Update version and HISTORY.md for 11.4.3 release

Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/14881

Read-only DB instances can share a directory with a live writer, so their view of live files is only a snapshot from the time they opened. After read-only DB open began setting `opened_successfully_` for its intended open-success semantics, that state had an unintended side effect: the common close path treated a successful read-only open like a read-write open and ran obsolete-file cleanup. If the writer created or made files live after the read-only handle opened, that cleanup could use the stale read-only live set and delete files still needed by the writer.

This change records whether a `DBImpl` was opened read-only and skips close-time obsolete-file cleanup for read-only DBs instead of simply keeping `opened_successfully_=false`, which could be confusing and easily mistaken in the future again.

For completeness I also updated other callsites of `opened_successfully_`, but those should not be real bugs as ReadOnly DBs do not run flushes/compactions or write to WALs.

Reviewed By: xingbowang

Differential Revision: D109622445

fbshipit-source-id: d7be4b20fce86ccb218a63ac6f5b707b316aac79

.github/actions/pre-steps/action.yml

@@ -2,6 +2,13 @@ name: pre-steps
 runs:
   using: composite
   steps:
+  - name: Dump ulimits for diagnostics
+    run: |
+      echo "=== ulimits (soft) ==="
+      ulimit -a -S || true
+      echo "=== ulimits (hard) ==="
+      ulimit -a -H || true
+    shell: bash
   - name: Install lld linker for faster builds
     run: apt-get update -y && apt-get install -y lld 2>/dev/null || true
     shell: bash

.github/actions/windows-build-steps/action.yml

@@ -3,7 +3,7 @@ inputs:
   suite-run:
     description: Comma-separated list of test suites to run (empty to skip C++ tests)
     required: false
-    default: arena_test,db_basic_test,db_test,db_test2,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test
+    default: arena_test,db_basic_test,db_test,db_etc2_test,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test
   run-java:
     description: Whether to run Java tests
     required: false

.github/workflows/ai-review-analysis.yml

@@ -714,6 +714,8 @@ jobs:
           CODEX_HOME: /tmp/codex-home
           CODEX_MODEL: ${{ inputs.default_model }}
           CODEX_REASONING_EFFORT: ${{ steps.budget_codex.outputs.effort }}
+          BASE_SHA: ${{ steps.pr_info.outputs.base_sha }}
+          PR_TITLE: ${{ steps.pr_info.outputs.pr_title }}
         run: |
           if [ -z "${OPENAI_API_KEY}" ]; then
             echo "OPENAI_API_KEY not configured, skipping Codex review"
@@ -721,7 +723,9 @@ jobs:
           fi
           mkdir -p "${CODEX_HOME}"
           set +e
-          codex exec \
+          codex exec review \
+            --base "${BASE_SHA}" \
+            --title "${PR_TITLE}" \
             -m "${CODEX_MODEL}" \
             -c model_reasoning_effort="${CODEX_REASONING_EFFORT}" \
             --dangerously-bypass-approvals-and-sandbox \
@@ -1336,6 +1340,8 @@ jobs:
           CODEX_HOME: /tmp/codex-home
           CODEX_MODEL: ${{ inputs.selected_model != '' && inputs.selected_model || inputs.default_model }}
           CODEX_REASONING_EFFORT: ${{ steps.manual_budget_codex.outputs.effort }}
+          BASE_SHA: ${{ steps.pr_info.outputs.base_sha }}
+          PR_TITLE: ${{ steps.pr_info.outputs.pr_title }}
           COMMAND_TYPE: ${{ steps.request.outputs.type }}
         run: |
           mkdir -p "${CODEX_HOME}"
@@ -1348,7 +1354,9 @@ jobs:
               --output-last-message codex-review-output.md \
               - < /tmp/prompt.txt > codex-review-execution.log 2>&1
           else
-            codex exec \
+            codex exec review \
+              --base "${BASE_SHA}" \
+              --title "${PR_TITLE}" \
               -m "${CODEX_MODEL}" \
               -c model_reasoning_effort="${CODEX_REASONING_EFFORT}" \
               --dangerously-bypass-approvals-and-sandbox \

.github/workflows/pr-jobs.yml

@@ -373,14 +373,17 @@ jobs:
           crash_duration: 240
     container:
       image: ghcr.io/facebook/rocksdb_ubuntu:22.1
-      options: --shm-size=16gb
+      options: --shm-size=16gb --ulimit nofile=1048576:1048576
     steps:
     - uses: actions/checkout@v4.1.0
     - uses: "./.github/actions/pre-steps"
     - uses: "./.github/actions/setup-ccache"
       with:
         cache-key-prefix: mini-crashtest
-    - run: ulimit -S -n `ulimit -H -n` && make V=1 -j8 CRASH_TEST_EXT_ARGS='--duration=${{ matrix.crash_duration }} --max_key=2500000' ${{ matrix.crash_test_target }}
+    - run: |
+        ulimit -S -n $(ulimit -Hn) # Raise open files soft limit to hard limit
+        echo "Updated ulimit -Hn: $(ulimit -Hn) -Sn: $(ulimit -Sn)"
+        make V=1 -j8 CRASH_TEST_EXT_ARGS='--duration=${{ matrix.crash_duration }} --max_key=2500000' ${{ matrix.crash_test_target }}
     - uses: "./.github/actions/teardown-ccache"
       if: always()
     - uses: "./.github/actions/post-steps"
@@ -534,7 +537,7 @@ jobs:
           suite_run: db_test
           run_java: "false"
         - test_shard: other
-          suite_run: arena_test,db_basic_test,db_test2,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test
+          suite_run: arena_test,db_basic_test,db_etc2_test,db_merge_operand_test,bloom_test,c_test,coding_test,crc32c_test,dynamic_bloom_test,env_basic_test,env_test,hash_test,random_test
           run_java: "false"
         - test_shard: java
           suite_run: ""

.gitignore

@@ -52,7 +52,7 @@ GRTAGS
 GTAGS
 rocksdb_dump
 rocksdb_undump
-db_test2
+db_etc2_test
 trace_analyzer
 block_cache_trace_analyzer
 io_tracer_parser

BUCK

@@ -4868,6 +4868,12 @@ cpp_unittest_wrapper(name="db_encryption_test",
             extra_compiler_flags=[])
 
 
+cpp_unittest_wrapper(name="db_etc2_test",
+            srcs=["db/db_etc2_test.cc"],
+            deps=[":rocksdb_test_lib"],
+            extra_compiler_flags=[])
+
+
 cpp_unittest_wrapper(name="db_etc3_test",
             srcs=["db/db_etc3_test.cc"],
             deps=[":rocksdb_test_lib"],
@@ -5024,12 +5030,6 @@ cpp_unittest_wrapper(name="db_test",
             extra_compiler_flags=[])
 
 
-cpp_unittest_wrapper(name="db_test2",
-            srcs=["db/db_test2.cc"],
-            deps=[":rocksdb_test_lib"],
-            extra_compiler_flags=[])
-
-
 cpp_unittest_wrapper(name="db_universal_compaction_test",
             srcs=["db/db_universal_compaction_test.cc"],
             deps=[":rocksdb_test_lib"],

CLAUDE.md

@@ -209,14 +209,48 @@ The following patterns emerged as frequent sources of review feedback:
 ## Important tips
 
 ### Build system
-* There are 3 build system. Make, CMake, BUCK(meta internal).
+* There are 3 build system. Make for git clones, BUCK (meta internal) for hg
+  clones, and CMake for some special cases.
 * When a new .cc file is added, update Makefile, CMakeLists.txt, src.mk, BUCK.
 * Don't manually edit BUCK file, after updating src.mk, run
     /usr/local/bin/python3 buckifier/buckify_rocksdb.py to update it
-* Use make to build and run the test. CMake and BUCK are not used locally.
-* Use `make dbg` command to build all of the unit test in debug mode.
 * For -j in make command, use the number of CPU cores to decide it.
 
+### When to run `make clean` (avoid mixing build modes)
+
+The Makefile does **not** track build mode, so object files from a prior
+build are silently reused even when compiled with different flags, leading
+to confusing linker errors, sanitizer false negatives, ODR violations, or
+"phantom" bugs.
+
+Run `make clean` before switching any of these:
+* **`ASSERT_STATUS_CHECKED=1` ↔ unset** — changes the `Status` class layout (ABI break).
+* **Sanitizer builds** — toggling any of `COMPILE_WITH_ASAN=1`,
+    `COMPILE_WITH_UBSAN=1`, `COMPILE_WITH_TSAN=1` on/off.
+* `DEBUG_LEVEL=0` (release) ↔ `DEBUG_LEVEL=1` (debug, default for `make dbg`).
+* Different compilers, `OPT` levels, or other flags affecting codegen/ABI.
+
+**Notable exception:** `DEBUG_LEVEL=2` can be safely mixed with
+`DEBUG_LEVEL=1` — rebuild a subset of files with `DEBUG_LEVEL=2` to get
+extra/more accurate runtime checks for those files without a full clean.
+
+When in doubt, `make clean` is cheap insurance compared to chasing a
+phantom bug.
+
+### Source checks
+* Run `make check-sources` before committing. This catches non-ASCII
+    characters in source files and other source-level issues that CI will
+    reject. In particular, **do not use Unicode characters** (em dashes,
+    smart quotes, etc.) in comments or strings -- use ASCII equivalents
+    (`--` instead of em dash, `'` instead of smart quote, etc.).
+
+### RTTI and dynamic_cast
+* Production code and `db_stress` must build in **release mode
+    (`-fno-rtti`)**. Do not use `dynamic_cast` anywhere except unit tests.
+    Use `static_cast_with_check` from `util/cast_util.h` (validates with
+    `dynamic_cast` in debug builds, plain `static_cast` in release).
+* Unit tests (`*_test.cc`) are built in debug mode with RTTI enabled.
+
 ### Unit Test
 * After all of the unit tests are added, review them and try to extract common
     reusable utility functions to reduce code duplication due to copy past between

CMakeLists.txt

@@ -654,6 +654,8 @@ if(USE_FOLLY)
     FMT_INST_PATH)
     exec_program(ls ARGS -d ${FOLLY_INST_PATH}/../gflags* OUTPUT_VARIABLE
     GFLAGS_INST_PATH)
+    exec_program(ls ARGS -d ${FOLLY_INST_PATH}/../glog* OUTPUT_VARIABLE
+    GLOG_INST_PATH)
     set(Boost_DIR ${BOOST_INST_PATH}/lib/cmake/Boost-1.83.0)
     if(EXISTS ${FMT_INST_PATH}/lib64)
       set(fmt_DIR ${FMT_INST_PATH}/lib64/cmake/fmt)
@@ -661,6 +663,42 @@ if(USE_FOLLY)
       set(fmt_DIR ${FMT_INST_PATH}/lib/cmake/fmt)
     endif()
     set(gflags_DIR ${GFLAGS_INST_PATH}/lib/cmake/gflags)
+    if(EXISTS ${GLOG_INST_PATH}/lib64/cmake/glog)
+      set(GLOG_CMAKE_DIR ${GLOG_INST_PATH}/lib64/cmake/glog)
+    elseif(EXISTS ${GLOG_INST_PATH}/lib/cmake/glog)
+      set(GLOG_CMAKE_DIR ${GLOG_INST_PATH}/lib/cmake/glog)
+    endif()
+    if(NOT GLOG_CMAKE_DIR)
+      find_library(GETDEPS_GLOG_LIBRARY NAMES glogd glog
+        PATHS ${GLOG_INST_PATH}/lib64 ${GLOG_INST_PATH}/lib
+        NO_DEFAULT_PATH)
+      if(NOT GETDEPS_GLOG_LIBRARY OR
+         NOT EXISTS ${GLOG_INST_PATH}/include/glog/logging.h)
+        message(FATAL_ERROR "Could not find getdeps glog under "
+          "${GLOG_INST_PATH}")
+      endif()
+      set(GLOG_CMAKE_DIR ${CMAKE_CURRENT_BINARY_DIR}/getdeps-glog-cmake)
+      file(MAKE_DIRECTORY ${GLOG_CMAKE_DIR})
+      file(WRITE ${GLOG_CMAKE_DIR}/glog-config.cmake
+        "if(NOT TARGET glog::glog)\n"
+        "  add_library(glog::glog UNKNOWN IMPORTED)\n"
+        "  set_target_properties(glog::glog PROPERTIES\n"
+        "    IMPORTED_LOCATION \"${GETDEPS_GLOG_LIBRARY}\"\n"
+        "    INTERFACE_INCLUDE_DIRECTORIES \"${GLOG_INST_PATH}/include\")\n"
+        "endif()\n"
+        "set(glog_FOUND TRUE)\n"
+        "set(Glog_FOUND TRUE)\n"
+        "set(GLOG_FOUND TRUE)\n"
+        "set(GLOG_LIBRARY \"${GETDEPS_GLOG_LIBRARY}\")\n"
+        "set(GLOG_LIBRARIES \"${GETDEPS_GLOG_LIBRARY}\")\n"
+        "set(GLOG_INCLUDE_DIR \"${GLOG_INST_PATH}/include\")\n")
+    endif()
+    set(glog_DIR ${GLOG_CMAKE_DIR})
+    set(Glog_DIR ${GLOG_CMAKE_DIR})
+    # Unlike gflags, glog may also be installed system-wide. Pre-resolve the
+    # getdeps copy so folly-config.cmake cannot fall back to another version.
+    find_package(glog CONFIG REQUIRED PATHS ${GLOG_CMAKE_DIR}
+                 NO_DEFAULT_PATH)
 
     exec_program(sed ARGS -i 's/gflags_shared//g'
     ${FOLLY_INST_PATH}/lib/cmake/folly/folly-targets.cmake)
@@ -1453,6 +1491,7 @@ if(WITH_TESTS)
         db/db_clip_test.cc
         db/db_dynamic_level_test.cc
         db/db_encryption_test.cc
+        db/db_etc2_test.cc
         db/db_etc3_test.cc
         db/db_flush_test.cc
         db/db_inplace_update_test.cc
@@ -1476,7 +1515,6 @@ if(WITH_TESTS)
         db/db_table_properties_test.cc
         db/db_tailing_iter_test.cc
         db/db_test.cc
-        db/db_test2.cc
         db/db_logical_block_size_cache_test.cc
         db/db_universal_compaction_test.cc
         db/db_wal_test.cc

HISTORY.md

@@ -1,6 +1,63 @@
 # Rocksdb Change Log
 > NOTE: Entries for next release do not go here. Follow instructions in `unreleased_history/README.txt`
 
