properties =

db/compaction/compaction_picker.cc

@@ -133,8 +133,7 @@ CompactionPicker::CompactionPicker(const ImmutableOptions& ioptions,
 CompactionPicker::~CompactionPicker() = default;
 
 // Delete this compaction from the list of running compactions.
-void CompactionPicker::ReleaseCompactionFiles(Compaction* c,
-                                              const Status& status) {
+void CompactionPicker::ReleaseCompactionFiles(Compaction* c, Status status) {
   UnregisterCompaction(c);
   if (!status.ok()) {
     c->ResetNextCompactionIndex();
@@ -380,8 +379,7 @@ Compaction* CompactionPicker::CompactFiles(
       GetCompressionOptions(mutable_cf_options, vstorage, output_level),
       mutable_cf_options.default_write_temperature,
       compact_options.max_subcompactions,
-      /* grandparents */ {}, /* earliest_snapshot */ std::nullopt,
-      /* snapshot_checker */ nullptr, true);
+      /* grandparents */ {}, true);
   RegisterCompaction(c);
   return c;
 }
@@ -678,9 +676,7 @@ Compaction* CompactionPicker::CompactRange(
         GetCompressionOptions(mutable_cf_options, vstorage, output_level),
         mutable_cf_options.default_write_temperature,
         compact_range_options.max_subcompactions,
-        /* grandparents */ {}, /* earliest_snapshot */ std::nullopt,
-        /* snapshot_checker */ nullptr,
-        /* is manual */ true, trim_ts, /* score */ -1,
+        /* grandparents */ {}, /* is manual */ true, trim_ts, /* score */ -1,
         /* deletion_compaction */ false, /* l0_files_might_overlap */ true,
         CompactionReason::kUnknown,
         compact_range_options.blob_garbage_collection_policy,
@@ -869,7 +865,6 @@ Compaction* CompactionPicker::CompactRange(
       GetCompressionOptions(mutable_cf_options, vstorage, output_level),
       mutable_cf_options.default_write_temperature,
       compact_range_options.max_subcompactions, std::move(grandparents),
-      /* earliest_snapshot */ std::nullopt, /* snapshot_checker */ nullptr,
       /* is manual */ true, trim_ts, /* score */ -1,
       /* deletion_compaction */ false, /* l0_files_might_overlap */ true,
       CompactionReason::kUnknown,
@@ -1175,8 +1170,7 @@ void CompactionPicker::UnregisterCompaction(Compaction* c) {
 
 void CompactionPicker::PickFilesMarkedForCompaction(
     const std::string& cf_name, VersionStorageInfo* vstorage, int* start_level,
-    int* output_level, CompactionInputFiles* start_level_inputs,
-    std::function<bool(const FileMetaData*)> skip_marked_file) {
+    int* output_level, CompactionInputFiles* start_level_inputs) {
   if (vstorage->FilesMarkedForCompaction().empty()) {
     return;
   }
@@ -1186,9 +1180,6 @@ void CompactionPicker::PickFilesMarkedForCompaction(
     // If this assert() fails that means that some function marked some
     // files as being_compacted, but didn't call ComputeCompactionScore()
     assert(!level_file.second->being_compacted);
-    if (skip_marked_file(level_file.second)) {
-      return false;
-    }
     *start_level = level_file.first;
     *output_level =
         (*start_level == 0) ? vstorage->base_level() : *start_level + 1;

db/compaction/compaction_picker.h

@@ -16,7 +16,6 @@
 #include <vector>
 
 #include "db/compaction/compaction.h"
-#include "db/snapshot_checker.h"
 #include "db/version_set.h"
 #include "options/cf_options.h"
 #include "rocksdb/env.h"
@@ -56,17 +55,17 @@ class CompactionPicker {
   // Returns nullptr if there is no compaction to be done.
   // Otherwise returns a pointer to a heap-allocated object that
   // describes the compaction.  Caller should delete the result.
-  // Currently, only universal compaction will query existing snapshots and
-  // pass it to aid compaction picking. And it's only passed when user-defined
-  // timestamps is not enabled. The other compaction styles do not pass or use
-  // `existing_snapshots` or `snapshot_checker`.
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& existing_snapshots,
-      const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
-      LogBuffer* log_buffer) = 0;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     const MutableDBOptions& mutable_db_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) = 0;
 
+  // Return a compaction object for compacting the range [begin,end] in
+  // the specified level.  Returns nullptr if there is nothing in that
+  // level that overlaps the specified range.  Caller should delete
+  // the result.
+  //
   // The returned Compaction might not include the whole requested range.
   // In that case, compaction_end will be set to the next key that needs
   // compacting. In case the compaction will compact the whole range,
@@ -105,7 +104,7 @@ class CompactionPicker {
   // Free up the files that participated in a compaction
   //
   // Requirement: DB mutex held
-  void ReleaseCompactionFiles(Compaction* c, const Status& status);
+  void ReleaseCompactionFiles(Compaction* c, Status status);
 
   // Returns true if any one of the specified files are being compacted
   bool AreFilesInCompaction(const std::vector<FileMetaData*>& files);
@@ -204,11 +203,10 @@ class CompactionPicker {
                        const CompactionInputFiles& output_level_inputs,
                        std::vector<FileMetaData*>* grandparents);
 
-  void PickFilesMarkedForCompaction(
-      const std::string& cf_name, VersionStorageInfo* vstorage,
-      int* start_level, int* output_level,
-      CompactionInputFiles* start_level_inputs,
-      std::function<bool(const FileMetaData*)> skip_marked_file);
+  void PickFilesMarkedForCompaction(const std::string& cf_name,
+                                    VersionStorageInfo* vstorage,
+                                    int* start_level, int* output_level,
+                                    CompactionInputFiles* start_level_inputs);
 
   bool GetOverlappingL0Files(VersionStorageInfo* vstorage,
                              CompactionInputFiles* start_level_inputs,
@@ -259,13 +257,11 @@ class NullCompactionPicker : public CompactionPicker {
   virtual ~NullCompactionPicker() {}
 
   // Always return "nullptr"
-  Compaction* PickCompaction(
-      const std::string& /*cf_name*/,
-      const MutableCFOptions& /*mutable_cf_options*/,
-      const MutableDBOptions& /*mutable_db_options*/,
-      const std::vector<SequenceNumber>& /*existing_snapshots*/,
-      const SnapshotChecker* /*snapshot_checker*/,
-      VersionStorageInfo* /*vstorage*/, LogBuffer* /* log_buffer */) override {
+  Compaction* PickCompaction(const std::string& /*cf_name*/,
+                             const MutableCFOptions& /*mutable_cf_options*/,
+                             const MutableDBOptions& /*mutable_db_options*/,
+                             VersionStorageInfo* /*vstorage*/,
+                             LogBuffer* /* log_buffer */) override {
     return nullptr;
   }
 

db/compaction/compaction_picker_fifo.cc

@@ -118,9 +118,7 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
       std::move(inputs), 0, 0, 0, 0, kNoCompression,
       mutable_cf_options.compression_opts,
       mutable_cf_options.default_write_temperature,
-      /* max_subcompactions */ 0, {}, /* earliest_snapshot */ std::nullopt,
-      /* snapshot_checker */ nullptr,
-      /* is manual */ false,
+      /* max_subcompactions */ 0, {}, /* is manual */ false,
       /* trim_ts */ "", vstorage->CompactionScore(0),
       /* is deletion compaction */ true, /* l0_files_might_overlap */ true,
       CompactionReason::kFIFOTtl);
@@ -190,9 +188,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
             0 /* output path ID */, mutable_cf_options.compression,
             mutable_cf_options.compression_opts,
             mutable_cf_options.default_write_temperature,
-            0 /* max_subcompactions */, {},
-            /* earliest_snapshot */ std::nullopt,
-            /* snapshot_checker */ nullptr, /* is manual */ false,
+            0 /* max_subcompactions */, {}, /* is manual */ false,
             /* trim_ts */ "", vstorage->CompactionScore(0),
             /* is deletion compaction */ false,
             /* l0_files_might_overlap */ true,
@@ -288,9 +284,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
       /* output_path_id */ 0, kNoCompression,
       mutable_cf_options.compression_opts,
       mutable_cf_options.default_write_temperature,
-      /* max_subcompactions */ 0, {}, /* earliest_snapshot */ std::nullopt,
-      /* snapshot_checker */ nullptr,
-      /* is manual */ false,
+      /* max_subcompactions */ 0, {}, /* is manual */ false,
       /* trim_ts */ "", vstorage->CompactionScore(0),
       /* is deletion compaction */ true,
       /* l0_files_might_overlap */ true, CompactionReason::kFIFOMaxSize);
@@ -300,7 +294,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
 Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
     const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
-    LogBuffer* log_buffer) const {
+    LogBuffer* log_buffer) {
   const std::vector<FileTemperatureAge>& ages =
       mutable_cf_options.compaction_options_fifo
           .file_temperature_age_thresholds;
@@ -350,10 +344,12 @@ Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
   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 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) {
@@ -378,7 +374,7 @@ Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
         // cur_file is too fresh
         break;
       }
-      Temperature cur_target_temp = ages[0].temperature;
+      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) {
@@ -386,20 +382,35 @@ Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
         }
       }
       if (cur_file->temperature == cur_target_temp) {
-        continue;
+        if (inputs[0].empty()) {
+          continue;
+        } else {
+          break;
+        }
       }
 
       // cur_file needs to change temperature
-      assert(compaction_target_temp == Temperature::kLastTemperature);
-      compaction_target_temp = cur_target_temp;
-      inputs[0].files.push_back(cur_file);
-      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());
-      break;
+      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;
+      }
     }
   }
 
@@ -407,18 +418,15 @@ Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
     return nullptr;
   }
   assert(compaction_target_temp != Temperature::kLastTemperature);
-  // Only compact one file at a time.
-  assert(inputs.size() == 1);
-  assert(inputs[0].size() == 1);
+
   Compaction* c = new Compaction(
       vstorage, ioptions_, mutable_cf_options, mutable_db_options,
       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,
       compaction_target_temp,
-      /* max_subcompactions */ 0, {}, /* earliest_snapshot */ std::nullopt,
-      /* snapshot_checker */ nullptr,
-      /* is manual */ false, /* trim_ts */ "", vstorage->CompactionScore(0),
+      /* max_subcompactions */ 0, {}, /* is manual */ false, /* trim_ts */ "",
+      vstorage->CompactionScore(0),
       /* is deletion compaction */ false, /* l0_files_might_overlap */ true,
       CompactionReason::kChangeTemperature);
   return c;
@@ -426,9 +434,7 @@ Compaction* FIFOCompactionPicker::PickTemperatureChangeCompaction(
 
 Compaction* FIFOCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    const MutableDBOptions& mutable_db_options,
-    const std::vector<SequenceNumber>& /* existing_snapshots */,
-    const SnapshotChecker* /* snapshot_checker */, VersionStorageInfo* vstorage,
+    const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
     LogBuffer* log_buffer) {
   Compaction* c = nullptr;
   if (mutable_cf_options.ttl > 0) {
@@ -463,10 +469,8 @@ Compaction* FIFOCompactionPicker::CompactRange(
   assert(output_level == 0);
   *compaction_end = nullptr;
   LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, ioptions_.logger);
-  Compaction* c =
-      PickCompaction(cf_name, mutable_cf_options, mutable_db_options,
-                     /*existing_snapshots*/ {}, /*snapshot_checker*/ nullptr,
-                     vstorage, &log_buffer);
+  Compaction* c = PickCompaction(cf_name, mutable_cf_options,
+                                 mutable_db_options, vstorage, &log_buffer);
   log_buffer.FlushBufferToLog();
   return c;
 }

db/compaction/compaction_picker_fifo.h

@@ -18,12 +18,11 @@ class FIFOCompactionPicker : public CompactionPicker {
                        const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
 
-  Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& /* existing_snapshots */,
-      const SnapshotChecker* /* snapshot_checker */,
-      VersionStorageInfo* version, LogBuffer* log_buffer) override;
+  Compaction* PickCompaction(const std::string& cf_name,
+                             const MutableCFOptions& mutable_cf_options,
+                             const MutableDBOptions& mutable_db_options,
+                             VersionStorageInfo* version,
+                             LogBuffer* log_buffer) override;
 
   Compaction* CompactRange(const std::string& cf_name,
                            const MutableCFOptions& mutable_cf_options,
@@ -54,10 +53,9 @@ class FIFOCompactionPicker : public CompactionPicker {
                                  VersionStorageInfo* version,
                                  LogBuffer* log_buffer);
 
-  // Will pick one file to compact at a time, starting from the oldest file.
   Compaction* PickTemperatureChangeCompaction(
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
       const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
-      LogBuffer* log_buffer) const;
+      LogBuffer* log_buffer);
 };
 }  // namespace ROCKSDB_NAMESPACE

db/compaction/compaction_picker_level.cc

@@ -262,10 +262,7 @@ void LevelCompactionBuilder::SetupInitialFiles() {
   parent_index_ = base_index_ = -1;
 
   compaction_picker_->PickFilesMarkedForCompaction(
-      cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_,
-      /*skip_marked_file*/ [](const FileMetaData* /* file */) {
-        return false;
-      });
+      cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_);
   if (!start_level_inputs_.empty()) {
     compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
     return;
@@ -557,9 +554,7 @@ Compaction* LevelCompactionBuilder::GetCompaction() {
                          vstorage_->base_level()),
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level_),
       mutable_cf_options_.default_write_temperature,
-      /* max_subcompactions */ 0, std::move(grandparents_),
-      /* earliest_snapshot */ std::nullopt, /* snapshot_checker */ nullptr,
-      is_manual_,
+      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
       /* trim_ts */ "", start_level_score_, false /* deletion_compaction */,
       l0_files_might_overlap, compaction_reason_);
 
@@ -930,15 +925,11 @@ bool LevelCompactionBuilder::PickSizeBasedIntraL0Compaction() {
   }
   uint64_t l0_size = 0;
   for (const auto& file : l0_files) {
-    assert(file->compensated_file_size >= file->fd.GetFileSize());
-    // Compact down L0s with more deletions.
-    l0_size += file->compensated_file_size;
+    l0_size += file->fd.GetFileSize();
   }
-
-  // Avoid L0->Lbase compactions that are inefficient for write-amp.
-  const double kMultiplier =
-      std::max(10.0, mutable_cf_options_.max_bytes_for_level_multiplier) * 2;
-  const uint64_t min_lbase_size = MultiplyCheckOverflow(l0_size, kMultiplier);
+  const uint64_t min_lbase_size =
+      l0_size * static_cast<uint64_t>(std::max(
+                    10.0, mutable_cf_options_.max_bytes_for_level_multiplier));
   assert(min_lbase_size >= l0_size);
   const std::vector<FileMetaData*>& lbase_files =
       vstorage_->LevelFiles(/*level=*/base_level);
@@ -972,9 +963,7 @@ bool LevelCompactionBuilder::PickSizeBasedIntraL0Compaction() {
 
 Compaction* LevelCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    const MutableDBOptions& mutable_db_options,
-    const std::vector<SequenceNumber>& /*existing_snapshots */,
-    const SnapshotChecker* /*snapshot_checker*/, VersionStorageInfo* vstorage,
+    const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
     LogBuffer* log_buffer) {
   LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
                                  mutable_cf_options, ioptions_,

db/compaction/compaction_picker_level.h

@@ -20,12 +20,11 @@ class LevelCompactionPicker : public CompactionPicker {
   LevelCompactionPicker(const ImmutableOptions& ioptions,
                         const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
-  Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& /* existing_snapshots */,
-      const SnapshotChecker* /* snapshot_checker */,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer) override;
+  Compaction* PickCompaction(const std::string& cf_name,
+                             const MutableCFOptions& mutable_cf_options,
+                             const MutableDBOptions& mutable_db_options,
+                             VersionStorageInfo* vstorage,
+                             LogBuffer* log_buffer) override;
 
   bool NeedsCompaction(const VersionStorageInfo* vstorage) const override;
 };

db/compaction/compaction_picker_universal.cc

@@ -35,9 +35,7 @@ class UniversalCompactionBuilder {
   UniversalCompactionBuilder(
       const ImmutableOptions& ioptions, const InternalKeyComparator* icmp,
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& existing_snapshots,
-      const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
+      const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
       UniversalCompactionPicker* picker, LogBuffer* log_buffer)
       : ioptions_(ioptions),
         icmp_(icmp),
@@ -46,19 +44,7 @@ class UniversalCompactionBuilder {
         mutable_db_options_(mutable_db_options),
         vstorage_(vstorage),
         picker_(picker),
-        log_buffer_(log_buffer) {
-    assert(icmp_);
-    const auto* ucmp = icmp_->user_comparator();
-    assert(ucmp);
-    // These parameters are only passed when user-defined timestamp is not
-    // enabled.
-    if (ucmp->timestamp_size() == 0) {
-      earliest_snapshot_ = existing_snapshots.empty()
-                               ? kMaxSequenceNumber
-                               : existing_snapshots.at(0);
-      snapshot_checker_ = snapshot_checker;
-    }
-  }
+        log_buffer_(log_buffer) {}
 
   // Form and return the compaction object. The caller owns return object.
   Compaction* PickCompaction();
@@ -66,15 +52,12 @@ class UniversalCompactionBuilder {
  private:
   struct SortedRun {
     SortedRun(int _level, FileMetaData* _file, uint64_t _size,
-              uint64_t _compensated_file_size, bool _being_compacted,
-              bool _level_has_marked_standalone_rangedel)
+              uint64_t _compensated_file_size, bool _being_compacted)
         : level(_level),
           file(_file),
           size(_size),
           compensated_file_size(_compensated_file_size),
-          being_compacted(_being_compacted),
-          level_has_marked_standalone_rangedel(
-              _level_has_marked_standalone_rangedel) {
+          being_compacted(_being_compacted) {
       assert(compensated_file_size > 0);
       assert(level != 0 || file != nullptr);
     }
@@ -96,10 +79,6 @@ class UniversalCompactionBuilder {
     uint64_t size;
     uint64_t compensated_file_size;
     bool being_compacted;
-    // True if this level has any file that is a standalone range deletion file
-    // marked for compaction. Best effort is made to make only deletion
-    // triggered compaction pick this type of file.
-    bool level_has_marked_standalone_rangedel;
   };
 
   // Pick Universal compaction to limit read amplification
@@ -119,11 +98,6 @@ class UniversalCompactionBuilder {
 
   Compaction* PickDeleteTriggeredCompaction();
 
-  // Returns true if this given file (that is marked be compaction) should be
-  // skipped from being picked for now. We do this to best use standalone range
-  // tombstone files.
-  bool ShouldSkipMarkedFile(const FileMetaData* file) const;
-
   // Form a compaction from the sorted run indicated by start_index to the
   // oldest sorted run.
   // The caller is responsible for making sure that those files are not in
@@ -260,18 +234,8 @@ class UniversalCompactionBuilder {
   VersionStorageInfo* vstorage_;
   UniversalCompactionPicker* picker_;
   LogBuffer* log_buffer_;
-  // Optional earliest snapshot at time of compaction picking. This is only
-  // provided if the column family doesn't enable user-defined timestamps.
-  // And this information is only passed to `Compaction` picked by deletion
-  // triggered compaction for possible optimizations.
-  std::optional<SequenceNumber> earliest_snapshot_;
-  const SnapshotChecker* snapshot_checker_;
-  // Mapping from file id to its index in the sorted run for the files that are
-  // marked for compaction. This is only populated when snapshot info is
-  // populated.
-  std::map<uint64_t, size_t> file_marked_for_compaction_to_sorted_run_index_;
 
-  std::vector<UniversalCompactionBuilder::SortedRun> CalculateSortedRuns(
+  static std::vector<UniversalCompactionBuilder::SortedRun> CalculateSortedRuns(
       const VersionStorageInfo& vstorage, int last_level,
       uint64_t* max_run_size);
 
@@ -430,13 +394,11 @@ bool UniversalCompactionPicker::NeedsCompaction(
 
 Compaction* UniversalCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    const MutableDBOptions& mutable_db_options,
-    const std::vector<SequenceNumber>& existing_snapshots,
-    const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
+    const MutableDBOptions& mutable_db_options, VersionStorageInfo* vstorage,
     LogBuffer* log_buffer) {
-  UniversalCompactionBuilder builder(
-      ioptions_, icmp_, cf_name, mutable_cf_options, mutable_db_options,
-      existing_snapshots, snapshot_checker, vstorage, this, log_buffer);
+  UniversalCompactionBuilder builder(ioptions_, icmp_, cf_name,
+                                     mutable_cf_options, mutable_db_options,
+                                     vstorage, this, log_buffer);
   return builder.PickCompaction();
 }
 
@@ -486,20 +448,14 @@ UniversalCompactionBuilder::CalculateSortedRuns(
   *max_run_size = 0;
   std::vector<UniversalCompactionBuilder::SortedRun> ret;
   for (FileMetaData* f : vstorage.LevelFiles(0)) {
-    if (earliest_snapshot_.has_value() && f->marked_for_compaction) {
-      file_marked_for_compaction_to_sorted_run_index_.emplace(f->fd.GetNumber(),
-                                                              ret.size());
-    }
-    ret.emplace_back(
-        0, f, f->fd.GetFileSize(), f->compensated_file_size, f->being_compacted,
-        f->marked_for_compaction && f->FileIsStandAloneRangeTombstone());
+    ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
+                     f->being_compacted);
     *max_run_size = std::max(*max_run_size, f->fd.GetFileSize());
   }
   for (int level = 1; level <= last_level; level++) {
     uint64_t total_compensated_size = 0U;
     uint64_t total_size = 0U;
     bool being_compacted = false;
-    bool level_has_marked_standalone_rangedel = false;
     for (FileMetaData* f : vstorage.LevelFiles(level)) {
       total_compensated_size += f->compensated_file_size;
       total_size += f->fd.GetFileSize();
@@ -511,57 +467,16 @@ UniversalCompactionBuilder::CalculateSortedRuns(
       if (f->being_compacted) {
         being_compacted = f->being_compacted;
       }
-      level_has_marked_standalone_rangedel =
-          level_has_marked_standalone_rangedel ||
-          (f->marked_for_compaction && f->FileIsStandAloneRangeTombstone());
-      if (earliest_snapshot_.has_value() && f->marked_for_compaction) {
-        file_marked_for_compaction_to_sorted_run_index_.emplace(
-            f->fd.GetNumber(), ret.size());
-      }
     }
     if (total_compensated_size > 0) {
       ret.emplace_back(level, nullptr, total_size, total_compensated_size,
-                       being_compacted, level_has_marked_standalone_rangedel);
+                       being_compacted);
     }
     *max_run_size = std::max(*max_run_size, total_size);
   }
   return ret;
 }
 
-bool UniversalCompactionBuilder::ShouldSkipMarkedFile(
-    const FileMetaData* file) const {
-  assert(file->marked_for_compaction);
-  if (!earliest_snapshot_.has_value()) {
-    return false;
-  }
-  if (!file->FileIsStandAloneRangeTombstone()) {
-    return false;
-  }
-  // Skip until earliest snapshot advances at or above this standalone range
-  // tombstone file. `DB::ReleaseSnapshot` will re-examine and schedule
-  // compaction for it.
-  if (!DataIsDefinitelyInSnapshot(file->fd.largest_seqno,
-                                  earliest_snapshot_.value(),
-                                  snapshot_checker_)) {
-    return true;
-  }
-
-  auto iter = file_marked_for_compaction_to_sorted_run_index_.find(
-      file->fd.GetNumber());
-  assert(iter != file_marked_for_compaction_to_sorted_run_index_.end());
-  size_t idx = iter->second;
-  const SortedRun* succeeding_sorted_run =
-      idx < sorted_runs_.size() - 1 ? &sorted_runs_[idx + 1] : nullptr;
-  // Marked standalone range tombstone file is best used if it's in the start
-  // input level. Skip to let that compaction happen first.
-  if (succeeding_sorted_run &&
-      succeeding_sorted_run->level_has_marked_standalone_rangedel) {
-    return true;
-  }
-
-  return false;
-}
-
 // Universal style of compaction. Pick files that are contiguous in
 // time-range to compact.
 Compaction* UniversalCompactionBuilder::PickCompaction() {
@@ -665,8 +580,7 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
         // Get the total number of sorted runs that are not being compacted
         int num_sr_not_compacted = 0;
         for (size_t i = 0; i < sorted_runs_.size(); i++) {
-          if (sorted_runs_[i].being_compacted == false &&
-              !sorted_runs_[i].level_has_marked_standalone_rangedel) {
+          if (sorted_runs_[i].being_compacted == false) {
             num_sr_not_compacted++;
           }
         }
@@ -829,24 +743,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
     for (sr = nullptr; loop < sorted_runs_.size(); loop++) {
       sr = &sorted_runs_[loop];
 
-      if (!sr->being_compacted && !sr->level_has_marked_standalone_rangedel) {
+      if (!sr->being_compacted) {
         candidate_count = 1;
         break;
       }
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf));
-      if (sr->being_compacted) {
-        ROCKS_LOG_BUFFER(log_buffer_,
-                         "[%s] Universal: %s"
-                         "[%d] being compacted, skipping",
-                         cf_name_.c_str(), file_num_buf, loop);
-      } else if (sr->level_has_marked_standalone_rangedel) {
-        ROCKS_LOG_BUFFER(log_buffer_,
-                         "[%s] Universal: %s"
-                         "[%d] has standalone range tombstone files marked for "
-                         "compaction, skipping",
-                         cf_name_.c_str(), file_num_buf, loop);
-      }
+      ROCKS_LOG_BUFFER(log_buffer_,
+                       "[%s] Universal: %s"
+                       "[%d] being compacted, skipping",
+                       cf_name_.c_str(), file_num_buf, loop);
 
       sr = nullptr;
     }
@@ -867,8 +773,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
          candidate_count < max_files_to_compact && i < sorted_runs_.size();
          i++) {
       const SortedRun* succeeding_sr = &sorted_runs_[i];
-      if (succeeding_sr->being_compacted ||
-          succeeding_sr->level_has_marked_standalone_rangedel) {
+      if (succeeding_sr->being_compacted) {
         break;
       }
       // Pick files if the total/last candidate file size (increased by the
@@ -1018,8 +923,6 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
                                               output_level, enable_compression),
                         mutable_cf_options_.default_write_temperature,
                         /* max_subcompactions */ 0, grandparents,
-                        /* earliest_snapshot */ std::nullopt,
-                        /* snapshot_checker */ nullptr,
                         /* is manual */ false, /* trim_ts */ "", score_,
                         false /* deletion_compaction */,
                         /* l0_files_might_overlap */ true, compaction_reason);
@@ -1036,8 +939,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
   const size_t end_index = ShouldSkipLastSortedRunForSizeAmpCompaction()
                                ? sorted_runs_.size() - 2
                                : sorted_runs_.size() - 1;
-  if (sorted_runs_[end_index].being_compacted ||
-      sorted_runs_[end_index].level_has_marked_standalone_rangedel) {
+  if (sorted_runs_[end_index].being_compacted) {
     return nullptr;
   }
   const uint64_t base_sr_size = sorted_runs_[end_index].size;
@@ -1048,23 +950,14 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
   // Get longest span (i.e, [start_index, end_index]) of available sorted runs
   while (start_index > 0) {
     const SortedRun* sr = &sorted_runs_[start_index - 1];
-    if (sr->being_compacted || sr->level_has_marked_standalone_rangedel) {
+    if (sr->being_compacted) {
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-      if (sr->being_compacted) {
-        ROCKS_LOG_BUFFER(
-            log_buffer_,
-            "[%s] Universal: stopping at sorted run undergoing compaction: "
-            "%s[%" ROCKSDB_PRIszt "]",
-            cf_name_.c_str(), file_num_buf, start_index - 1);
-      } else if (sr->level_has_marked_standalone_rangedel) {
-        ROCKS_LOG_BUFFER(
-            log_buffer_,
-            "[%s] Universal: stopping at sorted run that has standalone range "
-            "tombstone files marked for compaction: "
-            "%s[%" ROCKSDB_PRIszt "]",
-            cf_name_.c_str(), file_num_buf, start_index - 1);
-      }
+      ROCKS_LOG_BUFFER(
+          log_buffer_,
+          "[%s] Universal: stopping at sorted run undergoing compaction: "
+          "%s[%" ROCKSDB_PRIszt "]",
+          cf_name_.c_str(), file_num_buf, start_index - 1);
       break;
     }
     candidate_size += sr->compensated_file_size;
@@ -1364,10 +1257,7 @@ Compaction* UniversalCompactionBuilder::PickIncrementalForReduceSizeAmp(
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level,
                             true /* enable_compression */),
       mutable_cf_options_.default_write_temperature,
-      /* max_subcompactions */ 0, /* grandparents */ {},
-      /* earliest_snapshot */ std::nullopt,
-      /* snapshot_checker */ nullptr,
-      /* is manual */ false,
+      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
       /* trim_ts */ "", score_, false /* deletion_compaction */,
       /* l0_files_might_overlap */ true,
       CompactionReason::kUniversalSizeAmplification);
@@ -1398,7 +1288,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
         continue;
       }
       FileMetaData* f = vstorage_->LevelFiles(0)[loop];
-      if (f->marked_for_compaction && !ShouldSkipMarkedFile(f)) {
+      if (f->marked_for_compaction) {
         start_level_inputs.files.push_back(f);
         start_index =
             static_cast<int>(loop);  // Consider this as the first candidate.
@@ -1412,7 +1302,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
 
     for (size_t loop = start_index + 1; loop < sorted_runs_.size(); loop++) {
       SortedRun* sr = &sorted_runs_[loop];
-      if (sr->being_compacted || sr->level_has_marked_standalone_rangedel) {
+      if (sr->being_compacted) {
         break;
       }
 
@@ -1431,10 +1321,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
     // leveled. We pick one of the files marked for compaction and compact with
     // overlapping files in the adjacent level.
     picker_->PickFilesMarkedForCompaction(cf_name_, vstorage_, &start_level,
-                                          &output_level, &start_level_inputs,
-                                          [this](const FileMetaData* file) {
-                                            return ShouldSkipMarkedFile(file);
-                                          });
+                                          &output_level, &start_level_inputs);
     if (start_level_inputs.empty()) {
       return nullptr;
     }
@@ -1514,9 +1401,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
       GetCompressionType(vstorage_, mutable_cf_options_, output_level, 1),
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level),
       mutable_cf_options_.default_write_temperature,
-      /* max_subcompactions */ 0, grandparents, earliest_snapshot_,
-      snapshot_checker_,
-      /* is manual */ false,
+      /* max_subcompactions */ 0, grandparents, /* is manual */ false,
       /* trim_ts */ "", score_, false /* deletion_compaction */,
       /* l0_files_might_overlap */ true,
       CompactionReason::kFilesMarkedForCompaction);
@@ -1609,10 +1494,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionWithSortedRunRange(
       GetCompressionOptions(mutable_cf_options_, vstorage_, output_level,
                             true /* enable_compression */),
       mutable_cf_options_.default_write_temperature,
-      /* max_subcompactions */ 0, /* grandparents */ {},
-      /* earliest_snapshot */ std::nullopt,
-      /* snapshot_checker */ nullptr,
-      /* is manual */ false,
+      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
       /* trim_ts */ "", score_, false /* deletion_compaction */,
       /* l0_files_might_overlap */ true, compaction_reason);
 }
@@ -1633,8 +1515,7 @@ Compaction* UniversalCompactionBuilder::PickPeriodicCompaction() {
   // included in the compaction.
 
   size_t start_index = sorted_runs_.size();
-  while (start_index > 0 && !sorted_runs_[start_index - 1].being_compacted &&
-         !sorted_runs_[start_index - 1].level_has_marked_standalone_rangedel) {
+  while (start_index > 0 && !sorted_runs_[start_index - 1].being_compacted) {
     start_index--;
   }
   if (start_index == sorted_runs_.size()) {

db/compaction/compaction_picker_universal.h

@@ -10,7 +10,6 @@
 #pragma once
 
 #include "db/compaction/compaction_picker.h"
-#include "db/snapshot_checker.h"
 
 namespace ROCKSDB_NAMESPACE {
 class UniversalCompactionPicker : public CompactionPicker {
@@ -18,12 +17,11 @@ class UniversalCompactionPicker : public CompactionPicker {
   UniversalCompactionPicker(const ImmutableOptions& ioptions,
                             const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
-  Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      const MutableDBOptions& mutable_db_options,
-      const std::vector<SequenceNumber>& existing_snapshots,
-      const SnapshotChecker* snapshot_checker, VersionStorageInfo* vstorage,
-      LogBuffer* log_buffer) override;
+  Compaction* PickCompaction(const std::string& cf_name,
+                             const MutableCFOptions& mutable_cf_options,
+                             const MutableDBOptions& mutable_db_options,
+                             VersionStorageInfo* vstorage,
+                             LogBuffer* log_buffer) override;
   int MaxOutputLevel() const override { return NumberLevels() - 1; }
 
   bool NeedsCompaction(const VersionStorageInfo* vstorage) const override;

db/compaction/compaction_service_job.cc

@@ -39,8 +39,12 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
           MakeTableFileName(file->fd.GetNumber()));
     }
   }
-
-  compaction_input.cf_name = compaction->column_family_data()->GetName();
+  compaction_input.column_family.name =
+      compaction->column_family_data()->GetName();
+  compaction_input.column_family.options =
+      compaction->column_family_data()->GetLatestCFOptions();
+  compaction_input.db_options =
+      BuildDBOptions(db_options_, mutable_db_options_copy_);
   compaction_input.snapshots = existing_snapshots_;
   compaction_input.has_begin = sub_compact->start.has_value();
   compaction_input.begin =
@@ -48,14 +52,6 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
   compaction_input.has_end = sub_compact->end.has_value();
   compaction_input.end =
       compaction_input.has_end ? sub_compact->end->ToString() : "";
-  compaction_input.options_file_number =
-      sub_compact->compaction->input_version()
-          ->version_set()
-          ->options_file_number();
-
-  TEST_SYNC_POINT_CALLBACK(
-      "CompactionServiceJob::ProcessKeyValueCompactionWithCompactionService",
-      &compaction_input);
 
   std::string compaction_input_binary;
   Status s = compaction_input.Write(&compaction_input_binary);
@@ -74,13 +70,10 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
   ROCKS_LOG_INFO(
       db_options_.info_log,
       "[%s] [JOB %d] Starting remote compaction (output level: %d): %s",
-      compaction->column_family_data()->GetName().c_str(), job_id_,
+      compaction_input.column_family.name.c_str(), job_id_,
       compaction_input.output_level, input_files_oss.str().c_str());
-  CompactionServiceJobInfo info(
-      dbname_, db_id_, db_session_id_, GetCompactionId(sub_compact),
-      thread_pri_, compaction->compaction_reason(),
-      compaction->is_full_compaction(), compaction->is_manual_compaction(),
-      compaction->bottommost_level());
+  CompactionServiceJobInfo info(dbname_, db_id_, db_session_id_,
+                                GetCompactionId(sub_compact), thread_pri_);
   CompactionServiceScheduleResponse response =
       db_options_.compaction_service->Schedule(info, compaction_input_binary);
   switch (response.status) {
@@ -91,14 +84,13 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
           "CompactionService failed to schedule a remote compaction job.");
       ROCKS_LOG_WARN(db_options_.info_log,
                      "[%s] [JOB %d] Remote compaction failed to start.",
-                     compaction->column_family_data()->GetName().c_str(),
-                     job_id_);
+                     compaction_input.column_family.name.c_str(), job_id_);
       return response.status;
     case CompactionServiceJobStatus::kUseLocal:
       ROCKS_LOG_INFO(
           db_options_.info_log,
           "[%s] [JOB %d] Remote compaction fallback to local by API (Schedule)",
-          compaction->column_family_data()->GetName().c_str(), job_id_);
+          compaction_input.column_family.name.c_str(), job_id_);
       return response.status;
     default:
       assert(false);  // unknown status
@@ -107,7 +99,7 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
 
   ROCKS_LOG_INFO(db_options_.info_log,
                  "[%s] [JOB %d] Waiting for remote compaction...",
-                 compaction->column_family_data()->GetName().c_str(), job_id_);
+                 compaction_input.column_family.name.c_str(), job_id_);
   std::string compaction_result_binary;
   CompactionServiceJobStatus compaction_status =
       db_options_.compaction_service->Wait(response.scheduled_job_id,
@@ -117,7 +109,7 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     ROCKS_LOG_INFO(
         db_options_.info_log,
         "[%s] [JOB %d] Remote compaction fallback to local by API (Wait)",
-        compaction->column_family_data()->GetName().c_str(), job_id_);
+        compaction_input.column_family.name.c_str(), job_id_);
     return compaction_status;
   }
 
@@ -142,19 +134,15 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
           "result is returned).");
       compaction_result.status.PermitUncheckedError();
     }
-    ROCKS_LOG_WARN(
-        db_options_.info_log, "[%s] [JOB %d] Remote compaction failed.",
-        compaction->column_family_data()->GetName().c_str(), job_id_);
+    ROCKS_LOG_WARN(db_options_.info_log,
+                   "[%s] [JOB %d] Remote compaction failed.",
+                   compaction_input.column_family.name.c_str(), job_id_);
     return compaction_status;
   }
 
-  // CompactionServiceJobStatus::kSuccess was returned, but somehow we failed to
-  // read the result. Consider this as an installation failure
   if (!s.ok()) {
     sub_compact->status = s;
     compaction_result.status.PermitUncheckedError();
-    db_options_.compaction_service->OnInstallation(
-        response.scheduled_job_id, CompactionServiceJobStatus::kFailure);
     return CompactionServiceJobStatus::kFailure;
   }
   sub_compact->status = compaction_result.status;
@@ -166,14 +154,18 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     is_first_one = false;
   }
 
-  ROCKS_LOG_INFO(
-      db_options_.info_log,
-      "[%s] [JOB %d] Received remote compaction result, output path: "
-      "%s, files: %s",
-      compaction->column_family_data()->GetName().c_str(), job_id_,
-      compaction_result.output_path.c_str(), output_files_oss.str().c_str());
+  ROCKS_LOG_INFO(db_options_.info_log,
+                 "[%s] [JOB %d] Receive remote compaction result, output path: "
+                 "%s, files: %s",
+                 compaction_input.column_family.name.c_str(), job_id_,
+                 compaction_result.output_path.c_str(),
+                 output_files_oss.str().c_str());
+
+  if (!s.ok()) {
+    sub_compact->status = s;
+    return CompactionServiceJobStatus::kFailure;
+  }
 
-  // Installation Starts
   for (const auto& file : compaction_result.output_files) {
     uint64_t file_num = versions_->NewFileNumber();
     auto src_file = compaction_result.output_path + "/" + file.file_name;
@@ -182,8 +174,6 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     s = fs_->RenameFile(src_file, tgt_file, IOOptions(), nullptr);
     if (!s.ok()) {
       sub_compact->status = s;
-      db_options_.compaction_service->OnInstallation(
-          response.scheduled_job_id, CompactionServiceJobStatus::kFailure);
       return CompactionServiceJobStatus::kFailure;
     }
 
@@ -192,8 +182,6 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     s = fs_->GetFileSize(tgt_file, IOOptions(), &file_size, nullptr);
     if (!s.ok()) {
       sub_compact->status = s;
-      db_options_.compaction_service->OnInstallation(
-          response.scheduled_job_id, CompactionServiceJobStatus::kFailure);
       return CompactionServiceJobStatus::kFailure;
     }
     meta.fd = FileDescriptor(file_num, compaction->output_path_id(), file_size,
@@ -203,8 +191,6 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     meta.oldest_ancester_time = file.oldest_ancester_time;
     meta.file_creation_time = file.file_creation_time;
     meta.epoch_number = file.epoch_number;
-    meta.file_checksum = file.file_checksum;
-    meta.file_checksum_func_name = file.file_checksum_func_name;
     meta.marked_for_compaction = file.marked_for_compaction;
     meta.unique_id = file.unique_id;
 
@@ -212,19 +198,14 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     sub_compact->Current().AddOutput(std::move(meta),
                                      cfd->internal_comparator(), false, true,
                                      file.paranoid_hash);
-    sub_compact->Current().UpdateTableProperties(file.table_properties);
   }
   sub_compact->compaction_job_stats = compaction_result.stats;
   sub_compact->Current().SetNumOutputRecords(
-      compaction_result.stats.num_output_records);
-  sub_compact->Current().SetNumOutputFiles(
-      compaction_result.stats.num_output_files);
-  sub_compact->Current().AddBytesWritten(compaction_result.bytes_written);
+      compaction_result.num_output_records);
+  sub_compact->Current().SetTotalBytes(compaction_result.total_bytes);
   RecordTick(stats_, REMOTE_COMPACT_READ_BYTES, compaction_result.bytes_read);
   RecordTick(stats_, REMOTE_COMPACT_WRITE_BYTES,
              compaction_result.bytes_written);
-  db_options_.compaction_service->OnInstallation(
-      response.scheduled_job_id, CompactionServiceJobStatus::kSuccess);
   return CompactionServiceJobStatus::kSuccess;
 }
 
@@ -239,18 +220,6 @@ void CompactionServiceCompactionJob::RecordCompactionIOStats() {
   CompactionJob::RecordCompactionIOStats();
 }
 
-void CompactionServiceCompactionJob::UpdateCompactionJobStats(
-    const InternalStats::CompactionStats& stats) const {
-  compaction_job_stats_->elapsed_micros = stats.micros;
-
-  // output information only in remote compaction
-  compaction_job_stats_->total_output_bytes = stats.bytes_written;
-  compaction_job_stats_->total_output_bytes_blob = stats.bytes_written_blob;
-  compaction_job_stats_->num_output_records = stats.num_output_records;
-  compaction_job_stats_->num_output_files = stats.num_output_files;
-  compaction_job_stats_->num_output_files_blob = stats.num_output_files_blob;
-}
-
 CompactionServiceCompactionJob::CompactionServiceCompactionJob(
     int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
     const MutableDBOptions& mutable_db_options, const FileOptions& file_options,
@@ -286,11 +255,11 @@ Status CompactionServiceCompactionJob::Run() {
 
   auto* c = compact_->compaction;
   assert(c->column_family_data() != nullptr);
-  const VersionStorageInfo* storage_info = c->input_version()->storage_info();
-  assert(storage_info);
-  assert(storage_info->NumLevelFiles(compact_->compaction->level()) > 0);
-  write_hint_ = storage_info->CalculateSSTWriteHint(c->output_level());
+  assert(c->column_family_data()->current()->storage_info()->NumLevelFiles(
+             compact_->compaction->level()) > 0);
 
+  write_hint_ =
+      c->column_family_data()->CalculateSSTWriteHint(c->output_level());
   bottommost_level_ = c->bottommost_level();
 
   Slice begin = compaction_input_.begin;
@@ -305,12 +274,7 @@ Status CompactionServiceCompactionJob::Run() {
 
   log_buffer_->FlushBufferToLog();
   LogCompaction();
-
-  compaction_result_->stats.Reset();
-
   const uint64_t start_micros = db_options_.clock->NowMicros();
-  c->GetOrInitInputTableProperties();
-
   // Pick the only sub-compaction we should have
   assert(compact_->sub_compact_states.size() == 1);
   SubcompactionState* sub_compact = compact_->sub_compact_states.data();
@@ -348,32 +312,20 @@ Status CompactionServiceCompactionJob::Run() {
   if (status.ok()) {
     status = io_s;
   }
+  if (status.ok()) {
+    // TODO: Add verify_table()
+  }
+
+  // Finish up all book-keeping to unify the subcompaction results
+  compact_->AggregateCompactionStats(compaction_stats_, *compaction_job_stats_);
+  UpdateCompactionStats();
+  RecordCompactionIOStats();
 
   LogFlush(db_options_.info_log);
   compact_->status = status;
   compact_->status.PermitUncheckedError();
 
-  // Build Compaction Job Stats
-
-  // 1. Aggregate CompactionOutputStats into Internal Compaction Stats
-  // (compaction_stats_) and aggregate Compaction Job Stats
-  // (compaction_job_stats_) from the sub compactions
-  compact_->AggregateCompactionStats(compaction_stats_, *compaction_job_stats_);
-
-  // 2. Update the Output information in the Compaction Job Stats with
-  // aggregated Internal Compaction Stats.
-  UpdateCompactionJobStats(compaction_stats_.stats);
-
-  // 3. Set fields that are not propagated as part of aggregations above
-  compaction_result_->stats.is_manual_compaction = c->is_manual_compaction();
-  compaction_result_->stats.is_full_compaction = c->is_full_compaction();
-  compaction_result_->stats.is_remote_compaction = true;
-
-  // 4. Update IO Stats that are not part of the aggregations above (bytes_read,
-  // bytes_written)
-  RecordCompactionIOStats();
-
-  // Build Output
+  // Build compaction result
   compaction_result_->output_level = compact_->compaction->output_level();
   compaction_result_->output_path = output_path_;
   for (const auto& output_file : sub_compact->GetOutputs()) {
@@ -382,14 +334,16 @@ Status CompactionServiceCompactionJob::Run() {
         MakeTableFileName(meta.fd.GetNumber()), meta.fd.smallest_seqno,
         meta.fd.largest_seqno, meta.smallest.Encode().ToString(),
         meta.largest.Encode().ToString(), meta.oldest_ancester_time,
-        meta.file_creation_time, meta.epoch_number, meta.file_checksum,
-        meta.file_checksum_func_name, output_file.validator.GetHash(),
-        meta.marked_for_compaction, meta.unique_id,
-        output_file.table_properties);
+        meta.file_creation_time, meta.epoch_number,
+        output_file.validator.GetHash(), meta.marked_for_compaction,
+        meta.unique_id);
   }
+  InternalStats::CompactionStatsFull compaction_stats;
+  sub_compact->AggregateCompactionStats(compaction_stats);
+  compaction_result_->num_output_records =
+      compaction_stats.stats.num_output_records;
+  compaction_result_->total_bytes = compaction_stats.TotalBytesWritten();
 
-  TEST_SYNC_POINT_CALLBACK("CompactionServiceCompactionJob::Run:0",
-                           &compaction_result_);
   return status;
 }
 
@@ -442,9 +396,42 @@ static std::unordered_map<std::string, OptionTypeInfo> cfd_type_info = {
 };
 
 static std::unordered_map<std::string, OptionTypeInfo> cs_input_type_info = {
-    {"cf_name",
-     {offsetof(struct CompactionServiceInput, cf_name),
-      OptionType::kEncodedString}},
+    {"column_family",
+     OptionTypeInfo::Struct(
+         "column_family", &cfd_type_info,
+         offsetof(struct CompactionServiceInput, column_family),
+         OptionVerificationType::kNormal, OptionTypeFlags::kNone)},
+    {"db_options",
+     {offsetof(struct CompactionServiceInput, db_options),
+      OptionType::kConfigurable, OptionVerificationType::kNormal,
+      OptionTypeFlags::kNone,
+      [](const ConfigOptions& opts, const std::string& /*name*/,
+         const std::string& value, void* addr) {
+        auto options = static_cast<DBOptions*>(addr);
+        return GetDBOptionsFromString(opts, DBOptions(), value, options);
+      },
+      [](const ConfigOptions& opts, const std::string& /*name*/,
+         const void* addr, std::string* value) {
+        const auto options = static_cast<const DBOptions*>(addr);
+        std::string result;
+        auto status = GetStringFromDBOptions(opts, *options, &result);
+        *value = "{" + result + "}";
+        return status;
+      },
+      [](const ConfigOptions& opts, const std::string& name, const void* addr1,
+         const void* addr2, std::string* mismatch) {
+        const auto this_one = static_cast<const DBOptions*>(addr1);
+        const auto that_one = static_cast<const DBOptions*>(addr2);
+        auto this_conf = DBOptionsAsConfigurable(*this_one);
+        auto that_conf = DBOptionsAsConfigurable(*that_one);
+        std::string mismatch_opt;
+        bool result =
+            this_conf->AreEquivalent(opts, that_conf.get(), &mismatch_opt);
+        if (!result) {
+          *mismatch = name + "." + mismatch_opt;
+        }
+        return result;
+      }}},
     {"snapshots", OptionTypeInfo::Vector<uint64_t>(
                       offsetof(struct CompactionServiceInput, snapshots),
                       OptionVerificationType::kNormal, OptionTypeFlags::kNone,
@@ -472,163 +459,6 @@ static std::unordered_map<std::string, OptionTypeInfo> cs_input_type_info = {
     {"end",
      {offsetof(struct CompactionServiceInput, end), OptionType::kEncodedString,
       OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-    {"options_file_number",
-     {offsetof(struct CompactionServiceInput, options_file_number),
-      OptionType::kUInt64T, OptionVerificationType::kNormal,
-      OptionTypeFlags::kNone}},
-};
-static std::unordered_map<std::string, OptionTypeInfo>
-    table_properties_type_info = {
-        {"orig_file_number",
-         {offsetof(struct TableProperties, orig_file_number),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"data_size",
-         {offsetof(struct TableProperties, data_size), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"index_size",
-         {offsetof(struct TableProperties, index_size), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"index_partitions",
-         {offsetof(struct TableProperties, index_partitions),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"top_level_index_size",
-         {offsetof(struct TableProperties, top_level_index_size),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"index_key_is_user_key",
-         {offsetof(struct TableProperties, index_key_is_user_key),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"index_value_is_delta_encoded",
-         {offsetof(struct TableProperties, index_value_is_delta_encoded),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"filter_size",
-         {offsetof(struct TableProperties, filter_size), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"raw_key_size",
-         {offsetof(struct TableProperties, raw_key_size), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"raw_value_size",
-         {offsetof(struct TableProperties, raw_value_size),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"num_data_blocks",
-         {offsetof(struct TableProperties, num_data_blocks),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"num_entries",
-         {offsetof(struct TableProperties, num_entries), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"num_filter_entries",
-         {offsetof(struct TableProperties, num_filter_entries),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"num_deletions",
-         {offsetof(struct TableProperties, num_deletions), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"num_merge_operands",
-         {offsetof(struct TableProperties, num_merge_operands),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"num_range_deletions",
-         {offsetof(struct TableProperties, num_range_deletions),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"format_version",
-         {offsetof(struct TableProperties, format_version),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"fixed_key_len",
-         {offsetof(struct TableProperties, fixed_key_len), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"column_family_id",
-         {offsetof(struct TableProperties, column_family_id),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"creation_time",
-         {offsetof(struct TableProperties, creation_time), OptionType::kUInt64T,
-          OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-        {"oldest_key_time",
-         {offsetof(struct TableProperties, oldest_key_time),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"file_creation_time",
-         {offsetof(struct TableProperties, file_creation_time),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"slow_compression_estimated_data_size",
-         {offsetof(struct TableProperties,
-                   slow_compression_estimated_data_size),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"fast_compression_estimated_data_size",
-         {offsetof(struct TableProperties,
-                   fast_compression_estimated_data_size),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"external_sst_file_global_seqno_offset",
-         {offsetof(struct TableProperties,
-                   external_sst_file_global_seqno_offset),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"tail_start_offset",
-         {offsetof(struct TableProperties, tail_start_offset),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"user_defined_timestamps_persisted",
-         {offsetof(struct TableProperties, user_defined_timestamps_persisted),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"key_largest_seqno",
-         {offsetof(struct TableProperties, key_largest_seqno),
-          OptionType::kUInt64T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"db_id",
-         {offsetof(struct TableProperties, db_id), OptionType::kEncodedString}},
-        {"db_session_id",
-         {offsetof(struct TableProperties, db_session_id),
-          OptionType::kEncodedString}},
-        {"db_host_id",
-         {offsetof(struct TableProperties, db_host_id),
-          OptionType::kEncodedString}},
-        {"column_family_name",
-         {offsetof(struct TableProperties, column_family_name),
-          OptionType::kEncodedString}},
-        {"filter_policy_name",
-         {offsetof(struct TableProperties, filter_policy_name),
-          OptionType::kEncodedString}},
-        {"comparator_name",
-         {offsetof(struct TableProperties, comparator_name),
-          OptionType::kEncodedString}},
-        {"merge_operator_name",
-         {offsetof(struct TableProperties, merge_operator_name),
-          OptionType::kEncodedString}},
-        {"prefix_extractor_name",
-         {offsetof(struct TableProperties, prefix_extractor_name),
-          OptionType::kEncodedString}},
-        {"property_collectors_names",
-         {offsetof(struct TableProperties, property_collectors_names),
-          OptionType::kEncodedString}},
-        {"compression_name",
-         {offsetof(struct TableProperties, compression_name),
-          OptionType::kEncodedString}},
-        {"compression_options",
-         {offsetof(struct TableProperties, compression_options),
-          OptionType::kEncodedString}},
-        {"seqno_to_time_mapping",
-         {offsetof(struct TableProperties, seqno_to_time_mapping),
-          OptionType::kEncodedString}},
-        {"user_collected_properties",
-         OptionTypeInfo::StringMap(
-             offsetof(struct TableProperties, user_collected_properties),
-             OptionVerificationType::kNormal, OptionTypeFlags::kNone)},
-        {"readable_properties",
-         OptionTypeInfo::StringMap(
-             offsetof(struct TableProperties, readable_properties),
-             OptionVerificationType::kNormal, OptionTypeFlags::kNone)},
 };
 
 static std::unordered_map<std::string, OptionTypeInfo>
@@ -665,14 +495,6 @@ static std::unordered_map<std::string, OptionTypeInfo>
          {offsetof(struct CompactionServiceOutputFile, epoch_number),
           OptionType::kUInt64T, OptionVerificationType::kNormal,
           OptionTypeFlags::kNone}},
-        {"file_checksum",
-         {offsetof(struct CompactionServiceOutputFile, file_checksum),
-          OptionType::kEncodedString, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
-        {"file_checksum_func_name",
-         {offsetof(struct CompactionServiceOutputFile, file_checksum_func_name),
-          OptionType::kEncodedString, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
         {"paranoid_hash",
          {offsetof(struct CompactionServiceOutputFile, paranoid_hash),
           OptionType::kUInt64T, OptionVerificationType::kNormal,
@@ -686,11 +508,6 @@ static std::unordered_map<std::string, OptionTypeInfo>
              offsetof(struct CompactionServiceOutputFile, unique_id),
              OptionVerificationType::kNormal, OptionTypeFlags::kNone,
              {0, OptionType::kUInt64T})},
-        {"table_properties",
-         OptionTypeInfo::Struct(
-             "table_properties", &table_properties_type_info,
-             offsetof(struct CompactionServiceOutputFile, table_properties),
-             OptionVerificationType::kNormal, OptionTypeFlags::kNone)},
 };
 
 static std::unordered_map<std::string, OptionTypeInfo>
@@ -738,10 +555,6 @@ static std::unordered_map<std::string, OptionTypeInfo>
          {offsetof(struct CompactionJobStats, is_manual_compaction),
           OptionType::kBoolean, OptionVerificationType::kNormal,
           OptionTypeFlags::kNone}},
-        {"is_remote_compaction",
-         {offsetof(struct CompactionJobStats, is_remote_compaction),
-          OptionType::kBoolean, OptionVerificationType::kNormal,
-          OptionTypeFlags::kNone}},
         {"total_input_bytes",
          {offsetof(struct CompactionJobStats, total_input_bytes),
           OptionType::kUInt64T, OptionVerificationType::kNormal,
@@ -910,6 +723,14 @@ static std::unordered_map<std::string, OptionTypeInfo> cs_result_type_info = {
      {offsetof(struct CompactionServiceResult, output_path),
       OptionType::kEncodedString, OptionVerificationType::kNormal,
       OptionTypeFlags::kNone}},
+    {"num_output_records",
+     {offsetof(struct CompactionServiceResult, num_output_records),
+      OptionType::kUInt64T, OptionVerificationType::kNormal,
+      OptionTypeFlags::kNone}},
+    {"total_bytes",
+     {offsetof(struct CompactionServiceResult, total_bytes),
+      OptionType::kUInt64T, OptionVerificationType::kNormal,
+      OptionTypeFlags::kNone}},
     {"bytes_read",
      {offsetof(struct CompactionServiceResult, bytes_read),
       OptionType::kUInt64T, OptionVerificationType::kNormal,

db/compaction/compaction_service_test.cc

@@ -3,9 +3,9 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
-#include "rocksdb/utilities/options_util.h"
 #include "table/unique_id_impl.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -21,10 +21,8 @@ class MyTestCompactionService : public CompactionService {
       : db_path_(std::move(db_path)),
         options_(options),
         statistics_(statistics),
-        start_info_("na", "na", "na", 0, Env::TOTAL, CompactionReason::kUnknown,
-                    false, false, false),
-        wait_info_("na", "na", "na", 0, Env::TOTAL, CompactionReason::kUnknown,
-                   false, false, false),
+        start_info_("na", "na", "na", 0, Env::TOTAL),
+        wait_info_("na", "na", "na", 0, Env::TOTAL),
         listeners_(listeners),
         table_properties_collector_factories_(
             std::move(table_properties_collector_factories)) {}
@@ -99,12 +97,8 @@ class MyTestCompactionService : public CompactionService {
     Status s =
         DB::OpenAndCompact(options, db_path_, db_path_ + "/" + scheduled_job_id,
                            compaction_input, result, options_override);
-    {
-      InstrumentedMutexLock l(&mutex_);
-      if (is_override_wait_result_) {
-        *result = override_wait_result_;
-      }
-      result_ = *result;
+    if (is_override_wait_result_) {
+      *result = override_wait_result_;
     }
     compaction_num_.fetch_add(1);
     if (s.ok()) {
@@ -114,11 +108,6 @@ class MyTestCompactionService : public CompactionService {
     }
   }
 
-  void OnInstallation(const std::string& /*scheduled_job_id*/,
-                      CompactionServiceJobStatus status) override {
-    final_updated_status_ = status;
-  }
-
   int GetCompactionNum() { return compaction_num_.load(); }
 
   CompactionServiceJobInfo GetCompactionInfoForStart() { return start_info_; }
@@ -147,14 +136,6 @@ class MyTestCompactionService : public CompactionService {
 
   void SetCanceled(bool canceled) { canceled_ = canceled; }
 
-  void GetResult(CompactionServiceResult* deserialized) {
-    CompactionServiceResult::Read(result_, deserialized).PermitUncheckedError();
-  }
-
-  CompactionServiceJobStatus GetFinalCompactionServiceJobStatus() {
-    return final_updated_status_.load();
-  }
-
  private:
   InstrumentedMutex mutex_;
   std::atomic_int compaction_num_{0};
@@ -172,14 +153,11 @@ class MyTestCompactionService : public CompactionService {
   CompactionServiceJobStatus override_wait_status_ =
       CompactionServiceJobStatus::kFailure;
   bool is_override_wait_result_ = false;
-  std::string result_;
   std::string override_wait_result_;
   std::vector<std::shared_ptr<EventListener>> listeners_;
   std::vector<std::shared_ptr<TablePropertiesCollectorFactory>>
       table_properties_collector_factories_;
   std::atomic_bool canceled_{false};
-  std::atomic<CompactionServiceJobStatus> final_updated_status_{
-      CompactionServiceJobStatus::kUseLocal};
 };
 
 class CompactionServiceTest : public DBTestBase {
@@ -277,8 +255,6 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
 
   auto my_cs = GetCompactionService();
   ASSERT_GE(my_cs->GetCompactionNum(), 1);
-  ASSERT_EQ(CompactionServiceJobStatus::kSuccess,
-            my_cs->GetFinalCompactionServiceJobStatus());
 
   // make sure the compaction statistics is only recorded on the remote side
   ASSERT_GE(compactor_statistics->getTickerCount(COMPACT_WRITE_BYTES), 1);
@@ -342,34 +318,6 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
   ReopenWithColumnFamilies({kDefaultColumnFamilyName, "cf_1", "cf_2", "cf_3"},
                            options);
   ASSERT_GT(verify_passed, 0);
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  if (s.IsAborted()) {
-    ASSERT_NOK(result.status);
-  } else {
-    ASSERT_OK(result.status);
-  }
-  ASSERT_GE(result.stats.elapsed_micros, 1);
-  ASSERT_GE(result.stats.cpu_micros, 1);
-
-  ASSERT_EQ(20, result.stats.num_output_records);
-  ASSERT_EQ(result.output_files.size(), result.stats.num_output_files);
-
-  uint64_t total_size = 0;
-  for (auto output_file : result.output_files) {
-    std::string file_name = result.output_path + "/" + output_file.file_name;
-
-    uint64_t file_size = 0;
-    ASSERT_OK(options.env->GetFileSize(file_name, &file_size));
-    ASSERT_GT(file_size, 0);
-    total_size += file_size;
-  }
-  ASSERT_EQ(total_size, result.stats.total_output_bytes);
-
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_FALSE(result.stats.is_full_compaction);
-
   Close();
 }
 
@@ -408,515 +356,6 @@ TEST_F(CompactionServiceTest, ManualCompaction) {
   ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
   ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
   VerifyTestData();
-
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-}
-
-TEST_F(CompactionServiceTest, PreservedOptionsLocalCompaction) {
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = 2;
-  options.disable_auto_compactions = true;
-  DestroyAndReopen(options);
-
-  Random rnd(301);
-  for (auto i = 0; i < 2; ++i) {
-    for (auto j = 0; j < 10; ++j) {
-      ASSERT_OK(
-          Put("foo" + std::to_string(i * 10 + j), rnd.RandomString(1024)));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::ProcessKeyValueCompaction()::Processing", [&](void* arg) {
-        auto compaction = static_cast<Compaction*>(arg);
-        std::string options_file_name = OptionsFileName(
-            dbname_,
-            compaction->input_version()->version_set()->options_file_number());
-
-        // Change option twice to make sure the very first OPTIONS file gets
-        // purged
-        ASSERT_OK(dbfull()->SetOptions(
-            {{"level0_file_num_compaction_trigger", "4"}}));
-        ASSERT_EQ(4, dbfull()->GetOptions().level0_file_num_compaction_trigger);
-        ASSERT_OK(dbfull()->SetOptions(
-            {{"level0_file_num_compaction_trigger", "6"}}));
-        ASSERT_EQ(6, dbfull()->GetOptions().level0_file_num_compaction_trigger);
-        dbfull()->TEST_DeleteObsoleteFiles();
-
-        // For non-remote compactions, OPTIONS file can be deleted while
-        // using option at the start of the compaction
-        Status s = env_->FileExists(options_file_name);
-        ASSERT_NOK(s);
-        ASSERT_TRUE(s.IsNotFound());
-        // Should be old value
-        ASSERT_EQ(2, compaction->mutable_cf_options()
-                         ->level0_file_num_compaction_trigger);
-        ASSERT_TRUE(dbfull()->min_options_file_numbers_.empty());
-      });
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  Status s = dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_TRUE(s.ok());
-}
-
-TEST_F(CompactionServiceTest, PreservedOptionsRemoteCompaction) {
-  // For non-remote compaction do not preserve options file
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = 2;
-  options.disable_auto_compactions = true;
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-
-  Random rnd(301);
-  for (auto i = 0; i < 2; ++i) {
-    for (auto j = 0; j < 10; ++j) {
-      ASSERT_OK(
-          Put("foo" + std::to_string(i * 10 + j), rnd.RandomString(1024)));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"CompactionServiceTest::OptionsFileChanged",
-        "DBImplSecondary::OpenAndCompact::BeforeLoadingOptions:1"}});
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "DBImplSecondary::OpenAndCompact::BeforeLoadingOptions:0",
-      [&](void* arg) {
-        auto options_file_number = static_cast<uint64_t*>(arg);
-        // Change the option twice before the compaction run
-        ASSERT_OK(dbfull()->SetOptions(
-            {{"level0_file_num_compaction_trigger", "4"}}));
-        ASSERT_EQ(4, dbfull()->GetOptions().level0_file_num_compaction_trigger);
-        ASSERT_TRUE(dbfull()->versions_->options_file_number() >
-                    *options_file_number);
-
-        // Change the option twice before the compaction run
-        ASSERT_OK(dbfull()->SetOptions(
-            {{"level0_file_num_compaction_trigger", "5"}}));
-        ASSERT_EQ(5, dbfull()->GetOptions().level0_file_num_compaction_trigger);
-        ASSERT_TRUE(dbfull()->versions_->options_file_number() >
-                    *options_file_number);
-
-        TEST_SYNC_POINT("CompactionServiceTest::OptionsFileChanged");
-      });
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionServiceJob::ProcessKeyValueCompactionWithCompactionService",
-      [&](void* arg) {
-        auto input = static_cast<CompactionServiceInput*>(arg);
-        std::string options_file_name =
-            OptionsFileName(dbname_, input->options_file_number);
-
-        ASSERT_OK(env_->FileExists(options_file_name));
-        ASSERT_FALSE(dbfull()->min_options_file_numbers_.empty());
-        ASSERT_EQ(dbfull()->min_options_file_numbers_.front(),
-                  input->options_file_number);
-
-        DBOptions db_options;
-        ConfigOptions config_options;
-        std::vector<ColumnFamilyDescriptor> all_column_families;
-        config_options.env = env_;
-        ASSERT_OK(LoadOptionsFromFile(config_options, options_file_name,
-                                      &db_options, &all_column_families));
-        bool has_cf = false;
-        for (auto& cf : all_column_families) {
-          if (cf.name == input->cf_name) {
-            // Should be old value
-            ASSERT_EQ(2, cf.options.level0_file_num_compaction_trigger);
-            has_cf = true;
-          }
-        }
-        ASSERT_TRUE(has_cf);
-      });
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::ProcessKeyValueCompaction()::Processing", [&](void* arg) {
-        auto compaction = static_cast<Compaction*>(arg);
-        ASSERT_EQ(2, compaction->mutable_cf_options()
-                         ->level0_file_num_compaction_trigger);
-      });
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  Status s = dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_TRUE(s.ok());
-
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-}
-
-class EventVerifier : public EventListener {
- public:
-  explicit EventVerifier(uint64_t expected_num_input_records,
-                         size_t expected_num_input_files,
-                         uint64_t expected_num_output_records,
-                         size_t expected_num_output_files,
-                         const std::string& expected_smallest_output_key_prefix,
-                         const std::string& expected_largest_output_key_prefix,
-                         bool expected_is_remote_compaction_on_begin,
-                         bool expected_is_remote_compaction_on_complete)
-      : expected_num_input_records_(expected_num_input_records),
-        expected_num_input_files_(expected_num_input_files),
-        expected_num_output_records_(expected_num_output_records),
-        expected_num_output_files_(expected_num_output_files),
-        expected_smallest_output_key_prefix_(
-            expected_smallest_output_key_prefix),
-        expected_largest_output_key_prefix_(expected_largest_output_key_prefix),
-        expected_is_remote_compaction_on_begin_(
-            expected_is_remote_compaction_on_begin),
-        expected_is_remote_compaction_on_complete_(
-            expected_is_remote_compaction_on_complete) {}
-  void OnCompactionBegin(DB* /*db*/, const CompactionJobInfo& ci) override {
-    ASSERT_EQ(expected_num_input_files_, ci.input_files.size());
-    ASSERT_EQ(expected_num_input_files_, ci.input_file_infos.size());
-    ASSERT_EQ(expected_is_remote_compaction_on_begin_,
-              ci.stats.is_remote_compaction);
-    ASSERT_TRUE(ci.stats.is_manual_compaction);
-    ASSERT_FALSE(ci.stats.is_full_compaction);
-  }
-  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
-    ASSERT_GT(ci.stats.elapsed_micros, 0);
-    ASSERT_GT(ci.stats.cpu_micros, 0);
-    ASSERT_EQ(expected_num_input_records_, ci.stats.num_input_records);
-    ASSERT_EQ(expected_num_input_files_, ci.stats.num_input_files);
-    ASSERT_EQ(expected_num_output_records_, ci.stats.num_output_records);
-    ASSERT_EQ(expected_num_output_files_, ci.stats.num_output_files);
-    ASSERT_EQ(expected_smallest_output_key_prefix_,
-              ci.stats.smallest_output_key_prefix);
-    ASSERT_EQ(expected_largest_output_key_prefix_,
-              ci.stats.largest_output_key_prefix);
-    ASSERT_GT(ci.stats.total_input_bytes, 0);
-    ASSERT_GT(ci.stats.total_output_bytes, 0);
-    ASSERT_EQ(ci.stats.num_input_records,
-              ci.stats.num_output_records + ci.stats.num_records_replaced);
-    ASSERT_EQ(expected_is_remote_compaction_on_complete_,
-              ci.stats.is_remote_compaction);
-    ASSERT_TRUE(ci.stats.is_manual_compaction);
-    ASSERT_FALSE(ci.stats.is_full_compaction);
-  }
-
- private:
-  uint64_t expected_num_input_records_;
-  size_t expected_num_input_files_;
-  uint64_t expected_num_output_records_;
-  size_t expected_num_output_files_;
-  std::string expected_smallest_output_key_prefix_;
-  std::string expected_largest_output_key_prefix_;
-  bool expected_is_remote_compaction_on_begin_;
-  bool expected_is_remote_compaction_on_complete_;
-};
-
-TEST_F(CompactionServiceTest, VerifyStats) {
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  auto event_verifier = std::make_shared<EventVerifier>(
-      30 /* expected_num_input_records */, 3 /* expected_num_input_files */,
-      20 /* expected_num_output_records */, 1 /* expected_num_output_files */,
-      "key00000" /* expected_smallest_output_key_prefix */,
-      "key00001" /* expected_largest_output_key_prefix */,
-      true /* expected_is_remote_compaction_on_begin */,
-      true /* expected_is_remote_compaction_on_complete */);
-  options.listeners.push_back(event_verifier);
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-
-  std::string start_str = Key(0);
-  std::string end_str = Key(1);
-  Slice start(start_str);
-  Slice end(end_str);
-  uint64_t comp_num = my_cs->GetCompactionNum();
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), &start, &end));
-  ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
-  VerifyTestData();
-
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-}
-
-TEST_F(CompactionServiceTest, VerifyStatsLocalFallback) {
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  auto event_verifier = std::make_shared<EventVerifier>(
-      30 /* expected_num_input_records */, 3 /* expected_num_input_files */,
-      20 /* expected_num_output_records */, 1 /* expected_num_output_files */,
-      "key00000" /* expected_smallest_output_key_prefix */,
-      "key00001" /* expected_largest_output_key_prefix */,
-      true /* expected_is_remote_compaction_on_begin */,
-      false /* expected_is_remote_compaction_on_complete */);
-  options.listeners.push_back(event_verifier);
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-  my_cs->OverrideStartStatus(CompactionServiceJobStatus::kUseLocal);
-
-  std::string start_str = Key(0);
-  std::string end_str = Key(1);
-  Slice start(start_str);
-  Slice end(end_str);
-  uint64_t comp_num = my_cs->GetCompactionNum();
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), &start, &end));
-  // Remote Compaction did not happen
-  ASSERT_EQ(my_cs->GetCompactionNum(), comp_num);
-  VerifyTestData();
-}
-
-TEST_F(CompactionServiceTest, CorruptedOutput) {
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-
-  std::string start_str = Key(15);
-  std::string end_str = Key(45);
-  Slice start(start_str);
-  Slice end(end_str);
-  uint64_t comp_num = my_cs->GetCompactionNum();
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionServiceCompactionJob::Run:0", [&](void* arg) {
-        CompactionServiceResult* compaction_result =
-            *(static_cast<CompactionServiceResult**>(arg));
-        ASSERT_TRUE(compaction_result != nullptr &&
-                    !compaction_result->output_files.empty());
-        // Corrupt files here
-        for (const auto& output_file : compaction_result->output_files) {
-          std::string file_name =
-              compaction_result->output_path + "/" + output_file.file_name;
-
-          uint64_t file_size = 0;
-          Status s = options.env->GetFileSize(file_name, &file_size);
-          ASSERT_OK(s);
-          ASSERT_GT(file_size, 0);
-
-          ASSERT_OK(test::CorruptFile(env_, file_name, 0,
-                                      static_cast<int>(file_size),
-                                      true /* verifyChecksum */));
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  // CompactRange() should fail
-  Status s = db_->CompactRange(CompactRangeOptions(), &start, &end);
-  ASSERT_NOK(s);
-  ASSERT_TRUE(s.IsCorruption());
-
-  ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  // On the worker side, the compaction is considered success
-  // Verification is done on the primary side
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-}
-
-TEST_F(CompactionServiceTest, CorruptedOutputParanoidFileCheck) {
-  for (bool paranoid_file_check_enabled : {false, true}) {
-    SCOPED_TRACE("paranoid_file_check_enabled=" +
-                 std::to_string(paranoid_file_check_enabled));
-
-    Options options = CurrentOptions();
-    Destroy(options);
-    options.disable_auto_compactions = true;
-    options.paranoid_file_checks = paranoid_file_check_enabled;
-    ReopenWithCompactionService(&options);
-    GenerateTestData();
-
-    auto my_cs = GetCompactionService();
-
-    std::string start_str = Key(15);
-    std::string end_str = Key(45);
-    Slice start(start_str);
-    Slice end(end_str);
-    uint64_t comp_num = my_cs->GetCompactionNum();
-
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-        "CompactionServiceCompactionJob::Run:0", [&](void* arg) {
-          CompactionServiceResult* compaction_result =
-              *(static_cast<CompactionServiceResult**>(arg));
-          ASSERT_TRUE(compaction_result != nullptr &&
-                      !compaction_result->output_files.empty());
-          // Corrupt files here
-          for (const auto& output_file : compaction_result->output_files) {
-            std::string file_name =
-                compaction_result->output_path + "/" + output_file.file_name;
-
-            // Corrupt very small range of bytes. This corruption is so small
-            // that this isn't caught by default light-weight check
-            ASSERT_OK(test::CorruptFile(env_, file_name, 0, 1,
-                                        false /* verifyChecksum */));
-          }
-        });
-    SyncPoint::GetInstance()->EnableProcessing();
-
-    Status s = db_->CompactRange(CompactRangeOptions(), &start, &end);
-    if (paranoid_file_check_enabled) {
-      ASSERT_NOK(s);
-      ASSERT_EQ(Status::Corruption("Paranoid checksums do not match"), s);
-    } else {
-      // CompactRange() goes through if paranoid file check is not enabled
-      ASSERT_OK(s);
-    }
-
-    ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
-
-    SyncPoint::GetInstance()->DisableProcessing();
-    SyncPoint::GetInstance()->ClearAllCallBacks();
-
-    // On the worker side, the compaction is considered success
-    // Verification is done on the primary side
-    CompactionServiceResult result;
-    my_cs->GetResult(&result);
-    ASSERT_OK(result.status);
-    ASSERT_TRUE(result.stats.is_manual_compaction);
-    ASSERT_TRUE(result.stats.is_remote_compaction);
-  }
-}
-
-TEST_F(CompactionServiceTest, TruncatedOutput) {
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-
-  std::string start_str = Key(15);
-  std::string end_str = Key(45);
-  Slice start(start_str);
-  Slice end(end_str);
-  uint64_t comp_num = my_cs->GetCompactionNum();
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionServiceCompactionJob::Run:0", [&](void* arg) {
-        CompactionServiceResult* compaction_result =
-            *(static_cast<CompactionServiceResult**>(arg));
-        ASSERT_TRUE(compaction_result != nullptr &&
-                    !compaction_result->output_files.empty());
-        // Truncate files here
-        for (const auto& output_file : compaction_result->output_files) {
-          std::string file_name =
-              compaction_result->output_path + "/" + output_file.file_name;
-
-          uint64_t file_size = 0;
-          Status s = options.env->GetFileSize(file_name, &file_size);
-          ASSERT_OK(s);
-          ASSERT_GT(file_size, 0);
-
-          ASSERT_OK(test::TruncateFile(env_, file_name, file_size / 2));
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  // CompactRange() should fail
-  Status s = db_->CompactRange(CompactRangeOptions(), &start, &end);
-  ASSERT_NOK(s);
-  ASSERT_TRUE(s.IsCorruption());
-
-  ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  // On the worker side, the compaction is considered success
-  // Verification is done on the primary side
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
-}
-
-TEST_F(CompactionServiceTest, CustomFileChecksum) {
-  Options options = CurrentOptions();
-  options.file_checksum_gen_factory = GetFileChecksumGenCrc32cFactory();
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-
-  std::string start_str = Key(15);
-  std::string end_str = Key(45);
-  Slice start(start_str);
-  Slice end(end_str);
-  uint64_t comp_num = my_cs->GetCompactionNum();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionServiceCompactionJob::Run:0", [&](void* arg) {
-        CompactionServiceResult* compaction_result =
-            *(static_cast<CompactionServiceResult**>(arg));
-        ASSERT_TRUE(compaction_result != nullptr &&
-                    !compaction_result->output_files.empty());
-        // Validate Checksum files here
-        for (const auto& output_file : compaction_result->output_files) {
-          std::string file_name =
-              compaction_result->output_path + "/" + output_file.file_name;
-
-          FileChecksumGenContext gen_context;
-          gen_context.file_name = file_name;
-          std::unique_ptr<FileChecksumGenerator> file_checksum_gen =
-              options.file_checksum_gen_factory->CreateFileChecksumGenerator(
-                  gen_context);
-
-          std::unique_ptr<SequentialFile> file_reader;
-          uint64_t file_size = 0;
-          Status s = options.env->GetFileSize(file_name, &file_size);
-          ASSERT_OK(s);
-          ASSERT_GT(file_size, 0);
-
-          s = options.env->NewSequentialFile(file_name, &file_reader,
-                                             EnvOptions());
-          ASSERT_OK(s);
-
-          Slice result;
-          std::unique_ptr<char[]> scratch(new char[file_size]);
-          s = file_reader->Read(file_size, &result, scratch.get());
-          ASSERT_OK(s);
-
-          file_checksum_gen->Update(scratch.get(), result.size());
-          file_checksum_gen->Finalize();
-
-          // Verify actual checksum and the func name
-          ASSERT_EQ(file_checksum_gen->Name(),
-                    output_file.file_checksum_func_name);
-          ASSERT_EQ(file_checksum_gen->GetChecksum(),
-                    output_file.file_checksum);
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), &start, &end));
-  ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  CompactionServiceResult result;
-  my_cs->GetResult(&result);
-  ASSERT_OK(result.status);
-  ASSERT_TRUE(result.stats.is_manual_compaction);
-  ASSERT_TRUE(result.stats.is_remote_compaction);
 }
 