+## 11.4.3 (06/24/2026)
+### Bug Fixes
+* Fixed a bug where closing a read-only DB instance could delete live SST files created by a concurrent read-write DB sharing the same directory.
+
+## 11.4.2 (06/08/2026)
+### Public API Changes
+* Added experimental read-scoped block buffer provider API, configured through `ReadOptions::read_scoped_block_buffer_provider`, for supported block-based table iterator scans and MultiScan reads to use caller-provided read-scoped storage for final data-block contents. When configured, supported provider-backed scan data-block reads bypass the data-block cache. The provider is ignored when mmap reads are enabled. RocksDB may still use ordinary temporary scratch for serialized block bytes, such as when a block may be compressed. Get and MultiGet do not currently provide API guarantees for this provider.
+
+### Bug Fixes
+* Fixed a use after free bug in Multiscan when async IO is used
+
+## 11.4.1 (06/05/2026)
+* No-op patch used to sync with internal fb version.
+
+## 11.4.0 (06/02/2026)
+### Public API Changes
+* Added `rocksdb_options_set_memtable_batch_lookup_optimization()` and `rocksdb_options_get_memtable_batch_lookup_optimization()` to the C API, exposing the existing `AdvancedColumnFamilyOptions::memtable_batch_lookup_optimization` field. This allows C API users (and downstream language bindings) to enable the skip-list memtable's batch-lookup optimization for `MultiGet`, which caches the search path between consecutive keys and reduces per-key cost from O(log N) to O(log d) where d is the distance between consecutive keys.
+* Added `rocksdb_readoptions_set_optimize_multiget_for_io()` and `rocksdb_readoptions_get_optimize_multiget_for_io()` to the C API, exposing the existing `ReadOptions::optimize_multiget_for_io` field. This allows C API users (and downstream language bindings) to opt out of the multi-level parallel MultiGet path, which only takes effect when the library is built with `USE_COROUTINES`.
+* Added `rocksdb_block_based_table_index_block_search_type_auto` enum constant and the `rocksdb_block_based_options_set_uniform_cv_threshold()` setter to the C API. The constant exposes `BlockSearchType::kAuto`, and the setter exposes `BlockBasedTableOptions::uniform_cv_threshold`. Both are required for `kAuto` index-block search to take effect from the C API: without setting `uniform_cv_threshold >= 0`, the per-block `is_uniform` footer bit is never written, and `kAuto` falls back to binary search at read time.
+* Added `EventListener::OnDBShutdownBegin`, a callback that fires once when a DB begins shutdown, including when RocksDB cleans up a failed `DB::Open()` attempt.
+* Added a new PerfContext counter `blob_cache_read_byte` for blob cache bytes read.
+
+### Behavior Changes
+* Remote compaction now falls back to local compaction when the primary cannot deserialize a successful `CompactionServiceResult` before installing any remote output files.
+* StringToMap (rocksdb/convenience.h) now preserves the outer braces of nested values so each map entry is in self-contained form and can be embedded directly into another `key=value;` string (e.g. SetOptions) without losing inner ';' delimiters. A new symmetric MapToString utility is provided.
+
+### Bug Fixes
+* Fixed a bug where `AbortAllCompactions()` could leave automatic compaction work unscheduled when aborting before the background worker picked it, causing compaction and write stalls until DB restart.
+* Fix a bug where db had a false positive compaction corruption error due to remote compaction service result with `has_accurate_num_input_records=false` not being serialized.
+* Fixed WritePrepared TransactionDB cleanup after retryable commit or rollback write failures so prepared transactions remain rollbackable instead of leaving unresolved prepared state.
+* Fix a rare corruption bug for tiered compaction that incorrectly moved last level range tombstones into proximal level. This corruption error is surfaced when force_consistency_checks is enabled.
+
+### Performance Improvements
+* Reduce the likelihood of user-facing metadata operations blocking on MANIFEST rotation when file creation is slow, such as on remote storage. MANIFEST write batches containing foreground edits from `CreateColumnFamily()`, `DropColumnFamily()`, `CreateColumnFamilyWithImport()`, `IngestExternalFile()`, and `DeleteFilesInRanges()` now get a relaxed file size threshold for triggering MANIFEST rotation; background-only MANIFEST write batches, such as compaction and flush, continue to use the normal threshold. This change should make auto-tuning manifest file size more attractive (see `max_manifest_file_size` and `max_manifest_space_amp_pct` options).
+
+## 11.3.0 (05/15/2026)
+### New Features
+* Add experimental DB option `async_wal_precreate` to precreate the next WAL file in a background thread and reduce foreground WAL rotation latency. The option is sanitized to false when WAL recycling is enabled.
+* Added a new `EventListener::OnCompactionPreCommit` callback that fires after a compaction job finishes but before its input files are released (i.e. while `FileMetaData::being_compacted` is still true). Listeners that maintain bookkeeping of which files are currently being compacted can clean up such state in this new callback to avoid races with concurrent compaction picking, where another thread might pick up the same files for a new compaction immediately after `being_compacted` is flipped back to false but before `OnCompactionCompleted` fires. The default implementation is a no-op so this is not a breaking change.
+* Add mutable DBOption `optimize_manifest_for_recovery` (default false). When enabled, RocksDB can reduce recovery work after a clean shutdown, which may lower DB::Open latency on warm reopens.
+* Added public utility APIs `ParseCompressionNameForDisplay()` to convert `TableProperties::compression_name` into a human-readable compression name for both legacy and format_version 7+ SST metadata, including custom `CompressionManager`-provided display names for custom compression types.
+* Add `reuse_manifest_on_open` DBOption (default false). When enabled, DB::Open reuses the existing MANIFEST file for append instead of creating a fresh one, avoiding the cost of serializing the entire database state into a new MANIFEST on the first post-open write. To prevent this feature from interfering with manifest file size auto-tuning, an extra forward-compatible field is now always added to the MANIFEST (to track the last "compacted" size).
+
+### Behavior Changes
+* Read-only open with `error_if_wal_file_exists=true` now tolerates empty WAL files so empty precreated WALs do not prevent inspection.
+* WriteCommitted TransactionDB now matches WritePrepared and WriteUnprepared compaction filtering in both single- and two-write-queue modes: a compaction filter's FilterMergeOperand will not be invoked on merge operands at or below the latest published sequence number.
+
+### Bug Fixes
+* Fixed blob-backed wide-column merge reads to preserve correct status
+propagation and resolution across memtable, read-only, and secondary DB
+paths.
+* Fixed a bug where `DB::GetCreationTimeOfOldestFile()` could return inaccurate results instead of the real creation time when called shortly after opening a legacy DB (one whose manifest lacks `file_creation_time`) with `open_files_async = true`. The API now waits for background SST file loading to complete only when needed; modern DBs are unaffected.
+* Fixed merge reads against wide-column/blob-backed base values to preserve precise failure statuses, including `GetMergeOperands()` and direct-write memtable reads.
+* Fix bug in range tombstone synthesis that covers live keys added during an IngestExternalFile
+* Reject the empty string as a column family name in `DB::CreateColumnFamily` / `DB::CreateColumnFamilies`. Previously such calls returned OK and a usable handle, but the column family was not persisted in the manifest, so any data written to it was silently lost on DB reopen.
+* Fixed a bug where a WriteCommitted TransactionDB using commit-bypass WBWI ingestion could drop an entry that is still visible at the published sequence boundary.
+
 ## 11.2.0 (04/18/2026)
 ### New Features
 * Added experimental `DBOptions::fast_sst_open` option. When enabled, RocksDB retrieves opaque file system metadata for SST files after flush, compaction, and external file ingestion, persists it in the MANIFEST, and passes it back to the file system on subsequent file opens to accelerate DB open time.

Makefile

@@ -327,6 +327,9 @@ missing_make_config_paths := $(shell				\
 $(foreach path, $(missing_make_config_paths), \
 	$(warning Warning: $(path) does not exist))
 
+# This (the first rule) must depend on "all".
+default: all
+
 ifeq ($(PLATFORM), OS_AIX)
 # no debug info
 else ifneq ($(PLATFORM), IOS)
@@ -485,9 +488,6 @@ ifdef ROCKSDB_MODIFY_NPHASH
   PLATFORM_CXXFLAGS += -DROCKSDB_MODIFY_NPHASH=1
 endif
 
-# This (the first rule) must depend on "all".
-default: all
-
 WARNING_FLAGS = -W -Wextra -Wall -Wsign-compare -Wshadow \
   -Wunused-parameter
 
@@ -887,23 +887,43 @@ coverage: clean
 parallel_tests = $(patsubst %,parallel_%,$(PARALLEL_TEST))
 .PHONY: gen_parallel_tests $(parallel_tests)
 # Shard size controls how many test cases run per process. The actual number
-# of shards per binary is: min(ceil(test_count / GTEST_SHARD_SIZE), NCORES * 8)
+# of shards per binary is: min(ceil(test_count / shard_size), NCORES * 8)
 # This adapts to machine size: many small shards on beefy machines, fewer
 # larger shards on CI (typically 2-4 cores).
 GTEST_SHARD_SIZE ?= 10
 NCORES ?= $(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
 
+# Per-binary overrides for GTEST_SHARD_SIZE, used to chop up binaries whose
+# individual test cases are slow enough that the default of 10 leaves one
+# shard on the critical path of "make check". Format: whitespace-separated
+# tokens "BINARY:SIZE". Sizes were tuned from `make suggest-slow-tests`
+# output to keep max shard time under ~20s on a beefy box. Reducing too far
+# adds per-shard fixed overhead, so don't use 1 unless individual tests are
+# >5s.
+SHARD_SIZE_OVERRIDES ?= \
+  point_lock_manager_stress_test:1 \
+  external_sst_file_test:1 \
+  external_sst_file_basic_test:2 \
+  db_test:3 \
+  compaction_service_test:1
+
 $(parallel_tests):
 	$(AM_V_at)TEST_BINARY=$(patsubst parallel_%,%,$@); \
   TEST_COUNT=` \
     (./$$TEST_BINARY --gtest_list_tests 2>/dev/null || echo "  list_failure") \
     | grep -c '^ '`; \
 	if [ "$$TEST_COUNT" -le 0 ]; then TEST_COUNT=1; fi; \
+	SHARD_SIZE=$(GTEST_SHARD_SIZE); \
+	for o in $(SHARD_SIZE_OVERRIDES); do \
+		case "$$o" in \
+			"$$TEST_BINARY":*) SHARD_SIZE=$${o#*:} ;; \
+		esac; \
+	done; \
 	MAX_SHARDS=$$(( $(NCORES) * 8 )); \
-	NUM_SHARDS=$$(( (TEST_COUNT + $(GTEST_SHARD_SIZE) - 1) / $(GTEST_SHARD_SIZE) )); \
+	NUM_SHARDS=$$(( (TEST_COUNT + SHARD_SIZE - 1) / SHARD_SIZE )); \
 	if [ "$$NUM_SHARDS" -gt "$$MAX_SHARDS" ]; then NUM_SHARDS=$$MAX_SHARDS; fi; \
 	if [ "$$NUM_SHARDS" -le 0 ]; then NUM_SHARDS=1; fi; \
-	echo "  Generating $$NUM_SHARDS shards for $$TEST_BINARY ($$TEST_COUNT tests)"; \
+	echo "  Generating $$NUM_SHARDS shards for $$TEST_BINARY ($$TEST_COUNT tests, shard_size=$$SHARD_SIZE)"; \
 	SHARD_IDX=0; \
 	while [ "$$SHARD_IDX" -lt "$$NUM_SHARDS" ]; do \
 		if [ -n "$(CI_TOTAL_SHARDS)" ] && [ $$(( $$SHARD_IDX % $(CI_TOTAL_SHARDS) )) -ne $(CI_SHARD_INDEX) ]; then \
@@ -929,31 +949,64 @@ gen_parallel_tests:
 	$(AM_V_at)$(FIND) t -type f -name 'run-*' -exec rm -f {} \;
 	$(MAKE) $(parallel_tests)
 
-# Reorder input lines (which are one per test) so that the
-# longest-running tests appear first in the output.
-# Do this by prefixing each selected name with its duration,
-# sort the resulting names, and remove the leading numbers.
-# FIXME: the "100" we prepend is a fake time, for now.
-# FIXME: squirrel away timings from each run and use them
-# (when present) on subsequent runs to order these tests.
+# Reorder input lines (one per test or per shard) so the longest-running
+# tests/shards start first under "make check" parallel scheduling. The trick
+# is to prefix matched names with a fake duration (100), sort numerically
+# descending, then strip the prefix. Slow-matched tests therefore come ahead
+# of all unmatched tests; ordering within each group is unspecified.
 #
-# Without this reordering, these two tests would happen to start only
-# after almost all other tests had completed, thus adding 100 seconds
-# to the duration of parallel "make check".  That's the difference
-# between 4 minutes (old) and 2m20s (new).
+# Why this matters: gnu_parallel hands out jobs in input order. If a slow
+# test starts only after most others have finished, the run is bottlenecked
+# on its tail. Front-loading slow tests overlaps them with the bulk of
+# faster ones for much better wall-clock time.
 #
-# 152.120 PASS t/DBTest.FileCreationRandomFailure
-# 107.816 PASS t/DBTest.EncodeDecompressedBlockSizeTest
+# Maintenance:
+#   1) Run `make check` so LOG is up-to-date.
+#   2) Run `make suggest-slow-tests` to see candidate slow binaries.
+#   3) Add binaries with high per-shard time (slow critical path) or high
+#      total time across many shards (need early queueing for fan-out).
+# Each alternative is wrapped in `^.*NAME.*$$` so the *whole input line* is
+# captured into $$1; then `s,(...),100 $$1,` prepends "100 " to the line.
 #
-# With sharded test execution, prioritize binaries known to be slow.
-# These generate many shards and should start early for good load balancing.
+# Tiers below are based on observed timings (see suggest-slow-tests).
+# Tier 1: max single-shard time >= 30s (critical-path bottlenecks).
+# Tier 2: max single-shard time 15-30s.
+# Tier 3: huge total time across many tiny shards; front-loading them keeps
+#         the tail of the run busy while big shards finish.
 slow_test_regexp = \
-	^.*block_based_table_reader_test.*$$|^.*table_test.*$$|^.*block_test.*$$|^.*write_prepared_transaction_test.*$$|^.*transaction_test.*$$|^.*external_sst_file_test.*$$|^.*db_wal_test.*$$|^.*db_with_timestamp_basic_test.*$$|^.*db_test-.*$$
+	^.*point_lock_manager_stress_test.*$$|^.*db_test.*$$|^.*external_sst_file_test.*$$|^.*compaction_service_test.*$$|^.*corruption_test.*$$|^.*comparator_db_test.*$$|^.*external_sst_file_basic_test.*$$|^.*rate_limiter_test.*$$|^.*db_compaction_test.*$$|^.*write_prepared_transaction_test.*$$|^.*db_merge_operator_test.*$$|\
+	^.*db_dynamic_level_test.*$$|^.*db_bloom_filter_test.*$$|^.*error_handler_fs_test.*$$|^.*merge_helper_test.*$$|^.*transaction_test.*$$|^.*db_kv_checksum_test.*$$|^.*inlineskiplist_test.*$$|\
+	^.*db_with_timestamp_basic_test.*$$|^.*table_test.*$$|^.*db_wal_test.*$$|^.*block_based_table_reader_test.*$$|^.*block_test.*$$
 prioritize_long_running_tests =						\
   perl -pe 's,($(slow_test_regexp)),100 $$1,'				\
     | sort -k1,1gr							\
     | sed 's/^[.0-9]* //'
 
+# Helper: print binaries observed to be slow in the last `make check` run.
+# Use this to decide whether `slow_test_regexp` above needs updating.
+# Aggregates per-binary across shards; flags any binary whose max single-shard
+# time is >= 20s OR whose total time is >= 200s.
+.PHONY: suggest-slow-tests
+suggest-slow-tests:
+	@if [ ! -s LOG ]; then \
+	  echo "No (or empty) LOG file. Run 'make check' first." >&2; exit 1; \
+	fi
+	@bash -c '$(quoted_perl_command)' < LOG | awk '\
+	  { \
+	    t=$$1; name=$$3; \
+	    sub(/^t\/run-/, "", name); \
+	    sub(/-shard-[0-9]+$$/, "", name); \
+	    total[name] += t; \
+	    if (t > max[name]) max[name] = t; \
+	    count[name]++; \
+	  } \
+	  END { \
+	    printf "%8s %8s %5s  %s\n", "TOTAL_s", "MAX_s", "SHRDS", "BINARY"; \
+	    for (n in total) \
+	      if (max[n] >= 20 || total[n] >= 200) \
+	        printf "%8.1f %8.1f %5d  %s\n", total[n], max[n], count[n], n; \
+	  }' | (read header; echo "$$header"; sort -k2,2gr)
+
 # "make check" uses
 # Run with "make J=1 check" to disable parallelism in "make check".
 # Run with "make J=200% check" to run two parallel jobs per core.
@@ -990,7 +1043,7 @@ check_0:
 		        awk -v s=$(CI_SHARD_INDEX) -v n=$(CI_TOTAL_SHARDS) '(NR-1)%n==s'; \
 		      else cat; fi; \
 		fi; \
-		find t -name 'run-*' -print; \
+		$(FIND) t -name 'run-*' -print; \
 	} \
 	  | $(prioritize_long_running_tests)				\
 	  | grep -E '$(tests-regexp)'					\
@@ -1012,7 +1065,7 @@ valgrind_check_0:
 	  '  run "make watch-log" in a separate window' '';		\
 	{								\
 	  printf './%s\n' $(filter-out $(PARALLEL_TEST) %skiplist_test options_settable_test, $(TESTS));		\
-	  find t -name 'run-*' -print; \
+	  $(FIND) t -name 'run-*' -print; \
 	}								\
 	  | $(prioritize_long_running_tests)				\
 	  | grep -E '$(tests-regexp)'					\
@@ -1230,11 +1283,17 @@ clean-not-downloaded: clean-ext-libraries-bin clean-rocks clean-not-downloaded-r
 
 clean-rocks:
 # Not practical to exactly match all versions/variants in naming (e.g. debug or not)
-	rm -f ${LIBNAME}*.so* ${LIBNAME}*.a
-	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(MICROBENCHS)
-	rm -rf $(CLEAN_FILES) ios-x86 ios-arm scan_build_report
-	$(FIND) . -name "*.[oda]" -exec rm -f {} \;
-	$(FIND) . -type f \( -name "*.gcda" -o -name "*.gcno" \) -exec rm -f {} \;
+	@echo Removing link targets
+	@rm -f ${LIBNAME}*.so* ${LIBNAME}*.a $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(MICROBENCHS)
+	@echo Finding and cleaning other files
+	@rm -rf $(CLEAN_FILES) ios-x86 ios-arm scan_build_report
+	@if $(FIND) Makefile -regextype awk &> /dev/null; then \
+		$(FIND) . -regextype awk \
+			-regex '.*/([.].*|third-party)' -prune -o \
+			-type f -regex '.*[.]([oda]|gcda|gcno)' -exec rm -f {} \; ; \
+	else \
+		$(FIND) . -name "*.[oda]" -exec rm -f {} \; ; \
+	fi
 
 clean-rocksjava: clean-rocks
 	rm -rf jl jls
@@ -1247,7 +1306,7 @@ clean-ext-libraries-all:
 	rm -rf bzip2* snappy* zlib* lz4* zstd*
 
 clean-ext-libraries-bin:
-	find . -maxdepth 1 -type d \( -name bzip2\* -or -name snappy\* -or -name zlib\* -or -name lz4\* -or -name zstd\* \) -prune -exec rm -rf {} \;
+	$(FIND) . -maxdepth 1 -type d \( -name bzip2\* -or -name snappy\* -or -name zlib\* -or -name lz4\* -or -name zstd\* \) -prune -exec rm -rf {} \;
 
 tags:
 	ctags -R .
@@ -1525,7 +1584,7 @@ db_open_with_config_test: $(OBJ_DIR)/db/db_open_with_config_test.o $(TEST_LIBRAR
 db_test: $(OBJ_DIR)/db/db_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
-db_test2: $(OBJ_DIR)/db/db_test2.o $(TEST_LIBRARY) $(LIBRARY)
+db_etc2_test: $(OBJ_DIR)/db/db_etc2_test.o $(TEST_LIBRARY) $(LIBRARY)
 	$(AM_LINK)
 
 db_etc3_test: $(OBJ_DIR)/db/db_etc3_test.o $(TEST_LIBRARY) $(LIBRARY)

build_tools/getdeps_fallback_mirror.py

@@ -1,62 +1,188 @@
 #!/usr/bin/env python3
+#  Copyright (c) Meta Platforms, Inc. and affiliates.
+#  This source code is licensed under both the GPLv2 (found in the COPYING file in the root directory)
+#  and the Apache 2.0 License (found in the LICENSE.Apache file in the root directory).
 """
 Pre-download packages with unreliable mirrors using fallback mirrors.
 Reads package info from folly's getdeps manifest files.
 """
-import sys
-import os
-import hashlib
-import subprocess
 import configparser
+import hashlib
+import os
+import shutil
+import sys
+import urllib.request
+
+DOWNLOAD_TIMEOUT_SECONDS = 120
+DOWNLOAD_CHUNK_BYTES = 64 * 1024
+MAX_DOWNLOAD_BYTES = 50 * 1024 * 1024
+
+MIRROR_FALLBACKS = {
+    "ftpmirror.gnu.org/gnu/": [
+        "https://mirrors.kernel.org/gnu/",
+        "https://ftpmirror.gnu.org/gnu/",
+        "https://ftp.gnu.org/gnu/",
+    ],
+    "ftp.gnu.org/gnu/": [
+        "https://mirrors.kernel.org/gnu/",
+        "https://ftpmirror.gnu.org/gnu/",
+        "https://ftp.gnu.org/gnu/",
+    ],
+}
+
+# These packages must have URLs matching MIRROR_FALLBACKS; other packages are
+# left for getdeps.py's normal download path.
+PACKAGES_TO_CHECK = ("autoconf", "automake", "libtool", "libiberty")
+
 
 def sha256_file(path):
     """Calculate SHA256 hash of a file."""
     h = hashlib.sha256()
     try:
-        with open(path, 'rb') as f:
-            for chunk in iter(lambda: f.read(65536), b''):
+        with open(path, "rb") as f:
+            for chunk in iter(lambda: f.read(65536), b""):
                 h.update(chunk)
         return h.hexdigest()
     except Exception:
         return None
 