 TEST_F(CompactionServiceTest, CancelCompactionOnRemoteSide) {
@@ -998,8 +437,6 @@ TEST_F(CompactionServiceTest, InvalidResult) {
   Slice end(end_str);
   Status s = db_->CompactRange(CompactRangeOptions(), &start, &end);
   ASSERT_FALSE(s.ok());
-  ASSERT_EQ(CompactionServiceJobStatus::kFailure,
-            my_cs->GetFinalCompactionServiceJobStatus());
 }
 
 TEST_F(CompactionServiceTest, SubCompaction) {
@@ -1149,20 +586,11 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
                               {file.db_path + "/" + file.name}, 2));
   info = my_cs->GetCompactionInfoForStart();
   ASSERT_EQ(Env::USER, info.priority);
-  ASSERT_EQ(CompactionReason::kManualCompaction, info.compaction_reason);
-  ASSERT_EQ(true, info.is_manual_compaction);
-  ASSERT_EQ(false, info.is_full_compaction);
-  ASSERT_EQ(true, info.bottommost_level);
   info = my_cs->GetCompactionInfoForWait();
   ASSERT_EQ(Env::USER, info.priority);
-  ASSERT_EQ(CompactionReason::kManualCompaction, info.compaction_reason);
-  ASSERT_EQ(true, info.is_manual_compaction);
-  ASSERT_EQ(false, info.is_full_compaction);
-  ASSERT_EQ(true, info.bottommost_level);
 
   // Test priority BOTTOM
   env_->SetBackgroundThreads(1, Env::BOTTOM);
-  // This will set bottommost_level = true but is_full_compaction = false
   options.num_levels = 2;
   ReopenWithCompactionService(&options);
   my_cs =
@@ -1185,71 +613,9 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
   }
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
   info = my_cs->GetCompactionInfoForStart();
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum, info.compaction_reason);
-  ASSERT_EQ(false, info.is_manual_compaction);
-  ASSERT_EQ(false, info.is_full_compaction);
-  ASSERT_EQ(true, info.bottommost_level);
   ASSERT_EQ(Env::BOTTOM, info.priority);
   info = my_cs->GetCompactionInfoForWait();
   ASSERT_EQ(Env::BOTTOM, info.priority);
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum, info.compaction_reason);
-  ASSERT_EQ(false, info.is_manual_compaction);
-  ASSERT_EQ(false, info.is_full_compaction);
-  ASSERT_EQ(true, info.bottommost_level);
-
-  // Test Non-Bottommost Level
-  options.num_levels = 4;
-  ReopenWithCompactionService(&options);
-  my_cs =
-      static_cast_with_check<MyTestCompactionService>(GetCompactionService());
-
-  for (int i = 0; i < options.level0_file_num_compaction_trigger; i++) {
-    for (int j = 0; j < 10; j++) {
-      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value_new_new" + std::to_string(key_id)));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  info = my_cs->GetCompactionInfoForStart();
-  ASSERT_EQ(false, info.is_manual_compaction);
-  ASSERT_EQ(false, info.is_full_compaction);
-  ASSERT_EQ(false, info.bottommost_level);
-  info = my_cs->GetCompactionInfoForWait();
-  ASSERT_EQ(false, info.is_manual_compaction);
-  ASSERT_EQ(false, info.is_full_compaction);
-  ASSERT_EQ(false, info.bottommost_level);
-
-  // Test Full Compaction + Bottommost Level
-  options.num_levels = 6;
-  ReopenWithCompactionService(&options);
-  my_cs =
-      static_cast_with_check<MyTestCompactionService>(GetCompactionService());
-
-  for (int i = 0; i < 20; i++) {
-    for (int j = 0; j < 10; j++) {
-      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value_new_new" + std::to_string(key_id)));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  CompactRangeOptions cro;
-  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
-  ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
-
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  info = my_cs->GetCompactionInfoForStart();
-  ASSERT_EQ(true, info.is_manual_compaction);
-  ASSERT_EQ(true, info.is_full_compaction);
-  ASSERT_EQ(true, info.bottommost_level);
-  ASSERT_EQ(CompactionReason::kManualCompaction, info.compaction_reason);
-  info = my_cs->GetCompactionInfoForWait();
-  ASSERT_EQ(true, info.is_manual_compaction);
-  ASSERT_EQ(true, info.is_full_compaction);
-  ASSERT_EQ(true, info.bottommost_level);
-  ASSERT_EQ(CompactionReason::kManualCompaction, info.compaction_reason);
 }
 
 TEST_F(CompactionServiceTest, FallbackLocalAuto) {

db/compaction/compaction_state.cc

@@ -39,7 +39,7 @@ void CompactionState::AggregateCompactionStats(
     InternalStats::CompactionStatsFull& compaction_stats,
     CompactionJobStats& compaction_job_stats) {
   for (const auto& sc : sub_compact_states) {
-    sc.AggregateCompactionOutputStats(compaction_stats);
+    sc.AggregateCompactionStats(compaction_stats);
     compaction_job_stats.Add(sc.compaction_job_stats);
   }
 }

db/compaction/subcompaction_state.cc

@@ -13,7 +13,7 @@
 #include "rocksdb/sst_partitioner.h"
 
 namespace ROCKSDB_NAMESPACE {
-void SubcompactionState::AggregateCompactionOutputStats(
+void SubcompactionState::AggregateCompactionStats(
     InternalStats::CompactionStatsFull& compaction_stats) const {
   compaction_stats.stats.Add(compaction_outputs_.stats_);
   if (HasPenultimateLevelOutputs()) {

db/compaction/subcompaction_state.h

@@ -179,7 +179,7 @@ class SubcompactionState {
 
   void Cleanup(Cache* cache);
 
-  void AggregateCompactionOutputStats(
+  void AggregateCompactionStats(
       InternalStats::CompactionStatsFull& compaction_stats) const;
 
   CompactionOutputs& Current() const {

db/compaction/tiered_compaction_test.cc

@@ -2512,7 +2512,6 @@ TEST_P(IteratorWriteTimeTest, ReadFromMemtables) {
                               start_time + kSecondsPerRecording * (i + 1));
       }
     }
-    ASSERT_EQ(kNumKeys, i);
     ASSERT_OK(iter->status());
   }
 
@@ -2532,13 +2531,12 @@ TEST_P(IteratorWriteTimeTest, ReadFromMemtables) {
       }
     }
     ASSERT_OK(iter->status());
-    ASSERT_EQ(-1, i);
   }
 
   // Reopen the DB and disable the seqno to time recording, data with user
   // specified write time can still get a write time before it's flushed.
   options.preserve_internal_time_seconds = 0;
-  Reopen(options);
+  DestroyAndReopen(options);
   ASSERT_OK(TimedPut(Key(kKeyWithWriteTime), rnd.RandomString(100),
                      kUserSpecifiedWriteTime));
   {
@@ -2615,7 +2613,6 @@ TEST_P(IteratorWriteTimeTest, ReadFromSstFile) {
       }
     }
     ASSERT_OK(iter->status());
-    ASSERT_EQ(kNumKeys, i);
   }
 
   // Backward iteration
@@ -2635,13 +2632,12 @@ TEST_P(IteratorWriteTimeTest, ReadFromSstFile) {
       }
     }
     ASSERT_OK(iter->status());
-    ASSERT_EQ(-1, i);
   }
 
   // Reopen the DB and disable the seqno to time recording. Data retrieved from
   // SST files still have write time available.
   options.preserve_internal_time_seconds = 0;
-  Reopen(options);
+  DestroyAndReopen(options);
 
   dbfull()->TEST_WaitForPeriodicTaskRun(
       [&] { mock_clock_->MockSleepForSeconds(kSecondsPerRecording); });
@@ -2667,7 +2663,6 @@ TEST_P(IteratorWriteTimeTest, ReadFromSstFile) {
                               start_time + kSecondsPerRecording * (i + 1));
       }
     }
-    ASSERT_EQ(kNumKeys, i);
     ASSERT_OK(iter->status());
   }
 
@@ -2691,7 +2686,6 @@ TEST_P(IteratorWriteTimeTest, ReadFromSstFile) {
       VerifyKeyAndWriteTime(iter.get(), Key(i), 0);
     }
     ASSERT_OK(iter->status());
-    ASSERT_EQ(kNumKeys, i);
   }
   Close();
 }

db/convenience.cc

@@ -87,7 +87,7 @@ Status VerifySstFileChecksumInternal(const Options& options,
       options.block_protection_bytes_per_key, false /* skip_filters */,
       !kImmortal, false /* force_direct_prefetch */, -1 /* level */);
   reader_options.largest_seqno = largest_seqno;
-  s = options.table_factory->NewTableReader(
+  s = ioptions.table_factory->NewTableReader(
       read_options, reader_options, std::move(file_reader), file_size,
       &table_reader, false /* prefetch_index_and_filter_in_cache */);
   if (!s.ok()) {

db/db_basic_test.cc

@@ -688,100 +688,76 @@ TEST_F(DBBasicTest, IdentityAcrossRestarts) {
   constexpr size_t kMinIdSize = 10;
   do {
     for (bool with_manifest : {false, true}) {
-      for (bool write_file : {false, true}) {
-        std::string idfilename = IdentityFileName(dbname_);
-        std::string id1, tmp;
-        ASSERT_OK(db_->GetDbIdentity(id1));
-        ASSERT_GE(id1.size(), kMinIdSize);
+      std::string idfilename = IdentityFileName(dbname_);
+      std::string id1, tmp;
+      ASSERT_OK(db_->GetDbIdentity(id1));
+      ASSERT_GE(id1.size(), kMinIdSize);
 
-        Options options = CurrentOptions();
-        options.write_dbid_to_manifest = with_manifest;
-        options.write_identity_file = true;  // initially
-        Reopen(options);
-        std::string id2;
-        ASSERT_OK(db_->GetDbIdentity(id2));
-        // id2 should match id1 because identity was not regenerated
-        ASSERT_EQ(id1, id2);
-        ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
-        ASSERT_EQ(tmp, id2);
+      Options options = CurrentOptions();
+      options.write_dbid_to_manifest = with_manifest;
+      Reopen(options);
+      std::string id2;
+      ASSERT_OK(db_->GetDbIdentity(id2));
+      // id2 should match id1 because identity was not regenerated
+      ASSERT_EQ(id1, id2);
+      ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
+      ASSERT_EQ(tmp, id2);
 
-        if (write_file) {
-          // Recover from deleted/missing IDENTITY
-          ASSERT_OK(env_->DeleteFile(idfilename));
-        } else {
-          // Transition to no IDENTITY file
-          options.write_identity_file = false;
-          if (!with_manifest) {
-            // Incompatible options, should fail
-            ASSERT_NOK(TryReopen(options));
-            // Back to a usable config and continue
-            options.write_identity_file = true;
-            Reopen(options);
-            continue;
-          }
-        }
-        Reopen(options);
-        std::string id3;
-        ASSERT_OK(db_->GetDbIdentity(id3));
-        if (with_manifest) {
-          // id3 should match id1 because identity was restored from manifest
-          ASSERT_EQ(id1, id3);
-        } else {
-          // id3 should NOT match id1 because identity was regenerated
-          ASSERT_NE(id1, id3);
-          ASSERT_GE(id3.size(), kMinIdSize);
-        }
-        if (write_file) {
-          ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
-          ASSERT_EQ(tmp, id3);
-
-          // Recover from truncated IDENTITY
-          std::unique_ptr<WritableFile> w;
-          ASSERT_OK(env_->NewWritableFile(idfilename, &w, EnvOptions()));
-          ASSERT_OK(w->Close());
-        } else {
-          ASSERT_TRUE(env_->FileExists(idfilename).IsNotFound());
-        }
-        Reopen(options);
-        std::string id4;
-        ASSERT_OK(db_->GetDbIdentity(id4));
-        if (with_manifest) {
-          // id4 should match id1 because identity was restored from manifest
-          ASSERT_EQ(id1, id4);
-        } else {
-          // id4 should NOT match id1 because identity was regenerated
-          ASSERT_NE(id1, id4);
-          ASSERT_GE(id4.size(), kMinIdSize);
-        }
-        std::string silly_id = "asdf123456789";
-        if (write_file) {
-          ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
-          ASSERT_EQ(tmp, id4);
-
-          // Recover from overwritten IDENTITY
-          std::unique_ptr<WritableFile> w;
-          ASSERT_OK(env_->NewWritableFile(idfilename, &w, EnvOptions()));
-          ASSERT_OK(w->Append(silly_id));
-          ASSERT_OK(w->Close());
-        } else {
-          ASSERT_TRUE(env_->FileExists(idfilename).IsNotFound());
-        }
-        Reopen(options);
-        std::string id5;
-        ASSERT_OK(db_->GetDbIdentity(id5));
-        if (with_manifest) {
-          // id4 should match id1 because identity was restored from manifest
-          ASSERT_EQ(id1, id5);
-        } else {
-          ASSERT_EQ(id5, silly_id);
-        }
-        if (write_file) {
-          ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
-          ASSERT_EQ(tmp, id5);
-        } else {
-          ASSERT_TRUE(env_->FileExists(idfilename).IsNotFound());
-        }
+      // Recover from deleted/missing IDENTITY
+      ASSERT_OK(env_->DeleteFile(idfilename));
+      Reopen(options);
+      std::string id3;
+      ASSERT_OK(db_->GetDbIdentity(id3));
+      if (with_manifest) {
+        // id3 should match id1 because identity was restored from manifest
+        ASSERT_EQ(id1, id3);
+      } else {
+        // id3 should NOT match id1 because identity was regenerated
+        ASSERT_NE(id1, id3);
+        ASSERT_GE(id3.size(), kMinIdSize);
       }
+      ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
+      ASSERT_EQ(tmp, id3);
+
+      // Recover from truncated IDENTITY
+      {
+        std::unique_ptr<WritableFile> w;
+        ASSERT_OK(env_->NewWritableFile(idfilename, &w, EnvOptions()));
+        ASSERT_OK(w->Close());
+      }
+      Reopen(options);
+      std::string id4;
+      ASSERT_OK(db_->GetDbIdentity(id4));
+      if (with_manifest) {
+        // id4 should match id1 because identity was restored from manifest
+        ASSERT_EQ(id1, id4);
+      } else {
+        // id4 should NOT match id1 because identity was regenerated
+        ASSERT_NE(id1, id4);
+        ASSERT_GE(id4.size(), kMinIdSize);
+      }
+      ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
+      ASSERT_EQ(tmp, id4);
+
+      // Recover from overwritten IDENTITY
+      std::string silly_id = "asdf123456789";
+      {
+        std::unique_ptr<WritableFile> w;
+        ASSERT_OK(env_->NewWritableFile(idfilename, &w, EnvOptions()));
+        ASSERT_OK(w->Append(silly_id));
+        ASSERT_OK(w->Close());
+      }
+      Reopen(options);
+      std::string id5;
+      ASSERT_OK(db_->GetDbIdentity(id5));
+      if (with_manifest) {
+        // id4 should match id1 because identity was restored from manifest
+        ASSERT_EQ(id1, id5);
+      } else {
+        ASSERT_EQ(id5, silly_id);
+      }
+      ASSERT_OK(ReadFileToString(env_, idfilename, &tmp));
+      ASSERT_EQ(tmp, id5);
     }
   } while (ChangeCompactOptions());
 }
@@ -3431,46 +3407,6 @@ class TableFileListener : public EventListener {
   InstrumentedMutex mutex_;
   std::unordered_map<std::string, std::vector<std::string>> cf_to_paths_;
 };
-
-class FlushTableFileListener : public EventListener {
- public:
-  void OnTableFileCreated(const TableFileCreationInfo& info) override {
-    InstrumentedMutexLock lock(&mutex_);
-    if (info.reason != TableFileCreationReason::kFlush) {
-      return;
-    }
-    cf_to_flushed_files_[info.cf_name].push_back(info.file_path);
-  }
-  std::vector<std::string>& GetFlushedFiles(const std::string& cf_name) {
-    InstrumentedMutexLock lock(&mutex_);
-    return cf_to_flushed_files_[cf_name];
-  }
-
- private:
-  InstrumentedMutex mutex_;
-  std::unordered_map<std::string, std::vector<std::string>>
-      cf_to_flushed_files_;
-};
-
-class FlushBlobFileListener : public EventListener {
- public:
-  void OnBlobFileCreated(const BlobFileCreationInfo& info) override {
-    InstrumentedMutexLock lock(&mutex_);
-    if (info.reason != BlobFileCreationReason::kFlush) {
-      return;
-    }
-    cf_to_flushed_blobs_files_[info.cf_name].push_back(info.file_path);
-  }
-  std::vector<std::string>& GetFlushedBlobFiles(const std::string& cf_name) {
-    InstrumentedMutexLock lock(&mutex_);
-    return cf_to_flushed_blobs_files_[cf_name];
-  }
-
- private:
-  InstrumentedMutex mutex_;
-  std::unordered_map<std::string, std::vector<std::string>>
-      cf_to_flushed_blobs_files_;
-};
 }  // anonymous namespace
 
 TEST_F(DBBasicTest, LastSstFileNotInManifest) {
@@ -3576,121 +3512,6 @@ TEST_F(DBBasicTest, RecoverWithMissingFiles) {
   }
 }
 
-// Param 0: whether to enable blob DB.
-// Param 1: when blob DB is enabled, whether to also delete the missing L0
-// file's associated blob file.
-class BestEffortsRecoverIncompleteVersionTest
-    : public DBTestBase,
-      public testing::WithParamInterface<std::tuple<bool, bool>> {
- public:
-  BestEffortsRecoverIncompleteVersionTest()
-      : DBTestBase("best_efforts_recover_incomplete_version_test",
-                   /*env_do_fsync=*/false) {}
-};
-
-TEST_P(BestEffortsRecoverIncompleteVersionTest, Basic) {
-  Options options = CurrentOptions();
-  options.enable_blob_files = std::get<0>(GetParam());
-  bool delete_blob_file_too = std::get<1>(GetParam());
-  DestroyAndReopen(options);
-  FlushTableFileListener* flush_table_listener = new FlushTableFileListener();
-  FlushBlobFileListener* flush_blob_listener = new FlushBlobFileListener();
-  // Disable auto compaction to simplify SST file name tracking.
-  options.disable_auto_compactions = true;
-  options.listeners.emplace_back(flush_table_listener);
-  options.listeners.emplace_back(flush_blob_listener);
-  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
-  std::vector<std::string> all_cf_names = {kDefaultColumnFamilyName, "pikachu",
-                                           "eevee"};
-  int num_cfs = static_cast<int>(handles_.size());
-  ASSERT_EQ(3, num_cfs);
-  std::string start = "a";
-  Slice start_slice = start;
-  std::string end = "d";
-  Slice end_slice = end;
-  for (int cf = 0; cf != num_cfs; ++cf) {
-    ASSERT_OK(Put(cf, "a", "a_value"));
-    ASSERT_OK(Flush(cf));
-    // Compact file to L1 to avoid trivial file move in the next compaction
-    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), handles_[cf],
-                                &start_slice, &end_slice));
-    ASSERT_OK(Put(cf, "a", "a_value_new"));
-    ASSERT_OK(Flush(cf));
-    ASSERT_OK(Put(cf, "b", "b_value"));
-    ASSERT_OK(Flush(cf));
-    ASSERT_OK(Put(cf, "f", "f_value"));
-    ASSERT_OK(Flush(cf));
-    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), handles_[cf],
-                                &start_slice, &end_slice));
-  }
-
-  dbfull()->TEST_DeleteObsoleteFiles();
-
-  // Delete the most recent L0 file which is before a compaction.
-  for (int i = 0; i < num_cfs; ++i) {
-    std::vector<std::string>& files =
-        flush_table_listener->GetFlushedFiles(all_cf_names[i]);
-    ASSERT_EQ(4, files.size());
-    ASSERT_OK(env_->DeleteFile(files[files.size() - 1]));
-    if (options.enable_blob_files) {
-      std::vector<std::string>& blob_files =
-          flush_blob_listener->GetFlushedBlobFiles(all_cf_names[i]);
-      ASSERT_EQ(4, blob_files.size());
-      if (delete_blob_file_too) {
-        ASSERT_OK(env_->DeleteFile(blob_files[files.size() - 1]));
-      }
-    }
-  }
-  options.best_efforts_recovery = true;
-  ReopenWithColumnFamilies(all_cf_names, options);
-
-  for (int i = 0; i < num_cfs; ++i) {
-    auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
-    ColumnFamilyData* cfd = cfh->cfd();
-    VersionStorageInfo* vstorage = cfd->current()->storage_info();
-    // The L0 file flushed right before the last compaction is missing.
-    ASSERT_EQ(0, vstorage->LevelFiles(0).size());
-    // Only the output of the last compaction is available.
-    ASSERT_EQ(1, vstorage->LevelFiles(1).size());
-  }
-  // Verify data
-  ReadOptions read_opts;
-  read_opts.total_order_seek = true;
-  for (int i = 0; i < num_cfs; ++i) {
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts, handles_[i]));
-    iter->SeekToFirst();
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_OK(iter->status());
-    ASSERT_EQ("a", iter->key());
-    ASSERT_EQ("a_value_new", iter->value());
-    iter->Next();
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_OK(iter->status());
-    ASSERT_EQ("b", iter->key());
-    ASSERT_EQ("b_value", iter->value());
-    iter->Next();
-    ASSERT_FALSE(iter->Valid());
-    ASSERT_OK(iter->status());
-  }
-
-  // Write more data.
-  for (int cf = 0; cf < num_cfs; ++cf) {
-    ASSERT_OK(Put(cf, "g", "g_value"));
-    ASSERT_OK(Flush(cf));
-    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), handles_[cf], nullptr,
-                                nullptr));
-    std::string value;
-    ASSERT_OK(db_->Get(ReadOptions(), handles_[cf], "g", &value));
-    ASSERT_EQ("g_value", value);
-  }
-}
-
-INSTANTIATE_TEST_CASE_P(BestEffortsRecoverIncompleteVersionTest,
-                        BestEffortsRecoverIncompleteVersionTest,
-                        testing::Values(std::make_tuple(false, false),
-                                        std::make_tuple(true, false),
-                                        std::make_tuple(true, true)));
-
 TEST_F(DBBasicTest, BestEffortsRecoveryTryMultipleManifests) {
   Options options = CurrentOptions();
   options.env = env_;

db/db_block_cache_test.cc

@@ -563,7 +563,7 @@ TEST_P(DBBlockCacheTest1, WarmCacheWithBlocksDuringFlush) {
   }
 }
 
-TEST_F(DBBlockCacheTest, DynamicOptions) {
+TEST_F(DBBlockCacheTest, DynamicallyWarmCacheDuringFlush) {
   Options options = CurrentOptions();
   options.create_if_missing = true;
   options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
@@ -578,74 +578,39 @@ TEST_F(DBBlockCacheTest, DynamicOptions) {
   DestroyAndReopen(options);
 
   std::string value(kValueSize, 'a');
-  auto st = options.statistics;
 
-  size_t i = 1;
-  ASSERT_OK(Put(std::to_string(i), value));
-  ASSERT_OK(Flush());
-  ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+  for (size_t i = 1; i <= 5; i++) {
+    ASSERT_OK(Put(std::to_string(i), value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(1,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
 
-  ASSERT_EQ(value, Get(std::to_string(i)));
-  ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-  ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
-  ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
+    ASSERT_EQ(value, Get(std::to_string(i)));
+    ASSERT_EQ(0,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+    ASSERT_EQ(
+        0, options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
+    ASSERT_EQ(1,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
+  }
 
-  ++i;
   ASSERT_OK(dbfull()->SetOptions(
       {{"block_based_table_factory", "{prepopulate_block_cache=kDisable;}"}}));
 
-  ASSERT_OK(Put(std::to_string(i), value));
-  ASSERT_OK(Flush());
-  ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+  for (size_t i = 6; i <= kNumBlocks; i++) {
+    ASSERT_OK(Put(std::to_string(i), value));
+    ASSERT_OK(Flush());
+    ASSERT_EQ(0,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
 
-  ASSERT_EQ(value, Get(std::to_string(i)));
-  ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-  ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
-  ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
-
-  ++i;
-  ASSERT_OK(dbfull()->SetOptions({{"block_based_table_factory",
-                                   "{prepopulate_block_cache=kFlushOnly;}"}}));
-
-  ASSERT_OK(Put(std::to_string(i), value));
-  ASSERT_OK(Flush());
-  ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-
-  ASSERT_EQ(value, Get(std::to_string(i)));
-  ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-  ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
-  ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
-
-  ++i;
-  // NOT YET SUPPORTED
-  // FIXME: find a way to make this fail again (until well supported)
-  // ASSERT_NOK(dbfull()->SetOptions(
-  //    {{"block_based_table_factory", "{block_cache=null;}"}}));
-
-  // ASSERT_OK(Put(std::to_string(i), value));
-  // ASSERT_OK(Flush());
-  // ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-
-  // ASSERT_EQ(value, Get(std::to_string(i)));
-  // ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-  // ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
-  // ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
-
-  // ++i;
-
-  // NOT YET SUPPORTED
-  // FIXME: find a way to make this fail again (until well supported)
-  // ASSERT_NOK(dbfull()->SetOptions(
-  //    {{"block_based_table_factory", "{block_cache=1M;}"}}));
-
-  // ASSERT_OK(Put(std::to_string(i), value));
-  // ASSERT_OK(Flush());
-  // ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-
-  // ASSERT_EQ(value, Get(std::to_string(i)));
-  // ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
-  // ASSERT_EQ(0, st->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
-  // ASSERT_EQ(1, st->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
+    ASSERT_EQ(value, Get(std::to_string(i)));
+    ASSERT_EQ(1,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_ADD));
+    ASSERT_EQ(
+        1, options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_MISS));
+    ASSERT_EQ(0,
+              options.statistics->getAndResetTickerCount(BLOCK_CACHE_DATA_HIT));
+  }
 }
 #endif
 

db/db_compaction_test.cc

@@ -6146,7 +6146,7 @@ TEST_F(DBCompactionTest, CompactionLimiter) {
 
   std::vector<std::string> pending_compaction_cfs;
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "EnqueuePendingCompaction::cfd", [&](void* arg) {
+      "SchedulePendingCompaction::cfd", [&](void* arg) {
         const std::string& cf_name =
             static_cast<ColumnFamilyData*>(arg)->GetName();
         pending_compaction_cfs.emplace_back(cf_name);
@@ -9357,13 +9357,12 @@ TEST_F(DBCompactionTest, FIFOChangeTemperature) {
     ASSERT_OK(Flush());
 
     ASSERT_OK(Put(Key(0), "value1"));
+    env_->MockSleepForSeconds(800);
     ASSERT_OK(Put(Key(2), "value2"));
     ASSERT_OK(Flush());
 
-    // First two L0 files both become eligible for temperature change compaction
-    // They should be compacted one-by-one.
     ASSERT_OK(Put(Key(0), "value1"));
-    env_->MockSleepForSeconds(1200);
+    env_->MockSleepForSeconds(800);
     ASSERT_OK(Put(Key(2), "value2"));
     ASSERT_OK(Flush());
     ASSERT_OK(dbfull()->TEST_WaitForCompact());

db/db_filesnapshot.cc

@@ -21,7 +21,6 @@
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/metadata.h"
-#include "rocksdb/transaction_log.h"
 #include "rocksdb/types.h"
 #include "test_util/sync_point.h"
 #include "util/file_checksum_helper.h"
@@ -93,11 +92,6 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
 }
 
 Status DBImpl::GetSortedWalFiles(VectorWalPtr& files) {
-  return GetSortedWalFilesImpl(files,
-                               /*need_seqnos*/ true);
-}
-
-Status DBImpl::GetSortedWalFilesImpl(VectorWalPtr& files, bool need_seqnos) {
   // Record tracked WALs as a (minimum) cross-check for directory scan
   std::vector<uint64_t> required_by_manifest;
 
@@ -123,10 +117,7 @@ Status DBImpl::GetSortedWalFilesImpl(VectorWalPtr& files, bool need_seqnos) {
     }
   }
 
-  // NOTE: need to include archived WALs because needed WALs might have been
-  // archived since getting required_by_manifest set
-  Status s = wal_manager_.GetSortedWalFiles(files, need_seqnos,
-                                            /*include_archived*/ true);
+  Status s = wal_manager_.GetSortedWalFiles(files);
 
   // DisableFileDeletions / EnableFileDeletions not supported in read-only DB
   if (deletions_disabled.ok()) {
@@ -215,12 +206,7 @@ Status DBImpl::GetLiveFilesStorageInfo(
     } else if (opts.wal_size_for_flush > 0) {
       // FIXME: avoid querying the filesystem for current WAL state
       // If the outstanding WAL files are small, we skip the flush.
-      // Don't take archived log size into account when calculating wal
-      // size for flush, and don't need to verify consistency with manifest
-      // here & now.
-      s = wal_manager_.GetSortedWalFiles(live_wal_files,
-                                         /* need_seqnos */ false,
-                                         /*include_archived*/ false);
+      s = GetSortedWalFiles(live_wal_files);
 
       if (!s.ok()) {
         return s;
@@ -231,7 +217,6 @@ Status DBImpl::GetLiveFilesStorageInfo(
       // We may be able to cover 2PC case too.
       uint64_t total_wal_size = 0;
       for (auto& wal : live_wal_files) {
-        assert(wal->Type() == kAliveLogFile);
         total_wal_size += wal->SizeFileBytes();
       }
       if (total_wal_size < opts.wal_size_for_flush) {
@@ -443,8 +428,7 @@ Status DBImpl::GetLiveFilesStorageInfo(
   // WAL files.
   if (s.ok()) {
     // FIXME: avoid querying the filesystem for current WAL state
-    s = GetSortedWalFilesImpl(live_wal_files,
-                              /* need_seqnos */ false);
+    s = GetSortedWalFiles(live_wal_files);
   }
   if (!s.ok()) {
     return s;

db/db_follower_test.cc

@@ -289,12 +289,10 @@ TEST_F(DBFollowerTest, RetryCatchup) {
       {"DBImplFollower::TryCatchupWithLeader:Begin1", "Leader::Start"},
       {"DBImpl::BackgroundCompaction:Start",
        "DBImplFollower::TryCatchupWithLeader:Begin2"},
-      {"VersionEditHandlerPointInTime::MaybeCreateVersionBeforeApplyEdit:"
-       "Begin1",
+      {"VersionEditHandlerPointInTime::MaybeCreateVersion:Begin1",
        "DBImpl::BackgroundCompaction:BeforeCompaction"},
       {"DBImpl::BackgroundCallCompaction:PurgedObsoleteFiles",
-       "VersionEditHandlerPointInTime::MaybeCreateVersionBeforeApplyEdit:"
-       "Begin2"},
+       "VersionEditHandlerPointInTime::MaybeCreateVersion:Begin2"},
       {"DBImplFollower::TryCatchupWithLeader:End", "Follower::WaitForCatchup"},
   });
   SyncPoint::GetInstance()->EnableProcessing();
@@ -337,12 +335,10 @@ TEST_F(DBFollowerTest, RetryCatchupManifestRollover) {
   SyncPoint::GetInstance()->LoadDependency({
       {"DBImplFollower::TryCatchupWithLeader:Begin1", "Leader::Start"},
       {"Leader::Flushed", "DBImplFollower::TryCatchupWithLeader:Begin2"},
-      {"VersionEditHandlerPointInTime::MaybeCreateVersionBeforeApplyEdit:"
-       "Begin1",
+      {"VersionEditHandlerPointInTime::MaybeCreateVersion:Begin1",
        "Leader::Done"},
       {"DBImpl::BackgroundCallCompaction:PurgedObsoleteFiles",
-       "VersionEditHandlerPointInTime::MaybeCreateVersionBeforeApplyEdit:"
-       "Begin2"},
+       "VersionEditHandlerPointInTime::MaybeCreateVersion:Begin2"},
       {"DBImplFollower::TryCatchupWithLeader:End",
        "Follower::WaitForCatchup:1"},
   });

db/db_impl/db_impl.cc

@@ -392,8 +392,8 @@ Status DBImpl::ResumeImpl(DBRecoverContext context) {
       if (!s.ok()) {
         io_s = versions_->io_status();
         if (!io_s.ok()) {
-          error_handler_.SetBGError(io_s,
-                                    BackgroundErrorReason::kManifestWrite);
+          s = error_handler_.SetBGError(io_s,
+                                        BackgroundErrorReason::kManifestWrite);
         }
       }
     }
@@ -473,7 +473,7 @@ Status DBImpl::ResumeImpl(DBRecoverContext context) {
 
   if (s.ok()) {
     for (auto cfd : *versions_->GetColumnFamilySet()) {
-      EnqueuePendingCompaction(cfd);
+      SchedulePendingCompaction(cfd);
     }
     MaybeScheduleFlushOrCompaction();
   }
@@ -530,11 +530,6 @@ Status DBImpl::MaybeReleaseTimestampedSnapshotsAndCheck() {
   return Status::OK();
 }
 