+
 def parse_manifest(manifest_path):
     """Parse a getdeps manifest file to extract download info."""
-    config = configparser.ConfigParser()
+    # folly manifests can contain bare keys in sections unrelated to downloads.
+    config = configparser.ConfigParser(allow_no_value=True, interpolation=None)
     try:
-        config.read(manifest_path)
-        if 'download' in config:
-            return {
-                'url': config['download'].get('url', ''),
-                'sha256': config['download'].get('sha256', ''),
-            }
-    except Exception:
-        pass
+        with open(manifest_path, encoding="utf-8") as manifest_file:
+            config.read_file(manifest_file)
+    except Exception as ex:
+        print(f"  {os.path.basename(manifest_path)}: WARNING - parse failed: {ex}")
+        return None
+
+    if "download" in config:
+        return {
+            "url": config["download"].get("url", ""),
+            "sha256": config["download"].get("sha256", ""),
+        }
     return None
 
+
+def file_size(path):
+    try:
+        return os.path.getsize(path)
+    except Exception:
+        return None
+
+
 def get_fallback_mirrors(url):
     """Get fallback mirror URLs for a given URL."""
-    # Fallback mirror patterns for known unreliable hosts
-    mirror_fallbacks = {
-        "ftp.gnu.org/gnu/": [
-            "https://mirrors.kernel.org/gnu/",
-            "https://ftpmirror.gnu.org/gnu/",
-            "https://ftp.gnu.org/gnu/",
-        ],
-        "ftpmirror.gnu.org/gnu/": [
-            "https://mirrors.kernel.org/gnu/",
-            "https://ftpmirror.gnu.org/gnu/",
-            "https://ftp.gnu.org/gnu/",
-        ],
-    }
-
-    for pattern, mirrors in mirror_fallbacks.items():
+    for pattern, mirrors in MIRROR_FALLBACKS.items():
         if pattern in url:
             # Extract the path after the pattern
             path_start = url.find(pattern) + len(pattern)
             path = url[path_start:]
             return [mirror + path for mirror in mirrors]
-    return [url]  # No fallback, use original
+    return []
+
+
+def download_url(url, filepath):
+    """Download URL to filepath without leaving partial files behind."""
+    tmp_filepath = filepath + ".tmp"
+    if os.path.exists(tmp_filepath):
+        os.remove(tmp_filepath)
+
+    request = urllib.request.Request(
+        url, headers={"User-Agent": "rocksdb-getdeps-fallback/1.0"}
+    )
+    try:
+        with urllib.request.urlopen(
+            request, timeout=DOWNLOAD_TIMEOUT_SECONDS
+        ) as response, open(tmp_filepath, "wb") as output:
+            copied = 0
+            while True:
+                chunk = response.read(DOWNLOAD_CHUNK_BYTES)
+                if not chunk:
+                    break
+
+                copied += len(chunk)
+                if copied > MAX_DOWNLOAD_BYTES:
+                    raise Exception(
+                        f"download exceeds {MAX_DOWNLOAD_BYTES} bytes"
+                    )
+                output.write(chunk)
+        os.replace(tmp_filepath, filepath)
+    finally:
+        if os.path.exists(tmp_filepath):
+            os.remove(tmp_filepath)
+
+
+def prepare_download(package, info, download_dir, cache_dir):
+    url = info["url"]
+    expected_sha256 = info["sha256"]
+    mirrors = get_fallback_mirrors(url)
+    if not mirrors:
+        return False
+
+    if not expected_sha256:
+        print(f"  {package}: WARNING - skipped fallback without sha256")
+        return False
+
+    # getdeps uses format: {package}-{filename}
+    filename = f"{package}-{os.path.basename(url)}"
+    filepath = os.path.join(download_dir, filename)
+    cache_path = os.path.join(cache_dir, filename)
+
+    # Check if already valid.
+    actual_sha256 = sha256_file(filepath) if os.path.exists(filepath) else None
+    if actual_sha256 == expected_sha256:
+        print(f"  {filename}: OK (already downloaded)")
+        return True
+    if actual_sha256 is not None:
+        print(
+            f"  {filename}: WARNING - removing invalid download "
+            f"sha256={actual_sha256}"
+        )
+        os.remove(filepath)
+
+    # The cache is only an opportunistic single-build accelerator; callers
+    # should not share it across concurrent builds without external locking.
+    actual_sha256 = sha256_file(cache_path) if os.path.exists(cache_path) else None
+    if actual_sha256 == expected_sha256:
+        print(f"  {filename}: OK (from cache)")
+        shutil.copy2(cache_path, filepath)
+        return True
+    if actual_sha256 is not None:
+        print(
+            f"  {filename}: WARNING - removing invalid cache "
+            f"sha256={actual_sha256}"
+        )
+        os.remove(cache_path)
+
+    # Try fallback mirrors.
+    for mirror_url in mirrors:
+        print(f"  {filename}: trying {mirror_url}...")
+        try:
+            download_url(mirror_url, filepath)
+        except Exception as ex:
+            print(f"  {filename}: WARNING - download failed: {ex}")
+            continue
+
+        actual_sha256 = sha256_file(filepath)
+        if actual_sha256 == expected_sha256:
+            size = file_size(filepath)
+            print(f"  {filename}: OK (downloaded, {size} bytes)")
+            shutil.copy2(filepath, cache_path)
+            return True
+
+        size = file_size(filepath)
+        print(
+            f"  {filename}: WARNING - sha256 mismatch from {mirror_url}: "
+            f"expected={expected_sha256} actual={actual_sha256} size={size}"
+        )
+        os.remove(filepath)
+
+    print(f"  {filename}: WARNING - all mirrors failed")
+    return False
+
 
 def main():
     if len(sys.argv) != 4:
@@ -64,60 +190,39 @@ def main():
         sys.exit(1)
 
     download_dir, cache_dir, manifests_dir = sys.argv[1], sys.argv[2], sys.argv[3]
+    os.makedirs(download_dir, exist_ok=True)
+    os.makedirs(cache_dir, exist_ok=True)
 
-    # Packages known to have unreliable mirrors
-    packages_to_check = ["autoconf", "automake", "libtool"]
-
-    for package in packages_to_check:
+    checked = 0
+    ready = 0
+    for package in PACKAGES_TO_CHECK:
         manifest_path = os.path.join(manifests_dir, package)
-        if not os.path.exists(manifest_path):
+        if not os.path.isfile(manifest_path):
             continue
 
         info = parse_manifest(manifest_path)
-        if not info or not info['url'] or not info['sha256']:
+        if not info or not info["url"]:
             continue
 
-        # Determine filename from URL
-        url = info['url']
-        expected_sha256 = info['sha256']
-        url_filename = os.path.basename(url)
-
-        # getdeps uses format: {package}-{filename}
-        filename = f"{package}-{url_filename}"
-        filepath = os.path.join(download_dir, filename)
-        cache_path = os.path.join(cache_dir, filename)
-
-        # Check if already valid
-        if os.path.exists(filepath) and sha256_file(filepath) == expected_sha256:
-            print(f"  {filename}: OK (already downloaded)")
+        if not info["sha256"]:
+            print(f"  {package}: WARNING - skipped fallback without sha256")
             continue
 
-        # Check cache
-        if os.path.exists(cache_path) and sha256_file(cache_path) == expected_sha256:
-            print(f"  {filename}: OK (from cache)")
-            subprocess.run(['cp', cache_path, filepath], check=True)
+        if not get_fallback_mirrors(info["url"]):
+            print(
+                f"  {package}: WARNING - skipped fallback without known mirror "
+                f"for {info['url']}"
+            )
             continue
 
-        # Try fallback mirrors
-        mirrors = get_fallback_mirrors(url)
-        downloaded = False
-        for mirror_url in mirrors:
-            print(f"  {filename}: trying {mirror_url}...")
-            try:
-                subprocess.run(['wget', '-q', '-O', filepath, mirror_url], check=True, timeout=120)
-                if sha256_file(filepath) == expected_sha256:
-                    print(f"  {filename}: OK (downloaded)")
-                    subprocess.run(['cp', filepath, cache_path], check=False)
-                    downloaded = True
-                    break
-                else:
-                    os.remove(filepath)
-            except Exception:
-                if os.path.exists(filepath):
-                    os.remove(filepath)
+        checked += 1
+        try:
+            if prepare_download(package, info, download_dir, cache_dir):
+                ready += 1
+        except Exception as ex:
+            print(f"  {package}: WARNING - fallback preparation failed: {ex}")
 
-        if not downloaded:
-            print(f"  {filename}: WARNING - all mirrors failed")
+    print(f"  fallback mirror downloads ready: {ready}/{checked}")
 
 if __name__ == "__main__":
     main()

db/blob/blob_file_reader.cc

@@ -20,6 +20,7 @@
 #include "table/format.h"
 #include "table/multiget_context.h"
 #include "test_util/sync_point.h"
+#include "util/aligned_buffer.h"
 #include "util/compression.h"
 #include "util/stop_watch.h"
 
@@ -165,7 +166,7 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
 
   Slice header_slice;
   Buffer buf;
-  AlignedBuf aligned_buf;
+  AlignedBuffer direct_io_buffer;
 
   {
     TEST_SYNC_POINT("BlobFileReader::ReadHeader:ReadFromFile");
@@ -175,7 +176,7 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
 
     const Status s =
         ReadFromFile(file_reader, read_options, read_offset, read_size,
-                     statistics, &header_slice, &buf, &aligned_buf);
+                     statistics, &header_slice, &buf, &direct_io_buffer);
     if (!s.ok()) {
       return s;
     }
@@ -216,7 +217,7 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
 
   Slice footer_slice;
   Buffer buf;
-  AlignedBuf aligned_buf;
+  AlignedBuffer direct_io_buffer;
 
   {
     TEST_SYNC_POINT("BlobFileReader::ReadFooter:ReadFromFile");
@@ -226,7 +227,7 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
 
     const Status s =
         ReadFromFile(file_reader, read_options, read_offset, read_size,
-                     statistics, &footer_slice, &buf, &aligned_buf);
+                     statistics, &footer_slice, &buf, &direct_io_buffer);
     if (!s.ok()) {
       return s;
     }
@@ -257,10 +258,11 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
                                     const ReadOptions& read_options,
                                     uint64_t read_offset, size_t read_size,
                                     Statistics* statistics, Slice* slice,
-                                    Buffer* buf, AlignedBuf* aligned_buf) {
+                                    Buffer* buf,
+                                    AlignedBuffer* direct_io_buffer) {
   assert(slice);
   assert(buf);
-  assert(aligned_buf);
+  assert(direct_io_buffer);
 
   assert(file_reader);
 
@@ -277,15 +279,15 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
 
   if (file_reader->use_direct_io()) {
     constexpr char* scratch = nullptr;
+    AlignedBufferAllocationContext direct_io_context{direct_io_buffer};
 
     s = file_reader->Read(io_options, read_offset, read_size, slice, scratch,
-                          aligned_buf, &dbg);
+                          &direct_io_context, &dbg);
   } else {
     buf->reset(new char[read_size]);
-    constexpr AlignedBuf* aligned_scratch = nullptr;
 
     s = file_reader->Read(io_options, read_offset, read_size, slice, buf->get(),
-                          aligned_scratch, &dbg);
+                          nullptr, &dbg);
   }
 
   if (!s.ok()) {
@@ -349,7 +351,7 @@ Status BlobFileReader::GetBlob(
 
   Slice record_slice;
   Buffer buf;
-  AlignedBuf aligned_buf;
+  AlignedBuffer direct_io_buffer;
 
   bool prefetched = false;
 
@@ -379,7 +381,7 @@ Status BlobFileReader::GetBlob(
     const Status s =
         ReadFromFile(file_reader_.get(), read_options, record_offset,
                      static_cast<size_t>(record_size), statistics_,
-                     &record_slice, &buf, &aligned_buf);
+                     &record_slice, &buf, &direct_io_buffer);
     if (!s.ok()) {
       return s;
     }
@@ -477,7 +479,7 @@ void BlobFileReader::MultiGetBlob(
   }
 
   Buffer buf;
-  AlignedBuf aligned_buf;
+  AlignedBuffer direct_io_buffer;
 
   Status s;
   bool direct_io = file_reader_->use_direct_io();
@@ -500,8 +502,9 @@ void BlobFileReader::MultiGetBlob(
   IODebugContext dbg;
   s = file_reader_->PrepareIOOptions(read_options, opts, &dbg);
   if (s.ok()) {
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
     s = file_reader_->MultiRead(opts, read_reqs.data(), read_reqs.size(),
-                                direct_io ? &aligned_buf : nullptr, &dbg);
+                                &direct_io_context, &dbg);
   }
   if (!s.ok()) {
     for (auto& req : read_reqs) {

db/blob/blob_file_reader.h

@@ -108,7 +108,7 @@ class BlobFileReader {
                              const ReadOptions& read_options,
                              uint64_t read_offset, size_t read_size,
                              Statistics* statistics, Slice* slice, Buffer* buf,
-                             AlignedBuf* aligned_buf);
+                             AlignedBuffer* direct_io_buffer);
 
   static Status VerifyBlob(const Slice& record_slice, const Slice& user_key,
                            uint64_t value_size);

db/blob/blob_source.cc

@@ -74,6 +74,7 @@ Status BlobSource::GetBlobFromCache(
     assert(cached_blob->GetValue());
 
     PERF_COUNTER_ADD(blob_cache_hit_count, 1);
+    PERF_COUNTER_ADD(blob_cache_read_byte, cached_blob->GetValue()->size());
     RecordTick(statistics_, BLOB_DB_CACHE_HIT);
     RecordTick(statistics_, BLOB_DB_CACHE_BYTES_READ,
                cached_blob->GetValue()->size());

db/blob/blob_source_test.cc

@@ -229,6 +229,7 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
     // Retrieved the blob cache num_blobs * 3 times via TEST_BlobInCache,
     // GetBlob, and TEST_BlobInCache.
     ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count, 0);
+    ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte, 0);
     ASSERT_EQ((int)get_perf_context()->blob_read_count, num_blobs);
     ASSERT_EQ((int)get_perf_context()->blob_read_byte, total_bytes);
     ASSERT_GE((int)get_perf_context()->blob_checksum_time, 0);
@@ -262,6 +263,8 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
       blob_bytes += blob_sizes[i];
       total_bytes += bytes_read;
       ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count, i);
+      ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte,
+                blob_bytes - blob_sizes[i]);
       ASSERT_EQ((int)get_perf_context()->blob_read_count, i + 1);
       ASSERT_EQ((int)get_perf_context()->blob_read_byte, total_bytes);
 
@@ -269,11 +272,13 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
                                                blob_offsets[i]));
 
       ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count, i + 1);
+      ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte, blob_bytes);
       ASSERT_EQ((int)get_perf_context()->blob_read_count, i + 1);
       ASSERT_EQ((int)get_perf_context()->blob_read_byte, total_bytes);
     }
 
     ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count, num_blobs);
+    ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte, blob_bytes);
     ASSERT_EQ((int)get_perf_context()->blob_read_count, num_blobs);
     ASSERT_EQ((int)get_perf_context()->blob_read_byte, total_bytes);
 
@@ -312,6 +317,7 @@ TEST_F(BlobSourceTest, GetBlobsFromCache) {
     // Retrieved the blob cache num_blobs * 3 times via TEST_BlobInCache,
     // GetBlob, and TEST_BlobInCache.
     ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count, num_blobs * 3);
+    ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte, blob_bytes * 3);
     ASSERT_EQ((int)get_perf_context()->blob_read_count, 0);  // without i/o
     ASSERT_EQ((int)get_perf_context()->blob_read_byte, 0);   // without i/o
 
@@ -690,6 +696,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
     // TEST_BlobInCache.
     ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count,
               num_blobs * blob_files);
+    ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte,
+              blob_value_bytes * blob_files);
     ASSERT_EQ((int)get_perf_context()->blob_read_count,
               num_blobs * blob_files);  // blocking i/o
     ASSERT_EQ((int)get_perf_context()->blob_read_byte,
@@ -750,6 +758,8 @@ TEST_F(BlobSourceTest, MultiGetBlobsFromMultiFiles) {
     // via MultiGetBlob and TEST_BlobInCache.
     ASSERT_EQ((int)get_perf_context()->blob_cache_hit_count,
               num_blobs * blob_files * 2);
+    ASSERT_EQ((int)get_perf_context()->blob_cache_read_byte,
+              blob_value_bytes * blob_files * 2);
     ASSERT_EQ((int)get_perf_context()->blob_read_count,
               0);  // blocking i/o
     ASSERT_EQ((int)get_perf_context()->blob_read_byte,

db/c.cc

@@ -3771,6 +3771,11 @@ void rocksdb_block_based_options_set_index_block_search_type(
       static_cast<BlockBasedTableOptions::BlockSearchType>(v);
 }
 
+void rocksdb_block_based_options_set_uniform_cv_threshold(
+    rocksdb_block_based_table_options_t* options, double v) {
+  options->rep.uniform_cv_threshold = v;
+}
+
 void rocksdb_block_based_options_set_data_block_hash_ratio(
     rocksdb_block_based_table_options_t* options, double v) {
   options->rep.data_block_hash_table_util_ratio = v;
@@ -5286,6 +5291,15 @@ size_t rocksdb_options_get_recycle_log_file_num(rocksdb_options_t* opt) {
   return opt->rep.recycle_log_file_num;
 }
 
+void rocksdb_options_set_async_wal_precreate(rocksdb_options_t* opt,
+                                             unsigned char v) {
+  opt->rep.async_wal_precreate = v;
+}
+
+unsigned char rocksdb_options_get_async_wal_precreate(rocksdb_options_t* opt) {
+  return opt->rep.async_wal_precreate;
+}
+
 void rocksdb_options_set_soft_pending_compaction_bytes_limit(
     rocksdb_options_t* opt, size_t v) {
   opt->rep.soft_pending_compaction_bytes_limit = v;
@@ -5389,6 +5403,16 @@ size_t rocksdb_options_get_memtable_huge_page_size(rocksdb_options_t* opt) {
   return opt->rep.memtable_huge_page_size;
 }
 
+void rocksdb_options_set_memtable_batch_lookup_optimization(
+    rocksdb_options_t* opt, unsigned char v) {
+  opt->rep.memtable_batch_lookup_optimization = v;
+}
+
+unsigned char rocksdb_options_get_memtable_batch_lookup_optimization(
+    rocksdb_options_t* opt) {
+  return opt->rep.memtable_batch_lookup_optimization;
+}
+
 void rocksdb_options_set_hash_skip_list_rep(rocksdb_options_t* opt,
                                             size_t bucket_count,
                                             int32_t skiplist_height,
@@ -5820,6 +5844,8 @@ uint64_t rocksdb_perfcontext_metric(rocksdb_perfcontext_t* context,
       return rep->number_async_seek;
     case rocksdb_blob_cache_hit_count:
       return rep->blob_cache_hit_count;
+    case rocksdb_blob_cache_read_byte:
+      return rep->blob_cache_read_byte;
     case rocksdb_blob_read_count:
       return rep->blob_read_count;
     case rocksdb_blob_read_byte:
@@ -6238,6 +6264,16 @@ unsigned char rocksdb_readoptions_get_async_io(rocksdb_readoptions_t* opt) {
   return opt->rep.async_io;
 }
 
+void rocksdb_readoptions_set_optimize_multiget_for_io(
+    rocksdb_readoptions_t* opt, unsigned char v) {
+  opt->rep.optimize_multiget_for_io = v;
+}
+
+unsigned char rocksdb_readoptions_get_optimize_multiget_for_io(
+    rocksdb_readoptions_t* opt) {
+  return opt->rep.optimize_multiget_for_io;
+}
+
 void rocksdb_readoptions_set_timestamp(rocksdb_readoptions_t* opt,
                                        const char* ts, size_t tslen) {
   if (ts == nullptr) {

db/c_test.c

@@ -888,6 +888,9 @@ int main(int argc, char** argv) {
   rocksdb_block_based_options_set_block_cache(table_options, cache);
   rocksdb_block_based_options_set_data_block_index_type(table_options, 1);
   rocksdb_block_based_options_set_data_block_hash_ratio(table_options, 0.75);
+  rocksdb_block_based_options_set_index_block_search_type(
+      table_options, rocksdb_block_based_table_index_block_search_type_auto);
+  rocksdb_block_based_options_set_uniform_cv_threshold(table_options, 0.2);
   rocksdb_block_based_options_set_top_level_index_pinning_tier(table_options,
                                                                1);
   rocksdb_block_based_options_set_partition_pinning_tier(table_options, 2);
@@ -2812,6 +2815,15 @@ int main(int argc, char** argv) {
     rocksdb_options_set_memtable_huge_page_size(o, 25);
     CheckCondition(25 == rocksdb_options_get_memtable_huge_page_size(o));
 
+    // memtable_batch_lookup_optimization defaults to 0; flip to 1 to verify
+    // the setter is wired through to the underlying C++ ColumnFamilyOptions
+    // field.
+    CheckCondition(0 ==
+                   rocksdb_options_get_memtable_batch_lookup_optimization(o));
+    rocksdb_options_set_memtable_batch_lookup_optimization(o, 1);
+    CheckCondition(1 ==
+                   rocksdb_options_get_memtable_batch_lookup_optimization(o));
+
     rocksdb_options_set_max_successive_merges(o, 26);
     CheckCondition(26 == rocksdb_options_get_max_successive_merges(o));
 
@@ -2869,6 +2881,9 @@ int main(int argc, char** argv) {
     rocksdb_options_set_track_and_verify_wals_in_manifest(o, 42);
     CheckCondition(1 ==
                    rocksdb_options_get_track_and_verify_wals_in_manifest(o));
+    CheckCondition(0 == rocksdb_options_get_async_wal_precreate(o));
+    rocksdb_options_set_async_wal_precreate(o, 1);
+    CheckCondition(1 == rocksdb_options_get_async_wal_precreate(o));
 
     /* Blob Options */
     rocksdb_options_set_enable_blob_files(o, 1);
@@ -2995,6 +3010,8 @@ int main(int argc, char** argv) {
                    rocksdb_options_get_memtable_prefix_bloom_size_ratio(copy));
     CheckCondition(24 == rocksdb_options_get_max_compaction_bytes(copy));
     CheckCondition(25 == rocksdb_options_get_memtable_huge_page_size(copy));
+    CheckCondition(
+        1 == rocksdb_options_get_memtable_batch_lookup_optimization(copy));
     CheckCondition(26 == rocksdb_options_get_max_successive_merges(copy));
     CheckCondition(27 == rocksdb_options_get_bloom_locality(copy));
     CheckCondition(1 == rocksdb_options_get_inplace_update_support(copy));
@@ -3429,6 +3446,12 @@ int main(int argc, char** argv) {
     rocksdb_readoptions_set_async_io(ro, 1);
     CheckCondition(1 == rocksdb_readoptions_get_async_io(ro));
 
+    // optimize_multiget_for_io defaults to true (1); flip to 0 to verify the
+    // setter is wired through to the underlying C++ ReadOptions field.
+    CheckCondition(1 == rocksdb_readoptions_get_optimize_multiget_for_io(ro));
+    rocksdb_readoptions_set_optimize_multiget_for_io(ro, 0);
+    CheckCondition(0 == rocksdb_readoptions_get_optimize_multiget_for_io(ro));
+
     rocksdb_readoptions_destroy(ro);
   }
 

db/compaction/compaction.h

@@ -454,6 +454,18 @@ class Compaction {
     return notify_on_compaction_completion_;
   }
 
+  // Called by DBImpl::NotifyOnCompactionPreCommit to ensure the
+  // OnCompactionPreCommit listener callback fires at most once per
+  // compaction lifecycle, even though the notify helper is invoked at multiple
+  // potential ReleaseCompactionFiles() sites for safety.
+  void SetNotifyOnCompactionPreCommitCalled() {
+    notify_on_compaction_pre_commit_called_ = true;
+  }
+
+  bool WasNotifyOnCompactionPreCommitCalled() const {
+    return notify_on_compaction_pre_commit_called_;
+  }
+
   static constexpr int kInvalidLevel = -1;
 
   // Evaluate proximal output level. If the compaction supports
@@ -626,6 +638,12 @@ class Compaction {
   // begin.
   bool notify_on_compaction_completion_;
 
+  // Tracks whether OnCompactionPreCommit has already fired for this
+  // compaction. The notify helper is called from multiple potential
+  // ReleaseCompactionFiles() call sites; this flag guarantees that listeners
+  // observe the callback exactly once per compaction.
+  bool notify_on_compaction_pre_commit_called_ = false;
+
   // Enable/disable GC collection for blobs during compaction.
   bool enable_blob_garbage_collection_;
 

db/compaction/compaction_job.cc

@@ -2065,10 +2065,18 @@ Status CompactionJob::FinishCompactionOutputFile(
     std::pair<SequenceNumber, SequenceNumber> keep_seqno_range{
         0, kMaxSequenceNumber};
     if (sub_compact->compaction->SupportsPerKeyPlacement()) {
+      // Point entries are routed to proximal output only when their seqno is
+      // strictly greater than `proximal_after_seqno_`. Range tombstones use a
+      // [lower, upper) filter, so split them at the next seqno to preserve the
+      // same boundary.
+      SequenceNumber range_del_split_seqno = proximal_after_seqno_;
+      if (range_del_split_seqno < kMaxSequenceNumber) {
+        range_del_split_seqno++;
+      }
       if (outputs.IsProximalLevel()) {
-        keep_seqno_range.first = proximal_after_seqno_;
+        keep_seqno_range.first = range_del_split_seqno;
       } else {
-        keep_seqno_range.second = proximal_after_seqno_;
+        keep_seqno_range.second = range_del_split_seqno;
       }
     }
     CompactionIterationStats range_del_out_stats;

db/compaction/compaction_service_job.cc

@@ -189,14 +189,24 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
     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;
+    // Wait() returned kSuccess, but the primary host could not deserialize the
+    // remote result before importing any output files into this DB. The remote
+    // output is still isolated in the service-managed staging directory, so it
+    // is safe to fall back to local compaction for the same job and notify the
+    // service via OnInstallation(kUseLocal).
+    assert(sub_compact->status.ok());
+    assert(sub_compact->GetMutableCompactionOutputs().empty());
+    assert(sub_compact->GetMutableProximalOutputs().empty());
+    ROCKS_LOG_WARN(db_options_.info_log,
+                   "[%s] [JOB %d] Failed to parse remote compaction result "
+                   "(%s), falling back to local compaction",
+                   compaction->column_family_data()->GetName().c_str(), job_id_,
+                   s.ToString().c_str());
     compaction_result.status.PermitUncheckedError();
     db_options_.compaction_service->OnInstallation(
-        response.scheduled_job_id, CompactionServiceJobStatus::kFailure);
-    return CompactionServiceJobStatus::kFailure;
+        response.scheduled_job_id, CompactionServiceJobStatus::kUseLocal);
+    return CompactionServiceJobStatus::kUseLocal;
   }
   sub_compact->status = compaction_result.status;
 
@@ -641,6 +651,10 @@ static std::unordered_map<std::string, OptionTypeInfo>
         {"cpu_micros",
          {offsetof(struct CompactionJobStats, cpu_micros), OptionType::kUInt64T,
           OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
+        {"has_accurate_num_input_records",
+         {offsetof(struct CompactionJobStats, has_accurate_num_input_records),
+          OptionType::kBoolean, OptionVerificationType::kNormal,
+          OptionTypeFlags::kNone}},
         {"num_input_records",
          {offsetof(struct CompactionJobStats, num_input_records),
           OptionType::kUInt64T, OptionVerificationType::kNormal,

db/compaction/compaction_service_test.cc

@@ -127,6 +127,7 @@ class MyTestCompactionService : public CompactionService {
 
   void OnInstallation(const std::string& /*scheduled_job_id*/,
                       CompactionServiceJobStatus status) override {
+    installation_callback_count_.fetch_add(1);
     final_updated_status_ = status;
   }
 
@@ -167,6 +168,8 @@ class MyTestCompactionService : public CompactionService {
     return final_updated_status_.load();
   }
 
+  int GetOnInstallationCount() { return installation_callback_count_.load(); }
+
  protected:
   InstrumentedMutex mutex_;
   const std::string db_path_;
@@ -195,6 +198,7 @@ class MyTestCompactionService : public CompactionService {
   std::vector<std::shared_ptr<EventListener>> listeners_;
   std::vector<std::shared_ptr<TablePropertiesCollectorFactory>>
       table_properties_collector_factories_;
+  std::atomic_int installation_callback_count_{0};
   std::atomic<CompactionServiceJobStatus> final_updated_status_{
       CompactionServiceJobStatus::kUseLocal};
 
@@ -939,6 +943,37 @@ TEST_F(CompactionServiceTest, VerifyInputRecordCount) {
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
+TEST_F(CompactionServiceTest, InaccurateInputRecordCount) {
+  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->stats.has_accurate_num_input_records = false;
+        compaction_result->stats.num_input_records = 0;
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), &start, &end));
+  ASSERT_GE(my_cs->GetCompactionNum(), comp_num + 1);
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
 TEST_F(CompactionServiceTest, EmptyResult) {
   Options options = CurrentOptions();
   options.disable_auto_compactions = true;
@@ -1448,7 +1483,7 @@ TEST_F(CompactionServiceTest, FailedToStart) {
   ASSERT_TRUE(s.IsIncomplete());
 }
 
-TEST_F(CompactionServiceTest, InvalidResult) {
+TEST_F(CompactionServiceTest, InvalidResultFallsBackToLocal) {
   Options options = CurrentOptions();
   options.disable_auto_compactions = true;
   ReopenWithCompactionService(&options);
@@ -1456,15 +1491,22 @@ TEST_F(CompactionServiceTest, InvalidResult) {
   GenerateTestData();
 
   auto my_cs = GetCompactionService();
+  ASSERT_EQ(0, my_cs->GetOnInstallationCount());
   my_cs->OverrideWaitResult("Invalid Str");
+  int compaction_num_before = my_cs->GetCompactionNum();
 
   std::string start_str = Key(15);
   std::string end_str = Key(45);
   Slice start(start_str);
   Slice end(end_str);
+  // The remote result is malformed before any installation starts, so the
+  // primary should recover by rerunning the compaction locally for this job.
   Status s = db_->CompactRange(CompactRangeOptions(), &start, &end);
-  ASSERT_FALSE(s.ok());
-  ASSERT_EQ(CompactionServiceJobStatus::kFailure,
+  ASSERT_OK(s);
+  ASSERT_GE(my_cs->GetCompactionNum(), compaction_num_before + 1);
+  VerifyTestData();
+  ASSERT_EQ(1, my_cs->GetOnInstallationCount());
+  ASSERT_EQ(CompactionServiceJobStatus::kUseLocal,
             my_cs->GetFinalCompactionServiceJobStatus());
 }
 

db/compaction/tiered_compaction_test.cc

@@ -2897,6 +2897,61 @@ TEST_P(PrecludeLastLevelTest, RangeDelsCauseFileEndpointsToOverlap) {
   Close();
 }
 
+TEST_F(PrecludeLastLevelTestBase,
+       RangeDelAtProximalSeqnoBoundaryStaysInLastLevel) {
+  constexpr int kNumLevels = 7;
+
+  Options options = CurrentOptions();
+  options.env = mock_env_.get();
+  options.num_levels = kNumLevels;
+  options.disable_auto_compactions = true;
+  DestroyAndReopen(options);
+  Defer close_db([&] { Close(); });
+
+  ASSERT_OK(Put(Key(2), "old"));
+  ASSERT_OK(Put(Key(12), "old"));
+  ManagedSnapshot snapshot(db_.get());
+  ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), Key(2),
+                             Key(12)));
+  ASSERT_OK(Flush());
+  MoveFilesToLevel(6);
+
+  const int l5_file_keys[][2] = {{0, 4}, {5, 9}};
+  for (const auto& l5_file : l5_file_keys) {
+    ASSERT_OK(Put(Key(l5_file[0]), "hot"));
+    ASSERT_OK(Put(Key(l5_file[1]), "hot"));
+    ASSERT_OK(Flush());
+    MoveFilesToLevel(5);
+  }
+  ASSERT_EQ("0,0,0,0,0,2,1", FilesPerLevel());
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "CompactionJob::PrepareTimes():preclude_last_level_min_seqno",
+      [](void* arg) { *static_cast<SequenceNumber*>(arg) = 0; });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  ASSERT_OK(db_->SetOptions({{"preclude_last_level_data_seconds", "10000"}}));
+
+  auto l5_files = GetLevelFileMetadatas(5);
+  auto l6_files = GetLevelFileMetadatas(6);
+  ASSERT_EQ(2, l5_files.size());
+  ASSERT_EQ(1, l6_files.size());
+
+  ASSERT_OK(db_->CompactFiles(CompactionOptions(),
+                              {MakeTableFileName(l5_files[1]->fd.GetNumber()),
+                               MakeTableFileName(l6_files[0]->fd.GetNumber())},
+                              6));
+
+  uint64_t l6_range_deletions = 0;
+  for (auto* f : GetLevelFileMetadatas(5)) {
+    ASSERT_EQ(0, f->num_range_deletions);
+  }
+  for (auto* f : GetLevelFileMetadatas(6)) {
+    l6_range_deletions += f->num_range_deletions;
+  }
+  ASSERT_GT(l6_range_deletions, 0);
+}
+
 // Tests DBIter::GetProperty("rocksdb.iterator.write-time") return a data's
 // approximate write unix time.
 class IteratorWriteTimeTest

db/db_basic_test.cc

@@ -761,6 +761,111 @@ TEST_F(DBBasicTest, ReuseManifestOnOpenFullStackComposition) {
   EXPECT_EQ("v", Get("k"));
 }
 