-void DBImpl::UntrackDataFiles() {
-  TrackOrUntrackFiles(/*existing_data_files=*/{},
-                      /*track=*/false);
-}
-
 Status DBImpl::CloseHelper() {
   // Guarantee that there is no background error recovery in progress before
   // continuing with the shutdown
@@ -659,9 +654,8 @@ Status DBImpl::CloseHelper() {
   // We need to release them before the block cache is destroyed. The block
   // cache may be destroyed inside versions_.reset(), when column family data
   // list is destroyed, so leaving handles in table cache after
-  // versions_.reset() may cause issues. Here we clean all unreferenced handles
-  // in table cache, and (for certain builds/conditions) assert that no obsolete
-  // files are hanging around unreferenced (leak) in the table/blob file cache.
+  // versions_.reset() may cause issues.
+  // Here we clean all unreferenced handles in table cache.
   // Now we assume all user queries have finished, so only version set itself
   // can possibly hold the blocks from block cache. After releasing unreferenced
   // handles here, only handles held by version set left and inside
@@ -669,22 +663,12 @@ Status DBImpl::CloseHelper() {
   // time a handle is released, we erase it from the cache too. By doing that,
   // we can guarantee that after versions_.reset(), table cache is empty
   // so the cache can be safely destroyed.
-#ifndef NDEBUG
-  TEST_VerifyNoObsoleteFilesCached(/*db_mutex_already_held=*/true);
-#endif  // !NDEBUG
   table_cache_->EraseUnRefEntries();
 
   for (auto& txn_entry : recovered_transactions_) {
     delete txn_entry.second;
   }
 
-  // Return an unowned SstFileManager to a consistent state
-  if (immutable_db_options_.sst_file_manager && !own_sfm_) {
-    mutex_.Unlock();
-    UntrackDataFiles();
-    mutex_.Lock();
-  }
-
   // versions need to be destroyed before table_cache since it can hold
   // references to table_cache.
   {
@@ -933,8 +917,8 @@ Status DBImpl::RegisterRecordSeqnoTimeWorker(const ReadOptions& read_options,
             read_options, write_options, &edit, &mutex_,
             directories_.GetDbDir());
         if (!s.ok() && versions_->io_status().IsIOError()) {
-          error_handler_.SetBGError(versions_->io_status(),
-                                    BackgroundErrorReason::kManifestWrite);
+          s = error_handler_.SetBGError(versions_->io_status(),
+                                        BackgroundErrorReason::kManifestWrite);
         }
       }
 
@@ -1157,13 +1141,6 @@ void DBImpl::DumpStats() {
         continue;
       }
 
-      auto* table_factory =
-          cfd->GetCurrentMutableCFOptions()->table_factory.get();
-      assert(table_factory != nullptr);
-      // FIXME: need to a shared_ptr if/when block_cache is going to be mutable
-      Cache* cache =
-          table_factory->GetOptions<Cache>(TableFactory::kBlockCacheOpts());
-
       // Release DB mutex for gathering cache entry stats. Pass over all
       // column families for this first so that other stats are dumped
       // near-atomically.
@@ -1172,6 +1149,10 @@ void DBImpl::DumpStats() {
 
       // Probe block cache for problems (if not already via another CF)
       if (immutable_db_options_.info_log) {
+        auto* table_factory = cfd->ioptions()->table_factory.get();
+        assert(table_factory != nullptr);
+        Cache* cache =
+            table_factory->GetOptions<Cache>(TableFactory::kBlockCacheOpts());
         if (cache && probed_caches.insert(cache).second) {
           cache->ReportProblems(immutable_db_options_.info_log);
         }
@@ -1545,7 +1526,7 @@ Status DBImpl::FlushWAL(const WriteOptions& write_options, bool sync) {
                       io_s.ToString().c_str());
       // In case there is a fs error we should set it globally to prevent the
       // future writes
-      WALIOStatusCheck(io_s);
+      IOStatusCheck(io_s);
       // whether sync or not, we should abort the rest of function upon error
       return static_cast<Status>(io_s);
     }
@@ -1702,7 +1683,7 @@ IOStatus DBImpl::SyncWalImpl(bool include_current_wal,
                     io_s.ToString().c_str());
     // In case there is a fs error we should set it globally to prevent the
     // future writes
-    WALIOStatusCheck(io_s);
+    IOStatusCheck(io_s);
   }
   if (io_s.ok() && need_wal_dir_sync) {
     io_s = directories_.GetWalDir()->FsyncWithDirOptions(
@@ -1744,8 +1725,8 @@ Status DBImpl::ApplyWALToManifest(const ReadOptions& read_options,
       read_options, write_options, synced_wals, &mutex_,
       directories_.GetDbDir());
   if (!status.ok() && versions_->io_status().IsIOError()) {
-    error_handler_.SetBGError(versions_->io_status(),
-                              BackgroundErrorReason::kManifestWrite);
+    status = error_handler_.SetBGError(versions_->io_status(),
+                                       BackgroundErrorReason::kManifestWrite);
   }
   return status;
 }
@@ -2073,34 +2054,30 @@ InternalIterator* DBImpl::NewInternalIterator(
     bool allow_unprepared_value, ArenaWrappedDBIter* db_iter) {
   InternalIterator* internal_iter;
   assert(arena != nullptr);
-  auto prefix_extractor =
-      super_version->mutable_cf_options.prefix_extractor.get();
   // Need to create internal iterator from the arena.
   MergeIteratorBuilder merge_iter_builder(
       &cfd->internal_comparator(), arena,
-      // FIXME? It's not clear what interpretation of prefix seek is needed
-      // here, and no unit test cares about the value provided here.
-      !read_options.total_order_seek && prefix_extractor != nullptr,
+      !read_options.total_order_seek &&
+          super_version->mutable_cf_options.prefix_extractor != nullptr,
       read_options.iterate_upper_bound);
   // Collect iterator for mutable memtable
   auto mem_iter = super_version->mem->NewIterator(
-      read_options, super_version->GetSeqnoToTimeMapping(), arena,
-      super_version->mutable_cf_options.prefix_extractor.get());
+      read_options, super_version->GetSeqnoToTimeMapping(), arena);
   Status s;
   if (!read_options.ignore_range_deletions) {
-    std::unique_ptr<TruncatedRangeDelIterator> mem_tombstone_iter;
+    TruncatedRangeDelIterator* mem_tombstone_iter = nullptr;
     auto range_del_iter = super_version->mem->NewRangeTombstoneIterator(
         read_options, sequence, false /* immutable_memtable */);
     if (range_del_iter == nullptr || range_del_iter->empty()) {
       delete range_del_iter;
     } else {
-      mem_tombstone_iter = std::make_unique<TruncatedRangeDelIterator>(
+      mem_tombstone_iter = new TruncatedRangeDelIterator(
           std::unique_ptr<FragmentedRangeTombstoneIterator>(range_del_iter),
           &cfd->ioptions()->internal_comparator, nullptr /* smallest */,
           nullptr /* largest */);
     }
-    merge_iter_builder.AddPointAndTombstoneIterator(
-        mem_iter, std::move(mem_tombstone_iter));
+    merge_iter_builder.AddPointAndTombstoneIterator(mem_iter,
+                                                    mem_tombstone_iter);
   } else {
     merge_iter_builder.AddIterator(mem_iter);
   }
@@ -2109,7 +2086,6 @@ InternalIterator* DBImpl::NewInternalIterator(
   if (s.ok()) {
     super_version->imm->AddIterators(
         read_options, super_version->GetSeqnoToTimeMapping(),
-        super_version->mutable_cf_options.prefix_extractor.get(),
         &merge_iter_builder, !read_options.ignore_range_deletions);
   }
   TEST_SYNC_POINT_CALLBACK("DBImpl::NewInternalIterator:StatusCallback", &s);
@@ -2500,8 +2476,7 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
         RecordTick(stats_, MEMTABLE_HIT);
       }
     }
-    if (!s.ok() && !s.IsMergeInProgress() && !s.IsNotFound()) {
-      assert(done);
+    if (!done && !s.ok() && !s.IsMergeInProgress()) {
       ReturnAndCleanupSuperVersion(cfd, sv);
       return s;
     }
@@ -3167,11 +3142,10 @@ Status DBImpl::MultiGetImpl(
   StopWatch sw(immutable_db_options_.clock, stats_, DB_MULTIGET);
 
   assert(sorted_keys);
-  assert(start_key + num_keys <= sorted_keys->size());
   // Clear the timestamps for returning results so that we can distinguish
   // between tombstone or key that has never been written
-  for (size_t i = start_key; i < start_key + num_keys; ++i) {
-    KeyContext* kctx = (*sorted_keys)[i];
+  for (auto* kctx : *sorted_keys) {
+    assert(kctx);
     if (kctx->timestamp) {
       kctx->timestamp->clear();
     }
@@ -3234,8 +3208,6 @@ Status DBImpl::MultiGetImpl(
       s = Status::Aborted();
       break;
     }
-    // This could be a long-running operation
-    ROCKSDB_THREAD_YIELD_HOOK();
   }
 
   // Post processing (decrement reference counts and record statistics)
@@ -3857,9 +3829,6 @@ Iterator* DBImpl::NewIterator(const ReadOptions& _read_options,
     }
   }
   if (read_options.tailing) {
-    read_options.total_order_seek |=
-        immutable_db_options_.prefix_seek_opt_in_only;
-
     auto iter = new ForwardIterator(this, read_options, cfd, sv,
                                     /* allow_unprepared_value */ true);
     result = NewDBIterator(
@@ -3993,25 +3962,14 @@ std::unique_ptr<IterType> DBImpl::NewMultiCfIterator(
           "Different comparators are being used across CFs"));
     }
   }
-
   std::vector<Iterator*> child_iterators;
   Status s = NewIterators(_read_options, column_families, &child_iterators);
   if (!s.ok()) {
     return error_iterator_func(s);
   }
-
-  assert(column_families.size() == child_iterators.size());
-
-  std::vector<std::pair<ColumnFamilyHandle*, std::unique_ptr<Iterator>>>
-      cfh_iter_pairs;
-  cfh_iter_pairs.reserve(column_families.size());
-  for (size_t i = 0; i < column_families.size(); ++i) {
-    cfh_iter_pairs.emplace_back(column_families[i], child_iterators[i]);
-  }
-
-  return std::make_unique<ImplType>(_read_options,
-                                    column_families[0]->GetComparator(),
-                                    std::move(cfh_iter_pairs));
+  return std::make_unique<ImplType>(column_families[0]->GetComparator(),
+                                    column_families,
+                                    std::move(child_iterators));
 }
 
 Status DBImpl::NewIterators(
@@ -4072,9 +4030,6 @@ Status DBImpl::NewIterators(
 
   assert(cf_sv_pairs.size() == column_families.size());
   if (read_options.tailing) {
-    read_options.total_order_seek |=
-        immutable_db_options_.prefix_seek_opt_in_only;
-
     for (const auto& cf_sv_pair : cf_sv_pairs) {
       auto iter = new ForwardIterator(this, read_options, cf_sv_pair.cfd,
                                       cf_sv_pair.super_version,
@@ -4315,8 +4270,8 @@ void DBImpl::ReleaseSnapshot(const Snapshot* s) {
     }
     // Avoid to go through every column family by checking a global threshold
     // first.
-    CfdList cf_scheduled;
     if (oldest_snapshot > bottommost_files_mark_threshold_) {
+      CfdList cf_scheduled;
       for (auto* cfd : *versions_->GetColumnFamilySet()) {
         if (!cfd->ioptions()->allow_ingest_behind) {
           cfd->current()->storage_info()->UpdateOldestSnapshot(
@@ -4325,7 +4280,7 @@ void DBImpl::ReleaseSnapshot(const Snapshot* s) {
                    ->storage_info()
                    ->BottommostFilesMarkedForCompaction()
                    .empty()) {
-            EnqueuePendingCompaction(cfd);
+            SchedulePendingCompaction(cfd);
             MaybeScheduleFlushOrCompaction();
             cf_scheduled.push_back(cfd);
           }
@@ -4348,24 +4303,6 @@ void DBImpl::ReleaseSnapshot(const Snapshot* s) {
       }
       bottommost_files_mark_threshold_ = new_bottommost_files_mark_threshold;
     }
-
-    // Avoid to go through every column family by checking a global threshold
-    // first.
-    if (oldest_snapshot >= standalone_range_deletion_files_mark_threshold_) {
-      for (auto* cfd : *versions_->GetColumnFamilySet()) {
-        if (cfd->IsDropped() || CfdListContains(cf_scheduled, cfd)) {
-          continue;
-        }
-        if (oldest_snapshot >=
-            cfd->current()
-                ->storage_info()
-                ->standalone_range_tombstone_files_mark_threshold()) {
-          EnqueuePendingCompaction(cfd);
-          MaybeScheduleFlushOrCompaction();
-          cf_scheduled.push_back(cfd);
-        }
-      }
-    }
   }
   delete casted_s;
 }
@@ -4817,24 +4754,6 @@ void DBImpl::ReleaseFileNumberFromPendingOutputs(
   }
 }
 
-std::list<uint64_t>::iterator DBImpl::CaptureOptionsFileNumber() {
-  // We need to remember the iterator of our insert, because after the
-  // compaction is done, we need to remove that element from
-  // min_options_file_numbers_.
-  min_options_file_numbers_.push_back(versions_->options_file_number());
-  auto min_options_file_numbers_inserted_elem = min_options_file_numbers_.end();
-  --min_options_file_numbers_inserted_elem;
-  return min_options_file_numbers_inserted_elem;
-}
-
-void DBImpl::ReleaseOptionsFileNumber(
-    std::unique_ptr<std::list<uint64_t>::iterator>& v) {
-  if (v.get() != nullptr) {
-    min_options_file_numbers_.erase(*v.get());
-    v.reset();
-  }
-}
-
 Status DBImpl::GetUpdatesSince(
     SequenceNumber seq, std::unique_ptr<TransactionLogIterator>* iter,
     const TransactionLogIterator::ReadOptions& read_options) {
@@ -5198,12 +5117,11 @@ Status DBImpl::GetDbIdentity(std::string& identity) const {
   return Status::OK();
 }
 
-Status DBImpl::GetDbIdentityFromIdentityFile(const IOOptions& opts,
-                                             std::string* identity) const {
+Status DBImpl::GetDbIdentityFromIdentityFile(std::string* identity) const {
   std::string idfilename = IdentityFileName(dbname_);
   const FileOptions soptions;
 
-  Status s = ReadFileToString(fs_.get(), idfilename, opts, identity);
+  Status s = ReadFileToString(fs_.get(), idfilename, identity);
   if (!s.ok()) {
     return s;
   }
@@ -5514,8 +5432,7 @@ Status DBImpl::WriteOptionsFile(const WriteOptions& write_options,
                                    file_name, fs_.get());
 
   if (s.ok()) {
-    s = RenameTempFileToOptionsFile(file_name,
-                                    db_options.compaction_service != nullptr);
+    s = RenameTempFileToOptionsFile(file_name);
   }
 
   if (!s.ok() && GetEnv()->FileExists(file_name).ok()) {
@@ -5592,8 +5509,7 @@ Status DBImpl::DeleteObsoleteOptionsFiles() {
   return Status::OK();
 }
 
-Status DBImpl::RenameTempFileToOptionsFile(const std::string& file_name,
-                                           bool is_remote_compaction_enabled) {
+Status DBImpl::RenameTempFileToOptionsFile(const std::string& file_name) {
   Status s;
 
   uint64_t options_file_number = versions_->NewFileNumber();
@@ -5637,7 +5553,7 @@ Status DBImpl::RenameTempFileToOptionsFile(const std::string& file_name,
       my_disable_delete_obsolete_files = disable_delete_obsolete_files_;
     }
 
-    if (!my_disable_delete_obsolete_files && !is_remote_compaction_enabled) {
+    if (!my_disable_delete_obsolete_files) {
       // TODO: Should we check for errors here?
       DeleteObsoleteOptionsFiles().PermitUncheckedError();
     }
@@ -5870,6 +5786,7 @@ Status DBImpl::IngestExternalFile(
 Status DBImpl::IngestExternalFiles(
     const std::vector<IngestExternalFileArg>& args) {
   // TODO: plumb Env::IOActivity, Env::IOPriority
+  const ReadOptions read_options;
   const WriteOptions write_options;
 
   if (args.empty()) {
@@ -5895,10 +5812,6 @@ Status DBImpl::IngestExternalFiles(
       snprintf(err_msg, 128, "external_files[%zu] is empty", i);
       return Status::InvalidArgument(err_msg);
     }
-    if (i && args[i].options.fill_cache != args[i - 1].options.fill_cache) {
-      return Status::InvalidArgument(
-          "fill_cache should be the same across ingestion options.");
-    }
   }
   for (const auto& arg : args) {
     const IngestExternalFileOptions& ingest_opts = arg.options;
@@ -5915,17 +5828,6 @@ Status DBImpl::IngestExternalFiles(
             "timestamps enabled doesn't support ingest behind.");
       }
     }
-    if (ingest_opts.allow_db_generated_files) {
-      if (ingest_opts.write_global_seqno) {
-        return Status::NotSupported(
-            "write_global_seqno is deprecated and does not work with "
-            "allow_db_generated_files.");
-      }
-    }
-    if (ingest_opts.move_files && ingest_opts.link_files) {
-      return Status::InvalidArgument(
-          "`move_files` and `link_files` can not both be true.");
-    }
   }
 
   // TODO (yanqin) maybe handle the case in which column_families have
@@ -6086,8 +5988,6 @@ Status DBImpl::IngestExternalFiles(
       }
     }
     if (status.ok()) {
-      ReadOptions read_options;
-      read_options.fill_cache = args[0].options.fill_cache;
       autovector<ColumnFamilyData*> cfds_to_commit;
       autovector<const MutableCFOptions*> mutable_cf_options_list;
       autovector<autovector<VersionEdit*>> edit_lists;
@@ -6834,62 +6734,6 @@ void DBImpl::RecordSeqnoToTimeMapping(uint64_t populate_historical_seconds) {
   }
 }
 
-void DBImpl::TrackOrUntrackFiles(
-    const std::vector<std::string>& existing_data_files, bool track) {
-  auto sfm = static_cast_with_check<SstFileManagerImpl>(
-      immutable_db_options_.sst_file_manager.get());
-  assert(sfm);
-  std::vector<ColumnFamilyMetaData> metadata;
-  GetAllColumnFamilyMetaData(&metadata);
-  auto action = [&](const std::string& file_path,
-                    std::optional<uint64_t> size) {
-    if (track) {
-      if (size) {
-        sfm->OnAddFile(file_path, *size).PermitUncheckedError();
-      } else {
-        sfm->OnAddFile(file_path).PermitUncheckedError();
-      }
-    } else {
-      sfm->OnUntrackFile(file_path).PermitUncheckedError();
-    }
-  };
-
-  std::unordered_set<std::string> referenced_files;
-  for (const auto& md : metadata) {
-    for (const auto& lmd : md.levels) {
-      for (const auto& fmd : lmd.files) {
-        // We're assuming that each sst file name exists in at most one of
-        // the paths.
-        std::string file_path =
-            fmd.directory + kFilePathSeparator + fmd.relative_filename;
-        action(file_path, fmd.size);
-        referenced_files.insert(file_path);
-      }
-    }
-    for (const auto& bmd : md.blob_files) {
-      std::string name = bmd.blob_file_name;
-      // The BlobMetaData.blob_file_name may start with "/".
-      if (!name.empty() && name[0] == kFilePathSeparator) {
-        name = name.substr(1);
-      }
-      // We're assuming that each blob file name exists in at most one of
-      // the paths.
-      std::string file_path = bmd.blob_file_path + kFilePathSeparator + name;
-      action(file_path, bmd.blob_file_size);
-      referenced_files.insert(file_path);
-    }
-  }
-
-  for (const auto& file_path : existing_data_files) {
-    if (referenced_files.find(file_path) != referenced_files.end()) {
-      continue;
-    }
-    // There shouldn't be any duplicated files. In case there is, SstFileManager
-    // will take care of deduping it.
-    action(file_path, /*size=*/std::nullopt);
-  }
-}
-
 void DBImpl::InstallSeqnoToTimeMappingInSV(
     std::vector<SuperVersionContext>* sv_contexts) {
   mutex_.AssertHeld();

db/db_impl/db_impl.h

@@ -482,8 +482,7 @@ class DBImpl : public DB {
 
   Status GetDbIdentity(std::string& identity) const override;
 
-  virtual Status GetDbIdentityFromIdentityFile(const IOOptions& opts,
-                                               std::string* identity) const;
+  virtual Status GetDbIdentityFromIdentityFile(std::string* identity) const;
 
   Status GetDbSessionId(std::string& session_id) const override;
 
@@ -509,8 +508,6 @@ class DBImpl : public DB {
   Status GetLiveFiles(std::vector<std::string>&, uint64_t* manifest_file_size,
                       bool flush_memtable = true) override;
   Status GetSortedWalFiles(VectorWalPtr& files) override;
-  Status GetSortedWalFilesImpl(VectorWalPtr& files, bool need_seqnos);
-
   // Get the known flushed sizes of WALs that might still be written to
   // or have pending sync.
   // NOTE: unlike alive_log_files_, this function includes WALs that might
@@ -854,8 +851,6 @@ class DBImpl : public DB {
 
   uint64_t GetObsoleteSstFilesSize();
 
-  uint64_t MinOptionsFileNumberToKeep();
-
   // 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
@@ -1154,8 +1149,6 @@ class DBImpl : public DB {
   // Get the background error status
   Status TEST_GetBGError();
 
-  bool TEST_IsRecoveryInProgress();
-
   // Return the maximum overlapping data (in bytes) at next level for any
   // file at a level >= 1.
   uint64_t TEST_MaxNextLevelOverlappingBytes(
@@ -1200,7 +1193,9 @@ class DBImpl : public DB {
 
   uint64_t TEST_total_log_size() const { return total_log_size_; }
 
-  void TEST_GetAllBlockCaches(std::unordered_set<const Cache*>* cache_set);
+  // Returns column family name to ImmutableCFOptions map.
+  Status TEST_GetAllImmutableCFOptions(
+      std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map);
 
   // Return the lastest MutableCFOptions of a column family
   Status TEST_GetLatestMutableCFOptions(ColumnFamilyHandle* column_family,
@@ -1240,13 +1235,8 @@ class DBImpl : public DB {
   static Status TEST_ValidateOptions(const DBOptions& db_options) {
     return ValidateOptions(db_options);
   }
-#endif  // NDEBUG
 
-  // In certain configurations, verify that the table/blob file cache only
-  // contains entries for live files, to check for effective leaks of open
-  // files. This can only be called when purging of obsolete files has
-  // "settled," such as during parts of DB Close().
-  void TEST_VerifyNoObsoleteFilesCached(bool db_mutex_already_held) const;
+#endif  // NDEBUG
 
   // persist stats to column family "_persistent_stats"
   void PersistStats();
@@ -1469,8 +1459,7 @@ class DBImpl : public DB {
   // The following two functions can only be called when:
   // 1. WriteThread::Writer::EnterUnbatched() is used.
   // 2. db_mutex is NOT held
-  Status RenameTempFileToOptionsFile(const std::string& file_name,
-                                     bool is_remote_compaction_enabled);
+  Status RenameTempFileToOptionsFile(const std::string& file_name);
   Status DeleteObsoleteOptionsFiles();
 
   void NotifyOnManualFlushScheduled(autovector<ColumnFamilyData*> cfds,
@@ -1591,12 +1580,11 @@ class DBImpl : public DB {
 
   virtual bool OwnTablesAndLogs() const { return true; }
 
-  // Read/create DB identity file (as appropriate), and write DB ID to
-  // version_edit if provided.
+  // Setup DB identity file, and write DB ID to manifest if necessary.
   Status SetupDBId(const WriteOptions& write_options, bool read_only,
-                   bool is_new_db, bool is_retry, VersionEdit* version_edit);
-  // Assign db_id_ and write DB ID to version_edit if provided.
-  void SetDBId(std::string&& id, bool read_only, VersionEdit* version_edit);
+                   RecoveryContext* recovery_ctx);
+  // Assign db_id_ and write DB ID to manifest if necessary.
+  void SetDBId(std::string&& id, bool read_only, RecoveryContext* recovery_ctx);
 
   // Collect a deduplicated collection of paths used by this DB, including
   // dbname_, DBOptions.db_paths, ColumnFamilyOptions.cf_paths.
@@ -1626,15 +1614,9 @@ class DBImpl : public DB {
   // vast majority of all files), since it already has the file size
   // on record, we don't need to query the file system. Otherwise, we query the
   // file system for the size of an unreferenced file.
-  // REQUIRES: mutex unlocked
   void TrackExistingDataFiles(
       const std::vector<std::string>& existing_data_files);
 
-  // Untrack data files in sst manager. This is only called during DB::Close on
-  // an unowned SstFileManager, to return it to a consistent state.
-  // REQUIRES: mutex unlocked
-  void UntrackDataFiles();
-
   // SetDbSessionId() should be called in the constuctor DBImpl()
   // to ensure that db_session_id_ gets updated every time the DB is opened
   void SetDbSessionId();
@@ -1701,8 +1683,6 @@ class DBImpl : public DB {
   friend class XFTransactionWriteHandler;
   friend class DBBlobIndexTest;
   friend class WriteUnpreparedTransactionTest_RecoveryTest_Test;
-  friend class CompactionServiceTest_PreservedOptionsLocalCompaction_Test;
-  friend class CompactionServiceTest_PreservedOptionsRemoteCompaction_Test;
 #endif
 
   struct CompactionState;
@@ -1908,10 +1888,6 @@ class DBImpl : public DB {
     Env::Priority compaction_pri_;
   };
 
-  static bool IsRecoveryFlush(FlushReason flush_reason) {
-    return flush_reason == FlushReason::kErrorRecoveryRetryFlush ||
-           flush_reason == FlushReason::kErrorRecovery;
-  }
   // Initialize the built-in column family for persistent stats. Depending on
   // whether on-disk persistent stats have been enabled before, it may either
   // create a new column family and column family handle or just a column family
@@ -1974,13 +1950,6 @@ class DBImpl : public DB {
   void ReleaseFileNumberFromPendingOutputs(
       std::unique_ptr<std::list<uint64_t>::iterator>& v);
 
-  // Similar to pending_outputs, preserve OPTIONS file. Used for remote
-  // compaction.
-  std::list<uint64_t>::iterator CaptureOptionsFileNumber();
-  void ReleaseOptionsFileNumber(
-      std::unique_ptr<std::list<uint64_t>::iterator>& v);
-
-  // Sets bg error if there is an error writing to WAL.
   IOStatus SyncClosedWals(const WriteOptions& write_options,
                           JobContext* job_context, VersionEdit* synced_wals,
                           bool error_recovery_in_prog);
@@ -2063,8 +2032,7 @@ class DBImpl : public DB {
   // REQUIRES: mutex held
   void SelectColumnFamiliesForAtomicFlush(
       autovector<ColumnFamilyData*>* selected_cfds,
-      const autovector<ColumnFamilyData*>& provided_candidate_cfds = {},
-      FlushReason flush_reason = FlushReason::kOthers);
+      const autovector<ColumnFamilyData*>& provided_candidate_cfds = {});
 
   // Force current memtable contents to be flushed.
   Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options,
@@ -2091,18 +2059,17 @@ class DBImpl : public DB {
   // memtable pending flush.
   // resuming_from_bg_err indicates whether the caller is attempting to resume
   // from background error.
-  Status WaitForFlushMemTable(
-      ColumnFamilyData* cfd, const uint64_t* flush_memtable_id = nullptr,
-      bool resuming_from_bg_err = false,
-      std::optional<FlushReason> flush_reason = std::nullopt) {
+  Status WaitForFlushMemTable(ColumnFamilyData* cfd,
+                              const uint64_t* flush_memtable_id = nullptr,
+                              bool resuming_from_bg_err = false) {
     return WaitForFlushMemTables({cfd}, {flush_memtable_id},
-                                 resuming_from_bg_err, flush_reason);
+                                 resuming_from_bg_err);
   }
   // Wait for memtables to be flushed for multiple column families.
   Status WaitForFlushMemTables(
       const autovector<ColumnFamilyData*>& cfds,
       const autovector<const uint64_t*>& flush_memtable_ids,
-      bool resuming_from_bg_err, std::optional<FlushReason> flush_reason);
+      bool resuming_from_bg_err);
 
   inline void WaitForPendingWrites() {
     mutex_.AssertHeld();
@@ -2200,7 +2167,7 @@ class DBImpl : public DB {
 
   // Used by WriteImpl to update bg_error_ when IO error happens, e.g., write
   // WAL, sync WAL fails, if paranoid check is enabled.
-  void WALIOStatusCheck(const IOStatus& status);
+  void IOStatusCheck(const IOStatus& status);
 
   // Used by WriteImpl to update bg_error_ in case of memtable insert error.
   void MemTableInsertStatusCheck(const Status& memtable_insert_status);
@@ -2213,10 +2180,6 @@ class DBImpl : public DB {
                           JobContext* job_context, LogBuffer* log_buffer,
                           CompactionJobInfo* compaction_job_info);
 
-  // REQUIRES: mutex unlocked
-  void TrackOrUntrackFiles(const std::vector<std::string>& existing_data_files,
-                           bool track);
-
   ColumnFamilyData* GetColumnFamilyDataByName(const std::string& cf_name);
 
   void MaybeScheduleFlushOrCompaction();
@@ -2246,27 +2209,10 @@ class DBImpl : public DB {
   void GenerateFlushRequest(const autovector<ColumnFamilyData*>& cfds,
                             FlushReason flush_reason, FlushRequest* req);
 
-  // Below functions are for executing flush, compaction in the background. A
-  // dequeue is the communication channel between threads that asks for the work
-  // to be done and the available threads in the thread pool that pick it up to
-  // execute it. We use these terminologies to describe the state of the work
-  // and its transitions:
-  // 1) It becomes pending once it's successfully enqueued into the
-  //    corresponding dequeue, a work in this state is also called unscheduled.
-  //    Counter `unscheduled_*_` counts work in this state.
-  // 2) When `MaybeScheduleFlushOrCompaction` schedule a thread to run `BGWork*`
-  //    for the work, it becomes scheduled
-  //    Counter `bg_*_scheduled_` counts work in this state.
-  // 3) Once the thread start to execute `BGWork*`, the work is popped from the
-  //    dequeue, it is now in running state
-  //    Counter `num_running_*_` counts work in this state.
-  // 4) Eventually, the work is finished. We don't need to specifically track
-  //    finished work.
-
   // Returns true if `req` is successfully enqueued.
-  bool EnqueuePendingFlush(const FlushRequest& req);
+  bool SchedulePendingFlush(const FlushRequest& req);
 
-  void EnqueuePendingCompaction(ColumnFamilyData* cfd);
+  void SchedulePendingCompaction(ColumnFamilyData* cfd);
   void SchedulePendingPurge(std::string fname, std::string dir_to_sync,
                             FileType type, uint64_t number, int job_id);
   static void BGWorkCompaction(void* arg);
@@ -2402,9 +2348,6 @@ class DBImpl : public DB {
   bool HaveManualCompaction(ColumnFamilyData* cfd);
   bool MCOverlap(ManualCompactionState* m, ManualCompactionState* m1);
   void UpdateDeletionCompactionStats(const std::unique_ptr<Compaction>& c);
-
-  // May open and read table files for table property.
-  // Should not be called while holding mutex_.
   void BuildCompactionJobInfo(const ColumnFamilyData* cfd, Compaction* c,
                               const Status& st,
                               const CompactionJobStats& compaction_job_stats,
@@ -2771,11 +2714,6 @@ class DBImpl : public DB {
   // State is protected with db mutex.
   std::list<uint64_t> pending_outputs_;
 
-  // Similar to pending_outputs_, FindObsoleteFiles()/PurgeObsoleteFiles() never
-  // deletes any OPTIONS file that has number bigger than any of the file number
-  // in min_options_file_numbers_.
-  std::list<uint64_t> min_options_file_numbers_;
-
   // flush_queue_ and compaction_queue_ hold column families that we need to
   // flush and compact, respectively.
   // A column family is inserted into flush_queue_ when it satisfies condition
@@ -2898,11 +2836,6 @@ class DBImpl : public DB {
   // garbages, among all column families.
   SequenceNumber bottommost_files_mark_threshold_ = kMaxSequenceNumber;
 
-  // The min threshold to trigger compactions for standalone range deletion
-  // files that are marked for compaction.
-  SequenceNumber standalone_range_deletion_files_mark_threshold_ =
-      kMaxSequenceNumber;
-
   LogsWithPrepTracker logs_with_prep_tracker_;
 
   // Callback for compaction to check if a key is visible to a snapshot.
@@ -3003,14 +2936,6 @@ DBOptions SanitizeOptions(const std::string& db, const DBOptions& src,
 CompressionType GetCompressionFlush(const ImmutableCFOptions& ioptions,
                                     const MutableCFOptions& mutable_cf_options);
 
-// Return a VersionEdit for the DB's recovery when the `memtables` of the
-// specified column family are obsolete. Specifically, the min log number to
-// keep, and the WAL files that can be deleted.
-VersionEdit GetDBRecoveryEditForObsoletingMemTables(
-    VersionSet* vset, const ColumnFamilyData& cfd,
-    const autovector<VersionEdit*>& edit_list,
-    const autovector<MemTable*>& memtables, LogsWithPrepTracker* prep_tracker);
-
 // Return the earliest log file to keep after the memtable flush is
 // finalized.
 // `cfd_to_flush` is the column family whose memtable (specified in

db/db_impl/db_impl_compaction_flush.cc

@@ -1561,12 +1561,6 @@ Status DBImpl::CompactFilesImpl(
 
   compaction_job.Prepare();
 
-  std::unique_ptr<std::list<uint64_t>::iterator> min_options_file_number_elem;
-  if (immutable_db_options().compaction_service != nullptr) {
-    min_options_file_number_elem.reset(
-        new std::list<uint64_t>::iterator(CaptureOptionsFileNumber()));
-  }
-
   mutex_.Unlock();
   TEST_SYNC_POINT("CompactFilesImpl:0");
   TEST_SYNC_POINT("CompactFilesImpl:1");
@@ -1576,10 +1570,6 @@ Status DBImpl::CompactFilesImpl(
   TEST_SYNC_POINT("CompactFilesImpl:3");
   mutex_.Lock();
 
-  if (immutable_db_options().compaction_service != nullptr) {
-    ReleaseOptionsFileNumber(min_options_file_number_elem);
-  }
-
   bool compaction_released = false;
   Status status =
       compaction_job.Install(*c->mutable_cf_options(), &compaction_released);
@@ -1605,12 +1595,10 @@ Status DBImpl::CompactFilesImpl(
 
   ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
 
-  mutex_.Unlock();
   if (compaction_job_info != nullptr) {
     BuildCompactionJobInfo(cfd, c.get(), s, compaction_job_stats,
                            job_context->job_id, compaction_job_info);
   }
-  mutex_.Lock();
 
   if (status.ok()) {
     // Done
@@ -1862,9 +1850,8 @@ Status DBImpl::ReFitLevel(ColumnFamilyData* cfd, int level, int target_level) {
         mutable_cf_options.compression_opts,
         mutable_cf_options.default_write_temperature,
         0 /* max_subcompactions, not applicable */,
-        {} /* grandparents, not applicable */,
-        std::nullopt /* earliest_snapshot */, nullptr /* snapshot_checker */,
-        false /* is manual */, "" /* trim_ts */, -1 /* score, not applicable */,
+        {} /* grandparents, not applicable */, false /* is manual */,
+        "" /* trim_ts */, -1 /* score, not applicable */,
         false /* is deletion compaction, not applicable */,
         false /* l0_files_might_overlap, not applicable */,
         CompactionReason::kRefitLevel));
@@ -1891,7 +1878,7 @@ Status DBImpl::ReFitLevel(ColumnFamilyData* cfd, int level, int target_level) {
     Status status = versions_->LogAndApply(cfd, mutable_cf_options,
                                            read_options, write_options, &edit,
                                            &mutex_, directories_.GetDbDir());
-    c->MarkFilesBeingCompacted(false);
+
     cfd->compaction_picker()->UnregisterCompaction(c.get());
     c.reset();
 
@@ -2317,15 +2304,13 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
     }
     WaitForPendingWrites();
 
-    if (!cfd->mem()->IsEmpty() || !cached_recoverable_state_empty_.load() ||
-        IsRecoveryFlush(flush_reason)) {
+    if (!cfd->mem()->IsEmpty() || !cached_recoverable_state_empty_.load()) {
       s = SwitchMemtable(cfd, &context);
     }
     const uint64_t flush_memtable_id = std::numeric_limits<uint64_t>::max();
     if (s.ok()) {
       if (cfd->imm()->NumNotFlushed() != 0 || !cfd->mem()->IsEmpty() ||
-          !cached_recoverable_state_empty_.load() ||
-          IsRecoveryFlush(flush_reason)) {
+          !cached_recoverable_state_empty_.load()) {
         FlushRequest req{flush_reason, {{cfd, flush_memtable_id}}};
         flush_reqs.emplace_back(std::move(req));
         memtable_ids_to_wait.emplace_back(
@@ -2388,7 +2373,7 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
         ColumnFamilyData* loop_cfd =
             req.cfd_to_max_mem_id_to_persist.begin()->first;
         bool already_queued_for_flush = loop_cfd->queued_for_flush();
-        bool flush_req_enqueued = EnqueuePendingFlush(req);
+        bool flush_req_enqueued = SchedulePendingFlush(req);
         if (already_queued_for_flush || flush_req_enqueued) {
           loop_cfd->SetFlushSkipReschedule();
         }
@@ -2418,8 +2403,7 @@ Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
     }
     s = WaitForFlushMemTables(
         cfds, flush_memtable_ids,
-        flush_reason == FlushReason::kErrorRecovery /* resuming_from_bg_err */,
-        flush_reason);
+        flush_reason == FlushReason::kErrorRecovery /* resuming_from_bg_err */);
     InstrumentedMutexLock lock_guard(&mutex_);
     for (auto* tmp_cfd : cfds) {
       tmp_cfd->UnrefAndTryDelete();
@@ -2503,7 +2487,7 @@ Status DBImpl::AtomicFlushMemTables(
     }
     WaitForPendingWrites();
 
-    SelectColumnFamiliesForAtomicFlush(&cfds, candidate_cfds, flush_reason);
+    SelectColumnFamiliesForAtomicFlush(&cfds, candidate_cfds);
 
     // Unref the newly generated candidate cfds (when not provided) in
     // `candidate_cfds`
@@ -2514,8 +2498,7 @@ Status DBImpl::AtomicFlushMemTables(
     }
 
     for (auto cfd : cfds) {
-      if (cfd->mem()->IsEmpty() && cached_recoverable_state_empty_.load() &&
-          !IsRecoveryFlush(flush_reason)) {
+      if (cfd->mem()->IsEmpty() && cached_recoverable_state_empty_.load()) {
         continue;
       }
       cfd->Ref();
@@ -2540,7 +2523,7 @@ Status DBImpl::AtomicFlushMemTables(
         }
       }
       GenerateFlushRequest(cfds, flush_reason, &flush_req);
-      EnqueuePendingFlush(flush_req);
+      SchedulePendingFlush(flush_req);
       MaybeScheduleFlushOrCompaction();
     }
 
@@ -2561,8 +2544,7 @@ Status DBImpl::AtomicFlushMemTables(
     }
     s = WaitForFlushMemTables(
         cfds, flush_memtable_ids,
-        flush_reason == FlushReason::kErrorRecovery /* resuming_from_bg_err */,
-        flush_reason);
+        flush_reason == FlushReason::kErrorRecovery /* resuming_from_bg_err */);
     InstrumentedMutexLock lock_guard(&mutex_);
     for (auto* cfd : cfds) {
       cfd->UnrefAndTryDelete();
@@ -2596,7 +2578,7 @@ Status DBImpl::RetryFlushesForErrorRecovery(FlushReason flush_reason,
   if (immutable_db_options_.atomic_flush) {
     FlushRequest flush_req;
     GenerateFlushRequest(cfds, flush_reason, &flush_req);
-    EnqueuePendingFlush(flush_req);
+    SchedulePendingFlush(flush_req);
     for (auto& iter : flush_req.cfd_to_max_mem_id_to_persist) {
       flush_memtable_ids.push_back(iter.second);
     }
@@ -2610,7 +2592,7 @@ Status DBImpl::RetryFlushesForErrorRecovery(FlushReason flush_reason,
           flush_reason,
           {{cfd,
             std::numeric_limits<uint64_t>::max() /* max_mem_id_to_persist */}}};
-      if (EnqueuePendingFlush(flush_req)) {
+      if (SchedulePendingFlush(flush_req)) {
         cfd->SetFlushSkipReschedule();
       };
     }
@@ -2625,7 +2607,7 @@ Status DBImpl::RetryFlushesForErrorRecovery(FlushReason flush_reason,
       flush_memtable_id_ptrs.push_back(&flush_memtable_id);
     }
     s = WaitForFlushMemTables(cfds, flush_memtable_id_ptrs,
-                              true /* resuming_from_bg_err */, flush_reason);
+                              true /* resuming_from_bg_err */);
     mutex_.Lock();
   }
 
@@ -2725,7 +2707,7 @@ Status DBImpl::WaitUntilFlushWouldNotStallWrites(ColumnFamilyData* cfd,
 Status DBImpl::WaitForFlushMemTables(
     const autovector<ColumnFamilyData*>& cfds,
     const autovector<const uint64_t*>& flush_memtable_ids,
-    bool resuming_from_bg_err, std::optional<FlushReason> flush_reason) {
+    bool resuming_from_bg_err) {
   int num = static_cast<int>(cfds.size());
   // Wait until the compaction completes
   InstrumentedMutexLock l(&mutex_);
@@ -2763,15 +2745,7 @@ Status DBImpl::WaitForFlushMemTables(
                  (flush_memtable_ids[i] != nullptr &&
                   cfds[i]->imm()->GetEarliestMemTableID() >
                       *flush_memtable_ids[i])) {
-        // Make file ingestion's flush wait until SuperVersion is also updated
-        // since after flush, it does range overlapping check and file level
-        // assignment with the current SuperVersion.
-        if (!flush_reason.has_value() ||
-            flush_reason.value() != FlushReason::kExternalFileIngestion ||
-            cfds[i]->GetSuperVersion()->imm->GetID() ==
-                cfds[i]->imm()->current()->GetID()) {
-          ++num_finished;
-        }
+        ++num_finished;
       }
     }
     if (1 == num_dropped && 1 == num) {
@@ -2971,7 +2945,6 @@ void DBImpl::AddToCompactionQueue(ColumnFamilyData* cfd) {
   cfd->Ref();
   compaction_queue_.push_back(cfd);
   cfd->set_queued_for_compaction(true);
-  ++unscheduled_compactions_;
 }
 
 ColumnFamilyData* DBImpl::PopFirstFromCompactionQueue() {
@@ -3027,7 +3000,7 @@ ColumnFamilyData* DBImpl::PickCompactionFromQueue(
   return cfd;
 }
 
-bool DBImpl::EnqueuePendingFlush(const FlushRequest& flush_req) {
+bool DBImpl::SchedulePendingFlush(const FlushRequest& flush_req) {
   mutex_.AssertHeld();
   bool enqueued = false;
   if (reject_new_background_jobs_) {
@@ -3063,15 +3036,16 @@ bool DBImpl::EnqueuePendingFlush(const FlushRequest& flush_req) {
   return enqueued;
 }
 
-void DBImpl::EnqueuePendingCompaction(ColumnFamilyData* cfd) {
+void DBImpl::SchedulePendingCompaction(ColumnFamilyData* cfd) {
   mutex_.AssertHeld();
   if (reject_new_background_jobs_) {
     return;
   }
   if (!cfd->queued_for_compaction() && cfd->NeedsCompaction()) {
-    TEST_SYNC_POINT_CALLBACK("EnqueuePendingCompaction::cfd",
+    TEST_SYNC_POINT_CALLBACK("SchedulePendingCompaction::cfd",
                              static_cast<void*>(cfd));
     AddToCompactionQueue(cfd);
+    ++unscheduled_compactions_;
   }
 }
 
@@ -3239,7 +3213,7 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
 #ifndef NDEBUG
       flush_req.reschedule_count += 1;
 #endif /* !NDEBUG */
-      EnqueuePendingFlush(flush_req);
+      SchedulePendingFlush(flush_req);
       *reason = flush_reason;
       *flush_rescheduled_to_retain_udt = true;
       return Status::TryAgain();
@@ -3562,14 +3536,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       is_manual && manual_compaction->disallow_trivial_move;
 
   CompactionJobStats compaction_job_stats;
-  // Set is_remote_compaction to true on CompactionBegin Event if
-  // compaction_service is set except for trivial moves. We do not know whether
-  // remote compaction will actually be successfully scheduled, or fall back to
-  // local at this time. CompactionCompleted event will tell the truth where
-  // the compaction actually happened.
-  compaction_job_stats.is_remote_compaction =
-      immutable_db_options().compaction_service != nullptr;
-
   Status status;
   if (!error_handler_.IsBGWorkStopped()) {
     if (shutting_down_.load(std::memory_order_acquire)) {
@@ -3690,20 +3656,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       // compaction is not necessary. Need to make sure mutex is held
       // until we make a copy in the following code
       TEST_SYNC_POINT("DBImpl::BackgroundCompaction():BeforePickCompaction");
-      SnapshotChecker* snapshot_checker = nullptr;
-      std::vector<SequenceNumber> snapshot_seqs;
-      // This info is not useful for other scenarios, so save querying existing
-      // snapshots for those cases.
-      if (cfd->ioptions()->compaction_style == kCompactionStyleUniversal &&
-          cfd->user_comparator()->timestamp_size() == 0) {
-        SequenceNumber earliest_write_conflict_snapshot;
-        GetSnapshotContext(job_context, &snapshot_seqs,
-                           &earliest_write_conflict_snapshot,
-                           &snapshot_checker);
-        assert(is_snapshot_supported_ || snapshots_.empty());
-      }
       c.reset(cfd->PickCompaction(*mutable_cf_options, mutable_db_options_,
-                                  snapshot_seqs, snapshot_checker, log_buffer));
+                                  log_buffer));
       TEST_SYNC_POINT("DBImpl::BackgroundCompaction():AfterPickCompaction");
 
       if (c != nullptr) {
@@ -3719,6 +3673,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
               ->ComputeCompactionScore(*(c->immutable_options()),
                                        *(c->mutable_cf_options()));
           AddToCompactionQueue(cfd);
+          ++unscheduled_compactions_;
 
           c.reset();
           // Don't need to sleep here, because BackgroundCallCompaction
@@ -3747,6 +3702,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
           if (cfd->NeedsCompaction()) {
             // Yes, we need more compactions!
             AddToCompactionQueue(cfd);
+            ++unscheduled_compactions_;
             MaybeScheduleFlushOrCompaction();
           }
         }
@@ -3807,8 +3763,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     ThreadStatusUtil::SetThreadOperation(ThreadStatus::OP_COMPACTION);
 
     compaction_job_stats.num_input_files = c->num_input_files(0);
-    // Trivial moves do not get compacted remotely
-    compaction_job_stats.is_remote_compaction = false;
 
     NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
                             compaction_job_stats, job_context->job_id);
@@ -3944,12 +3898,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
         &bg_bottom_compaction_scheduled_);
     compaction_job.Prepare();
 
-    std::unique_ptr<std::list<uint64_t>::iterator> min_options_file_number_elem;
-    if (immutable_db_options().compaction_service != nullptr) {
-      min_options_file_number_elem.reset(
-          new std::list<uint64_t>::iterator(CaptureOptionsFileNumber()));
-    }
-
     NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
                             compaction_job_stats, job_context->job_id);
     mutex_.Unlock();
@@ -3959,11 +3907,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     compaction_job.Run().PermitUncheckedError();
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
     mutex_.Lock();
-
-    if (immutable_db_options().compaction_service != nullptr) {
-      ReleaseOptionsFileNumber(min_options_file_number_elem);
-    }
-
     status =
         compaction_job.Install(*c->mutable_cf_options(), &compaction_released);
     io_s = compaction_job.io_status();
@@ -4049,6 +3992,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
                                    *(c->mutable_cf_options()));
       if (!cfd->queued_for_compaction()) {
         AddToCompactionQueue(cfd);
+        ++unscheduled_compactions_;
       }
     }
   }
@@ -4217,7 +4161,7 @@ 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;
-  const auto& input_table_properties = c->GetOrInitInputTableProperties();
+  const auto& input_table_properties = c->GetInputTableProperties();
   const auto& output_table_properties = c->GetOutputTableProperties();
   compaction_job_info->table_properties.insert(input_table_properties.begin(),
                                                input_table_properties.end());
@@ -4310,23 +4254,17 @@ void DBImpl::InstallSuperVersionAndScheduleWork(
   // newer snapshot created and released frequently, the compaction will be
   // triggered soon anyway.
   bottommost_files_mark_threshold_ = kMaxSequenceNumber;
-  standalone_range_deletion_files_mark_threshold_ = kMaxSequenceNumber;
   for (auto* my_cfd : *versions_->GetColumnFamilySet()) {
     if (!my_cfd->ioptions()->allow_ingest_behind) {
       bottommost_files_mark_threshold_ = std::min(
           bottommost_files_mark_threshold_,
           my_cfd->current()->storage_info()->bottommost_files_mark_threshold());
     }
-    standalone_range_deletion_files_mark_threshold_ =
-        std::min(standalone_range_deletion_files_mark_threshold_,
-                 cfd->current()
-                     ->storage_info()
-                     ->standalone_range_tombstone_files_mark_threshold());
   }
 
   // Whenever we install new SuperVersion, we might need to issue new flushes or
   // compactions.
-  EnqueuePendingCompaction(cfd);
+  SchedulePendingCompaction(cfd);
   MaybeScheduleFlushOrCompaction();
 
   // Update max_total_in_memory_state_

db/db_impl/db_impl_debug.cc

@@ -9,7 +9,6 @@
 
 #ifndef NDEBUG
 
-#include "db/blob/blob_file_cache.h"
 #include "db/column_family.h"
 #include "db/db_impl/db_impl.h"
 #include "db/error_handler.h"
@@ -200,11 +199,6 @@ Status DBImpl::TEST_GetBGError() {
   return error_handler_.GetBGError();
 }
 
-bool DBImpl::TEST_IsRecoveryInProgress() {
-  InstrumentedMutexLock l(&mutex_);
-  return error_handler_.IsRecoveryInProgress();
-}
-
 void DBImpl::TEST_LockMutex() { mutex_.Lock(); }
 
 void DBImpl::TEST_UnlockMutex() { mutex_.Unlock(); }
@@ -233,16 +227,23 @@ uint64_t DBImpl::TEST_LogfileNumber() {
   return logfile_number_;
 }
 
-void DBImpl::TEST_GetAllBlockCaches(
-    std::unordered_set<const Cache*>* cache_set) {
-  InstrumentedMutexLock l(&mutex_);
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    if (const auto bbto =
-            cfd->GetCurrentMutableCFOptions()
-                ->table_factory->GetOptions<BlockBasedTableOptions>()) {
-      cache_set->insert(bbto->block_cache.get());
+Status DBImpl::TEST_GetAllImmutableCFOptions(
+    std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map) {
+  std::vector<std::string> cf_names;
+  std::vector<const ImmutableCFOptions*> iopts;
+  {
+    InstrumentedMutexLock l(&mutex_);
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      cf_names.push_back(cfd->GetName());
+      iopts.push_back(cfd->ioptions());
     }
   }
+  iopts_map->clear();
+  for (size_t i = 0; i < cf_names.size(); ++i) {
+    iopts_map->insert({cf_names[i], iopts[i]});
+  }
+
+  return Status::OK();
 }
 
 uint64_t DBImpl::TEST_FindMinLogContainingOutstandingPrep() {
@@ -322,49 +323,5 @@ size_t DBImpl::TEST_EstimateInMemoryStatsHistorySize() const {
   InstrumentedMutexLock l(&const_cast<DBImpl*>(this)->stats_history_mutex_);
   return EstimateInMemoryStatsHistorySize();
 }
-
-void DBImpl::TEST_VerifyNoObsoleteFilesCached(
-    bool db_mutex_already_held) const {
-  // This check is somewhat expensive and obscure to make a part of every
-  // unit test in every build variety. Thus, we only enable it for ASAN builds.
-  if (!kMustFreeHeapAllocations) {
-    return;
-  }
-
-  std::optional<InstrumentedMutexLock> l;
-  if (db_mutex_already_held) {
-    mutex_.AssertHeld();
-  } else {
-    l.emplace(&mutex_);
-  }
-
-  std::vector<uint64_t> live_files;
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    if (cfd->IsDropped()) {
-      continue;
-    }
-    // Sneakily add both SST and blob files to the same list
-    cfd->current()->AddLiveFiles(&live_files, &live_files);
-  }
-  std::sort(live_files.begin(), live_files.end());
-
-  auto fn = [&live_files](const Slice& key, Cache::ObjectPtr, size_t,
-                          const Cache::CacheItemHelper* helper) {
-    if (helper != BlobFileCache::GetHelper()) {
-      // Skip non-blob files for now
-      // FIXME: diagnose and fix the leaks of obsolete SST files revealed in
-      // unit tests.
-      return;
-    }
-    // See TableCache and BlobFileCache
-    assert(key.size() == sizeof(uint64_t));
-    uint64_t file_number;
-    GetUnaligned(reinterpret_cast<const uint64_t*>(key.data()), &file_number);
-    // Assert file is in sorted live_files
-    assert(
-        std::binary_search(live_files.begin(), live_files.end(), file_number));
-  };
-  table_cache_->ApplyToAllEntries(fn, {});
-}
 }  // namespace ROCKSDB_NAMESPACE
 #endif  // NDEBUG

db/db_impl/db_impl_experimental.cc

@@ -47,7 +47,7 @@ Status DBImpl::SuggestCompactRange(ColumnFamilyHandle* column_family,
     // compaction score
     vstorage->ComputeCompactionScore(*cfd->ioptions(),
                                      *cfd->GetLatestMutableCFOptions());
-    EnqueuePendingCompaction(cfd);
+    SchedulePendingCompaction(cfd);
     MaybeScheduleFlushOrCompaction();
   }
   return Status::OK();

db/db_impl/db_impl_files.cc

@@ -43,14 +43,6 @@ uint64_t DBImpl::GetObsoleteSstFilesSize() {
   return versions_->GetObsoleteSstFilesSize();
 }
 
-uint64_t DBImpl::MinOptionsFileNumberToKeep() {
-  mutex_.AssertHeld();
-  if (!min_options_file_numbers_.empty()) {
-    return *min_options_file_numbers_.begin();
-  }
-  return std::numeric_limits<uint64_t>::max();
-}
-
 Status DBImpl::DisableFileDeletions() {
   Status s;
   int my_disable_delete_obsolete_files;
@@ -155,7 +147,6 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
   // here but later find newer generated unfinalized files while scanning.
   job_context->min_pending_output = MinObsoleteSstNumberToKeep();
   job_context->files_to_quarantine = error_handler_.GetFilesToQuarantine();
-  job_context->min_options_file_number = MinOptionsFileNumberToKeep();
 
   // Get obsolete files.  This function will also update the list of
   // pending files in VersionSet().
@@ -507,7 +498,7 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
                                 dbname_);
 
   // File numbers of most recent two OPTIONS file in candidate_files (found in
-  // previous FindObsoleteFiles(full_scan=true))
+  // previos FindObsoleteFiles(full_scan=true))
   // At this point, there must not be any duplicate file numbers in
   // candidate_files.
   uint64_t optsfile_num1 = std::numeric_limits<uint64_t>::min();
@@ -528,11 +519,6 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
     }
   }
 
-  // For remote compactions, we need to keep OPTIONS file that may get
-  // referenced by the remote worker
-
-  optsfile_num2 = std::min(optsfile_num2, state.min_options_file_number);
-
   // Close WALs before trying to delete them.
   for (const auto w : state.logs_to_free) {
     // TODO: maybe check the return value of Close.
@@ -736,38 +722,6 @@ void DBImpl::DeleteObsoleteFiles() {
   mutex_.Lock();
 }
 
-VersionEdit GetDBRecoveryEditForObsoletingMemTables(
-    VersionSet* vset, const ColumnFamilyData& cfd,
-    const autovector<VersionEdit*>& edit_list,
-    const autovector<MemTable*>& memtables, LogsWithPrepTracker* prep_tracker) {
-  VersionEdit wal_deletion_edit;
-  uint64_t min_wal_number_to_keep = 0;
-  assert(edit_list.size() > 0);
-  if (vset->db_options()->allow_2pc) {
-    // Note that if mempurge is successful, the edit_list will
-    // not be applicable (contains info of new min_log number to keep,
-    // and level 0 file path of SST file created during normal flush,
-    // so both pieces of information are irrelevant after a successful
-    // mempurge operation).
-    min_wal_number_to_keep = PrecomputeMinLogNumberToKeep2PC(
-        vset, cfd, edit_list, memtables, prep_tracker);
-
-    // We piggyback the information of earliest log file to keep in the
-    // manifest entry for the last file flushed.
-  } else {
-    min_wal_number_to_keep =
-        PrecomputeMinLogNumberToKeepNon2PC(vset, cfd, edit_list);
-  }
-
-  wal_deletion_edit.SetMinLogNumberToKeep(min_wal_number_to_keep);
-  if (vset->db_options()->track_and_verify_wals_in_manifest) {
-    if (min_wal_number_to_keep > vset->GetWalSet().GetMinWalNumberToKeep()) {
-      wal_deletion_edit.DeleteWalsBefore(min_wal_number_to_keep);
-    }
-  }
-  return wal_deletion_edit;
-}
-
 uint64_t FindMinPrepLogReferencedByMemTable(
     VersionSet* vset, const autovector<MemTable*>& memtables_to_flush) {
   uint64_t min_log = 0;
@@ -967,65 +921,57 @@ uint64_t PrecomputeMinLogNumberToKeep2PC(
 }
 
 void DBImpl::SetDBId(std::string&& id, bool read_only,
-                     VersionEdit* version_edit) {
+                     RecoveryContext* recovery_ctx) {
   assert(db_id_.empty());
   assert(!id.empty());
   db_id_ = std::move(id);
-  if (!read_only && version_edit) {
-    assert(version_edit != nullptr);
+  if (!read_only && immutable_db_options_.write_dbid_to_manifest) {
+    assert(recovery_ctx != nullptr);
     assert(versions_->GetColumnFamilySet() != nullptr);
-    version_edit->SetDBId(db_id_);
+    VersionEdit edit;
+    edit.SetDBId(db_id_);
     versions_->db_id_ = db_id_;
+    recovery_ctx->UpdateVersionEdits(
+        versions_->GetColumnFamilySet()->GetDefault(), edit);
   }
 }
 
 Status DBImpl::SetupDBId(const WriteOptions& write_options, bool read_only,
-                         bool is_new_db, bool is_retry,
-                         VersionEdit* version_edit) {
+                         RecoveryContext* recovery_ctx) {
   Status s;
-  if (!is_new_db) {
-    // Check for the IDENTITY file and create it if not there or
-    // broken or not matching manifest
-    std::string db_id_in_file;
-    s = fs_->FileExists(IdentityFileName(dbname_), IOOptions(), nullptr);
-    if (s.ok()) {
-      IOOptions opts;
-      if (is_retry) {
-        opts.verify_and_reconstruct_read = true;
-      }
-      s = GetDbIdentityFromIdentityFile(opts, &db_id_in_file);
-      if (s.ok() && !db_id_in_file.empty()) {
-        if (db_id_.empty()) {
-          // Loaded from file and wasn't already known from manifest
-          SetDBId(std::move(db_id_in_file), read_only, version_edit);
-          return s;
-        } else if (db_id_ == db_id_in_file) {
-          // Loaded from file and matches manifest
-          return s;
-        }
+  // Check for the IDENTITY file and create it if not there or
+  // broken or not matching manifest
+  std::string db_id_in_file;
+  s = fs_->FileExists(IdentityFileName(dbname_), IOOptions(), nullptr);
+  if (s.ok()) {
+    s = GetDbIdentityFromIdentityFile(&db_id_in_file);
+    if (s.ok() && !db_id_in_file.empty()) {
+      if (db_id_.empty()) {
+        // Loaded from file and wasn't already known from manifest
+        SetDBId(std::move(db_id_in_file), read_only, recovery_ctx);
+        return s;
+      } else if (db_id_ == db_id_in_file) {
+        // Loaded from file and matches manifest
+        return s;
       }
     }
-    if (s.IsNotFound()) {
-      s = Status::OK();
-    }
-    if (!s.ok()) {
-      assert(s.IsIOError());
-      return s;
-    }
+  }
+  if (s.IsNotFound()) {
+    s = Status::OK();
+  }
+  if (!s.ok()) {
+    assert(s.IsIOError());
+    return s;
   }
   // Otherwise IDENTITY file is missing or no good.
   // Generate new id if needed
   if (db_id_.empty()) {
-    SetDBId(env_->GenerateUniqueId(), read_only, version_edit);
+    SetDBId(env_->GenerateUniqueId(), read_only, recovery_ctx);
   }
   // Persist it to IDENTITY file if allowed
-  if (!read_only && immutable_db_options_.write_identity_file) {
-    s = SetIdentityFile(write_options, env_, dbname_,
-                        immutable_db_options_.metadata_write_temperature,
-                        db_id_);
+  if (!read_only) {
+    s = SetIdentityFile(write_options, env_, dbname_, db_id_);
   }
-  // NOTE: an obsolete IDENTITY file with write_identity_file=false is handled
-  // elsewhere, so that it's only deleted after successful recovery
   return s;
 }
 

db/db_impl/db_impl_open.cc

@@ -289,25 +289,27 @@ Status DBImpl::ValidateOptions(const DBOptions& db_options) {
           "start_time and end_time cannot be the same");
     }
   }
-
-  if (!db_options.write_dbid_to_manifest && !db_options.write_identity_file) {
-    return Status::InvalidArgument(
-        "write_dbid_to_manifest and write_identity_file cannot both be false");
-  }
   return Status::OK();
 }
 
 Status DBImpl::NewDB(std::vector<std::string>* new_filenames) {
-  VersionEdit new_db_edit;
+  VersionEdit new_db;
   const WriteOptions write_options(Env::IOActivity::kDBOpen);
-  Status s = SetupDBId(write_options, /*read_only=*/false, /*is_new_db=*/true,
-                       /*is_retry=*/false, &new_db_edit);
+  Status s = SetIdentityFile(write_options, env_, dbname_);
   if (!s.ok()) {
     return s;
   }
-  new_db_edit.SetLogNumber(0);
-  new_db_edit.SetNextFile(2);
-  new_db_edit.SetLastSequence(0);
+  if (immutable_db_options_.write_dbid_to_manifest) {
+    std::string temp_db_id;
+    s = GetDbIdentityFromIdentityFile(&temp_db_id);
+    if (!s.ok()) {
+      return s;
+    }
+    new_db.SetDBId(temp_db_id);
+  }
+  new_db.SetLogNumber(0);
+  new_db.SetNextFile(2);
+  new_db.SetLastSequence(0);
 
   ROCKS_LOG_INFO(immutable_db_options_.info_log, "Creating manifest 1 \n");
   const std::string manifest = DescriptorFileName(dbname_, 1);
@@ -317,12 +319,6 @@ Status DBImpl::NewDB(std::vector<std::string>* new_filenames) {
     }
     std::unique_ptr<FSWritableFile> file;
     FileOptions file_options = fs_->OptimizeForManifestWrite(file_options_);
-    // DB option takes precedence when not kUnknown
-    if (immutable_db_options_.metadata_write_temperature !=
-        Temperature::kUnknown) {
-      file_options.temperature =
-          immutable_db_options_.metadata_write_temperature;
-    }
     s = NewWritableFile(fs_.get(), manifest, &file, file_options);
     if (!s.ok()) {
       return s;
@@ -339,7 +335,7 @@ Status DBImpl::NewDB(std::vector<std::string>* new_filenames) {
         tmp_set.Contains(FileType::kDescriptorFile)));
     log::Writer log(std::move(file_writer), 0, false);
     std::string record;
-    new_db_edit.EncodeTo(&record);
+    new_db.EncodeTo(&record);
     s = log.AddRecord(write_options, record);
     if (s.ok()) {
       s = SyncManifest(&immutable_db_options_, write_options, log.file());
@@ -348,7 +344,6 @@ Status DBImpl::NewDB(std::vector<std::string>* new_filenames) {
   if (s.ok()) {
     // Make "CURRENT" file that points to the new manifest file.
     s = SetCurrentFile(write_options, fs_.get(), dbname_, 1,
-                       immutable_db_options_.metadata_write_temperature,
                        directories_.GetDbDir());
     if (new_filenames) {
       new_filenames->emplace_back(
@@ -525,7 +520,7 @@ Status DBImpl::Recover(
     }
     assert(s.ok());
   }
-  assert(is_new_db || db_id_.empty());
+  assert(db_id_.empty());
   Status s;
   bool missing_table_file = false;
   if (!immutable_db_options_.best_efforts_recovery) {
@@ -535,12 +530,6 @@ Status DBImpl::Recover(
                            /*no_error_if_files_missing=*/false, is_retry,
                            &desc_status);
     desc_status.PermitUncheckedError();
-    if (is_retry) {
-      RecordTick(stats_, FILE_READ_CORRUPTION_RETRY_COUNT);
-      if (desc_status.ok()) {
-        RecordTick(stats_, FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT);
-      }
-    }
     if (can_retry) {
       // If we're opening for the first time and the failure is likely due to
       // a corrupt MANIFEST file (could result in either the log::Reader
@@ -651,7 +640,7 @@ Status DBImpl::Recover(
                            f->fd.smallest_seqno, f->fd.largest_seqno,
                            f->marked_for_compaction,
                            f->temperature,  // this can be different from
-                           // `last_level_temperature`
+                                            // `last_level_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,
@@ -671,17 +660,7 @@ Status DBImpl::Recover(
       }
     }
   }
-  if (is_new_db) {
-    // Already set up DB ID in NewDB
-  } else if (immutable_db_options_.write_dbid_to_manifest && recovery_ctx) {
-    VersionEdit edit;
-    s = SetupDBId(write_options, read_only, is_new_db, is_retry, &edit);
-    recovery_ctx->UpdateVersionEdits(
-        versions_->GetColumnFamilySet()->GetDefault(), edit);
-  } else {
-    s = SetupDBId(write_options, read_only, is_new_db, is_retry, nullptr);
-  }
-  assert(!s.ok() || !db_id_.empty());
+  s = SetupDBId(write_options, read_only, recovery_ctx);
   ROCKS_LOG_INFO(immutable_db_options_.info_log, "DB ID: %s\n", db_id_.c_str());
   if (s.ok() && !read_only) {
     s = MaybeUpdateNextFileNumber(recovery_ctx);
@@ -1274,8 +1253,7 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& wal_numbers,
           reader.GetRecordedTimestampSize();
       status = HandleWriteBatchTimestampSizeDifference(
           &batch, running_ts_sz, record_ts_sz,
-          TimestampSizeConsistencyMode::kReconcileInconsistency, seq_per_batch_,
-          batch_per_txn_, &new_batch);
+          TimestampSizeConsistencyMode::kReconcileInconsistency, &new_batch);
       if (!status.ok()) {
         return status;
       }
@@ -1668,19 +1646,9 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
   Arena arena;
   Status s;
   TableProperties table_properties;
-  const auto* ucmp = cfd->internal_comparator().user_comparator();
-  assert(ucmp);
-  const size_t ts_sz = ucmp->timestamp_size();
-  const bool logical_strip_timestamp =
-      ts_sz > 0 && !cfd->ioptions()->persist_user_defined_timestamps;
   {
     ScopedArenaPtr<InternalIterator> iter(
-        logical_strip_timestamp
-            ? mem->NewTimestampStrippingIterator(
-                  ro, /*seqno_to_time_mapping=*/nullptr, &arena,
-                  /*prefix_extractor=*/nullptr, ts_sz)
-            : mem->NewIterator(ro, /*seqno_to_time_mapping=*/nullptr, &arena,
-                               /*prefix_extractor=*/nullptr));
+        mem->NewIterator(ro, /*seqno_to_time_mapping=*/nullptr, &arena));
     ROCKS_LOG_DEBUG(immutable_db_options_.info_log,
                     "[%s] [WriteLevel0TableForRecovery]"
                     " Level-0 table #%" PRIu64 ": started",
@@ -1699,8 +1667,7 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
     meta.oldest_ancester_time = current_time;
     meta.epoch_number = cfd->NewEpochNumber();
     {
-      auto write_hint =
-          cfd->current()->storage_info()->CalculateSSTWriteHint(/*level=*/0);
+      auto write_hint = cfd->CalculateSSTWriteHint(0);
       mutex_.Unlock();
 
       SequenceNumber earliest_write_conflict_snapshot;
@@ -1715,14 +1682,11 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
           range_del_iters;
       auto range_del_iter =
-          logical_strip_timestamp
-              ? mem->NewTimestampStrippingRangeTombstoneIterator(
-                    ro, kMaxSequenceNumber, ts_sz)
-              // This is called during recovery, where a live memtable is
-              // flushed directly. In this case, no fragmented tombstone list is
-              // cached in this memtable yet.
-              : mem->NewRangeTombstoneIterator(ro, kMaxSequenceNumber,
-                                               false /* immutable_memtable */);
+          // This is called during recovery, where a live memtable is flushed
+          // directly. In this case, no fragmented tombstone list is cached in
+          // this memtable yet.
+          mem->NewRangeTombstoneIterator(ro, kMaxSequenceNumber,
+                                         false /* immutable_memtable */);
       if (range_del_iter != nullptr) {
         range_del_iters.emplace_back(range_del_iter);
       }
@@ -1808,7 +1772,9 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
 
     // For UDT in memtable only feature, move up the cutoff timestamp whenever
     // a flush happens.
-    if (logical_strip_timestamp) {
+    const Comparator* ucmp = cfd->user_comparator();
+    size_t ts_sz = ucmp->timestamp_size();
+    if (ts_sz > 0 && !cfd->ioptions()->persist_user_defined_timestamps) {
       Slice mem_newest_udt = mem->GetNewestUDT();
       std::string full_history_ts_low = cfd->GetFullHistoryTsLow();
       if (full_history_ts_low.empty() ||
@@ -1964,10 +1930,6 @@ IOStatus DBImpl::CreateWAL(const WriteOptions& write_options,
       BuildDBOptions(immutable_db_options_, mutable_db_options_);
   FileOptions opt_file_options =
       fs_->OptimizeForLogWrite(file_options_, db_options);
-  // DB option takes precedence when not kUnknown
-  if (immutable_db_options_.wal_write_temperature != Temperature::kUnknown) {
-    opt_file_options.temperature = immutable_db_options_.wal_write_temperature;
-  }
   std::string wal_dir = immutable_db_options_.GetWalDir();
   std::string log_fname = LogFileName(wal_dir, log_file_num);
 