+// Regression test for WAL recovery while publishing a fresh MANIFEST. The test
+// stores SSTs in a separate DB path, injects failure after CURRENT points at
+// the new MANIFEST, and simulates crash cleanup; the recovered SST must survive
+// because the synced MANIFEST references it.
+TEST_F(DBBasicTest, RecoverySstDirSyncedBeforeFreshManifestPublish) {
+  auto fault_fs = std::make_shared<FaultInjectionTestFS>(env_->GetFileSystem());
+  std::unique_ptr<Env> fault_env(NewCompositeEnv(fault_fs));
+
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.disable_auto_compactions = true;
+  options.env = fault_env.get();
+  options.reuse_manifest_on_open = false;
+  options.db_paths.emplace_back(dbname_ + "_2", 1ULL << 30);
+
+  DestroyAndReopen(options);
+  ASSERT_OK(Put("base", "value"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(Put("recovered", "value"));
+  ASSERT_OK(db_->FlushWAL(true));
+  Close();
+
+  fault_fs->ResetState();
+
+  std::atomic<bool> fail_after_current_publish{true};
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::ProcessManifestWrites:AfterSetCurrentFile", [&](void* arg) {
+        if (fail_after_current_publish.exchange(false)) {
+          ASSERT_NE(nullptr, arg);
+          IOStatus* io_s = static_cast<IOStatus*>(arg);
+          ASSERT_OK(*io_s);
+          *io_s = IOStatus::IOError("injected current publish aftermath");
+        }
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  Status s = TryReopen(options);
+  ASSERT_TRUE(s.IsIOError()) << s.ToString();
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  ASSERT_OK(fault_fs->DeleteFilesCreatedAfterLastDirSync(IOOptions(), nullptr));
+
+  s = TryReopen(options);
+  ASSERT_OK(s);
+  ASSERT_EQ("value", Get("base"));
+  ASSERT_EQ("value", Get("recovered"));
+  Close();
+}
+
+// Regression test for WAL recovery while appending to a reused MANIFEST. The
+// first reopen forces recovery to create an SST and then fail after MANIFEST
+// sync. The simulated crash cleanup deletes files without a prior directory
+// sync; the recovered SST must survive because the synced MANIFEST references
+// it.
+TEST_F(DBBasicTest,
+       ReuseManifestOnOpenSyncsRecoverySstDirBeforeManifestAppend) {
+  auto fault_fs = std::make_shared<FaultInjectionTestFS>(env_->GetFileSystem());
+  std::unique_ptr<Env> fault_env(NewCompositeEnv(fault_fs));
+
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.disable_auto_compactions = true;
+  options.env = fault_env.get();
+  options.reuse_manifest_on_open = true;
+
+  DestroyAndReopen(options);
+  ASSERT_OK(Put("base", "value"));
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(Put("recovered", "value"));
+  ASSERT_OK(db_->FlushWAL(true));
+  Close();
+
+  fault_fs->ResetState();
+
+  std::atomic<bool> fail_after_manifest_sync{true};
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::ProcessManifestWrites:AfterSyncManifest", [&](void* arg) {
+        if (fail_after_manifest_sync.exchange(false)) {
+          ASSERT_NE(nullptr, arg);
+          IOStatus* io_s = static_cast<IOStatus*>(arg);
+          ASSERT_OK(*io_s);
+          *io_s = IOStatus::IOError("injected manifest sync aftermath");
+        }
+      });
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  Status s = TryReopen(options);
+  ASSERT_TRUE(s.IsIOError()) << s.ToString();
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  ASSERT_OK(fault_fs->DeleteFilesCreatedAfterLastDirSync(IOOptions(), nullptr));
+
+  s = TryReopen(options);
+  ASSERT_OK(s);
+  ASSERT_EQ("value", Get("base"));
+  ASSERT_EQ("value", Get("recovered"));
+  Close();
+}
+
 // Direct unit test for WritableFileWriter's initial_file_size parameter:
 // verifies the visible size accessors report the existing on-disk size
 // immediately, rather than the constructor's zero default.

db/db_bloom_filter_test.cc

@@ -2022,7 +2022,11 @@ TEST_F(DBBloomFilterTest, MutableFilterPolicy) {
   double expected_bpk = 10.0;
   // Other configs to try
   std::vector<std::pair<std::string, double>> configs = {
-      {"ribbonfilter:10:-1", 7.0}, {"bloomfilter:5", 5.0}, {"nullptr", 0.0}};
+      {"ribbonfilter:10:-1", 7.0},
+      {"bloomfilter:5", 5.0},
+      {"nullptr", 0.0},
+      // As serialized in OPTIONS file
+      {"{id=ribbonfilter:12:-1;bloom_before_level=-1;}", 8.4}};
 
   table_options.cache_index_and_filter_blocks = true;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));

db/db_compaction_abort_test.cc

@@ -427,6 +427,38 @@ TEST_F(DBCompactionAbortTest, AbortAutomaticCompaction) {
   }
 }
 
+TEST_F(DBCompactionAbortTest, AbortScheduledAutomaticCompactionBeforePick) {
+  // The goal is to cover an automatic compaction that has been scheduled, but
+  // aborts before the worker picks and removes a column family from the
+  // compaction queue. This pins the scheduler bookkeeping invariant that
+  // ResumeAllCompactions() must be able to schedule that still-queued work.
+  constexpr int kCompactionTrigger = 4;
+  constexpr int kNumL0Files = kCompactionTrigger + 1;
+  Options options = GetOptionsWithStats();
+  options.level0_file_num_compaction_trigger = kCompactionTrigger;
+  options.max_background_compactions = 1;
+  options.max_subcompactions = 1;
+  options.disable_auto_compactions = false;
+  Reopen(options);
+
+  SyncPointAbortHelper helper("BackgroundCallCompaction:0");
+  helper.Setup(dbfull());
+
+  PopulateData(/*num_files=*/kNumL0Files, /*keys_per_file=*/100,
+               /*value_size=*/1000);
+  helper.CleanupAndWait();
+
+  const uint64_t compact_write_bytes_before_resume =
+      stats_->getTickerCount(COMPACT_WRITE_BYTES);
+  dbfull()->ResumeAllCompactions();
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+  ASSERT_GT(stats_->getTickerCount(COMPACT_WRITE_BYTES),
+            compact_write_bytes_before_resume);
+  ASSERT_LT(NumTableFilesAtLevel(0), kNumL0Files);
+  VerifyDataIntegrity(/*num_keys=*/100);
+}
+
 TEST_F(DBCompactionAbortTest, AbortAndVerifyNoOutputFiles) {
   Options options = CurrentOptions();
   options.level0_file_num_compaction_trigger = 4;

db/db_etc2_test.cc

@@ -35,7 +35,7 @@ namespace ROCKSDB_NAMESPACE {
 
 class DBTest2 : public DBTestBase {
  public:
-  DBTest2() : DBTestBase("db_test2", /*env_do_fsync=*/true) {}
+  DBTest2() : DBTestBase("db_etc2_test", /*env_do_fsync=*/true) {}
 };
 
 TEST_F(DBTest2, OpenForReadOnly) {

db/db_etc3_test.cc

@@ -1,9 +1,12 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) Meta Platforms, Inc. and affiliates.
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
 #include "db/db_test_util.h"
+#include "rocksdb/convenience.h"
+#include "rocksdb/metadata.h"
+#include "rocksdb/sst_file_writer.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -43,50 +46,98 @@ TEST_F(DBEtc3Test, AutoTuneManifestSize) {
   ASSERT_EQ(DBOptions{}.max_manifest_space_amp_pct, 500);
 
   Options options = CurrentOptions();
-  ASSERT_OK(db_->SetOptions({{"level0_file_num_compaction_trigger", "20"}}));
+  // Test setup: create many flushed files. Keep level compaction semantics so
+  // DeleteFilesInRanges can remove non-L0 files, but prevent automatic
+  // compactions and write stalls from adding unrelated behavior.
+  options.disable_auto_compactions = true;
+  options.level0_slowdown_writes_trigger = 100;
+  options.level0_stop_writes_trigger = 200;
 
-  // Use large column family names to essentially control the amount of payload
-  // data needed for the manifest file. Drop manifest entries don't include the
-  // CF name so are small.
+  // Test strategy: use large column family names to control the rough amount
+  // of payload added to the MANIFEST. Drop manifest entries do not include the
+  // CF name, so they are small.
+  //
+  // Most CF helper calls piggy-back a background manifest write so the main
+  // auto-tuning phases continue to test the unrelaxed background threshold
+  // even though CF manipulation itself is foreground. Phase-specific foreground
+  // checks disable that piggy-backed background write.
   uint64_t prev_manifest_num = 0, cur_manifest_num = 0;
   std::deque<ColumnFamilyHandle*> handles;
   int counter = 5;
-  auto AddCfFn = [&]() {
+  auto UpdateManifestNumsFrom = [&](uint64_t before_manifest_num) {
+    prev_manifest_num = before_manifest_num;
+    cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
+  };
+  auto BackgroundManifestWriteFn = [&]() {
+    uint64_t before_manifest_num = cur_manifest_num;
+    ASSERT_OK(Put("x", std::to_string(counter++)));
+    ASSERT_OK(Flush());
+    UpdateManifestNumsFrom(before_manifest_num);
+  };
+  auto AddCfFn = [&](bool include_background_manifest_write = true) {
+    uint64_t before_manifest_num = cur_manifest_num;
     std::string name = "cf" + std::to_string(counter++);
     name.resize(1000, 'a');
     ASSERT_OK(db_->CreateColumnFamily(options, name, &handles.emplace_back()));
-    prev_manifest_num = cur_manifest_num;
     cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
+    if (include_background_manifest_write) {
+      BackgroundManifestWriteFn();
+    }
+    UpdateManifestNumsFrom(before_manifest_num);
   };
-  auto DropCfFn = [&]() {
+  auto DropCfFn = [&](bool include_background_manifest_write = true) {
+    uint64_t before_manifest_num = cur_manifest_num;
     ASSERT_OK(db_->DropColumnFamily(handles.front()));
     ASSERT_OK(db_->DestroyColumnFamilyHandle(handles.front()));
     handles.pop_front();
-    prev_manifest_num = cur_manifest_num;
-    cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
-  };
-  auto TrivialManifestWriteFn = [&]() {
-    ASSERT_OK(Put("x", std::to_string(counter++)));
-    ASSERT_OK(Flush());
-    prev_manifest_num = cur_manifest_num;
     cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
+    if (include_background_manifest_write) {
+      BackgroundManifestWriteFn();
+    }
+    UpdateManifestNumsFrom(before_manifest_num);
   };
 
+  // ---- Phase 1: foreground threshold relaxation is bounded ----
+  //
+  // Foreground operations should only get about 25% extra headroom, not an
+  // unbounded threshold. With 1000-byte CF names and a 3000-byte normal limit,
+  // the relaxed limit should allow the first four foreground-only CF additions
+  // but require rotation on the fifth.
+  options.max_manifest_file_size = 3000;
+  options.max_manifest_space_amp_pct = 0;
+  DestroyAndReopen(options);
+  cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
+  prev_manifest_num = cur_manifest_num;
+  for (int i = 1; i <= 4; ++i) {
+    AddCfFn(/*include_background_manifest_write=*/false);
+    ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+  }
+  AddCfFn(/*include_background_manifest_write=*/false);
+  ASSERT_LT(prev_manifest_num, cur_manifest_num);
+  while (!handles.empty()) {
+    ASSERT_OK(db_->DestroyColumnFamilyHandle(handles.front()));
+    handles.pop_front();
+  }
+
+  // ---- Phase 2: no auto-tuning means frequent rotation ----
+  //
   options.max_manifest_file_size = 1000000;
   options.max_manifest_space_amp_pct = 0;  // no auto-tuning yet
   DestroyAndReopen(options);
+  cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
+  prev_manifest_num = cur_manifest_num;
 
-  // With the generous (minimum) maximum manifest size, should not be rotated
+  // With the generous minimum manifest size, should not be rotated.
   AddCfFn();
   AddCfFn();
   AddCfFn();
   ASSERT_EQ(prev_manifest_num, cur_manifest_num);
 
-  // Change options for small max and (still) no auto-tuning
+  // Lower the minimum while still disabling auto-tuning.
   ASSERT_OK(db_->SetDBOptions({{"max_manifest_file_size", "3000"}}));
 
   // Takes effect on the next manifest write
-  TrivialManifestWriteFn();
+  BackgroundManifestWriteFn();
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
 
   // Now we have to rewrite the whole manifest on each write because the
@@ -97,28 +148,31 @@ TEST_F(DBEtc3Test, AutoTuneManifestSize) {
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
   AddCfFn();
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
-  TrivialManifestWriteFn();
+  BackgroundManifestWriteFn();
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
 
+  // ---- Phase 3: auto-tuning raises the background threshold ----
+  //
   // Enabling auto-tuning should fix this, immediately for next manifest writes.
-  // This will allow up to double-ish the size of the compacted manifest,
-  // which last should have been 4000 + some bytes.
+  // This will allow up to roughly double the size of the compacted manifest,
+  // which now includes CF entries plus the piggy-backed background writes.
   ASSERT_EQ(handles.size(), 4U);
-  ASSERT_OK(db_->SetDBOptions({{"max_manifest_space_amp_pct", "105"}}));
+  ASSERT_OK(db_->SetDBOptions({{"max_manifest_space_amp_pct", "95"}}));
 
-  // After 9 CF names should be enough to rotate the manifest
-  for (int i = 1; i <= 5; ++i) {
+  // Auto-tuning lets several more CF names accumulate in the MANIFEST before
+  // the piggy-backed background write crosses the threshold.
+  for (int i = 1; i <= 3; ++i) {
     if ((i % 2) == 1) {
       DropCfFn();
     }
     AddCfFn();
     ASSERT_EQ(prev_manifest_num, cur_manifest_num);
   }
-  TrivialManifestWriteFn();
+  AddCfFn();
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
 
-  // We now have a different last compacted manifest size, should be
-  // able to go beyond 9 CFs named in manifest this time.
+  // We now have a different last compacted manifest size, so the next
+  // threshold should be based on the newly compacted MANIFEST.
   ASSERT_EQ(handles.size(), 6U);
 
   DropCfFn();
@@ -128,11 +182,10 @@ TEST_F(DBEtc3Test, AutoTuneManifestSize) {
     AddCfFn();
     ASSERT_EQ(prev_manifest_num, cur_manifest_num);
   }
-  // We've written 10 named CFs to the manifest. We should be able to
-  // dynamically change the auto-tuning still based on the last "compacted"
-  // manifest size of 7000 + some bytes.
+  // We should be able to dynamically change the auto-tuning still based on
+  // the last "compacted" manifest size.
   ASSERT_OK(db_->SetDBOptions({{"max_manifest_space_amp_pct", "51"}}));
-  TrivialManifestWriteFn();
+  BackgroundManifestWriteFn();
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
   // And the "compacted" manifest size has reset again, so should be changed
   // again sooner.
@@ -141,13 +194,179 @@ TEST_F(DBEtc3Test, AutoTuneManifestSize) {
     AddCfFn();
     ASSERT_EQ(prev_manifest_num, cur_manifest_num);
   }
-  // Enough for manifest change
-  AddCfFn();
+
+  // ---- Phase 4: foreground operations use relaxed threshold ----
+  //
+  // The current MANIFEST is now large enough for the next background manifest
+  // write to rotate it, but still small enough for foreground operations to use
+  // their 25% extra headroom. Assert that each foreground operation stays on
+  // the same MANIFEST, then verify the next background write rotates.
+  const std::string external_files_dir = dbname_ + "/external_files";
+  ASSERT_OK(env_->CreateDirIfMissing(external_files_dir));
+  auto WriteExternalSstFile = [&](const std::string& file_name,
+                                  const std::string& key,
+                                  const std::string& value) {
+    const std::string file_path = external_files_dir + "/" + file_name;
+    Status ignored = env_->DeleteFile(file_path);
+    ignored.PermitUncheckedError();
+
+    SstFileWriter sst_file_writer(EnvOptions(), options);
+    ASSERT_OK(sst_file_writer.Open(file_path));
+    ASSERT_OK(sst_file_writer.Put(key, value));
+    ASSERT_OK(sst_file_writer.Finish());
+  };
+  auto IngestExternalFileForegroundManifestWriteFn =
+      [&](std::string* ingested_key) {
+        uint64_t before_manifest_num = cur_manifest_num;
+        const std::string key = "z" + std::to_string(counter++);
+        const std::string value = "v" + std::to_string(counter++);
+        const std::string file_name =
+            "ingest_" + std::to_string(counter++) + ".sst";
+        const std::string file_path = external_files_dir + "/" + file_name;
+        WriteExternalSstFile(file_name, key, value);
+
+        ASSERT_OK(
+            db_->IngestExternalFile({file_path}, IngestExternalFileOptions()));
+        ASSERT_EQ(value, Get(key));
+        *ingested_key = key;
+        Status ignored = env_->DeleteFile(file_path);
+        ignored.PermitUncheckedError();
+        UpdateManifestNumsFrom(before_manifest_num);
+      };
+  auto CreateColumnFamilyWithImportForegroundManifestWriteFn = [&]() {
+    uint64_t before_manifest_num = cur_manifest_num;
+    const std::string cf_name = "import_cf" + std::to_string(counter++);
+    const std::string key = "import" + std::to_string(counter++);
+    const std::string value = "v" + std::to_string(counter++);
+    const std::string file_name =
+        "import_" + std::to_string(counter++) + ".sst";
+    const std::string file_path = external_files_dir + "/" + file_name;
+    WriteExternalSstFile(file_name, key, value);
+
+    LiveFileMetaData file_metadata;
+    file_metadata.name = file_name;
+    file_metadata.db_path = external_files_dir;
+    file_metadata.smallest_seqno = 0;
+    file_metadata.largest_seqno = 0;
+    file_metadata.level = 0;
+    ExportImportFilesMetaData metadata;
+    metadata.files.push_back(file_metadata);
+    metadata.db_comparator_name = options.comparator->Name();
+
+    ColumnFamilyHandle* import_handle = nullptr;
+    ASSERT_OK(db_->CreateColumnFamilyWithImport(options, cf_name,
+                                                ImportColumnFamilyOptions(),
+                                                metadata, &import_handle));
+    ASSERT_NE(import_handle, nullptr);
+    handles.push_back(import_handle);
+
+    std::string result;
+    ASSERT_OK(db_->Get(ReadOptions(), import_handle, key, &result));
+    ASSERT_EQ(value, result);
+    Status ignored = env_->DeleteFile(file_path);
+    ignored.PermitUncheckedError();
+    UpdateManifestNumsFrom(before_manifest_num);
+  };
+  auto DeleteFilesInRangesForegroundManifestWriteFn =
+      [&](const std::string& key) {
+        uint64_t before_manifest_num = cur_manifest_num;
+        const std::string limit = key + "\xff";
+        std::vector<RangeOpt> ranges;
+        ranges.emplace_back(key, limit);
+        ASSERT_OK(DeleteFilesInRanges(db_.get(), db_->DefaultColumnFamily(),
+                                      ranges.data(), ranges.size(),
+                                      /*include_end=*/false));
+
+        std::string result;
+        ASSERT_TRUE(db_->Get(ReadOptions(), key, &result).IsNotFound());
+        UpdateManifestNumsFrom(before_manifest_num);
+      };
+
+  // Column family manipulation.
+  AddCfFn(/*include_background_manifest_write=*/false);
+  ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+
+  // SetOptions should not write to the MANIFEST. If that regresses, the write
+  // should be treated as a background write and rotate here.
+  {
+    ASSERT_OK(db_->SetOptions({{"level0_slowdown_writes_trigger", "101"}}));
+    UpdateManifestNumsFrom(cur_manifest_num);
+  }
+  ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+
+  // External file ingestion.
+  std::string ingested_key;
+  IngestExternalFileForegroundManifestWriteFn(&ingested_key);
+  ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+
+  // Imported column family creation.
+  CreateColumnFamilyWithImportForegroundManifestWriteFn();
+  ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+
+  // Physical file deletion by range.
+  DeleteFilesInRangesForegroundManifestWriteFn(ingested_key);
+  ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+
+  // Background flush.
+  BackgroundManifestWriteFn();
   ASSERT_LT(prev_manifest_num, cur_manifest_num);
 
+  // ---- Phase 5: persisted compacted manifest size survives close/reopen ----
+  // Close with CFs still live. Reopen with reuse_manifest_on_open so the
+  // manifest is NOT rewritten from scratch. The persisted compacted size
+  // should be loaded and used for auto-tuning.
+  // At this point we have 8 CF handles plus default.
+  ASSERT_EQ(handles.size(), 8U);
+
+  // Collect CF names for reopen, then release handles (Close needs this)
+  std::vector<std::string> cf_names = {"default"};
+  for (auto* h : handles) {
+    cf_names.push_back(h->GetName());
+  }
+  for (auto* h : handles) {
+    ASSERT_OK(db_->DestroyColumnFamilyHandle(h));
+  }
+  handles.clear();
+
+  Close();
+  // Use a max_manifest_file_size below the reused manifest size. Auto-tuning
+  // with the persisted compacted size at 200% amp keeps the tuned threshold
+  // high enough. Without persistence, the threshold would be
+  // max(max_manifest_file_size, 0 * anything) = max_manifest_file_size.
+  //
+  // With max_manifest_file_size set to 3000, missing persisted compacted size
+  // would keep tuned = 3000 and the first AddCf would rotate because the
+  // reused manifest is already larger. With persisted compacted size loaded,
+  // the tuned threshold is based on the compacted size, so no rotation until
+  // the manifest grows well beyond the minimum.
+  options.max_manifest_file_size = 3000;
+  options.max_manifest_space_amp_pct = 200;
+  options.reuse_manifest_on_open = true;
+  uint64_t manifest_num_before_reopen = cur_manifest_num;
+  ReopenWithColumnFamilies(cf_names, options);
+  cur_manifest_num = dbfull()->TEST_Current_Manifest_FileNo();
+
+  // With persistence: the manifest file number should NOT have changed
+  // during reopen, because the persisted compacted size keeps the tuned
+  // threshold high enough. Without persistence, last_compacted = 0, so
+  // tuned = max_manifest_file_size = 3000, and the first LogAndApply
+  // during Open rotates the manifest because it is already larger than 3000.
+  ASSERT_EQ(manifest_num_before_reopen, cur_manifest_num);
+
+  // Adding CFs should still not trigger rotation because the tuned threshold
+  // from the persisted compacted size exceeds the current manifest size.
+  for (int i = 1; i <= 4; ++i) {
+    AddCfFn();
+    ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+  }
+  for (int i = 1; i <= 4; ++i) {
+    AddCfFn();
+    ASSERT_EQ(prev_manifest_num, cur_manifest_num);
+  }
+
   // Wrap up
   while (!handles.empty()) {
-    DropCfFn();
+    DropCfFn(/*include_background_manifest_write=*/false);
   }
 }
 

db/db_impl/db_impl.cc

@@ -175,6 +175,7 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
                const bool seq_per_batch, const bool batch_per_txn,
                bool read_only)
     : dbname_(dbname),
+      read_only_(read_only),
       own_info_log_(options.info_log == nullptr),
       initial_db_options_(SanitizeOptions(dbname, options, read_only,
                                           &init_logger_creation_s_)),
@@ -495,6 +496,21 @@ void DBImpl::WaitForAsyncFileOpen() {
   }
 }
 
+void DBImpl::NotifyOnDBShutdownBegin() {
+  mutex_.AssertHeld();
+  if (shutdown_notification_sent_ || immutable_db_options_.listeners.empty()) {
+    return;
+  }
+  shutdown_notification_sent_ = true;
+
+  // release lock while notifying events
+  mutex_.Unlock();
+  for (const auto& listener : immutable_db_options_.listeners) {
+    listener->OnDBShutdownBegin(this);
+  }
+  mutex_.Lock();
+}
+
 // Will lock the mutex_,  will wait for completion if wait is true
 void DBImpl::CancelAllBackgroundWork(bool wait) {
   ROCKS_LOG_INFO(immutable_db_options_.info_log,
@@ -541,6 +557,9 @@ void DBImpl::CancelAllBackgroundWork(bool wait) {
     immutable_db_options_.compaction_service->CancelAwaitingJobs();
   }
 
+  if (!already_shutting_down) {
+    NotifyOnDBShutdownBegin();
+  }
   shutting_down_.store(true, std::memory_order_release);
   bg_cv_.SignalAll();
   if (!wait) {
@@ -653,7 +672,8 @@ void DBImpl::UnregisterBlobDirectWriteColumnFamily() {
 Status DBImpl::MaybeWriteWalMarkersToManifestOnClose() {
   mutex_.AssertHeld();
   if (!mutable_db_options_.optimize_manifest_for_recovery ||
-      !opened_successfully_ || versions_ == nullptr || logs_.empty()) {
+      !opened_successfully_ || read_only_ || versions_ == nullptr ||
+      logs_.empty()) {
     return Status::OK();
   }
 
@@ -789,12 +809,27 @@ Status DBImpl::CloseHelper() {
          bg_flush_scheduled_ || bg_purge_scheduled_ ||
          bg_pressure_callback_in_progress_ ||
          bg_async_file_open_state_ == AsyncFileOpenState::kScheduled ||
+         async_wal_precreate_state_ == AsyncWALPrecreateState::kScheduled ||
          pending_purge_obsolete_files_ ||
          error_handler_.IsRecoveryInProgress()) {
     TEST_SYNC_POINT("DBImpl::~DBImpl:WaitJob");
     bg_cv_.Wait();
   }
 
+  // Release any opened-but-unpublished WAL writer after the in-flight worker
+  // has published its result. Clear the DB-owned async slot while holding
+  // mutex_, but destroy the detached writer after dropping mutex_ because
+  // log::Writer / WritableFileWriter destruction can flush and close the file.
+  // The file itself can be left behind as an empty future WAL; recovery already
+  // tolerates it and marks its file number used if observed.
+  UnpublishedWAL unused_async_wal = std::move(async_wal_precreate_wal_);
+  async_wal_precreate_state_ = AsyncWALPrecreateState::kNotScheduled;
+  if (unused_async_wal.writer) {
+    mutex_.Unlock();
+    unused_async_wal.Reset();
+    mutex_.Lock();
+  }
+
   // Ensure subclasses don't forget to schedule async file opening
   assert(!immutable_db_options_.open_files_async || !opened_successfully_ ||
          bg_async_file_open_state_ != AsyncFileOpenState::kNotScheduled);
@@ -840,7 +875,7 @@ Status DBImpl::CloseHelper() {
   // manifest file), it is not able to identify live files correctly. As a
   // result, all "live" files can get deleted by accident. However, corrupted
   // manifest is recoverable by RepairDB().
-  if (opened_successfully_) {
+  if (opened_successfully_ && !read_only_) {
     JobContext job_context(next_job_id_.fetch_add(1));
     FindObsoleteFiles(&job_context, true);
 
@@ -5820,6 +5855,7 @@ Status DBImpl::DeleteFilesInRanges(ColumnFamilyHandle* column_family,
   }
 
   VersionEdit edit;
+  edit.MarkForegroundOperation();
   std::set<FileMetaData*> deleted_files;
   JobContext job_context(next_job_id_.fetch_add(1), true);
   {
@@ -6930,7 +6966,9 @@ Status DBImpl::IngestExternalFiles(
         assert(!cfd->IsDropped());
         cfds_to_commit.push_back(cfd);
         autovector<VersionEdit*> edit_list;
-        edit_list.push_back(ingestion_jobs[i].edit());
+        auto* edit = ingestion_jobs[i].edit();
+        edit->MarkForegroundOperation();
+        edit_list.push_back(edit);
         edit_lists.push_back(edit_list);
         ++num_entries;
       }
@@ -6945,7 +6983,6 @@ Status DBImpl::IngestExternalFiles(
       }
       status =
           versions_->LogAndApply(cfds_to_commit, read_options, write_options,
-
                                  edit_lists, &mutex_, directories_.GetDbDir());
       // It is safe to update VersionSet last seqno here after LogAndApply since
       // LogAndApply persists last sequence number from VersionEdits,
@@ -7078,6 +7115,7 @@ Status DBImpl::CreateColumnFamilyWithImport(
 
   SuperVersionContext dummy_sv_ctx(/* create_superversion */ true);
   VersionEdit dummy_edit;
+  dummy_edit.MarkForegroundOperation();
   uint64_t next_file_number = 0;
   std::unique_ptr<std::list<uint64_t>::iterator> pending_output_elem;
   {
@@ -7135,9 +7173,10 @@ Status DBImpl::CreateColumnFamilyWithImport(
 
       // Install job edit [Mutex will be unlocked here]
       if (status.ok()) {
-        status = versions_->LogAndApply(cfd, read_options, write_options,
-                                        import_job.edit(), &mutex_,
-                                        directories_.GetDbDir());
+        auto* edit = import_job.edit();
+        edit->MarkForegroundOperation();
+        status = versions_->LogAndApply(cfd, read_options, write_options, edit,
+                                        &mutex_, directories_.GetDbDir());
         if (status.ok()) {
           InstallSuperVersionForConfigChange(cfd, &sv_context);
         }
@@ -7568,6 +7607,7 @@ Status DBImpl::ReserveFileNumbersBeforeIngestion(
   // reuse the file number that has already assigned to the internal file,
   // and this will overwrite the external file. To protect the external
   // file, we have to make sure the file number will never being reused.
+  dummy_edit.MarkForegroundOperation();
   s = versions_->LogAndApply(cfd, read_options, write_options, &dummy_edit,
                              &mutex_, directories_.GetDbDir());
   if (s.ok()) {

db/db_impl/db_impl.h

@@ -15,6 +15,8 @@
 #include <limits>
 #include <list>
 #include <map>
+#include <memory>
+#include <optional>
 #include <set>
 #include <string>
 #include <unordered_map>
@@ -1372,6 +1374,7 @@ class DBImpl : public DB {
 
  protected:
   const std::string dbname_;
+  const bool read_only_;
   // TODO(peterd): unify with VersionSet::db_id_
   std::string db_id_;
   // db_session_id_ is an identifier that gets reset
@@ -1453,6 +1456,13 @@ class DBImpl : public DB {
   std::atomic<int> next_job_id_ = 1;
 
   std::atomic<bool> shutting_down_ = false;
+  // Protected by mutex_. This is separate from shutting_down_ because
+  // OnDBShutdownBegin must fire before shutting_down_ is published, and the
+  // notification releases mutex_ while invoking listeners. Marking that the
+  // notification has started prevents a concurrent or reentrant
+  // CancelAllBackgroundWork() call from firing it again during that unlocked
+  // callback window.
+  bool shutdown_notification_sent_ = false;
 
   // No new background jobs can be queued if true. This is used to prevent new
   // background jobs from being queued after WaitForCompact() completes waiting
@@ -1527,6 +1537,16 @@ class DBImpl : public DB {
                                    const Status& st,
                                    const CompactionJobStats& job_stats,
                                    int job_id);
+  // Fires the OnCompactionPreCommit listener callback. Mirrors
+  // NotifyOnCompactionCompleted but is invoked before ReleaseCompactionFiles()
+  // (i.e. while input files still have being_compacted == true). Idempotent:
+  // safe to call from multiple potential release sites; only fires once per
+  // compaction, and only if NotifyOnCompactionBegin previously fired.
+  void NotifyOnCompactionPreCommit(ColumnFamilyData* cfd, Compaction* c,
+                                   const Status& st,
+                                   const CompactionJobStats& job_stats,
+                                   int job_id);
+  void NotifyOnDBShutdownBegin();
   void NotifyOnMemTableSealed(ColumnFamilyData* cfd,
                               const MemTableInfo& mem_table_info);
 
@@ -2574,10 +2594,15 @@ class DBImpl : public DB {
   // Helper function to perform trivial move by updating manifest metadata
   // without rewriting data files. This is called when IsTrivialMove() is true.
   // REQUIRES: mutex held
-  // Returns: Status of the trivial move operation
-  Status PerformTrivialMove(Compaction& c, LogBuffer* log_buffer,
-                            bool& compaction_released, size_t& moved_files,
-                            size_t& moved_bytes);
+  // Populates the Compaction's edit with DeleteFile/AddFile entries for
+  // a trivial move (no data rewriting). Does not commit the edit.
+  void PrepareTrivialMoveEdit(Compaction& c, LogBuffer* log_buffer,
+                              size_t& moved_files, size_t& moved_bytes);
+
+  // REQUIRES: mutex held, PrepareTrivialMoveEdit already called
+  // Commits the trivial move by calling LogAndApply on the prepared edit.
+  // Returns: Status of the manifest write
+  Status CommitTrivialMove(Compaction& c, bool& compaction_released);
 
   // REQUIRES: mutex unlocked
   void TrackOrUntrackFiles(const std::vector<std::string>& existing_data_files,
@@ -2810,7 +2835,68 @@ class DBImpl : public DB {
   size_t GetWalPreallocateBlockSize(uint64_t write_buffer_size) const;
   Env::WriteLifeTimeHint CalculateWALWriteHint() { return Env::WLTH_SHORT; }
 