@@ -2007,7 +1969,46 @@ IOStatus DBImpl::CreateWAL(const WriteOptions& write_options,
 
 void DBImpl::TrackExistingDataFiles(
     const std::vector<std::string>& existing_data_files) {
-  TrackOrUntrackFiles(existing_data_files, /*track=*/true);
+  auto sfm = static_cast<SstFileManagerImpl*>(
+      immutable_db_options_.sst_file_manager.get());
+  assert(sfm);
+  std::vector<ColumnFamilyMetaData> metadata;
+  GetAllColumnFamilyMetaData(&metadata);
+
+  std::unordered_set<std::string> referenced_files;
+  for (const auto& md : metadata) {
+    for (const auto& lmd : md.levels) {
+      for (const auto& fmd : lmd.files) {
+        // We're assuming that each sst file name exists in at most one of
+        // the paths.
+        std::string file_path =
+            fmd.directory + kFilePathSeparator + fmd.relative_filename;
+        sfm->OnAddFile(file_path, fmd.size).PermitUncheckedError();
+        referenced_files.insert(file_path);
+      }
+    }
+    for (const auto& bmd : md.blob_files) {
+      std::string name = bmd.blob_file_name;
+      // The BlobMetaData.blob_file_name may start with "/".
+      if (!name.empty() && name[0] == kFilePathSeparator) {
+        name = name.substr(1);
+      }
+      // We're assuming that each blob file name exists in at most one of
+      // the paths.
+      std::string file_path = bmd.blob_file_path + kFilePathSeparator + name;
+      sfm->OnAddFile(file_path, bmd.blob_file_size).PermitUncheckedError();
+      referenced_files.insert(file_path);
+    }
+  }
+
+  for (const auto& file_path : existing_data_files) {
+    if (referenced_files.find(file_path) != referenced_files.end()) {
+      continue;
+    }
+    // There shouldn't be any duplicated files. In case there is, SstFileManager
+    // will take care of deduping it.
+    sfm->OnAddFile(file_path).PermitUncheckedError();
+  }
 }
 
 Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
@@ -2151,13 +2152,6 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
     s = impl->LogAndApplyForRecovery(recovery_ctx);
   }
 
-  if (s.ok() && !impl->immutable_db_options_.write_identity_file) {
-    // On successful recovery, delete an obsolete IDENTITY file to avoid DB ID
-    // inconsistency
-    impl->env_->DeleteFile(IdentityFileName(impl->dbname_))
-        .PermitUncheckedError();
-  }
-
   if (s.ok() && impl->immutable_db_options_.persist_stats_to_disk) {
     impl->mutex_.AssertHeld();
     s = impl->InitPersistStatsColumnFamily();

db/db_impl/db_impl_readonly.cc

@@ -265,8 +265,7 @@ Status OpenForReadOnlyCheckExistence(const DBOptions& db_options,
     const std::shared_ptr<FileSystem>& fs = db_options.env->GetFileSystem();
     std::string manifest_path;
     uint64_t manifest_file_number;
-    s = VersionSet::GetCurrentManifestPath(dbname, fs.get(), /*is_retry=*/false,
-                                           &manifest_path,
+    s = VersionSet::GetCurrentManifestPath(dbname, fs.get(), &manifest_path,
                                            &manifest_file_number);
   } else {
     // Historic behavior that doesn't necessarily make sense

db/db_impl/db_impl_secondary.cc

@@ -12,8 +12,7 @@
 #include "logging/auto_roll_logger.h"
 #include "logging/logging.h"
 #include "monitoring/perf_context_imp.h"
-#include "rocksdb/convenience.h"
-#include "rocksdb/utilities/options_util.h"
+#include "rocksdb/configurable.h"
 #include "util/cast_util.h"
 #include "util/write_batch_util.h"
 
@@ -233,8 +232,7 @@ Status DBImplSecondary::RecoverLogFiles(
           reader->GetRecordedTimestampSize();
       status = HandleWriteBatchTimestampSizeDifference(
           &batch, running_ts_sz, record_ts_sz,
-          TimestampSizeConsistencyMode::kVerifyConsistency, seq_per_batch_,
-          batch_per_txn_);
+          TimestampSizeConsistencyMode::kVerifyConsistency);
       if (!status.ok()) {
         break;
       }
@@ -940,105 +938,69 @@ Status DB::OpenAndCompact(
     const std::string& output_directory, const std::string& input,
     std::string* output,
     const CompactionServiceOptionsOverride& override_options) {
-  // Check for cancellation
   if (options.canceled && options.canceled->load(std::memory_order_acquire)) {
     return Status::Incomplete(Status::SubCode::kManualCompactionPaused);
   }
-
-  // 1. Deserialize Compaction Input
   CompactionServiceInput compaction_input;
   Status s = CompactionServiceInput::Read(input, &compaction_input);
   if (!s.ok()) {
     return s;
   }
 
-  // 2. Load the options
-  DBOptions db_options;
-  ConfigOptions config_options;
-  config_options.env = override_options.env;
-  std::vector<ColumnFamilyDescriptor> all_column_families;
-
-  TEST_SYNC_POINT_CALLBACK(
-      "DBImplSecondary::OpenAndCompact::BeforeLoadingOptions:0",
-      &compaction_input.options_file_number);
-  TEST_SYNC_POINT("DBImplSecondary::OpenAndCompact::BeforeLoadingOptions:1");
-  std::string options_file_name =
-      OptionsFileName(name, compaction_input.options_file_number);
-
-  s = LoadOptionsFromFile(config_options, options_file_name, &db_options,
-                          &all_column_families);
-  if (!s.ok()) {
-    return s;
+  compaction_input.db_options.max_open_files = -1;
+  compaction_input.db_options.compaction_service = nullptr;
+  if (compaction_input.db_options.statistics) {
+    compaction_input.db_options.statistics.reset();
   }
-
-  // 3. Override pointer configurations in DBOptions with
-  // CompactionServiceOptionsOverride
-  db_options.env = override_options.env;
-  db_options.file_checksum_gen_factory =
+  compaction_input.db_options.env = override_options.env;
+  compaction_input.db_options.file_checksum_gen_factory =
       override_options.file_checksum_gen_factory;
-  db_options.statistics = override_options.statistics;
-  db_options.listeners = override_options.listeners;
-  db_options.compaction_service = nullptr;
-  // We will close the DB after the compaction anyway.
-  // Open as many files as needed for the compaction.
-  db_options.max_open_files = -1;
+  compaction_input.db_options.statistics = override_options.statistics;
+  compaction_input.column_family.options.comparator =
+      override_options.comparator;
+  compaction_input.column_family.options.merge_operator =
+      override_options.merge_operator;
+  compaction_input.column_family.options.compaction_filter =
+      override_options.compaction_filter;
+  compaction_input.column_family.options.compaction_filter_factory =
+      override_options.compaction_filter_factory;
+  compaction_input.column_family.options.prefix_extractor =
+      override_options.prefix_extractor;
+  compaction_input.column_family.options.table_factory =
+      override_options.table_factory;
+  compaction_input.column_family.options.sst_partitioner_factory =
+      override_options.sst_partitioner_factory;
+  compaction_input.column_family.options.table_properties_collector_factories =
+      override_options.table_properties_collector_factories;
+  compaction_input.db_options.listeners = override_options.listeners;
 
-  // 4. Filter CFs that are needed for OpenAndCompact()
-  // We do not need to open all column families for the remote compaction.
-  // Only open default CF + target CF. If target CF == default CF, we will open
-  // just the default CF (Due to current limitation, DB cannot open without the
-  // default CF)
   std::vector<ColumnFamilyDescriptor> column_families;
-  for (auto& cf : all_column_families) {
-    if (cf.name == compaction_input.cf_name) {
-      cf.options.comparator = override_options.comparator;
-      cf.options.merge_operator = override_options.merge_operator;
-      cf.options.compaction_filter = override_options.compaction_filter;
-      cf.options.compaction_filter_factory =
-          override_options.compaction_filter_factory;
-      cf.options.prefix_extractor = override_options.prefix_extractor;
-      cf.options.table_factory = override_options.table_factory;
-      cf.options.sst_partitioner_factory =
-          override_options.sst_partitioner_factory;
-      cf.options.table_properties_collector_factories =
-          override_options.table_properties_collector_factories;
-      column_families.emplace_back(cf);
-    } else if (cf.name == kDefaultColumnFamilyName) {
-      column_families.emplace_back(cf);
-    }
+  column_families.push_back(compaction_input.column_family);
+  // TODO: we have to open default CF, because of an implementation limitation,
+  // currently we just use the same CF option from input, which is not collect
+  // and open may fail.
+  if (compaction_input.column_family.name != kDefaultColumnFamilyName) {
+    column_families.emplace_back(kDefaultColumnFamilyName,
+                                 compaction_input.column_family.options);
   }
 
-  // 5. Open db As Secondary
   DB* db;
   std::vector<ColumnFamilyHandle*> handles;
-  s = DB::OpenAsSecondary(db_options, name, output_directory, column_families,
-                          &handles, &db);
+
+  s = DB::OpenAsSecondary(compaction_input.db_options, name, output_directory,
+                          column_families, &handles, &db);
   if (!s.ok()) {
     return s;
   }
-  assert(db);
 
-  // 6. Find the handle of the Column Family that this will compact
-  ColumnFamilyHandle* cfh = nullptr;
-  for (auto* handle : handles) {
-    if (compaction_input.cf_name == handle->GetName()) {
-      cfh = handle;
-      break;
-    }
-  }
-  assert(cfh);
-
-  // 7. Run the compaction without installation.
-  // Output will be stored in the directory specified by output_directory
   CompactionServiceResult compaction_result;
   DBImplSecondary* db_secondary = static_cast_with_check<DBImplSecondary>(db);
-  s = db_secondary->CompactWithoutInstallation(options, cfh, compaction_input,
-                                               &compaction_result);
+  assert(handles.size() > 0);
+  s = db_secondary->CompactWithoutInstallation(
+      options, handles[0], compaction_input, &compaction_result);
 
-  // 8. Serialize the result
   Status serialization_status = compaction_result.Write(output);
 
-  // 9. Close the db and return
   for (auto& handle : handles) {
     delete handle;
   }

db/db_impl/db_impl_write.cc

@@ -556,35 +556,6 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
     const SequenceNumber current_sequence = last_sequence + 1;
     last_sequence += seq_inc;
 
-    if (log_context.need_log_sync) {
-      VersionEdit synced_wals;
-      log_write_mutex_.Lock();
-      if (status.ok()) {
-        MarkLogsSynced(logfile_number_, log_context.need_log_dir_sync,
-                       &synced_wals);
-      } else {
-        MarkLogsNotSynced(logfile_number_);
-      }
-      log_write_mutex_.Unlock();
-      if (status.ok() && synced_wals.IsWalAddition()) {
-        InstrumentedMutexLock l(&mutex_);
-        // TODO: plumb Env::IOActivity, Env::IOPriority
-        const ReadOptions read_options;
-        status = ApplyWALToManifest(read_options, write_options, &synced_wals);
-      }
-
-      // Requesting sync with two_write_queues_ is expected to be very rare. We
-      // hence provide a simple implementation that is not necessarily
-      // efficient.
-      if (status.ok() && two_write_queues_) {
-        if (manual_wal_flush_) {
-          status = FlushWAL(true);
-        } else {
-          status = SyncWAL();
-        }
-      }
-    }
-
     // PreReleaseCallback is called after WAL write and before memtable write
     if (status.ok()) {
       SequenceNumber next_sequence = current_sequence;
@@ -656,7 +627,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
 
   if (!io_s.ok()) {
     // Check WriteToWAL status
-    WALIOStatusCheck(io_s);
+    IOStatusCheck(io_s);
   }
   if (!w.CallbackFailed()) {
     if (!io_s.ok()) {
@@ -668,6 +639,34 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
     assert(pre_release_cb_status.ok());
   }
 
+  if (log_context.need_log_sync) {
+    VersionEdit synced_wals;
+    log_write_mutex_.Lock();
+    if (status.ok()) {
+      MarkLogsSynced(logfile_number_, log_context.need_log_dir_sync,
+                     &synced_wals);
+    } else {
+      MarkLogsNotSynced(logfile_number_);
+    }
+    log_write_mutex_.Unlock();
+    if (status.ok() && synced_wals.IsWalAddition()) {
+      InstrumentedMutexLock l(&mutex_);
+      // TODO: plumb Env::IOActivity, Env::IOPriority
+      const ReadOptions read_options;
+      status = ApplyWALToManifest(read_options, write_options, &synced_wals);
+    }
+
+    // Requesting sync with two_write_queues_ is expected to be very rare. We
+    // hence provide a simple implementation that is not necessarily efficient.
+    if (two_write_queues_) {
+      if (manual_wal_flush_) {
+        status = FlushWAL(true);
+      } else {
+        status = SyncWAL();
+      }
+    }
+  }
+
   bool should_exit_batch_group = true;
   if (in_parallel_group) {
     // CompleteParallelWorker returns true if this thread should
@@ -735,6 +734,17 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
     size_t total_byte_size = 0;
 
     if (w.status.ok()) {
+      // TODO: this use of operator bool on `tracer_` can avoid unnecessary lock
+      // grabs but does not seem thread-safe.
+      if (tracer_) {
+        InstrumentedMutexLock lock(&trace_mutex_);
+        if (tracer_ != nullptr && tracer_->IsWriteOrderPreserved()) {
+          for (auto* writer : wal_write_group) {
+            // TODO: maybe handle the tracing status?
+            tracer_->Write(writer->batch).PermitUncheckedError();
+          }
+        }
+      }
       SequenceNumber next_sequence = current_sequence;
       for (auto* writer : wal_write_group) {
         assert(writer);
@@ -749,22 +759,6 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
           }
         }
       }
-      // TODO: this use of operator bool on `tracer_` can avoid unnecessary lock
-      // grabs but does not seem thread-safe.
-      if (tracer_) {
-        InstrumentedMutexLock lock(&trace_mutex_);
-        if (tracer_ != nullptr && tracer_->IsWriteOrderPreserved()) {
-          for (auto* writer : wal_write_group) {
-            if (writer->CallbackFailed()) {
-              // When optimisitc txn conflict checking fails, we should
-              // not record to trace.
-              continue;
-            }
-            // TODO: maybe handle the tracing status?
-            tracer_->Write(writer->batch).PermitUncheckedError();
-          }
-        }
-      }
       if (w.disable_wal) {
         has_unpersisted_data_.store(true, std::memory_order_relaxed);
       }
@@ -804,7 +798,7 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
 
     if (!io_s.ok()) {
       // Check WriteToWAL status
-      WALIOStatusCheck(io_s);
+      IOStatusCheck(io_s);
     } else if (!w.CallbackFailed()) {
       WriteStatusCheck(w.status);
     }
@@ -974,17 +968,21 @@ Status DBImpl::WriteImplWALOnly(
   assert(w.state == WriteThread::STATE_GROUP_LEADER);
 
   if (publish_last_seq == kDoPublishLastSeq) {
+    Status status;
+
     // Currently we only use kDoPublishLastSeq in unordered_write
     assert(immutable_db_options_.unordered_write);
-
+    WriteContext write_context;
+    if (error_handler_.IsDBStopped()) {
+      status = error_handler_.GetBGError();
+    }
     // TODO(myabandeh): Make preliminary checks thread-safe so we could do them
     // without paying the cost of obtaining the mutex.
-    LogContext log_context;
-    WriteContext write_context;
-    Status status =
-        PreprocessWrite(write_options, &log_context, &write_context);
-    WriteStatusCheckOnLocked(status);
-
+    if (status.ok()) {
+      LogContext log_context;
+      status = PreprocessWrite(write_options, &log_context, &write_context);
+      WriteStatusCheckOnLocked(status);
+    }
     if (!status.ok()) {
       WriteThread::WriteGroup write_group;
       write_thread->EnterAsBatchGroupLeader(&w, &write_group);
@@ -1010,6 +1008,19 @@ Status DBImpl::WriteImplWALOnly(
   WriteThread::WriteGroup write_group;
   uint64_t last_sequence;
   write_thread->EnterAsBatchGroupLeader(&w, &write_group);
+  // Note: no need to update last_batch_group_size_ here since the batch writes
+  // to WAL only
+  // TODO: this use of operator bool on `tracer_` can avoid unnecessary lock
+  // grabs but does not seem thread-safe.
+  if (tracer_) {
+    InstrumentedMutexLock lock(&trace_mutex_);
+    if (tracer_ != nullptr && tracer_->IsWriteOrderPreserved()) {
+      for (auto* writer : write_group) {
+        // TODO: maybe handle the tracing status?
+        tracer_->Write(writer->batch).PermitUncheckedError();
+      }
+    }
+  }
 
   size_t pre_release_callback_cnt = 0;
   size_t total_byte_size = 0;
@@ -1024,23 +1035,6 @@ Status DBImpl::WriteImplWALOnly(
     }
   }
 
-  // Note: no need to update last_batch_group_size_ here since the batch writes
-  // to WAL only
-  // TODO: this use of operator bool on `tracer_` can avoid unnecessary lock
-  // grabs but does not seem thread-safe.
-  if (tracer_) {
-    InstrumentedMutexLock lock(&trace_mutex_);
-    if (tracer_ != nullptr && tracer_->IsWriteOrderPreserved()) {
-      for (auto* writer : write_group) {
-        if (writer->CallbackFailed()) {
-          continue;
-        }
-        // TODO: maybe handle the tracing status?
-        tracer_->Write(writer->batch).PermitUncheckedError();
-      }
-    }
-  }
-
   const bool concurrent_update = true;
   // Update stats while we are an exclusive group leader, so we know
   // that nobody else can be writing to these particular stats.
@@ -1086,7 +1080,7 @@ Status DBImpl::WriteImplWALOnly(
     // This error checking and return is moved up to avoid using uninitialized
     // last_sequence.
     if (!io_s.ok()) {
-      WALIOStatusCheck(io_s);
+      IOStatusCheck(io_s);
       write_thread->ExitAsBatchGroupLeader(write_group, status);
       return status;
     }
@@ -1184,7 +1178,7 @@ void DBImpl::WriteStatusCheck(const Status& status) {
   }
 }
 
-void DBImpl::WALIOStatusCheck(const IOStatus& io_status) {
+void DBImpl::IOStatusCheck(const IOStatus& io_status) {
   // Is setting bg_error_ enough here?  This will at least stop
   // compaction and fail any further writes.
   if ((immutable_db_options_.paranoid_checks && !io_status.ok() &&
@@ -1192,8 +1186,7 @@ void DBImpl::WALIOStatusCheck(const IOStatus& io_status) {
       io_status.IsIOFenced()) {
     mutex_.Lock();
     // Maybe change the return status to void?
-    error_handler_.SetBGError(io_status, BackgroundErrorReason::kWriteCallback,
-                              /*wal_related=*/true);
+    error_handler_.SetBGError(io_status, BackgroundErrorReason::kWriteCallback);
     mutex_.Unlock();
   } else {
     // Force writable file to be continue writable.
@@ -1211,7 +1204,8 @@ void DBImpl::MemTableInsertStatusCheck(const Status& status) {
     mutex_.Lock();
     assert(!error_handler_.IsBGWorkStopped());
     // Maybe change the return status to void?
-    error_handler_.SetBGError(status, BackgroundErrorReason::kMemTable);
+    error_handler_.SetBGError(status, BackgroundErrorReason::kMemTable)
+        .PermitUncheckedError();
     mutex_.Unlock();
   }
 }
@@ -1417,7 +1411,6 @@ IOStatus DBImpl::WriteToWAL(const WriteBatch& merged_batch,
   total_log_size_ += log_entry.size();
   log_file_number_size.AddSize(*log_size);
   log_empty_ = false;
-
   return io_s;
 }
 
@@ -1490,14 +1483,9 @@ IOStatus DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
         if (!io_s.ok()) {
           break;
         }
-        // If last sync failed on a later WAL, this could be a fully synced
-        // and closed WAL that just needs to be recorded as synced in the
-        // manifest.
-        if (auto* f = log.writer->file()) {
-          io_s = f->Sync(opts, immutable_db_options_.use_fsync);
-          if (!io_s.ok()) {
-            break;
-          }
+        io_s = log.writer->file()->Sync(opts, immutable_db_options_.use_fsync);
+        if (!io_s.ok()) {
+          break;
         }
       }
     }
@@ -1662,8 +1650,7 @@ Status DBImpl::WriteRecoverableState() {
 
 void DBImpl::SelectColumnFamiliesForAtomicFlush(
     autovector<ColumnFamilyData*>* selected_cfds,
-    const autovector<ColumnFamilyData*>& provided_candidate_cfds,
-    FlushReason flush_reason) {
+    const autovector<ColumnFamilyData*>& provided_candidate_cfds) {
   mutex_.AssertHeld();
   assert(selected_cfds);
 
@@ -1686,8 +1673,7 @@ void DBImpl::SelectColumnFamiliesForAtomicFlush(
       continue;
     }
     if (cfd->imm()->NumNotFlushed() != 0 || !cfd->mem()->IsEmpty() ||
-        !cached_recoverable_state_empty_.load() ||
-        IsRecoveryFlush(flush_reason)) {
+        !cached_recoverable_state_empty_.load()) {
       selected_cfds->push_back(cfd);
     }
   }
@@ -1799,13 +1785,13 @@ Status DBImpl::SwitchWAL(WriteContext* write_context) {
       if (!immutable_db_options_.atomic_flush) {
         FlushRequest flush_req;
         GenerateFlushRequest({cfd}, FlushReason::kWalFull, &flush_req);
-        EnqueuePendingFlush(flush_req);
+        SchedulePendingFlush(flush_req);
       }
     }
     if (immutable_db_options_.atomic_flush) {
       FlushRequest flush_req;
       GenerateFlushRequest(cfds, FlushReason::kWalFull, &flush_req);
-      EnqueuePendingFlush(flush_req);
+      SchedulePendingFlush(flush_req);
     }
     MaybeScheduleFlushOrCompaction();
   }
@@ -1891,13 +1877,13 @@ Status DBImpl::HandleWriteBufferManagerFlush(WriteContext* write_context) {
         FlushRequest flush_req;
         GenerateFlushRequest({cfd}, FlushReason::kWriteBufferManager,
                              &flush_req);
-        EnqueuePendingFlush(flush_req);
+        SchedulePendingFlush(flush_req);
       }
     }
     if (immutable_db_options_.atomic_flush) {
       FlushRequest flush_req;
       GenerateFlushRequest(cfds, FlushReason::kWriteBufferManager, &flush_req);
-      EnqueuePendingFlush(flush_req);
+      SchedulePendingFlush(flush_req);
     }
     MaybeScheduleFlushOrCompaction();
   }
@@ -2173,12 +2159,12 @@ Status DBImpl::ScheduleFlushes(WriteContext* context) {
       AssignAtomicFlushSeq(cfds);
       FlushRequest flush_req;
       GenerateFlushRequest(cfds, FlushReason::kWriteBufferFull, &flush_req);
-      EnqueuePendingFlush(flush_req);
+      SchedulePendingFlush(flush_req);
     } else {
       for (auto* cfd : cfds) {
         FlushRequest flush_req;
         GenerateFlushRequest({cfd}, FlushReason::kWriteBufferFull, &flush_req);
-        EnqueuePendingFlush(flush_req);
+        SchedulePendingFlush(flush_req);
       }
     }
     MaybeScheduleFlushOrCompaction();
@@ -2336,8 +2322,7 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
     // We may have lost data from the WritableFileBuffer in-memory buffer for
     // the current log, so treat it as a fatal error and set bg_error
     if (!io_s.ok()) {
-      error_handler_.SetBGError(io_s, BackgroundErrorReason::kMemTable,
-                                /*wal_related=*/true);
+      error_handler_.SetBGError(io_s, BackgroundErrorReason::kMemTable);
     } else {
       error_handler_.SetBGError(s, BackgroundErrorReason::kMemTable);
     }
@@ -2378,8 +2363,8 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
           read_options, write_options, &wal_deletion, &mutex_,
           directories_.GetDbDir());
       if (!s.ok() && versions_->io_status().IsIOError()) {
-        error_handler_.SetBGError(versions_->io_status(),
-                                  BackgroundErrorReason::kManifestWrite);
+        s = error_handler_.SetBGError(versions_->io_status(),
+                                      BackgroundErrorReason::kManifestWrite);
       }
       if (!s.ok()) {
         return s;

db/db_io_failure_test.cc

@@ -27,14 +27,12 @@ class CorruptionFS : public FileSystemWrapper {
         num_writable_file_errors_(0),
         corruption_trigger_(INT_MAX),
         read_count_(0),
-        corrupt_offset_(0),
-        corrupt_len_(0),
         rnd_(300),
         fs_buffer_(fs_buffer),
         verify_read_(verify_read) {}
   ~CorruptionFS() override {
     // Assert that the corruption was reset, which means it got triggered
-    assert(corruption_trigger_ == INT_MAX || corrupt_len_ > 0);
+    assert(corruption_trigger_ == INT_MAX);
   }
   const char* Name() const override { return "ErrorEnv"; }
 
@@ -50,10 +48,8 @@ class CorruptionFS : public FileSystemWrapper {
   }
 
   void SetCorruptionTrigger(const int trigger) {
-    MutexLock l(&mutex_);
     corruption_trigger_ = trigger;
     read_count_ = 0;
-    corrupt_fname_.clear();
   }
 
   IOStatus NewRandomAccessFile(const std::string& fname,
@@ -62,31 +58,25 @@ class CorruptionFS : public FileSystemWrapper {
                                IODebugContext* dbg) override {
     class CorruptionRandomAccessFile : public FSRandomAccessFileOwnerWrapper {
      public:
-      CorruptionRandomAccessFile(CorruptionFS& fs, const std::string& fname,
+      CorruptionRandomAccessFile(CorruptionFS& fs,
                                  std::unique_ptr<FSRandomAccessFile>& file)
-          : FSRandomAccessFileOwnerWrapper(std::move(file)),
-            fs_(fs),
-            fname_(fname) {}
+          : FSRandomAccessFileOwnerWrapper(std::move(file)), fs_(fs) {}
 
       IOStatus Read(uint64_t offset, size_t len, const IOOptions& opts,
                     Slice* result, char* scratch,
                     IODebugContext* dbg) const override {
         IOStatus s = target()->Read(offset, len, opts, result, scratch, dbg);
         if (opts.verify_and_reconstruct_read) {
-          fs_.MaybeResetOverlapWithCorruptedChunk(fname_, offset,
-                                                  result->size());
           return s;
         }
-
-        MutexLock l(&fs_.mutex_);
         if (s.ok() && ++fs_.read_count_ >= fs_.corruption_trigger_) {
+          fs_.read_count_ = 0;
           fs_.corruption_trigger_ = INT_MAX;
           char* data = const_cast<char*>(result->data());
           std::memcpy(
               data,
               fs_.rnd_.RandomString(static_cast<int>(result->size())).c_str(),
               result->size());
-          fs_.SetCorruptedChunk(fname_, offset, result->size());
         }
         return s;
       }
@@ -111,76 +101,14 @@ class CorruptionFS : public FileSystemWrapper {
         return IOStatus::OK();
       }
 
-      IOStatus Prefetch(uint64_t /*offset*/, size_t /*n*/,
-                        const IOOptions& /*options*/,
-                        IODebugContext* /*dbg*/) override {
-        return IOStatus::NotSupported("Prefetch");
-      }
-
      private:
       CorruptionFS& fs_;
-      std::string fname_;
     };
 
     std::unique_ptr<FSRandomAccessFile> file;
     IOStatus s = target()->NewRandomAccessFile(fname, opts, &file, dbg);
     EXPECT_OK(s);
-    result->reset(new CorruptionRandomAccessFile(*this, fname, file));
-
-    return s;
-  }
-
-  IOStatus NewSequentialFile(const std::string& fname,
-                             const FileOptions& file_opts,
-                             std::unique_ptr<FSSequentialFile>* result,
-                             IODebugContext* dbg) override {
-    class CorruptionSequentialFile : public FSSequentialFileOwnerWrapper {
-     public:
-      CorruptionSequentialFile(CorruptionFS& fs, const std::string& fname,
-                               std::unique_ptr<FSSequentialFile>& file)
-          : FSSequentialFileOwnerWrapper(std::move(file)),
-            fs_(fs),
-            fname_(fname),
-            offset_(0) {}
-
-      IOStatus Read(size_t len, const IOOptions& opts, Slice* result,
-                    char* scratch, IODebugContext* dbg) override {
-        IOStatus s = target()->Read(len, opts, result, scratch, dbg);
-        if (result->size() == 0 ||
-            fname_.find("IDENTITY") != std::string::npos) {
-          return s;
-        }
-
-        if (opts.verify_and_reconstruct_read) {
-          fs_.MaybeResetOverlapWithCorruptedChunk(fname_, offset_,
-                                                  result->size());
-          return s;
-        }
-
-        MutexLock l(&fs_.mutex_);
-        if (s.ok() && ++fs_.read_count_ >= fs_.corruption_trigger_) {
-          fs_.corruption_trigger_ = INT_MAX;
-          char* data = const_cast<char*>(result->data());
-          std::memcpy(
-              data,
-              fs_.rnd_.RandomString(static_cast<int>(result->size())).c_str(),
-              result->size());
-          fs_.SetCorruptedChunk(fname_, offset_, result->size());
-        }
-        offset_ += result->size();
-        return s;
-      }
-
-     private:
-      CorruptionFS& fs_;
-      std::string fname_;
-      size_t offset_;
-    };
-
-    std::unique_ptr<FSSequentialFile> file;
-    IOStatus s = target()->NewSequentialFile(fname, file_opts, &file, dbg);
-    EXPECT_OK(s);
-    result->reset(new CorruptionSequentialFile(*this, fname, file));
+    result->reset(new CorruptionRandomAccessFile(*this, file));
 
     return s;
   }
@@ -195,40 +123,12 @@ class CorruptionFS : public FileSystemWrapper {
     }
   }
 
-  void SetCorruptedChunk(const std::string& fname, size_t offset, size_t len) {
-    assert(corrupt_fname_.empty());
-
-    corrupt_fname_ = fname;
-    corrupt_offset_ = offset;
-    corrupt_len_ = len;
-  }
-
-  void MaybeResetOverlapWithCorruptedChunk(const std::string& fname,
-                                           size_t offset, size_t len) {
-    if (fname == corrupt_fname_ &&
-        ((offset <= corrupt_offset_ && (offset + len) > corrupt_offset_) ||
-         (offset >= corrupt_offset_ &&
-          offset < (corrupt_offset_ + corrupt_len_)))) {
-      corrupt_fname_.clear();
-    }
-  }
-
-  bool VerifyRetry() { return corrupt_len_ > 0 && corrupt_fname_.empty(); }
-
-  int read_count() { return read_count_; }
-
-  int corruption_trigger() { return corruption_trigger_; }
-
  private:
   int corruption_trigger_;
   int read_count_;
-  std::string corrupt_fname_;
-  size_t corrupt_offset_;
-  size_t corrupt_len_;
   Random rnd_;
   bool fs_buffer_;
   bool verify_read_;
-  port::Mutex mutex_;
 };
 }  // anonymous namespace
 
@@ -805,7 +705,6 @@ class DBIOCorruptionTest
   DBIOCorruptionTest() : DBIOFailureTest() {
     BlockBasedTableOptions bbto;
     options_ = CurrentOptions();
-    options_.statistics = CreateDBStatistics();
 
     base_env_ = env_;
     EXPECT_NE(base_env_, nullptr);
@@ -817,7 +716,6 @@ class DBIOCorruptionTest
     bbto.num_file_reads_for_auto_readahead = 0;
     options_.table_factory.reset(NewBlockBasedTableFactory(bbto));
     options_.disable_auto_compactions = true;
-    options_.max_file_opening_threads = 0;
 
     Reopen(options_);
   }
@@ -829,8 +727,6 @@ class DBIOCorruptionTest
 
   Status ReopenDB() { return TryReopen(options_); }
 
-  Statistics* stats() { return options_.statistics.get(); }
-
  protected:
   std::unique_ptr<Env> env_guard_;
   std::shared_ptr<CorruptionFS> fs_;
@@ -853,12 +749,8 @@ TEST_P(DBIOCorruptionTest, GetReadCorruptionRetry) {
   if (std::get<2>(GetParam())) {
     ASSERT_OK(s);
     ASSERT_EQ(val, "val1");
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
   } else {
     ASSERT_TRUE(s.IsCorruption());
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
   }
 }
 
@@ -881,12 +773,8 @@ TEST_P(DBIOCorruptionTest, IterReadCorruptionRetry) {
   }
   if (std::get<2>(GetParam())) {
     ASSERT_OK(iter->status());
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
   } else {
     ASSERT_TRUE(iter->status().IsCorruption());
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
   }
   delete iter;
 }
@@ -911,13 +799,9 @@ TEST_P(DBIOCorruptionTest, MultiGetReadCorruptionRetry) {
   if (std::get<2>(GetParam())) {
     ASSERT_EQ(values[0].ToString(), "val1");
     ASSERT_EQ(values[1].ToString(), "val2");
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
   } else {
     ASSERT_TRUE(statuses[0].IsCorruption());
     ASSERT_TRUE(statuses[1].IsCorruption());
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
   }
 }
 
@@ -934,9 +818,6 @@ TEST_P(DBIOCorruptionTest, CompactionReadCorruptionRetry) {
   Status s = dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
   if (std::get<2>(GetParam())) {
     ASSERT_OK(s);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
 
     std::string val;
     ReadOptions ro;
@@ -945,7 +826,6 @@ TEST_P(DBIOCorruptionTest, CompactionReadCorruptionRetry) {
     ASSERT_EQ(val, "val1");
   } else {
     ASSERT_TRUE(s.IsCorruption());
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
   }
 }
 
@@ -958,9 +838,6 @@ TEST_P(DBIOCorruptionTest, FlushReadCorruptionRetry) {
   Status s = Flush();
   if (std::get<2>(GetParam())) {
     ASSERT_OK(s);
-    ASSERT_GT(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_GT(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
 
     std::string val;
     ReadOptions ro;
@@ -969,7 +846,6 @@ TEST_P(DBIOCorruptionTest, FlushReadCorruptionRetry) {
     ASSERT_EQ(val, "val1");
   } else {
     ASSERT_NOK(s);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
   }
 }
 
@@ -986,142 +862,12 @@ TEST_P(DBIOCorruptionTest, ManifestCorruptionRetry) {
 
   if (std::get<2>(GetParam())) {
     ASSERT_OK(ReopenDB());
-    ASSERT_GT(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_GT(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
   } else {
     ASSERT_EQ(ReopenDB(), Status::Corruption());
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
   }
   SyncPoint::GetInstance()->DisableProcessing();
 }
 