-  IOStatus CreateWAL(const WriteOptions& write_options, uint64_t log_file_num,
+  // Returns true when async WAL precreation is enabled and compatible with the
+  // active WAL strategy. WAL recycling already avoids file creation latency, so
+  // precreation is disabled when recycle_log_file_num is non-zero.
+  bool AsyncWALPrecreateEnabled() const;
+
+  // A WAL file that has a reserved file number and may have an opened writer,
+  // but has not been added to DBImpl's in-memory logical WAL tracking lists
+  // (logs_ and alive_wal_files_).
+  struct UnpublishedWAL {
+    uint64_t log_number = 0;
+    std::unique_ptr<log::Writer> writer;
+
+    UnpublishedWAL() = default;
+    UnpublishedWAL(const UnpublishedWAL&) = delete;
+    UnpublishedWAL& operator=(const UnpublishedWAL&) = delete;
+
+    UnpublishedWAL(UnpublishedWAL&& other) noexcept {
+      *this = std::move(other);
+    }
+    UnpublishedWAL& operator=(UnpublishedWAL&& other) noexcept {
+      if (this != &other) {
+        log_number = other.log_number;
+        writer = std::move(other.writer);
+        other.Reset();
+      }
+      return *this;
+    }
+
+    void Reset() {
+      log_number = 0;
+      writer.reset();
+    }
+  };
+
+  // Reserves the next WAL file number and schedules a HIGH-priority background
+  // task to precreate that WAL file. A precreated WAL is not a logical WAL
+  // until a foreground WAL rotation consumes it.
+  void MaybeScheduleAsyncWALPrecreate(size_t preallocate_block_size);
+
+  // Background task for opening the reserved future WAL and publishing the
+  // result under mutex_.
+  static void BGWorkAsyncWALPrecreate(void* arg);
+
+  // Waits for an in-flight async WAL precreation and returns a prepared WAL if
+  // one is available. If precreation failed, returns an empty WAL and lets the
+  // foreground rotation create the WAL synchronously. Caller must hold mutex_.
+  UnpublishedWAL WaitForAsyncWALPrecreate();
+
+  // Opens and preallocates a WAL writer without writing logical WAL records.
+  // Used by async WAL precreation and by synchronous WAL creation.
+  IOStatus CreateWALWriter(const DBOptions& db_options, uint64_t log_file_num,
+                           uint64_t recycle_log_number,
+                           size_t preallocate_block_size,
+                           UnpublishedWAL* new_wal);
+
+  // Starts an opened WAL file by writing the initial records required before it
+  // can be installed as the current WAL for foreground writes.
+  IOStatus StartWALFile(const WriteOptions& write_options,
+                        const PredecessorWALInfo& predecessor_wal_info,
+                        log::Writer* new_log);
+  IOStatus CreateWAL(const DBOptions& db_options,
+                     const WriteOptions& write_options, uint64_t log_file_num,
                      uint64_t recycle_log_number, size_t preallocate_block_size,
                      const PredecessorWALInfo& predecessor_wal_info,
                      log::Writer** new_log);
@@ -3306,6 +3392,28 @@ class DBImpl : public DB {
   AsyncFileOpenState bg_async_file_open_state_ =
       AsyncFileOpenState::kNotScheduled;
 
+  // State machine for the single async WAL precreation slot protected by
+  // mutex_. Background precreation failure returns to kNotScheduled; foreground
+  // rotation handles it the same as no prepared WAL and creates one
+  // synchronously. kScheduled owns a reserved file number; kReady owns an
+  // opened writer that has not been started or added to logical WAL tracking.
+  enum class AsyncWALPrecreateState : uint8_t {
+    kNotScheduled = 0,  // No WAL precreate work is in-flight or ready.
+    kScheduled,         // Background task owns creation of the reserved WAL.
+    kReady,             // Reserved WAL writer is open but not logically live.
+  };
+
+  // Protected by mutex_. Tracks at most one background precreated WAL. A
+  // precreated WAL is only reserved empty storage until SwitchMemtable()
+  // consumes it and installs it in DBImpl's in-memory logical WAL tracking
+  // lists (logs_ and alive_wal_files_).
+  AsyncWALPrecreateState async_wal_precreate_state_ =
+      AsyncWALPrecreateState::kNotScheduled;
+
+  // Reserved in-flight/ready precreated WAL. The writer is populated only while
+  // state is kReady.
+  UnpublishedWAL async_wal_precreate_wal_;
+
   std::deque<ManualCompactionState*> manual_compaction_dequeue_;
 
   // shall we disable deletion of obsolete files

db/db_impl/db_impl_compaction_flush.cc

@@ -1581,9 +1581,8 @@ Status DBImpl::CompactFiles(const CompactionOptions& compact_options,
   return s;
 }
 
-Status DBImpl::PerformTrivialMove(Compaction& c, LogBuffer* log_buffer,
-                                  bool& compaction_released,
-                                  size_t& moved_files, size_t& moved_bytes) {
+void DBImpl::PrepareTrivialMoveEdit(Compaction& c, LogBuffer* log_buffer,
+                                    size_t& moved_files, size_t& moved_bytes) {
   mutex_.AssertHeld();
 
   ROCKS_LOG_BUFFER(log_buffer, "[%s] Moving %d files to level-%d\n",
@@ -1616,6 +1615,10 @@ Status DBImpl::PerformTrivialMove(Compaction& c, LogBuffer* log_buffer,
     }
     moved_files += c.num_input_files(l);
   }
+}
+
+Status DBImpl::CommitTrivialMove(Compaction& c, bool& compaction_released) {
+  mutex_.AssertHeld();
 
   // Install the new version
   const ReadOptions read_options(Env::IOActivity::kCompaction);
@@ -1740,8 +1743,8 @@ Status DBImpl::CompactFilesImpl(
     bool compaction_released = false;
     size_t moved_files = 0;
     size_t moved_bytes = 0;
-    Status status = PerformTrivialMove(
-        *c.get(), log_buffer, compaction_released, moved_files, moved_bytes);
+    PrepareTrivialMoveEdit(*c.get(), log_buffer, moved_files, moved_bytes);
+    Status status = CommitTrivialMove(*c.get(), compaction_released);
 
     if (status.ok()) {
       InstallSuperVersionAndScheduleWork(
@@ -2009,6 +2012,46 @@ void DBImpl::NotifyOnCompactionCompleted(
   // flush process.
 }
 
+void DBImpl::NotifyOnCompactionPreCommit(
+    ColumnFamilyData* cfd, Compaction* c, const Status& st,
+    const CompactionJobStats& compaction_job_stats, const int job_id) {
+  if (immutable_db_options_.listeners.size() == 0U) {
+    return;
+  }
+  mutex_.AssertHeld();
+  if (shutting_down_.load(std::memory_order_acquire)) {
+    return;
+  }
+
+  // Only fire if OnCompactionBegin has fired for this compaction.
+  if (c->ShouldNotifyOnCompactionCompleted() == false) {
+    return;
+  }
+  // Idempotency: ensure listeners observe at most one
+  // OnCompactionPreCommit per compaction lifecycle, even though the
+  // notify helper is invoked at multiple potential ReleaseCompactionFiles()
+  // sites for safety.
+  if (c->WasNotifyOnCompactionPreCommitCalled()) {
+    return;
+  }
+  c->SetNotifyOnCompactionPreCommitCalled();
+
+  int num_l0_files = cfd->current()->storage_info()->NumLevelFiles(0);
+  // release lock while notifying events
+  mutex_.Unlock();
+  TEST_SYNC_POINT("DBImpl::NotifyOnCompactionPreCommit::UnlockMutex");
+  {
+    CompactionJobInfo info{};
+    info.num_l0_files = num_l0_files;
+    BuildCompactionJobInfo(cfd, c, st, compaction_job_stats, job_id, &info);
+    for (const auto& listener : immutable_db_options_.listeners) {
+      listener->OnCompactionPreCommit(this, info);
+    }
+    info.status.PermitUncheckedError();
+  }
+  mutex_.Lock();
+}
+
 // REQUIREMENT: block all background work by calling PauseBackgroundWork()
 // before calling this function
 // TODO (hx235): Replace Status::NotSupported() with Status::Aborted() for
@@ -3180,7 +3223,7 @@ void DBImpl::ResumeAllCompactions() {
 void DBImpl::MaybeScheduleFlushOrCompaction() {
   mutex_.AssertHeld();
   TEST_SYNC_POINT("DBImpl::MaybeScheduleFlushOrCompaction:Start");
-  if (!opened_successfully_) {
+  if (!opened_successfully_ || read_only_) {
     // Compaction may introduce data race to DB open
     return;
   }
@@ -4024,6 +4067,13 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       status = Status::ShutdownInProgress();
     } else if (compaction_aborted_.load(std::memory_order_acquire) > 0) {
       status = Status::Incomplete(Status::SubCode::kCompactionAborted);
+      if (!is_prepicked) {
+        // This automatic compaction was scheduled from compaction_queue_, but
+        // abort happened before PickCompactionFromQueue() could remove the
+        // queued CF. Restore the unscheduled count so ResumeAllCompactions()
+        // can schedule the still-queued work.
+        unscheduled_compactions_++;
+      }
     } else if (is_manual &&
                manual_compaction->canceled.load(std::memory_order_acquire)) {
       status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
@@ -4031,10 +4081,14 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
   } else {
     status = error_handler_.GetBGError();
     // If we get here, it means a hard error happened after this compaction
-    // was scheduled by MaybeScheduleFlushOrCompaction(), but before it got
-    // a chance to execute. Since we didn't pop a cfd from the compaction
-    // queue, increment unscheduled_compactions_
-    unscheduled_compactions_++;
+    // was scheduled by MaybeScheduleFlushOrCompaction(), but before it got a
+    // chance to execute. Since non-prepicked work consumed an unscheduled
+    // compaction credit without popping a cfd from the compaction queue,
+    // restore the credit here. Prepicked work was scheduled directly and did
+    // not consume unscheduled_compactions_.
+    if (!is_prepicked) {
+      unscheduled_compactions_++;
+    }
   }
 
   if (!status.ok()) {
@@ -4255,6 +4309,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     for (const auto& f : *c->inputs(0)) {
       c->edit()->DeleteFile(c->level(), f->fd.GetNumber());
     }
+    NotifyOnCompactionPreCommit(c->column_family_data(), c.get(), status,
+                                compaction_job_stats, job_context->job_id);
     status = versions_->LogAndApply(
         c->column_family_data(), read_options, write_options, c->edit(),
         &mutex_, directories_.GetDbDir(),
@@ -4473,6 +4529,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
         ++out_file_metadata_it;
       }
 
+      NotifyOnCompactionPreCommit(c->column_family_data(), c.get(), status,
+                                  compaction_job_stats, job_context->job_id);
       status = versions_->LogAndApply(
           c->column_family_data(), read_options, write_options, c->edit(),
           &mutex_, directories_.GetDbDir(),
@@ -4549,8 +4607,12 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     // Perform the trivial move
     size_t moved_files = 0;
     size_t moved_bytes = 0;
-    status = PerformTrivialMove(*c.get(), log_buffer, compaction_released,
-                                moved_files, moved_bytes);
+    // Populate the edit first so that CompactionJobInfo has output file
+    // info when OnCompactionPreCommit fires.
+    PrepareTrivialMoveEdit(*c.get(), log_buffer, moved_files, moved_bytes);
+    NotifyOnCompactionPreCommit(c->column_family_data(), c.get(), status,
+                                compaction_job_stats, job_context->job_id);
+    status = CommitTrivialMove(*c.get(), compaction_released);
     io_s = versions_->io_status();
     InstallSuperVersionAndScheduleWork(
         c->column_family_data(), job_context->superversion_contexts.data());
@@ -4673,6 +4735,10 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       ReleaseOptionsFileNumber(min_options_file_number_elem);
     }
 
+    // Fire OnCompactionPreCommit before compaction_job.Install runs
+    // ReleaseCompactionFiles in its manifest write callback.
+    NotifyOnCompactionPreCommit(c->column_family_data(), c.get(), status,
+                                compaction_job_stats, job_context->job_id);
     status = compaction_job.Install(&compaction_released);
     io_s = compaction_job.io_status();
     if (status.ok()) {
@@ -4692,6 +4758,14 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
 
   if (c != nullptr) {
     if (!compaction_released) {
+      // Safety net: if any of the paths above did not fire the
+      // OnCompactionPreCommit notification (e.g. status was not OK and
+      // an early-out skipped the LogAndApply / Install), still fire the
+      // notify here while files are about to be released. The notify is
+      // idempotent and is a no-op if it has already fired (or if Begin never
+      // fired).
+      NotifyOnCompactionPreCommit(c->column_family_data(), c.get(), status,
+                                  compaction_job_stats, job_context->job_id);
       c->ReleaseCompactionFiles(status);
     } else {
 #ifndef NDEBUG

db/db_impl/db_impl_open.cc

@@ -21,6 +21,7 @@
 #include "file/writable_file_writer.h"
 #include "logging/logging.h"
 #include "monitoring/persistent_stats_history.h"
+#include "monitoring/statistics_impl.h"
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
 #include "rocksdb/options.h"
@@ -122,6 +123,16 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src,
     result.recycle_log_file_num = 0;
   }
 
+  if (result.async_wal_precreate && result.recycle_log_file_num != 0) {
+    // Async WAL precreation reserves a future log number, while WAL recycling
+    // chooses from old WAL files. Keep the recycling behavior and disable only
+    // the async optimization.
+    result.async_wal_precreate = false;
+    ROCKS_LOG_WARN(result.info_log,
+                   "async_wal_precreate is disabled since "
+                   "recycle_log_file_num is non-zero");
+  }
+
   if (result.db_paths.size() == 0) {
     result.db_paths.emplace_back(dbname, std::numeric_limits<uint64_t>::max());
   } else if (result.wal_dir.empty()) {
@@ -799,9 +810,19 @@ Status DBImpl::Recover(
 
     if (!wal_files.empty()) {
       if (error_if_wal_file_exists) {
-        return Status::Corruption(
-            "The db was opened in readonly mode with error_if_wal_file_exists"
-            "flag but a WAL file already exists");
+        for (const auto& wal_file : wal_files) {
+          uint64_t bytes;
+          s = env_->GetFileSize(wal_file.second, &bytes);
+          if (!s.ok()) {
+            return s;
+          }
+          if (bytes > 0) {
+            return Status::Corruption(
+                "The db was opened in readonly mode with "
+                "error_if_wal_file_exists flag but a non-empty WAL file "
+                "already exists");
+          }
+        }
       } else if (error_if_data_exists_in_wals) {
         for (auto& wal_file : wal_files) {
           uint64_t bytes;
@@ -2213,6 +2234,16 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
 
   constexpr int level = 0;
 
+  if (s.ok() && has_output) {
+    // Before publishing any recovery edit, make the new SST's directory entry
+    // durable. Reused MANIFESTs have no CURRENT update, and fresh MANIFEST
+    // publication should not be relied on to order the recovered SST entry.
+    s = GetDataDir(cfd, meta.fd.GetPathId())
+            ->FsyncWithDirOptions(
+                IOOptions(), nullptr,
+                DirFsyncOptions(DirFsyncOptions::FsyncReason::kNewFileSynced));
+  }
+
   if (s.ok() && has_output) {
     edit->AddFile(level, meta.fd.GetNumber(), meta.fd.GetPathId(),
                   meta.fd.GetFileSize(), meta.smallest, meta.largest,
@@ -2377,16 +2408,17 @@ Status DB::OpenAndTrimHistory(
   return s;
 }
 
-IOStatus DBImpl::CreateWAL(const WriteOptions& write_options,
-                           uint64_t log_file_num, uint64_t recycle_log_number,
-                           size_t preallocate_block_size,
-                           const PredecessorWALInfo& predecessor_wal_info,
-                           log::Writer** new_log) {
+IOStatus DBImpl::CreateWALWriter(const DBOptions& db_options,
+                                 uint64_t log_file_num,
+                                 uint64_t recycle_log_number,
+                                 size_t preallocate_block_size,
+                                 UnpublishedWAL* new_wal) {
+  assert(new_wal);
+  assert(new_wal->log_number == 0);
+  assert(new_wal->writer == nullptr);
   IOStatus io_s;
   std::unique_ptr<FSWritableFile> lfile;
 