-TEST_P(DBIOCorruptionTest, FooterReadCorruptionRetry) {
-  Random rnd(300);
-  bool retry = false;
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "ReadFooterFromFileInternal:0", [&](void* arg) {
-        Slice* data = static_cast<Slice*>(arg);
-        if (!retry) {
-          std::memcpy(const_cast<char*>(data->data()),
-                      rnd.RandomString(static_cast<int>(data->size())).c_str(),
-                      data->size());
-          retry = true;
-        }
-      });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("key1", "val1"));
-  Status s = Flush();
-  if (std::get<2>(GetParam())) {
-    ASSERT_OK(s);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
-
-    std::string val;
-    ReadOptions ro;
-    ro.async_io = std::get<1>(GetParam());
-    ASSERT_OK(dbfull()->Get(ro, "key1", &val));
-    ASSERT_EQ(val, "val1");
-  } else {
-    ASSERT_NOK(s);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
-    ASSERT_GT(stats()->getTickerCount(SST_FOOTER_CORRUPTION_COUNT), 0);
-  }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_P(DBIOCorruptionTest, TablePropertiesCorruptionRetry) {
-  Random rnd(300);
-  bool retry = false;
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "ReadTablePropertiesHelper:0", [&](void* arg) {
-        Slice* data = static_cast<Slice*>(arg);
-        if (!retry) {
-          std::memcpy(const_cast<char*>(data->data()),
-                      rnd.RandomString(static_cast<int>(data->size())).c_str(),
-                      data->size());
-          retry = true;
-        }
-      });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("key1", "val1"));
-  Status s = Flush();
-  if (std::get<2>(GetParam())) {
-    ASSERT_OK(s);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 1);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_SUCCESS_COUNT),
-              1);
-
-    std::string val;
-    ReadOptions ro;
-    ro.async_io = std::get<1>(GetParam());
-    ASSERT_OK(dbfull()->Get(ro, "key1", &val));
-    ASSERT_EQ(val, "val1");
-  } else {
-    ASSERT_NOK(s);
-    ASSERT_EQ(stats()->getTickerCount(FILE_READ_CORRUPTION_RETRY_COUNT), 0);
-  }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_P(DBIOCorruptionTest, DBOpenReadCorruptionRetry) {
-  if (!std::get<2>(GetParam())) {
-    return;
-  }
-  CorruptionFS* fs =
-      static_cast<CorruptionFS*>(env_guard_->GetFileSystem().get());
-
-  for (int sst = 0; sst < 3; ++sst) {
-    for (int key = 0; key < 100; ++key) {
-      std::stringstream ss;
-      ss << std::setw(3) << 100 * sst + key;
-      ASSERT_OK(Put("key" + ss.str(), "val" + ss.str()));
-    }
-    ASSERT_OK(Flush());
-  }
-  Close();
-
-  // DB open will create table readers unless we reduce the table cache
-  // capacity.
-  // SanitizeOptions will set max_open_files to minimum of 20. Table cache
-  // is allocated with max_open_files - 10 as capacity. So override
-  // max_open_files to 11 so table cache capacity will become 1. This will
-  // prevent file open during DB open and force the file to be opened
-  // during MultiGet
-  SyncPoint::GetInstance()->SetCallBack(
-      "SanitizeOptions::AfterChangeMaxOpenFiles", [&](void* arg) {
-        int* max_open_files = (int*)arg;
-        *max_open_files = 11;
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  // Progressively increase the IO count trigger for corruption, and verify
-  // that it was retried
-  int corruption_trigger = 1;
-  fs->SetCorruptionTrigger(corruption_trigger);
-  do {
-    fs->SetCorruptionTrigger(corruption_trigger);
-    ASSERT_OK(ReopenDB());
-    for (int sst = 0; sst < 3; ++sst) {
-      for (int key = 0; key < 100; ++key) {
-        std::stringstream ss;
-        ss << std::setw(3) << 100 * sst + key;
-        ASSERT_EQ(Get("key" + ss.str()), "val" + ss.str());
-      }
-    }
-    // Verify that the injected corruption was repaired
-    ASSERT_TRUE(fs->VerifyRetry());
-    corruption_trigger++;
-  } while (fs->corruption_trigger() == INT_MAX);
-}
-
 // The parameters are - 1. Use FS provided buffer, 2. Use async IO ReadOption,
 // 3. Retry with verify_and_reconstruct_read IOOption
 INSTANTIATE_TEST_CASE_P(DBIOCorruptionTest, DBIOCorruptionTest,

db/db_iter.cc

@@ -52,9 +52,7 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
       user_comparator_(cmp),
       merge_operator_(ioptions.merge_operator.get()),
       iter_(iter),
-      blob_reader_(version, read_options.read_tier,
-                   read_options.verify_checksums, read_options.fill_cache,
-                   read_options.io_activity),
+      version_(version),
       read_callback_(read_callback),
       sequence_(s),
       statistics_(ioptions.stats),
@@ -67,16 +65,20 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
       valid_(false),
       current_entry_is_merged_(false),
       is_key_seqnum_zero_(false),
-      prefix_same_as_start_(
-          prefix_extractor_ ? read_options.prefix_same_as_start : false),
+      prefix_same_as_start_(mutable_cf_options.prefix_extractor
+                                ? read_options.prefix_same_as_start
+                                : false),
       pin_thru_lifetime_(read_options.pin_data),
       expect_total_order_inner_iter_(prefix_extractor_ == nullptr ||
                                      read_options.total_order_seek ||
                                      read_options.auto_prefix_mode),
+      read_tier_(read_options.read_tier),
+      fill_cache_(read_options.fill_cache),
+      verify_checksums_(read_options.verify_checksums),
       expose_blob_index_(expose_blob_index),
-      allow_unprepared_value_(read_options.allow_unprepared_value),
       is_blob_(false),
       arena_mode_(arena_mode),
+      io_activity_(read_options.io_activity),
       cfh_(cfh),
       timestamp_ub_(read_options.timestamp),
       timestamp_lb_(read_options.iter_start_ts),
@@ -91,9 +93,6 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
   status_.PermitUncheckedError();
   assert(timestamp_size_ ==
          user_comparator_.user_comparator()->timestamp_size());
-  // prefix_seek_opt_in_only should force total_order_seek whereever the caller
-  // is duplicating the original ReadOptions
-  assert(!ioptions.prefix_seek_opt_in_only || read_options.total_order_seek);
 }
 
 Status DBIter::GetProperty(std::string prop_name, std::string* prop) {
@@ -150,7 +149,7 @@ void DBIter::Next() {
   PERF_CPU_TIMER_GUARD(iter_next_cpu_nanos, clock_);
   // Release temporarily pinned blocks from last operation
   ReleaseTempPinnedData();
-  ResetBlobData();
+  ResetBlobValue();
   ResetValueAndColumns();
   local_stats_.skip_count_ += num_internal_keys_skipped_;
   local_stats_.skip_count_--;
@@ -193,21 +192,29 @@ void DBIter::Next() {
   }
 }
 
-Status DBIter::BlobReader::RetrieveAndSetBlobValue(const Slice& user_key,
-                                                   const Slice& blob_index) {
+bool DBIter::SetBlobValueIfNeeded(const Slice& user_key,
+                                  const Slice& blob_index) {
+  assert(!is_blob_);
   assert(blob_value_.empty());
 
+  if (expose_blob_index_) {  // Stacked BlobDB implementation
+    is_blob_ = true;
+    return true;
+  }
+
   if (!version_) {
-    return Status::Corruption("Encountered unexpected blob index.");
+    status_ = Status::Corruption("Encountered unexpected blob index.");
+    valid_ = false;
+    return false;
   }
 
   // TODO: consider moving ReadOptions from ArenaWrappedDBIter to DBIter to
   // avoid having to copy options back and forth.
-  // TODO: plumb Env::IOPriority
+  // TODO: plumb Env::IOActivity, Env::IOPriority
   ReadOptions read_options;
   read_options.read_tier = read_tier_;
-  read_options.verify_checksums = verify_checksums_;
   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;
@@ -215,49 +222,14 @@ Status DBIter::BlobReader::RetrieveAndSetBlobValue(const Slice& user_key,
   const Status s = version_->GetBlob(read_options, user_key, blob_index,
                                      prefetch_buffer, &blob_value_, bytes_read);
 
-  if (!s.ok()) {
-    return s;
-  }
-
-  return Status::OK();
-}
-
-bool DBIter::SetValueAndColumnsFromBlobImpl(const Slice& user_key,
-                                            const Slice& blob_index) {
-  const Status s = blob_reader_.RetrieveAndSetBlobValue(user_key, blob_index);
   if (!s.ok()) {
     status_ = s;
     valid_ = false;
-    is_blob_ = false;
     return false;
   }
 
-  SetValueAndColumnsFromPlain(blob_reader_.GetBlobValue());
-
-  return true;
-}
-
-bool DBIter::SetValueAndColumnsFromBlob(const Slice& user_key,
-                                        const Slice& blob_index) {
-  assert(!is_blob_);
   is_blob_ = true;
-
-  if (expose_blob_index_) {
-    SetValueAndColumnsFromPlain(blob_index);
-    return true;
-  }
-
-  if (allow_unprepared_value_) {
-    assert(value_.empty());
-    assert(wide_columns_.empty());
-
-    assert(lazy_blob_index_.empty());
-    lazy_blob_index_ = blob_index;
-
-    return true;
-  }
-
-  return SetValueAndColumnsFromBlobImpl(user_key, blob_index);
+  return true;
 }
 
 bool DBIter::SetValueAndColumnsFromEntity(Slice slice) {
@@ -305,24 +277,6 @@ bool DBIter::SetValueAndColumnsFromMergeResult(const Status& merge_status,
   return true;
 }
 
-bool DBIter::PrepareValue() {
-  assert(valid_);
-
-  if (lazy_blob_index_.empty()) {
-    return true;
-  }
-
-  assert(allow_unprepared_value_);
-  assert(is_blob_);
-
-  const bool result =
-      SetValueAndColumnsFromBlobImpl(saved_key_.GetUserKey(), lazy_blob_index_);
-
-  lazy_blob_index_.clear();
-
-  return result;
-}
-
 // PRE: saved_key_ has the current user key if skipping_saved_key
 // POST: saved_key_ should have the next user key if valid_,
 //       if the current entry is a result of merge
@@ -452,7 +406,7 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
           case kTypeValuePreferredSeqno:
           case kTypeBlobIndex:
           case kTypeWideColumnEntity:
-            if (!PrepareValueInternal()) {
+            if (!PrepareValue()) {
               return false;
             }
             if (timestamp_lb_) {
@@ -464,9 +418,12 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
             }
 
             if (ikey_.type == kTypeBlobIndex) {
-              if (!SetValueAndColumnsFromBlob(ikey_.user_key, iter_.value())) {
+              if (!SetBlobValueIfNeeded(ikey_.user_key, iter_.value())) {
                 return false;
               }
+
+              SetValueAndColumnsFromPlain(expose_blob_index_ ? iter_.value()
+                                                             : blob_value_);
             } else if (ikey_.type == kTypeWideColumnEntity) {
               if (!SetValueAndColumnsFromEntity(iter_.value())) {
                 return false;
@@ -486,7 +443,7 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
             return true;
             break;
           case kTypeMerge:
-            if (!PrepareValueInternal()) {
+            if (!PrepareValue()) {
               return false;
             }
             saved_key_.SetUserKey(
@@ -581,8 +538,6 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
     } else {
       iter_.Next();
     }
-    // This could be a long-running operation due to tombstones, etc.
-    ROCKSDB_THREAD_YIELD_HOOK();
   } while (iter_.Valid());
 
   valid_ = false;
@@ -633,7 +588,7 @@ bool DBIter::MergeValuesNewToOld() {
       iter_.Next();
       break;
     }
-    if (!PrepareValueInternal()) {
+    if (!PrepareValue()) {
       return false;
     }
 
@@ -662,9 +617,23 @@ bool DBIter::MergeValuesNewToOld() {
           iter_.value(), iter_.iter()->IsValuePinned() /* operand_pinned */);
       PERF_COUNTER_ADD(internal_merge_count, 1);
     } else if (kTypeBlobIndex == ikey.type) {
-      if (!MergeWithBlobBaseValue(iter_.value(), ikey.user_key)) {
+      if (expose_blob_index_) {
+        status_ =
+            Status::NotSupported("BlobDB does not support merge operator.");
+        valid_ = false;
         return false;
       }
+      // hit a put, merge the put value with operands and store the
+      // final result in saved_value_. We are done!
+      if (!SetBlobValueIfNeeded(ikey.user_key, iter_.value())) {
+        return false;
+      }
+      valid_ = true;
+      if (!MergeWithPlainBaseValue(blob_value_, ikey.user_key)) {
+        return false;
+      }
+
+      ResetBlobValue();
 
       // iter_ is positioned after put
       iter_.Next();
@@ -672,7 +641,6 @@ bool DBIter::MergeValuesNewToOld() {
         valid_ = false;
         return false;
       }
-
       return true;
     } else if (kTypeWideColumnEntity == ikey.type) {
       if (!MergeWithWideColumnBaseValue(iter_.value(), ikey.user_key)) {
@@ -719,7 +687,7 @@ void DBIter::Prev() {
   PERF_COUNTER_ADD(iter_prev_count, 1);
   PERF_CPU_TIMER_GUARD(iter_prev_cpu_nanos, clock_);
   ReleaseTempPinnedData();
-  ResetBlobData();
+  ResetBlobValue();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
   bool ok = true;
@@ -956,7 +924,7 @@ bool DBIter::FindValueForCurrentKey() {
       return FindValueForCurrentKeyUsingSeek();
     }
 
-    if (!PrepareValueInternal()) {
+    if (!PrepareValue()) {
       return false;
     }
 
@@ -1071,9 +1039,21 @@ bool DBIter::FindValueForCurrentKey() {
         }
         return true;
       } else if (last_not_merge_type == kTypeBlobIndex) {
-        if (!MergeWithBlobBaseValue(pinned_value_, saved_key_.GetUserKey())) {
+        if (expose_blob_index_) {
+          status_ =
+              Status::NotSupported("BlobDB does not support merge operator.");
+          valid_ = false;
           return false;
         }
+        if (!SetBlobValueIfNeeded(saved_key_.GetUserKey(), pinned_value_)) {
+          return false;
+        }
+        valid_ = true;
+        if (!MergeWithPlainBaseValue(blob_value_, saved_key_.GetUserKey())) {
+          return false;
+        }
+
+        ResetBlobValue();
 
         return true;
       } else if (last_not_merge_type == kTypeWideColumnEntity) {
@@ -1098,9 +1078,13 @@ bool DBIter::FindValueForCurrentKey() {
 
       break;
     case kTypeBlobIndex:
-      if (!SetValueAndColumnsFromBlob(saved_key_.GetUserKey(), pinned_value_)) {
+      if (!SetBlobValueIfNeeded(saved_key_.GetUserKey(), pinned_value_)) {
         return false;
       }
+
+      SetValueAndColumnsFromPlain(expose_blob_index_ ? pinned_value_
+                                                     : blob_value_);
+
       break;
     case kTypeWideColumnEntity:
       if (!SetValueAndColumnsFromEntity(pinned_value_)) {
@@ -1187,7 +1171,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
     }
     return true;
   }
-  if (!PrepareValueInternal()) {
+  if (!PrepareValue()) {
     return false;
   }
   if (timestamp_size_ > 0) {
@@ -1204,9 +1188,12 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
       pinned_value_ = iter_.value();
     }
     if (ikey.type == kTypeBlobIndex) {
-      if (!SetValueAndColumnsFromBlob(ikey.user_key, pinned_value_)) {
+      if (!SetBlobValueIfNeeded(ikey.user_key, pinned_value_)) {
         return false;
       }
+
+      SetValueAndColumnsFromPlain(expose_blob_index_ ? pinned_value_
+                                                     : blob_value_);
     } else if (ikey.type == kTypeWideColumnEntity) {
       if (!SetValueAndColumnsFromEntity(pinned_value_)) {
         return false;
@@ -1254,7 +1241,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
         ikey.type == kTypeDeletionWithTimestamp) {
       break;
     }
-    if (!PrepareValueInternal()) {
+    if (!PrepareValue()) {
       return false;
     }
 
@@ -1272,9 +1259,21 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
           iter_.value(), iter_.iter()->IsValuePinned() /* operand_pinned */);
       PERF_COUNTER_ADD(internal_merge_count, 1);
     } else if (ikey.type == kTypeBlobIndex) {
-      if (!MergeWithBlobBaseValue(iter_.value(), saved_key_.GetUserKey())) {
+      if (expose_blob_index_) {
+        status_ =
+            Status::NotSupported("BlobDB does not support merge operator.");
+        valid_ = false;
         return false;
       }
+      if (!SetBlobValueIfNeeded(ikey.user_key, iter_.value())) {
+        return false;
+      }
+      valid_ = true;
+      if (!MergeWithPlainBaseValue(blob_value_, saved_key_.GetUserKey())) {
+        return false;
+      }
+
+      ResetBlobValue();
 
       return true;
     } else if (ikey.type == kTypeWideColumnEntity) {
@@ -1341,35 +1340,6 @@ bool DBIter::MergeWithPlainBaseValue(const Slice& value,
   return SetValueAndColumnsFromMergeResult(s, result_type);
 }
 
-bool DBIter::MergeWithBlobBaseValue(const Slice& blob_index,
-                                    const Slice& user_key) {
-  assert(!is_blob_);
-
-  if (expose_blob_index_) {
-    status_ =
-        Status::NotSupported("Legacy BlobDB does not support merge operator.");
-    valid_ = false;
-    return false;
-  }
-
-  const Status s = blob_reader_.RetrieveAndSetBlobValue(user_key, blob_index);
-  if (!s.ok()) {
-    status_ = s;
-    valid_ = false;
-    return false;
-  }
-
-  valid_ = true;
-
-  if (!MergeWithPlainBaseValue(blob_reader_.GetBlobValue(), user_key)) {
-    return false;
-  }
-
-  blob_reader_.ResetBlobValue();
-
-  return true;
-}
-
 bool DBIter::MergeWithWideColumnBaseValue(const Slice& entity,
                                           const Slice& user_key) {
   // `op_failure_scope` (an output parameter) is not provided (set to nullptr)
@@ -1559,7 +1529,7 @@ void DBIter::Seek(const Slice& target) {
 
   status_ = Status::OK();
   ReleaseTempPinnedData();
-  ResetBlobData();
+  ResetBlobValue();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
 
@@ -1635,7 +1605,7 @@ void DBIter::SeekForPrev(const Slice& target) {
 
   status_ = Status::OK();
   ReleaseTempPinnedData();
-  ResetBlobData();
+  ResetBlobValue();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
 
@@ -1696,7 +1666,7 @@ void DBIter::SeekToFirst() {
   status_.PermitUncheckedError();
   direction_ = kForward;
   ReleaseTempPinnedData();
-  ResetBlobData();
+  ResetBlobValue();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
   ClearSavedValue();
@@ -1759,7 +1729,7 @@ void DBIter::SeekToLast() {
   status_.PermitUncheckedError();
   direction_ = kReverse;
   ReleaseTempPinnedData();
-  ResetBlobData();
+  ResetBlobValue();
   ResetValueAndColumns();
   ResetInternalKeysSkippedCounter();
   ClearSavedValue();

db/db_iter.h

@@ -218,34 +218,7 @@ class DBIter final : public Iterator {
   }
   void set_valid(bool v) { valid_ = v; }
 
-  bool PrepareValue() override;
-
  private:
-  class BlobReader {
-   public:
-    BlobReader(const Version* version, ReadTier read_tier,
-               bool verify_checksums, bool fill_cache,
-               Env::IOActivity io_activity)
-        : version_(version),
-          read_tier_(read_tier),
-          verify_checksums_(verify_checksums),
-          fill_cache_(fill_cache),
-          io_activity_(io_activity) {}
-
-    const Slice& GetBlobValue() const { return blob_value_; }
-    Status RetrieveAndSetBlobValue(const Slice& user_key,
-                                   const Slice& blob_index);
-    void ResetBlobValue() { blob_value_.Reset(); }
-
-   private:
-    PinnableSlice blob_value_;
-    const Version* version_;
-    ReadTier read_tier_;
-    bool verify_checksums_;
-    bool fill_cache_;
-    Env::IOActivity io_activity_;
-  };
-
   // For all methods in this block:
   // PRE: iter_->Valid() && status_.ok()
   // Return false if there was an error, and status() is non-ok, valid_ = false;
@@ -326,6 +299,15 @@ class DBIter final : public Iterator {
                : user_comparator_.CompareWithoutTimestamp(a, b);
   }
 
+  // Retrieves the blob value for the specified user key using the given blob
+  // index when using the integrated BlobDB implementation.
+  bool SetBlobValueIfNeeded(const Slice& user_key, const Slice& blob_index);
+
+  void ResetBlobValue() {
+    is_blob_ = false;
+    blob_value_.Reset();
+  }
+
   void SetValueAndColumnsFromPlain(const Slice& slice) {
     assert(value_.empty());
     assert(wide_columns_.empty());
@@ -334,11 +316,6 @@ class DBIter final : public Iterator {
     wide_columns_.emplace_back(kDefaultWideColumnName, slice);
   }
 
-  bool SetValueAndColumnsFromBlobImpl(const Slice& user_key,
-                                      const Slice& blob_index);
-  bool SetValueAndColumnsFromBlob(const Slice& user_key,
-                                  const Slice& blob_index);
-
   bool SetValueAndColumnsFromEntity(Slice slice);
 
   bool SetValueAndColumnsFromMergeResult(const Status& merge_status,
@@ -349,21 +326,14 @@ class DBIter final : public Iterator {
     wide_columns_.clear();
   }
 
-  void ResetBlobData() {
-    blob_reader_.ResetBlobValue();
-    lazy_blob_index_.clear();
-    is_blob_ = false;
-  }
-
   // The following methods perform the actual merge operation for the
-  // no/plain/blob/wide-column base value cases.
+  // no base value/plain base value/wide-column base value cases.
   // If user-defined timestamp is enabled, `user_key` includes timestamp.
   bool MergeWithNoBaseValue(const Slice& user_key);
   bool MergeWithPlainBaseValue(const Slice& value, const Slice& user_key);
-  bool MergeWithBlobBaseValue(const Slice& blob_index, const Slice& user_key);
   bool MergeWithWideColumnBaseValue(const Slice& entity, const Slice& user_key);
 
-  bool PrepareValueInternal() {
+  bool PrepareValue() {
     if (!iter_.PrepareValue()) {
       assert(!iter_.status().ok());
       valid_ = false;
@@ -386,7 +356,7 @@ class DBIter final : public Iterator {
   UserComparatorWrapper user_comparator_;
   const MergeOperator* const merge_operator_;
   IteratorWrapper iter_;
-  BlobReader blob_reader_;
+  const Version* version_;
   ReadCallback* read_callback_;
   // Max visible sequence number. It is normally the snapshot seq unless we have
   // uncommitted data in db as in WriteUnCommitted.
@@ -406,6 +376,7 @@ class DBIter final : public Iterator {
   std::string saved_value_;
   Slice pinned_value_;
   // for prefix seek mode to support prev()
+  PinnableSlice blob_value_;
   // Value of the default column
   Slice value_;
   // All columns (i.e. name-value pairs)
@@ -439,13 +410,15 @@ class DBIter final : public Iterator {
   // Expect the inner iterator to maintain a total order.
   // prefix_extractor_ must be non-NULL if the value is false.
   const bool expect_total_order_inner_iter_;
+  ReadTier read_tier_;
+  bool fill_cache_;
+  bool verify_checksums_;
   // Whether the iterator is allowed to expose blob references. Set to true when
   // the stacked BlobDB implementation is used, false otherwise.
   bool expose_blob_index_;
-  bool allow_unprepared_value_;
-  Slice lazy_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_kv_checksum_test.cc

@@ -684,14 +684,13 @@ class DbMemtableKVChecksumTest : public DbKvChecksumTest {
   DbMemtableKVChecksumTest() : DbKvChecksumTest() {}
 
  protected:
-  const size_t kValueLenOffset = 12;
   // Indices in the memtable entry that we will not corrupt.
   // For memtable entry format, see comments in MemTable::Add().
   // We do not corrupt key length and value length fields in this test
   // case since it causes segfault and ASAN will complain.
   // For this test case, key and value are all of length 3, so
   // key length field is at index 0 and value length field is at index 12.
-  const std::set<size_t> index_not_to_corrupt{0, kValueLenOffset};
+  const std::set<size_t> index_not_to_corrupt{0, 12};
 
   void SkipNotToCorruptEntry() {
     if (index_not_to_corrupt.find(corrupt_byte_offset_) !=
@@ -738,8 +737,6 @@ TEST_P(DbMemtableKVChecksumTest, GetWithCorruptAfterMemtableInsert) {
         buf[corrupt_byte_offset_] += corrupt_byte_addend_;
         ++corrupt_byte_offset_;
       });
-  // Corrupt value only so that MultiGet below can find the key.
-  corrupt_byte_offset_ = kValueLenOffset + 1;
   SyncPoint::GetInstance()->EnableProcessing();
   Options options = CurrentOptions();
   options.memtable_protection_bytes_per_key =
@@ -748,17 +745,12 @@ TEST_P(DbMemtableKVChecksumTest, GetWithCorruptAfterMemtableInsert) {
     options.merge_operator = MergeOperators::CreateStringAppendOperator();
   }
 
-  std::string key = "key";
   SkipNotToCorruptEntry();
   while (MoreBytesToCorrupt()) {
     Reopen(options);
     ASSERT_OK(ExecuteWrite(nullptr));
     std::string val;
-    ASSERT_TRUE(db_->Get(ReadOptions(), key, &val).IsCorruption());
-    std::vector<std::string> vals = {val};
-    std::vector<Status> statuses = db_->MultiGet(
-        ReadOptions(), {db_->DefaultColumnFamily()}, {key}, &vals, nullptr);
-    ASSERT_TRUE(statuses[0].IsCorruption());
+    ASSERT_TRUE(db_->Get(ReadOptions(), "key", &val).IsCorruption());
     Destroy(options);
     SkipNotToCorruptEntry();
   }

db/db_memtable_test.cc

@@ -339,91 +339,6 @@ TEST_F(DBMemTableTest, ColumnFamilyId) {
   }
 }
 
-TEST_F(DBMemTableTest, IntegrityChecks) {
-  // We insert keys key000000, key000001 and key000002 into skiplist at fixed
-  // height 1 (smallest height). Then we corrupt the second key to aey000001 to
-  // make it smaller. With `paranoid_memory_checks` set to true, if the
-  // skip list sees key000000 and then aey000001, then it will report out of
-  // order keys with corruption status. With `paranoid_memory_checks` set
-  // to false, read/scan may return wrong results.
-  for (bool allow_data_in_error : {false, true}) {
-    Options options = CurrentOptions();
-    options.allow_data_in_errors = allow_data_in_error;
-    options.paranoid_memory_checks = true;
-    DestroyAndReopen(options);
-    SyncPoint::GetInstance()->SetCallBack(
-        "InlineSkipList::RandomHeight::height", [](void* h) {
-          auto height_ptr = static_cast<int*>(h);
-          *height_ptr = 1;
-        });
-    SyncPoint::GetInstance()->EnableProcessing();
-    ASSERT_OK(Put(Key(0), "val0"));
-    ASSERT_OK(Put(Key(2), "val2"));
-    // p will point to the buffer for encoded key000001
-    char* p = nullptr;
-    SyncPoint::GetInstance()->SetCallBack(
-        "MemTable::Add:BeforeReturn:Encoded", [&](void* encoded) {
-          p = const_cast<char*>(static_cast<Slice*>(encoded)->data());
-        });
-    ASSERT_OK(Put(Key(1), "val1"));
-    SyncPoint::GetInstance()->DisableProcessing();
-    SyncPoint::GetInstance()->ClearAllCallBacks();
-    ASSERT_TRUE(p);
-    // Offset 0 is key size, key bytes start at offset 1.
-    // "key000001 -> aey000001"
-    p[1] = 'a';
-
-    ReadOptions rops;
-    std::string val;
-    Status s = db_->Get(rops, Key(1), &val);
-    ASSERT_TRUE(s.IsCorruption());
-    std::string key0 = Slice(Key(0)).ToString(true);
-    ASSERT_EQ(s.ToString().find(key0) != std::string::npos,
-              allow_data_in_error);
-    // Without `paranoid_memory_checks`, NotFound will be returned.
-    // This would fail an assertion in InlineSkipList::FindGreaterOrEqual().
-    // If we remove the assertion, this passes.
-    // ASSERT_TRUE(db_->Get(ReadOptions(), Key(1), &val).IsNotFound());
-
-    std::vector<std::string> vals;
-    std::vector<Status> statuses = db_->MultiGet(
-        rops, {db_->DefaultColumnFamily()}, {Key(1)}, &vals, nullptr);
-    ASSERT_TRUE(statuses[0].IsCorruption());
-    ASSERT_EQ(statuses[0].ToString().find(key0) != std::string::npos,
-              allow_data_in_error);
-
-    std::unique_ptr<Iterator> iter{db_->NewIterator(rops)};
-    ASSERT_OK(iter->status());
-    iter->Seek(Key(1));
-    ASSERT_TRUE(iter->status().IsCorruption());
-    ASSERT_EQ(iter->status().ToString().find(key0) != std::string::npos,
-              allow_data_in_error);
-
-    iter->Seek(Key(0));
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_OK(iter->status());
-    // iterating through skip list at height at 1 should catch out-of-order keys
-    iter->Next();
-    ASSERT_TRUE(iter->status().IsCorruption());
-    ASSERT_EQ(iter->status().ToString().find(key0) != std::string::npos,
-              allow_data_in_error);
-    ASSERT_FALSE(iter->Valid());
-
-    iter->SeekForPrev(Key(2));
-    ASSERT_TRUE(iter->status().IsCorruption());
-    ASSERT_EQ(iter->status().ToString().find(key0) != std::string::npos,
-              allow_data_in_error);
-
-    // Internally DB Iter will iterate backwards (call Prev()) after
-    // SeekToLast() to find the correct internal key with the last user key.
-    // Prev() will do integrity checks and catch corruption.
-    iter->SeekToLast();
-    ASSERT_TRUE(iter->status().IsCorruption());
-    ASSERT_EQ(iter->status().ToString().find(key0) != std::string::npos,
-              allow_data_in_error);
-    ASSERT_FALSE(iter->Valid());
-  }
-}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_options_test.cc

@@ -231,33 +231,21 @@ TEST_F(DBOptionsTest, SetMutableTableOptions) {
   ASSERT_OK(dbfull()->SetOptions(
       cfh, {{"table_factory.block_size", "16384"},
             {"table_factory.block_restart_interval", "11"}}));
-  // Old c_bbto
-  ASSERT_EQ(c_bbto->block_size, 8192);
-  ASSERT_EQ(c_bbto->block_restart_interval, 7);
-  // New c_bbto
-  c_opts = dbfull()->GetOptions(cfh);
-  c_bbto = c_opts.table_factory->GetOptions<BlockBasedTableOptions>();
   ASSERT_EQ(c_bbto->block_size, 16384);
   ASSERT_EQ(c_bbto->block_restart_interval, 11);
 
   // Now set an option that is not mutable - options should not change
-  // FIXME: find a way to make this fail again
-  // ASSERT_NOK(
-  //    dbfull()->SetOptions(cfh, {{"table_factory.no_block_cache", "false"}}));
-  c_opts = dbfull()->GetOptions(cfh);
-  ASSERT_EQ(c_bbto, c_opts.table_factory->GetOptions<BlockBasedTableOptions>());
+  ASSERT_NOK(
+      dbfull()->SetOptions(cfh, {{"table_factory.no_block_cache", "false"}}));
   ASSERT_EQ(c_bbto->no_block_cache, true);
   ASSERT_EQ(c_bbto->block_size, 16384);
   ASSERT_EQ(c_bbto->block_restart_interval, 11);
 
   // Set some that are mutable and some that are not - options should not change
-  // FIXME: find a way to make this fail again
-  // ASSERT_NOK(dbfull()->SetOptions(
-  //     cfh, {{"table_factory.no_block_cache", "false"},
-  //           {"table_factory.block_size", "8192"},
-  //           {"table_factory.block_restart_interval", "7"}}));
-  c_opts = dbfull()->GetOptions(cfh);
-  ASSERT_EQ(c_bbto, c_opts.table_factory->GetOptions<BlockBasedTableOptions>());
+  ASSERT_NOK(dbfull()->SetOptions(
+      cfh, {{"table_factory.no_block_cache", "false"},
+            {"table_factory.block_size", "8192"},
+            {"table_factory.block_restart_interval", "7"}}));
   ASSERT_EQ(c_bbto->no_block_cache, true);
   ASSERT_EQ(c_bbto->block_size, 16384);
   ASSERT_EQ(c_bbto->block_restart_interval, 11);
@@ -268,8 +256,6 @@ TEST_F(DBOptionsTest, SetMutableTableOptions) {
       cfh, {{"table_factory.block_size", "8192"},
             {"table_factory.does_not_exist", "true"},
             {"table_factory.block_restart_interval", "7"}}));
-  c_opts = dbfull()->GetOptions(cfh);
-  ASSERT_EQ(c_bbto, c_opts.table_factory->GetOptions<BlockBasedTableOptions>());
   ASSERT_EQ(c_bbto->no_block_cache, true);
   ASSERT_EQ(c_bbto->block_size, 16384);
   ASSERT_EQ(c_bbto->block_restart_interval, 11);
@@ -285,7 +271,6 @@ TEST_F(DBOptionsTest, SetMutableTableOptions) {
             {"table_factory.block_restart_interval", "13"}}));
   c_opts = dbfull()->GetOptions(cfh);
   ASSERT_EQ(c_opts.blob_file_size, 32768);
-  c_bbto = c_opts.table_factory->GetOptions<BlockBasedTableOptions>();
   ASSERT_EQ(c_bbto->block_size, 16384);
   ASSERT_EQ(c_bbto->block_restart_interval, 13);
   // Set some on the table and a bad one on the ColumnFamily - options should
@@ -294,7 +279,6 @@ TEST_F(DBOptionsTest, SetMutableTableOptions) {
       cfh, {{"table_factory.block_size", "1024"},
             {"no_such_option", "32768"},
             {"table_factory.block_restart_interval", "7"}}));
-  ASSERT_EQ(c_bbto, c_opts.table_factory->GetOptions<BlockBasedTableOptions>());
   ASSERT_EQ(c_bbto->block_size, 16384);
   ASSERT_EQ(c_bbto->block_restart_interval, 13);
 }

db/db_rate_limiter_test.cc

@@ -245,13 +245,7 @@ TEST_P(DBRateLimiterOnReadTest, VerifyChecksum) {
   // In DirectIO, where we support tail prefetching, during table open, we only
   // do 1 read instead of 4 as described above. Actual checksum verification
   // reads stay the same.
-#ifdef OS_WIN
-  // No file system prefetch implemented for OS Win. During table open,
-  // we only do 1 read for BufferedIO.
-  int num_read_per_file = 4;
-#else
   int num_read_per_file = (!use_direct_io_) ? 7 : 4;
-#endif
   int expected = kNumFiles * num_read_per_file;
 
   ASSERT_EQ(expected, options_.rate_limiter->GetTotalRequests(Env::IO_USER));

db/db_secondary_test.cc

@@ -244,7 +244,7 @@ TEST_F(DBSecondaryTest, SimpleInternalCompaction) {
   ASSERT_EQ(largest.user_key().ToString(), "foo");
   ASSERT_EQ(result.output_level, 1);
   ASSERT_EQ(result.output_path, this->secondary_path_);
-  ASSERT_EQ(result.stats.num_output_records, 2);
+  ASSERT_EQ(result.num_output_records, 2);
   ASSERT_GT(result.bytes_written, 0);
   ASSERT_OK(result.status);
 }

db/db_sst_test.cc

@@ -383,16 +383,12 @@ TEST_F(DBSSTTest, DBWithSstFileManager) {
   ASSERT_EQ(files_moved, 0);
 
   Close();
-  ASSERT_EQ(sfm->GetTrackedFiles().size(), 0) << "sfm should be empty";
-  ASSERT_EQ(sfm->GetTotalSize(), 0) << "sfm should be empty";
   Reopen(options);
   ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
   ASSERT_EQ(sfm->GetTotalSize(), total_files_size);
 
   // Verify that we track all the files again after the DB is closed and opened
   Close();
-  ASSERT_EQ(sfm->GetTrackedFiles().size(), 0) << "sfm should be empty";
-  ASSERT_EQ(sfm->GetTotalSize(), 0) << "sfm should be empty";
   sst_file_manager.reset(NewSstFileManager(env_));
   options.sst_file_manager = sst_file_manager;
   sfm = static_cast<SstFileManagerImpl*>(sst_file_manager.get());
@@ -443,11 +439,6 @@ TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFiles) {
 
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
       "SstFileManagerImpl::OnMoveFile", [&](void* /*arg*/) { files_moved++; });
-
-  int64_t untracked_files = 0;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "SstFileManagerImpl::OnUntrackFile",
-      [&](void* /*arg*/) { ++untracked_files; });
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
 
   Options options = CurrentOptions();
@@ -494,10 +485,6 @@ TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFiles) {
   }
   ASSERT_EQ(sfm->GetTotalSize(), total_files_size);
   Close();
-  ASSERT_EQ(untracked_files, files_in_db.size());
-  untracked_files = 0;
-  ASSERT_EQ(sfm->GetTrackedFiles().size(), 0) << "sfm should be empty";
-  ASSERT_EQ(sfm->GetTotalSize(), 0) << "sfm should be empty";
 
   Reopen(options);
   ASSERT_EQ(sfm->GetTrackedFiles(), files_in_db);
@@ -505,10 +492,6 @@ TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFiles) {
 
   // Verify that we track all the files again after the DB is closed and opened.
   Close();
-  ASSERT_EQ(untracked_files, files_in_db.size());
-  untracked_files = 0;
-  ASSERT_EQ(sfm->GetTrackedFiles().size(), 0) << "sfm should be empty";
-  ASSERT_EQ(sfm->GetTotalSize(), 0) << "sfm should be empty";
 
   sst_file_manager.reset(NewSstFileManager(env_));
   options.sst_file_manager = sst_file_manager;
@@ -524,10 +507,6 @@ TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFiles) {
   ASSERT_EQ(files_deleted, 0);
   ASSERT_EQ(files_scheduled_to_delete, 0);
   Close();
-  ASSERT_EQ(untracked_files, files_in_db.size());
-  untracked_files = 0;
-  ASSERT_EQ(sfm->GetTrackedFiles().size(), 0) << "sfm should be empty";
-  ASSERT_EQ(sfm->GetTotalSize(), 0) << "sfm should be empty";
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
       "SstFileManagerImpl::ScheduleUnaccountedFileDeletion", [&](void* arg) {
         assert(arg);
@@ -687,9 +666,6 @@ TEST_F(DBSSTTest, DBWithSstFileManagerForBlobFilesWithGC) {
   }
 
   Close();
-  ASSERT_EQ(sfm->GetTrackedFiles().size(), 0) << "sfm should be empty";
-  ASSERT_EQ(sfm->GetTotalSize(), 0) << "sfm should be empty";
-
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
       "SstFileManagerImpl::ScheduleUnaccountedFileDeletion", [&](void* arg) {
         assert(arg);
@@ -941,12 +917,11 @@ TEST_P(DBWALTestWithParam, WALTrashCleanupOnOpen) {
   // Create 4 files in L0
   for (char v = 'a'; v <= 'd'; v++) {
     if (v == 'c') {
-      // Maximize the chance that the last log file will be preserved in trash
-      // before restarting the DB. (Enable slow deletion but at a very slow
-      // deletion rate)
+      // Maximize the change that the last log file will be preserved in trash
+      // before restarting the DB.
       // We have to set this on the 2nd to last file for it to delay deletion
       // on the last file. (Quirk of DeleteScheduler::BackgroundEmptyTrash())
-      options.sst_file_manager->SetDeleteRateBytesPerSecond(1);
+      options.sst_file_manager->SetDeleteRateBytesPerSecond(1024 * 1024);
     }
     ASSERT_OK(Put("Key2", DummyString(1024, v)));
     ASSERT_OK(Put("Key3", DummyString(1024, v)));

db/db_test.cc

@@ -1826,30 +1826,21 @@ TEST_F(DBTest, GetApproximateMemTableStats) {
   uint64_t count;
   uint64_t size;
 
-  // Because Random::GetTLSInstance() seed is reset in DBTestBase,
-  // this test is deterministic.
-
   std::string start = Key(50);
   std::string end = Key(60);
   Range r(start, end);
   db_->GetApproximateMemTableStats(r, &count, &size);
-  // When actual count is <= 10, it returns that as the minimum
-  EXPECT_EQ(count, 10);
-  EXPECT_EQ(size, 10440);
-
-  start = Key(20);
-  end = Key(100);
-  r = Range(start, end);
-  db_->GetApproximateMemTableStats(r, &count, &size);
-  EXPECT_EQ(count, 72);
-  EXPECT_EQ(size, 75168);
+  ASSERT_GT(count, 0);
+  ASSERT_LE(count, N);
+  ASSERT_GT(size, 6000);
+  ASSERT_LT(size, 204800);
 
   start = Key(500);
   end = Key(600);
   r = Range(start, end);
   db_->GetApproximateMemTableStats(r, &count, &size);
-  EXPECT_EQ(count, 0);
-  EXPECT_EQ(size, 0);
+  ASSERT_EQ(count, 0);
+  ASSERT_EQ(size, 0);
 
   ASSERT_OK(Flush());
 
@@ -1857,8 +1848,8 @@ TEST_F(DBTest, GetApproximateMemTableStats) {
   end = Key(60);
   r = Range(start, end);
   db_->GetApproximateMemTableStats(r, &count, &size);
-  EXPECT_EQ(count, 0);
-  EXPECT_EQ(size, 0);
+  ASSERT_EQ(count, 0);
+  ASSERT_EQ(size, 0);
 
   for (int i = 0; i < N; i++) {
     ASSERT_OK(Put(Key(1000 + i), rnd.RandomString(1024)));
@@ -1866,11 +1857,10 @@ TEST_F(DBTest, GetApproximateMemTableStats) {
 
   start = Key(100);
   end = Key(1020);
-  // Actually 20 keys in the range ^^
   r = Range(start, end);
   db_->GetApproximateMemTableStats(r, &count, &size);
-  EXPECT_EQ(count, 20);
-  EXPECT_EQ(size, 20880);
+  ASSERT_GT(count, 20);
+  ASSERT_GT(size, 6000);
 }
 
 TEST_F(DBTest, ApproximateSizes) {
@@ -5179,14 +5169,10 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel) {
   options.max_bytes_for_level_multiplier = 4;
   options.max_background_compactions = 1;
   options.num_levels = 5;
-  options.statistics = CreateDBStatistics();
 
   options.compression_per_level.resize(3);
-  // No compression for L0
   options.compression_per_level[0] = kNoCompression;
-  // No compression for the Ln whre L0 is compacted to
   options.compression_per_level[1] = kNoCompression;
-  // Snpapy compression for Ln+1
   options.compression_per_level[2] = kSnappyCompression;
 
   OnFileDeletionListener* listener = new OnFileDeletionListener();
@@ -5195,7 +5181,7 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel) {
   DestroyAndReopen(options);
 
   // Insert more than 80K. L4 should be base level. Neither L0 nor L4 should
-  // be compressed, so there shouldn't be any compression.
+  // be compressed, so total data size should be more than 80K.
   for (int i = 0; i < 20; i++) {
     ASSERT_OK(Put(Key(keys[i]), CompressibleString(&rnd, 4000)));
   }
@@ -5205,17 +5191,10 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel) {
   ASSERT_EQ(NumTableFilesAtLevel(1), 0);
   ASSERT_EQ(NumTableFilesAtLevel(2), 0);
   ASSERT_EQ(NumTableFilesAtLevel(3), 0);
-  ASSERT_TRUE(NumTableFilesAtLevel(0) > 0 || NumTableFilesAtLevel(4) > 0);
+  // Assuming each files' metadata is at least 50 bytes/
+  ASSERT_GT(SizeAtLevel(0) + SizeAtLevel(4), 20U * 4000U + 50U * 4);
 
-  // Verify there was no compression
-  auto num_block_compressed =
-      options.statistics->getTickerCount(NUMBER_BLOCK_COMPRESSED);
-  ASSERT_EQ(num_block_compressed, 0);
-
-  // Insert 400KB and there will be some files end up in L3. According to the
-  // above compression settings for each level, there will be some compression.
-  ASSERT_OK(options.statistics->Reset());
-  ASSERT_EQ(num_block_compressed, 0);
+  // Insert 400KB. Some data will be compressed
   for (int i = 21; i < 120; i++) {
     ASSERT_OK(Put(Key(keys[i]), CompressibleString(&rnd, 4000)));
   }
@@ -5223,14 +5202,9 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel) {
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
   ASSERT_EQ(NumTableFilesAtLevel(1), 0);
   ASSERT_EQ(NumTableFilesAtLevel(2), 0);
-  ASSERT_GE(NumTableFilesAtLevel(3), 1);
-  ASSERT_GE(NumTableFilesAtLevel(4), 1);
-
-  // Verify there was compression
-  num_block_compressed =
-      options.statistics->getTickerCount(NUMBER_BLOCK_COMPRESSED);
-  ASSERT_GT(num_block_compressed, 0);
 
+  ASSERT_LT(SizeAtLevel(0) + SizeAtLevel(3) + SizeAtLevel(4),
+            120U * 4000U + 50U * 24);
   // Make sure data in files in L3 is not compacted by removing all files
   // in L4 and calculate number of rows
   ASSERT_OK(dbfull()->SetOptions({
@@ -5250,12 +5224,6 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel) {
     num_keys++;
   }
   ASSERT_OK(iter->status());
-
-  ASSERT_EQ(NumTableFilesAtLevel(1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(2), 0);
-  ASSERT_GE(NumTableFilesAtLevel(3), 1);
-  ASSERT_EQ(NumTableFilesAtLevel(4), 0);
-
   ASSERT_GT(SizeAtLevel(0) + SizeAtLevel(3), num_keys * 4000U + num_keys * 10U);
 }
 

db/db_test2.cc

@@ -10,7 +10,6 @@
 #include <atomic>
 #include <cstdlib>
 #include <functional>
-#include <iostream>
 #include <memory>
 
 #include "db/db_test_util.h"
@@ -27,7 +26,6 @@
 #include "rocksdb/utilities/replayer.h"
 #include "rocksdb/wal_filter.h"
 #include "test_util/testutil.h"
-#include "util/defer.h"
 #include "util/random.h"
 #include "utilities/fault_injection_env.h"
 
@@ -5597,45 +5595,32 @@ TEST_F(DBTest2, PrefixBloomFilteredOut) {
   bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
   bbto.whole_key_filtering = false;
   options.table_factory.reset(NewBlockBasedTableFactory(bbto));
+  DestroyAndReopen(options);
 
-  // This test is also the primary test for prefix_seek_opt_in_only
-  for (bool opt_in : {false, true}) {
-    options.prefix_seek_opt_in_only = opt_in;
-    DestroyAndReopen(options);
+  // Construct two L1 files with keys:
+  // f1:[aaa1 ccc1] f2:[ddd0]
+  ASSERT_OK(Put("aaa1", ""));
+  ASSERT_OK(Put("ccc1", ""));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("ddd0", ""));
+  ASSERT_OK(Flush());
+  CompactRangeOptions cro;
+  cro.bottommost_level_compaction = BottommostLevelCompaction::kSkip;
+  ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
 
-    // Construct two L1 files with keys:
-    // f1:[aaa1 ccc1] f2:[ddd0]
-    ASSERT_OK(Put("aaa1", ""));
-    ASSERT_OK(Put("ccc1", ""));
-    ASSERT_OK(Flush());
-    ASSERT_OK(Put("ddd0", ""));
-    ASSERT_OK(Flush());
-    CompactRangeOptions cro;
-    cro.bottommost_level_compaction = BottommostLevelCompaction::kSkip;
-    ASSERT_OK(db_->CompactRange(cro, nullptr, nullptr));
+  Iterator* iter = db_->NewIterator(ReadOptions());
+  ASSERT_OK(iter->status());
 
-    ReadOptions ropts;
-    for (bool same : {false, true}) {
-      ropts.prefix_same_as_start = same;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(ropts));
-      ASSERT_OK(iter->status());
+  // Bloom filter is filterd out by f1.
+  // This is just one of several valid position following the contract.
+  // Postioning to ccc1 or ddd0 is also valid. This is just to validate
+  // the behavior of the current implementation. If underlying implementation
+  // changes, the test might fail here.
+  iter->Seek("bbb1");
+  ASSERT_OK(iter->status());
+  ASSERT_FALSE(iter->Valid());
 
-      iter->Seek("bbb1");
-      ASSERT_OK(iter->status());
-      if (opt_in && !same) {
-        // Unbounded total order seek
-        ASSERT_TRUE(iter->Valid());
-        ASSERT_EQ(iter->key(), "ccc1");
-      } else {
-        // Bloom filter is filterd out by f1. When same == false, this is just
-        // one valid position following the contract. Postioning to ccc1 or ddd0
-        // is also valid. This is just to validate the behavior of the current
-        // implementation. If underlying implementation changes, the test might
-        // fail here.
-        ASSERT_FALSE(iter->Valid());
-      }
-    }
-  }
+  delete iter;
 }
 
 TEST_F(DBTest2, RowCacheSnapshot) {
@@ -6000,7 +5985,6 @@ TEST_F(DBTest2, ChangePrefixExtractor) {
     // create a DB with block prefix index
     BlockBasedTableOptions table_options;
     Options options = CurrentOptions();
-    options.prefix_seek_opt_in_only = false;  // Use legacy prefix seek
 
     // Sometimes filter is checked based on upper bound. Assert counters
     // for that case. Otherwise, only check data correctness.
@@ -6560,235 +6544,6 @@ TEST_P(RenameCurrentTest, Compaction) {
   ASSERT_EQ("d_value", Get("d"));
 }
 
-TEST_F(DBTest2, VariousFileTemperatures) {
-  constexpr size_t kNumberFileTypes = static_cast<size_t>(kBlobFile) + 1U;
-
-  struct MyTestFS : public FileTemperatureTestFS {
-    explicit MyTestFS(const std::shared_ptr<FileSystem>& fs)
-        : FileTemperatureTestFS(fs) {
-      Reset();
-    }
-
-    IOStatus NewWritableFile(const std::string& fname, const FileOptions& opts,
-                             std::unique_ptr<FSWritableFile>* result,
-                             IODebugContext* dbg) override {
-      IOStatus ios =
-          FileTemperatureTestFS::NewWritableFile(fname, opts, result, dbg);
-      if (ios.ok()) {
-        uint64_t number;
-        FileType type;
-        if (ParseFileName(GetFileName(fname), &number, "LOG", &type)) {
-          if (type == kTableFile) {
-            // Not checked here
-          } else if (type == kWalFile) {
-            if (opts.temperature != expected_wal_temperature) {
-              std::cerr << "Attempt to open " << fname << " with temperature "
-                        << temperature_to_string[opts.temperature]
-                        << " rather than "
-                        << temperature_to_string[expected_wal_temperature]
-                        << std::endl;
-              assert(false);
-            }
-          } else if (type == kDescriptorFile) {
-            if (opts.temperature != expected_manifest_temperature) {
-              std::cerr << "Attempt to open " << fname << " with temperature "
-                        << temperature_to_string[opts.temperature]
-                        << " rather than "
-                        << temperature_to_string[expected_wal_temperature]
-                        << std::endl;
-              assert(false);
-            }
-          } else if (opts.temperature != expected_other_metadata_temperature) {
-            std::cerr << "Attempt to open " << fname << " with temperature "
-                      << temperature_to_string[opts.temperature]
-                      << " rather than "
-                      << temperature_to_string[expected_wal_temperature]
-                      << std::endl;
-            assert(false);
-          }
-          UpdateCount(type, 1);
-        }
-      }
-      return ios;
-    }
-
-    IOStatus RenameFile(const std::string& src, const std::string& dst,
-                        const IOOptions& options,
-                        IODebugContext* dbg) override {
-      IOStatus ios = FileTemperatureTestFS::RenameFile(src, dst, options, dbg);
-      if (ios.ok()) {
-        uint64_t number;
-        FileType src_type;
-        FileType dst_type;
-        assert(ParseFileName(GetFileName(src), &number, "LOG", &src_type));
-        assert(ParseFileName(GetFileName(dst), &number, "LOG", &dst_type));
-
-        UpdateCount(src_type, -1);
-        UpdateCount(dst_type, 1);
-      }
-      return ios;
-    }
-
-    void UpdateCount(FileType type, int delta) {
-      size_t i = static_cast<size_t>(type);
-      assert(i < kNumberFileTypes);
-      counts[i].FetchAddRelaxed(delta);
-    }
-
-    std::map<FileType, size_t> PopCounts() {
-      std::map<FileType, size_t> ret;
-      for (size_t i = 0; i < kNumberFileTypes; ++i) {
-        int c = counts[i].ExchangeRelaxed(0);
-        if (c > 0) {
-          ret[static_cast<FileType>(i)] = c;
-        }
-      }
-      return ret;
-    }
-
-    FileOptions OptimizeForLogWrite(
-        const FileOptions& file_options,
-        const DBOptions& /*db_options*/) const override {
-      FileOptions opts = file_options;
-      if (optimize_wal_temperature != Temperature::kUnknown) {
-        opts.temperature = optimize_wal_temperature;
-      }
-      return opts;
-    }
-
-    FileOptions OptimizeForManifestWrite(
-        const FileOptions& file_options) const override {
-      FileOptions opts = file_options;
-      if (optimize_manifest_temperature != Temperature::kUnknown) {
-        opts.temperature = optimize_manifest_temperature;
-      }
-      return opts;
-    }
-
-    void Reset() {
-      optimize_manifest_temperature = Temperature::kUnknown;
-      optimize_wal_temperature = Temperature::kUnknown;
-      expected_manifest_temperature = Temperature::kUnknown;
-      expected_other_metadata_temperature = Temperature::kUnknown;
-      expected_wal_temperature = Temperature::kUnknown;
-      for (auto& c : counts) {
-        c.StoreRelaxed(0);
-      }
-    }
-
-    Temperature optimize_manifest_temperature;
-    Temperature optimize_wal_temperature;
-    Temperature expected_manifest_temperature;
-    Temperature expected_other_metadata_temperature;
-    Temperature expected_wal_temperature;
-    std::array<RelaxedAtomic<int>, kNumberFileTypes> counts;
-  };
-
-  // We don't have enough non-unknown temps to confidently distinguish that
-  // a specific setting caused a specific outcome, in a single run. This is a
-  // reasonable work-around without blowing up test time. Only returns
-  // non-unknown temperatures.
-  auto RandomTemp = [] {
-    static std::vector<Temperature> temps = {
-        Temperature::kHot, Temperature::kWarm, Temperature::kCold};
-    return temps[Random::GetTLSInstance()->Uniform(
-        static_cast<int>(temps.size()))];
-  };
-
-  auto test_fs = std::make_shared<MyTestFS>(env_->GetFileSystem());
-  std::unique_ptr<Env> env(new CompositeEnvWrapper(env_, test_fs));
-  for (bool use_optimize : {false, true}) {
-    std::cerr << "use_optimize: " << std::to_string(use_optimize) << std::endl;
-    for (bool use_temp_options : {false, true}) {
-      std::cerr << "use_temp_options: " << std::to_string(use_temp_options)
-                << std::endl;
-
-      Options options = CurrentOptions();
-      // Currently require for last level temperature
-      options.compaction_style = kCompactionStyleUniversal;
-      options.env = env.get();
-      test_fs->Reset();
-      if (use_optimize) {
-        test_fs->optimize_manifest_temperature = RandomTemp();
-        test_fs->expected_manifest_temperature =
-            test_fs->optimize_manifest_temperature;
-        test_fs->optimize_wal_temperature = RandomTemp();
-        test_fs->expected_wal_temperature = test_fs->optimize_wal_temperature;
-      }
-      if (use_temp_options) {
-        options.metadata_write_temperature = RandomTemp();
-        test_fs->expected_manifest_temperature =
-            options.metadata_write_temperature;
-        test_fs->expected_other_metadata_temperature =
-            options.metadata_write_temperature;
-        options.wal_write_temperature = RandomTemp();
-        test_fs->expected_wal_temperature = options.wal_write_temperature;
-        options.last_level_temperature = RandomTemp();
-        options.default_write_temperature = RandomTemp();
-      }
-
-      DestroyAndReopen(options);
-      Defer closer([&] { Close(); });
-
-      using FTC = std::map<FileType, size_t>;
-      // Files on DB startup
-      ASSERT_EQ(test_fs->PopCounts(), FTC({{kWalFile, 1},
-                                           {kDescriptorFile, 2},
-                                           {kCurrentFile, 2},
-                                           {kIdentityFile, 1},
-                                           {kOptionsFile, 1}}));
-
-      // Temperature count map
-      using TCM = std::map<Temperature, size_t>;
-      ASSERT_EQ(test_fs->CountCurrentSstFilesByTemp(), TCM({}));
-
-      ASSERT_OK(Put("foo", "1"));
-      ASSERT_OK(Put("bar", "1"));
-      ASSERT_OK(Flush());
-      ASSERT_OK(Put("foo", "2"));
-      ASSERT_OK(Put("bar", "2"));
-      ASSERT_OK(Flush());
-
-      ASSERT_EQ(test_fs->CountCurrentSstFilesByTemp(),
-                TCM({{options.default_write_temperature, 2}}));
-
-      ASSERT_OK(db_->CompactRange({}, nullptr, nullptr));
-      ASSERT_OK(dbfull()->TEST_WaitForBackgroundWork());
-
-      ASSERT_EQ(test_fs->CountCurrentSstFilesByTemp(),
-                TCM({{options.last_level_temperature, 1}}));
-
-      ASSERT_OK(Put("foo", "3"));
-      ASSERT_OK(Put("bar", "3"));
-      ASSERT_OK(Flush());
-
-      // Just in memtable/WAL
-      ASSERT_OK(Put("dog", "3"));
-
-      {
-        TCM expected;
-        expected[options.default_write_temperature] += 1;
-        expected[options.last_level_temperature] += 1;
-        ASSERT_EQ(test_fs->CountCurrentSstFilesByTemp(), expected);
-      }
-
-      // New files during operation
-      ASSERT_EQ(test_fs->PopCounts(), FTC({{kWalFile, 3}, {kTableFile, 4}}));
-
-      Reopen(options);
-
-      // New files during re-open/recovery
-      ASSERT_EQ(test_fs->PopCounts(), FTC({{kWalFile, 1},
-                                           {kTableFile, 1},
-                                           {kDescriptorFile, 1},
-                                           {kCurrentFile, 1},
-                                           {kOptionsFile, 1}}));
-
-      Destroy(options);
-    }
-  }
-}
-
 TEST_F(DBTest2, LastLevelTemperature) {
   class TestListener : public EventListener {
    public:

db/db_test_util.cc

@@ -366,11 +366,6 @@ Options DBTestBase::GetOptions(
     table_options.block_cache = NewLRUCache(/* too small */ 1);
   }
 
-  // Test anticipated new default as much as reasonably possible (and remove
-  // this code when obsolete)
-  assert(!table_options.decouple_partitioned_filters);
-  table_options.decouple_partitioned_filters = true;
-
   bool can_allow_mmap = IsMemoryMappedAccessSupported();
   switch (option_config) {
     case kHashSkipList:
@@ -570,11 +565,6 @@ Options DBTestBase::GetOptions(
       options.unordered_write = false;
       break;
     }
-    case kBlockBasedTableWithBinarySearchWithFirstKeyIndex: {
-      table_options.index_type =
-          BlockBasedTableOptions::kBinarySearchWithFirstKey;
-      break;
-    }
 
     default:
       break;

db/db_test_util.h

@@ -831,15 +831,6 @@ class FileTemperatureTestFS : public FileSystemWrapper {
     return count;
   }
 
-  std::map<Temperature, size_t> CountCurrentSstFilesByTemp() {
-    MutexLock lock(&mu_);
-    std::map<Temperature, size_t> ret;
-    for (const auto& e : current_sst_file_temperatures_) {
-      ret[e.second]++;
-    }
-    return ret;
-  }
-
   void OverrideSstFileTemperature(uint64_t number, Temperature temp) {
     MutexLock lock(&mu_);
     current_sst_file_temperatures_[number] = temp;
@@ -851,7 +842,7 @@ class FileTemperatureTestFS : public FileSystemWrapper {
       requested_sst_file_temperatures_;
   std::map<uint64_t, Temperature> current_sst_file_temperatures_;
 
-  static std::string GetFileName(const std::string& fname) {
+  std::string GetFileName(const std::string& fname) {
     auto filename = fname.substr(fname.find_last_of(kFilePathSeparator) + 1);
     // workaround only for Windows that the file path could contain both Windows
     // FilePathSeparator and '/'
@@ -1050,7 +1041,6 @@ class DBTestBase : public testing::Test {
     kPartitionedFilterWithNewTableReaderForCompactions,
     kUniversalSubcompactions,
     kUnorderedWrite,
-    kBlockBasedTableWithBinarySearchWithFirstKeyIndex,
     // This must be the last line
     kEnd,
   };

db/db_universal_compaction_test.cc

@@ -213,6 +213,7 @@ TEST_P(DBTestUniversalCompaction, UniversalCompactionTrigger) {
   options.num_levels = num_levels_;
   options.write_buffer_size = 105 << 10;  // 105KB
   options.arena_block_size = 4 << 10;
+  options.target_file_size_base = 32 << 10;  // 32KB
   // trigger compaction if there are >= 4 files
   options.level0_file_num_compaction_trigger = 4;
   KeepFilterFactory* filter = new KeepFilterFactory(true);

db/db_wal_test.cc

@@ -1472,126 +1472,6 @@ TEST_F(DBWALTest, SyncMultipleLogs) {
   ASSERT_OK(dbfull()->SyncWAL());
 }
 
-TEST_F(DBWALTest, DISABLED_RecycleMultipleWalsCrash) {
-  Options options = CurrentOptions();
-  options.max_write_buffer_number = 5;
-  options.track_and_verify_wals_in_manifest = true;
-  options.max_bgerror_resume_count = 0;  // manual resume
-  options.recycle_log_file_num = 3;
-  options.wal_recovery_mode = WALRecoveryMode::kPointInTimeRecovery;
-
-  // Disable truncating recycled WALs to new size in posix env
-  // (approximating a crash)
-  SyncPoint::GetInstance()->SetCallBack(
-      "PosixWritableFile::Close",
-      [](void* arg) { *(static_cast<size_t*>(arg)) = 0; });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  // Re-open with desired options
-  DestroyAndReopen(options);
-  Defer closer([this]() { Close(); });
-
-  // Ensure WAL recycling wasn't sanitized away
-  ASSERT_EQ(db_->GetOptions().recycle_log_file_num,
-            options.recycle_log_file_num);
-
-  // Prepare external files for later ingestion
-  std::string sst_files_dir = dbname_ + "/sst_files/";
-  ASSERT_OK(DestroyDir(env_, sst_files_dir));
-  ASSERT_OK(env_->CreateDir(sst_files_dir));
-  std::string external_file1 = sst_files_dir + "file1.sst";
-  {
-    SstFileWriter sst_file_writer(EnvOptions(), options);
-    ASSERT_OK(sst_file_writer.Open(external_file1));
-    ASSERT_OK(sst_file_writer.Put("external1", "ex1"));
-    ExternalSstFileInfo file_info;
-    ASSERT_OK(sst_file_writer.Finish(&file_info));
-  }
-  std::string external_file2 = sst_files_dir + "file2.sst";
-  {
-    SstFileWriter sst_file_writer(EnvOptions(), options);
-    ASSERT_OK(sst_file_writer.Open(external_file2));
-    ASSERT_OK(sst_file_writer.Put("external2", "ex2"));
-    ExternalSstFileInfo file_info;
-    ASSERT_OK(sst_file_writer.Finish(&file_info));
-  }
-
-  // Populate some WALs to be recycled such that there will be extra data
-  // from an old incarnation of the WAL on recovery
-  ASSERT_OK(db_->PauseBackgroundWork());
-  ASSERT_OK(Put("ignore1", Random::GetTLSInstance()->RandomString(500)));
-  ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable());
-  ASSERT_OK(Put("ignore2", Random::GetTLSInstance()->RandomString(500)));
-  ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable());
-  ASSERT_OK(db_->ContinueBackgroundWork());
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put("ignore3", Random::GetTLSInstance()->RandomString(500)));
-  ASSERT_OK(Flush());
-
-  // Verify expected log files (still there for recycling)
-  std::vector<FileAttributes> files;
-  int log_count = 0;
-  ASSERT_OK(options.env->GetChildrenFileAttributes(dbname_, &files));
-  for (const auto& f : files) {
-    if (EndsWith(f.name, ".log")) {
-      EXPECT_GT(f.size_bytes, 500);
-      ++log_count;
-    }
-  }
-  EXPECT_EQ(log_count, 3);
-
-  // (Re-used recipe) Generate two inactive WALs and one active WAL, with a
-  // gap in sequence numbers to interfere with recovery
-  ASSERT_OK(db_->PauseBackgroundWork());
-  ASSERT_OK(Put("key1", "val1"));
-  ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable());
-  ASSERT_OK(Put("key2", "val2"));
-  ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable());
-  // Need a gap in sequence numbers, so e.g. ingest external file
-  // with an open snapshot
-  {
-    ManagedSnapshot snapshot(db_);
-    ASSERT_OK(
-        db_->IngestExternalFile({external_file1}, IngestExternalFileOptions()));
-  }
-  ASSERT_OK(Put("key3", "val3"));
-  ASSERT_OK(db_->SyncWAL());
-  // Need an SST file that is logically after that WAL, so that dropping WAL
-  // data is not a valid point in time.
-  {
-    ManagedSnapshot snapshot(db_);
-    ASSERT_OK(
-        db_->IngestExternalFile({external_file2}, IngestExternalFileOptions()));
-  }
-
-  // Approximate a crash, with respect to recycled WAL data extending past
-  // the end of the current WAL data (see SyncPoint callback above)
-  Close();
-
-  // Verify recycled log files haven't been truncated
-  files.clear();
-  log_count = 0;
-  ASSERT_OK(options.env->GetChildrenFileAttributes(dbname_, &files));
-  for (const auto& f : files) {
-    if (EndsWith(f.name, ".log")) {
-      EXPECT_GT(f.size_bytes, 500);
-      ++log_count;
-    }
-  }
-  EXPECT_EQ(log_count, 3);
-
-  // Verify no data loss after reopen.
-  Reopen(options);
-  EXPECT_EQ("val1", Get("key1"));
-  EXPECT_EQ("val2", Get("key2"));  // Passes because of adjacent seqnos
-  EXPECT_EQ("ex1", Get("external1"));
-  EXPECT_EQ("val3", Get("key3"));  // <- ONLY FAILURE! (Not a point in time)
-  EXPECT_EQ("ex2", Get("external2"));
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 TEST_F(DBWALTest, SyncWalPartialFailure) {
   class MyTestFileSystem : public FileSystemWrapper {
    public:
@@ -1652,7 +1532,7 @@ TEST_F(DBWALTest, SyncWalPartialFailure) {
   // * one inactive WAL, not synced, and
   // * one active WAL, not synced
   // with a single thread, to exercise as much logic as we reasonably can.
-  ASSERT_OK(db_->PauseBackgroundWork());
+  ASSERT_OK(static_cast_with_check<DBImpl>(db_)->PauseBackgroundWork());
   ASSERT_OK(Put("key1", "val1"));
   ASSERT_OK(static_cast_with_check<DBImpl>(db_)->TEST_SwitchMemtable());
   ASSERT_OK(db_->SyncWAL());
@@ -2877,83 +2757,6 @@ TEST_F(DBWALTest, EmptyWalReopenTest) {
   }
 }
 
-TEST_F(DBWALTest, RecoveryFlushSwitchWALOnEmptyMemtable) {
-  Options options = CurrentOptions();
-  auto fault_fs = std::make_shared<FaultInjectionTestFS>(FileSystem::Default());
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  options.env = fault_fs_env.get();
-  options.avoid_flush_during_shutdown = true;
-  DestroyAndReopen(options);
-
-  // Make sure the memtable switch in recovery flush happened after test checks
-  // the memtable is empty.
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBWALTest.RecoveryFlushSwitchWALOnEmptyMemtable:"
-        "AfterCheckMemtableEmpty",
-        "RecoverFromRetryableBGIOError:BeforeStart"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-  fault_fs->SetThreadLocalErrorContext(
-      FaultInjectionIOType::kMetadataWrite, 7 /* seed*/, 1 /* one_in */,
-      true /* retryable */, false /* has_data_loss*/);
-  fault_fs->EnableThreadLocalErrorInjection(
-      FaultInjectionIOType::kMetadataWrite);
-
-  WriteOptions wo;
-  wo.sync = true;
-  Status s = Put("k", "old_v", wo);
-  ASSERT_TRUE(s.IsIOError());
-  // To verify the key is not in memtable nor SST
-  ASSERT_TRUE(static_cast<ColumnFamilyHandleImpl*>(db_->DefaultColumnFamily())
-                  ->cfd()
-                  ->mem()
-                  ->IsEmpty());
-  ASSERT_EQ("NOT_FOUND", Get("k"));
-  TEST_SYNC_POINT(
-      "DBWALTest.RecoveryFlushSwitchWALOnEmptyMemtable:"
-      "AfterCheckMemtableEmpty");
-  SyncPoint::GetInstance()->DisableProcessing();
-
-  fault_fs->DisableThreadLocalErrorInjection(
-      FaultInjectionIOType::kMetadataWrite);
-
-  // Keep trying write until recovery of the previous IO error finishes
-  while (!s.ok()) {
-    options.env->SleepForMicroseconds(1000);
-    s = Put("k", "new_v");
-  }
-
-  // If recovery flush didn't switch WAL, we will end up having two duplicate
-  // WAL entries with same seqno and same key that violate assertion during WAL
-  // recovery and fail DB reopen
-  options.avoid_flush_during_recovery = false;
-  Reopen(options);
-
-  ASSERT_EQ("new_v", Get("k"));
-  Destroy(options);
-}
-
-TEST_F(DBWALTest, WALWriteErrorNoRecovery) {
-  Options options = CurrentOptions();
-  auto fault_fs = std::make_shared<FaultInjectionTestFS>(FileSystem::Default());
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  options.env = fault_fs_env.get();
-  options.manual_wal_flush = true;
-  DestroyAndReopen(options);
-  fault_fs->SetThreadLocalErrorContext(
-      FaultInjectionIOType::kWrite, 7 /* seed*/, 1 /* one_in */,
-      true /* retryable */, false /* has_data_loss*/);
-  fault_fs->EnableThreadLocalErrorInjection(FaultInjectionIOType::kWrite);
-
-  ASSERT_OK(Put("k", "v"));
-  Status s;
-  s = db_->FlushWAL(false);
-  ASSERT_TRUE(s.IsIOError());
-  s = dbfull()->TEST_GetBGError();
-  ASSERT_EQ(s.severity(), Status::Severity::kFatalError);
-  ASSERT_FALSE(dbfull()->TEST_IsRecoveryInProgress());
-  fault_fs->DisableThreadLocalErrorInjection(FaultInjectionIOType::kWrite);
-  Destroy(options);
-}
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_with_timestamp_basic_test.cc

@@ -172,70 +172,6 @@ TEST_F(DBBasicTestWithTimestamp, MixedCfs) {
   Close();
 }
 
-TEST_F(DBBasicTestWithTimestamp, MultiGetMultipleCfs) {
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.avoid_flush_during_shutdown = true;
-  options.comparator = &test_cmp;
-  DestroyAndReopen(options);
-
-  Options options1 = CurrentOptions();
-  options1.env = env_;
-  options1.comparator = &test_cmp;
-  ColumnFamilyHandle* handle = nullptr;
-  Status s = db_->CreateColumnFamily(options1, "data", &handle);
-  ASSERT_OK(s);
-
-  std::string ts = Timestamp(1, 0);
-  WriteBatch wb(0, 0, 0, kTimestampSize);
-  ASSERT_OK(wb.Put("a", "value"));
-  ASSERT_OK(wb.Put(handle, "a", "value"));
-  const auto ts_sz_func = [kTimestampSize](uint32_t /*cf_id*/) {
-    return kTimestampSize;
-  };
-  ASSERT_OK(wb.UpdateTimestamps(ts, ts_sz_func));
-  ASSERT_OK(db_->Write(WriteOptions(), &wb));
-
-  int num_keys = 2;
-  std::vector<Slice> keys;
-  std::vector<std::string> expected_values;
-  for (int i = 0; i < num_keys; i++) {
-    keys.push_back("a");
-    expected_values.push_back("value");
-  }
-  std::vector<ColumnFamilyHandle*> handles;
-  handles.push_back(db_->DefaultColumnFamily());
-  handles.push_back(handle);
-
-  {
-    Slice read_ts_slice(ts);
-    ReadOptions read_opts;
-    read_opts.timestamp = &read_ts_slice;
-
-    std::vector<PinnableSlice> values;
-    values.resize(num_keys);
-    std::vector<Status> statuses;
-    statuses.resize(num_keys);
-    std::vector<std::string> timestamps;
-    timestamps.resize(num_keys);
-
-    db_->MultiGet(read_opts, num_keys, handles.data(), keys.data(),
-                  values.data(), timestamps.data(), statuses.data());
-
-    for (int i = 0; i < num_keys; i++) {
-      ASSERT_OK(statuses[i]);
-      ASSERT_EQ(expected_values[i], values[i].ToString());
-      ASSERT_EQ(ts, timestamps[i]);
-    }
-  }
-
-  delete handle;
-  Close();
-}
-
 TEST_F(DBBasicTestWithTimestamp, CompactRangeWithSpecifiedRange) {
   Options options = CurrentOptions();
   options.env = env_;
@@ -832,7 +768,6 @@ TEST_P(DBBasicTestWithTimestampTableOptions, GetAndMultiGet) {
 
 TEST_P(DBBasicTestWithTimestampTableOptions, SeekWithPrefixLessThanKey) {
   Options options = CurrentOptions();
-  options.prefix_seek_opt_in_only = false;  // Use legacy prefix seek
   options.env = env_;
   options.create_if_missing = true;
   options.prefix_extractor.reset(NewFixedPrefixTransform(3));
@@ -1010,7 +945,6 @@ TEST_F(DBBasicTestWithTimestamp, ChangeIterationDirection) {
   TestComparator test_cmp(kTimestampSize);
   options.comparator = &test_cmp;
   options.prefix_extractor.reset(NewFixedPrefixTransform(1));
-  options.prefix_seek_opt_in_only = false;  // Use legacy prefix seek
   options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
   DestroyAndReopen(options);
   const std::vector<std::string> timestamps = {Timestamp(1, 1), Timestamp(0, 2),

db/dbformat.cc

@@ -272,23 +272,11 @@ LookupKey::LookupKey(const Slice& _user_key, SequenceNumber s,
 
 void IterKey::EnlargeBuffer(size_t key_size) {
   // If size is smaller than buffer size, continue using current buffer,
-  // or the inline one, as default
+  // or the static allocated one, as default
   assert(key_size > buf_size_);
   // Need to enlarge the buffer.
   ResetBuffer();
   buf_ = new char[key_size];
   buf_size_ = key_size;
 }
-
-void IterKey::EnlargeSecondaryBufferIfNeeded(size_t key_size) {
-  // If size is smaller than buffer size, continue using current buffer,
-  // or the inline one, as default
-  if (key_size <= secondary_buf_size_) {
-    return;
-  }
-  // Need to enlarge the secondary buffer.
-  ResetSecondaryBuffer();
-  secondary_buf_ = new char[key_size];
-  secondary_buf_size_ = key_size;
-}
 }  // namespace ROCKSDB_NAMESPACE