-  DBOptions db_options =
-      BuildDBOptions(immutable_db_options_, mutable_db_options_);
   FileOptions opt_file_options =
       fs_->OptimizeForLogWrite(file_options_, db_options);
   opt_file_options.write_hint = CalculateWALWriteHint();
@@ -2424,21 +2456,162 @@ IOStatus DBImpl::CreateWAL(const WriteOptions& write_options,
         Histograms::HISTOGRAM_ENUM_MAX /* hist_type */, listeners, nullptr,
         tmp_set.Contains(FileType::kWalFile),
         tmp_set.Contains(FileType::kWalFile)));
-    *new_log = new log::Writer(std::move(file_writer), log_file_num,
-                               immutable_db_options_.recycle_log_file_num > 0,
-                               immutable_db_options_.manual_wal_flush,
-                               immutable_db_options_.wal_compression,
-                               immutable_db_options_.track_and_verify_wals);
-    io_s = (*new_log)->AddCompressionTypeRecord(write_options);
-    if (io_s.ok()) {
-      io_s = (*new_log)->MaybeAddPredecessorWALInfo(write_options,
-                                                    predecessor_wal_info);
-    }
+    new_wal->log_number = log_file_num;
+    new_wal->writer = std::make_unique<log::Writer>(
+        std::move(file_writer), log_file_num,
+        immutable_db_options_.recycle_log_file_num > 0,
+        immutable_db_options_.manual_wal_flush,
+        immutable_db_options_.wal_compression,
+        immutable_db_options_.track_and_verify_wals);
   }
 
   return io_s;
 }
 
+IOStatus DBImpl::StartWALFile(const WriteOptions& write_options,
+                              const PredecessorWALInfo& predecessor_wal_info,
+                              log::Writer* new_log) {
+  assert(new_log);
+  IOStatus io_s = new_log->AddCompressionTypeRecord(write_options);
+  TEST_SYNC_POINT_CALLBACK("DBImpl::StartWALFile:AfterCompressionTypeRecord",
+                           &io_s);
+  if (io_s.ok()) {
+    io_s = new_log->MaybeAddPredecessorWALInfo(write_options,
+                                               predecessor_wal_info);
+  }
+  return io_s;
+}
+
+IOStatus DBImpl::CreateWAL(const DBOptions& db_options,
+                           const WriteOptions& write_options,
+                           uint64_t log_file_num, uint64_t recycle_log_number,
+                           size_t preallocate_block_size,
+                           const PredecessorWALInfo& predecessor_wal_info,
+                           log::Writer** new_log) {
+  assert(new_log);
+  assert(*new_log == nullptr);
+  UnpublishedWAL wal;
+  IOStatus io_s = CreateWALWriter(db_options, log_file_num, recycle_log_number,
+                                  preallocate_block_size, &wal);
+  if (io_s.ok()) {
+    io_s = StartWALFile(write_options, predecessor_wal_info, wal.writer.get());
+  }
+  if (io_s.ok()) {
+    *new_log = wal.writer.release();
+  }
+  return io_s;
+}
+
+bool DBImpl::AsyncWALPrecreateEnabled() const {
+  return immutable_db_options_.async_wal_precreate &&
+         immutable_db_options_.recycle_log_file_num == 0;
+}
+
+struct AsyncWALPrecreateContext {
+  DBImpl* db = nullptr;
+  DBOptions db_options;
+  uint64_t log_number = 0;
+  size_t preallocate_block_size = 0;
+};
+
+void DBImpl::MaybeScheduleAsyncWALPrecreate(size_t preallocate_block_size) {
+  mutex_.AssertHeld();
+
+  if (!AsyncWALPrecreateEnabled() ||
+      shutting_down_.load(std::memory_order_acquire) ||
+      error_handler_.IsBGWorkStopped() ||
+      async_wal_precreate_state_ != AsyncWALPrecreateState::kNotScheduled) {
+    return;
+  }
+
+  async_wal_precreate_wal_.Reset();
+  async_wal_precreate_wal_.log_number = versions_->NewFileNumber();
+  async_wal_precreate_state_ = AsyncWALPrecreateState::kScheduled;
+
+  auto* ctx = new AsyncWALPrecreateContext();
+  ctx->db = this;
+  ctx->db_options = BuildDBOptions(immutable_db_options_, mutable_db_options_);
+  ctx->log_number = async_wal_precreate_wal_.log_number;
+  ctx->preallocate_block_size = preallocate_block_size;
+  env_->Schedule(&DBImpl::BGWorkAsyncWALPrecreate, ctx, Env::Priority::HIGH,
+                 nullptr);
+}
+
+DBImpl::UnpublishedWAL DBImpl::WaitForAsyncWALPrecreate() {
+  mutex_.AssertHeld();
+  UnpublishedWAL result;
+
+  if (!AsyncWALPrecreateEnabled()) {
+    return result;
+  }
+
+  TEST_SYNC_POINT("DBImpl::WaitForAsyncWALPrecreate:Begin");
+  bool waited = false;
+  uint64_t wait_start_micros = 0;
+  while (async_wal_precreate_state_ == AsyncWALPrecreateState::kScheduled) {
+    TEST_SYNC_POINT("DBImpl::WaitForAsyncWALPrecreate:BeforeWait");
+    if (!waited) {
+      waited = true;
+      wait_start_micros = immutable_db_options_.clock->NowMicros();
+      RecordTick(stats_, WAL_PRECREATE_WAITED);
+    }
+    bg_cv_.Wait();
+  }
+  if (waited) {
+    RecordTick(stats_, WAL_PRECREATE_WAIT_MICROS,
+               immutable_db_options_.clock->NowMicros() - wait_start_micros);
+  }
+
+  if (async_wal_precreate_state_ == AsyncWALPrecreateState::kReady) {
+    result = std::move(async_wal_precreate_wal_);
+    async_wal_precreate_state_ = AsyncWALPrecreateState::kNotScheduled;
+    RecordTick(stats_, WAL_PRECREATE_HIT);
+    return result;
+  }
+
+  assert(async_wal_precreate_state_ == AsyncWALPrecreateState::kNotScheduled);
+  RecordTick(stats_, WAL_PRECREATE_MISS);
+  return result;
+}
+
+void DBImpl::BGWorkAsyncWALPrecreate(void* arg) {
+  TEST_SYNC_POINT("DBImpl::BGWorkAsyncWALPrecreate:Start");
+  std::unique_ptr<AsyncWALPrecreateContext> ctx(
+      static_cast<AsyncWALPrecreateContext*>(arg));
+  DBImpl* db = ctx->db;
+
+  UnpublishedWAL new_wal;
+  IOStatus io_s = db->CreateWALWriter(ctx->db_options, ctx->log_number,
+                                      0 /* recycle_log_number */,
+                                      ctx->preallocate_block_size, &new_wal);
+  if (!io_s.ok()) {
+    RecordTick(db->stats_, WAL_PRECREATE_FAILED);
+    ROCKS_LOG_WARN(db->immutable_db_options_.info_log,
+                   "Async WAL precreate failed for #%" PRIu64 ": %s",
+                   ctx->log_number, io_s.ToString().c_str());
+  }
+
+  TEST_SYNC_POINT("DBImpl::BGWorkAsyncWALPrecreate:BeforePublish");
+  TEST_SYNC_POINT("DBImpl::BGWorkAsyncWALPrecreate:Publish");
+  {
+    InstrumentedMutexLock l(&db->mutex_);
+    if (db->async_wal_precreate_state_ == AsyncWALPrecreateState::kScheduled &&
+        db->async_wal_precreate_wal_.log_number == ctx->log_number) {
+      if (io_s.ok()) {
+        db->async_wal_precreate_wal_ = std::move(new_wal);
+        db->async_wal_precreate_state_ = AsyncWALPrecreateState::kReady;
+      } else {
+        // Async WAL precreation is best-effort. Clear the slot so foreground
+        // rotation falls back to normal synchronous WAL creation.
+        db->async_wal_precreate_wal_.Reset();
+        db->async_wal_precreate_state_ = AsyncWALPrecreateState::kNotScheduled;
+      }
+    }
+    db->bg_cv_.SignalAll();
+  }
+  TEST_SYNC_POINT("DBImpl::BGWorkAsyncWALPrecreate:Done");
+}
+
 void DBImpl::TrackExistingDataFiles(
     const std::vector<std::string>& existing_data_files) {
   TrackOrUntrackFiles(existing_data_files, /*track=*/true);
@@ -2534,8 +2707,10 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
     // created during DB open with predecessor WALs from previous DB session due
     // to `avoid_flush_during_recovery == true`. This can protect the last WAL
     // recovered.
-    s = impl->CreateWAL(write_options, new_log_number, 0 /*recycle_log_number*/,
-                        preallocate_block_size,
+    const DBOptions db_options_snapshot =
+        BuildDBOptions(impl->immutable_db_options_, impl->mutable_db_options_);
+    s = impl->CreateWAL(db_options_snapshot, write_options, new_log_number,
+                        0 /*recycle_log_number*/, preallocate_block_size,
                         PredecessorWALInfo() /* predecessor_wal_info */,
                         &new_log);
     if (s.ok()) {
@@ -2740,6 +2915,8 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
     if (impl->immutable_db_options_.open_files_async) {
       impl->ScheduleAsyncFileOpening();
     }
+    impl->MaybeScheduleAsyncWALPrecreate(
+        impl->GetWalPreallocateBlockSize(max_write_buffer_size));
     impl->mutex_.Unlock();
   }
 

db/db_impl/db_impl_secondary.cc

@@ -105,10 +105,22 @@ Status DBImplSecondary::FindNewLogNumbers(std::vector<uint64_t>* logs) {
     return s;
   }
 
-  // if log_readers_ is non-empty, it means we have applied all logs with log
-  // numbers smaller than the smallest log in log_readers_, so there is no
-  // need to pass these logs to RecoverLogFiles
-  uint64_t log_number_min = 0;
+  // Drop readers only after MANIFEST replay says the WAL is obsolete. The
+  // primary can create a higher-number empty WAL before it stops appending to a
+  // lower-number current WAL, so seeing a higher-number WAL is not sufficient.
+  const uint64_t min_log_number_to_keep = versions_->min_log_number_to_keep();
+  for (auto iter = log_readers_.begin(); iter != log_readers_.end();) {
+    if (iter->first < min_log_number_to_keep) {
+      iter = log_readers_.erase(iter);
+    } else {
+      break;
+    }
+  }
+
+  // If log_readers_ is non-empty, it means we have applied all logs with log
+  // numbers smaller than the smallest retained log reader. Otherwise, manifest
+  // recovery tells us which older logs can be skipped.
+  uint64_t log_number_min = min_log_number_to_keep;
   if (!log_readers_.empty()) {
     log_number_min = log_readers_.begin()->first;
   }
@@ -321,12 +333,6 @@ Status DBImplSecondary::RecoverLogFiles(
       return status;
     }
   }
-  // remove logreaders from map after successfully recovering the WAL
-  if (log_readers_.size() > 1) {
-    auto erase_iter = log_readers_.begin();
-    std::advance(erase_iter, log_readers_.size() - 1);
-    log_readers_.erase(log_readers_.begin(), erase_iter);
-  }
   return status;
 }
 

db/db_impl/db_impl_write.cc

@@ -16,6 +16,7 @@
 #include "db/error_handler.h"
 #include "db/event_helpers.h"
 #include "db/wide/wide_columns_helper.h"
+#include "file/filename.h"
 #include "logging/logging.h"
 #include "memtable/wbwi_memtable.h"
 #include "monitoring/perf_context_imp.h"
@@ -3107,6 +3108,7 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
   const WriteOptions write_options;
 
   log::Writer* new_log = nullptr;
+  UnpublishedWAL prepared_wal;
   MemTable* new_mem = nullptr;
   IOStatus io_s;
 
@@ -3134,8 +3136,16 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
       !wal_recycle_files_.empty() && IsFileDeletionsEnabled()) {
     recycle_log_number = wal_recycle_files_.front();
   }
-  uint64_t new_log_number =
-      creating_new_log ? versions_->NewFileNumber() : cur_wal_number_;
+  uint64_t new_log_number = cur_wal_number_;
+  if (creating_new_log) {
+    prepared_wal = WaitForAsyncWALPrecreate();
+    if (prepared_wal.writer) {
+      new_log_number = prepared_wal.log_number;
+    } else {
+      assert(prepared_wal.log_number == 0);
+      new_log_number = versions_->NewFileNumber();
+    }
+  }
   // For use outside of holding DB mutex
   const MutableCFOptions mutable_cf_options_copy =
       cfd->GetLatestMutableCFOptions();
@@ -3156,6 +3166,8 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
   // Log this later after lock release. It may be outdated, e.g., if background
   // flush happens before logging, but that should be ok.
   int num_imm_unflushed = cfd->imm()->NumNotFlushed();
+  const DBOptions db_options_snapshot =
+      BuildDBOptions(immutable_db_options_, mutable_db_options_);
   const auto preallocate_block_size =
       GetWalPreallocateBlockSize(mutable_cf_options_copy.write_buffer_size);
   mutex_.Unlock();
@@ -3171,13 +3183,35 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
     wal_write_mutex_.Unlock();
     // TODO: Write buffer size passed in should be max of all CF's instead
     // of mutable_cf_options.write_buffer_size.
-    io_s = CreateWAL(write_options, new_log_number, recycle_log_number,
-                     preallocate_block_size, info, &new_log);
+    if (prepared_wal.writer) {
+      io_s = StartWALFile(write_options, info, prepared_wal.writer.get());
+      if (io_s.ok()) {
+        new_log = prepared_wal.writer.release();
+      }
+    } else {
+      io_s =
+          CreateWAL(db_options_snapshot, write_options, new_log_number,
+                    recycle_log_number, preallocate_block_size, info, &new_log);
+    }
     TEST_SYNC_POINT_CALLBACK("DBImpl::SwitchMemtable:AfterCreateWAL", &io_s);
     if (s.ok()) {
       s = io_s;
     }
   }
+  if (!s.ok() && prepared_wal.writer) {
+    const uint64_t prepared_wal_number = prepared_wal.log_number;
+    const std::string prepared_wal_fname =
+        LogFileName(immutable_db_options_.GetWalDir(), prepared_wal_number);
+    prepared_wal.Reset();
+    Status delete_s = env_->DeleteFile(prepared_wal_fname);
+    if (!delete_s.ok() && !delete_s.IsNotFound()) {
+      ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                     "Failed to delete unstarted async precreated WAL #%" PRIu64
+                     ": %s",
+                     prepared_wal_number, delete_s.ToString().c_str());
+    }
+    delete_s.PermitUncheckedError();
+  }
   if (s.ok()) {
     // FIXME: from the comment for GetEarliestSequenceNumber(), any key with
     //  seqno >= earliest_seqno should be in this or later memtable. This means
@@ -3359,6 +3393,7 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
   new_mem->Ref();
   cfd->SetMemtable(new_mem);
   InstallSuperVersionAndScheduleWork(cfd, &context->superversion_context);
+  MaybeScheduleAsyncWALPrecreate(preallocate_block_size);
 
   // Notify client that memtable is sealed, now that we have successfully
   // installed a new memtable

db/db_iter.cc

@@ -1480,7 +1480,9 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
     if (timestamp_lb_ != nullptr) {
       saved_key_.SetInternalKey(ikey);
     } else {
-      saved_key_.SetUserKey(ikey.user_key);
+      saved_key_.SetUserKey(
+          ikey.user_key,
+          !pin_thru_lifetime_ || !iter_.iter()->IsKeyPinned() /* copy */);
     }
 
     valid_ = true;

db/db_iter_test.cc

@@ -216,12 +216,19 @@ class TestIterator : public InternalIterator {
   bool IsKeyPinned() const override { return true; }
   bool IsValuePinned() const override { return true; }
 
+  void Prepare(const MultiScanArgs* /*scan_opts*/) override {
+    ++prepare_call_count_;
+  }
+
+  size_t prepare_call_count() const { return prepare_call_count_; }
+
  private:
   bool initialized_;
   bool valid_;
   size_t sequence_number_;
   size_t iter_;
   size_t steps_ = 0;
+  size_t prepare_call_count_ = 0;
 
   InternalKeyComparator cmp;
   std::vector<std::pair<std::string, std::string>> data_;
@@ -243,6 +250,53 @@ class DBIteratorTest : public testing::Test {
   DBIteratorTest() : env_(Env::Default()) {}
 };
 
+TEST_F(DBIteratorTest, PrepareForwardsValidatedScanRanges) {
+  Options options;
+  ImmutableOptions ioptions = ImmutableOptions(options);
+  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
+  TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+  internal_iter->AddPut("a", "val_a");
+  internal_iter->AddPut("b", "val_b");
+  internal_iter->Finish();
+
+  ReadOptions ro;
+  std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
+      env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
+      internal_iter, nullptr /* version */, 10 /* sequence */,
+      nullptr /* read_callback */, /*active_mem=*/nullptr));
+
+  MultiScanArgs scan_opts(BytewiseComparator());
+  scan_opts.insert("a", "c");
+
+  db_iter->Prepare(scan_opts);
+  ASSERT_OK(db_iter->status());
+  EXPECT_EQ(internal_iter->prepare_call_count(), 1);
+}
+
+TEST_F(DBIteratorTest, PrepareDoesNotForwardInvalidScanRanges) {
+  Options options;
+  ImmutableOptions ioptions = ImmutableOptions(options);
+  MutableCFOptions mutable_cf_options = MutableCFOptions(options);
+  TestIterator* internal_iter = new TestIterator(BytewiseComparator());
+  internal_iter->AddPut("a", "val_a");
+  internal_iter->AddPut("b", "val_b");
+  internal_iter->Finish();
+
+  ReadOptions ro;
+  std::unique_ptr<Iterator> db_iter(DBIter::NewIter(
+      env_, ro, ioptions, mutable_cf_options, BytewiseComparator(),
+      internal_iter, nullptr /* version */, 10 /* sequence */,
+      nullptr /* read_callback */, /*active_mem=*/nullptr));
+
+  MultiScanArgs scan_opts(BytewiseComparator());
+  scan_opts.insert("b", "d");
+  scan_opts.insert("a", "c");
+
+  db_iter->Prepare(scan_opts);
+  EXPECT_TRUE(db_iter->status().IsInvalidArgument());
+  EXPECT_EQ(internal_iter->prepare_call_count(), 0);
+}
+
 TEST_F(DBIteratorTest, DBIteratorPrevNext) {
   Options options;
   ImmutableOptions ioptions = ImmutableOptions(options);

db/db_iterator_test.cc

@@ -4395,6 +4395,71 @@ TEST_P(DBMultiScanIteratorTest, RangeAcrossFiles) {
   iter.reset();
 }
 
+TEST_P(DBMultiScanIteratorTest, SortedRangesSkipIODispatcherSort) {
+  auto options = CurrentOptions();
+  options.target_file_size_base = 100 << 10;
+  options.compaction_style = kCompactionStyleUniversal;
+  options.num_levels = 50;
+  options.compression = kNoCompression;
+  DestroyAndReopen(options);
+
+  auto key = [](int i) {
+    std::stringstream ss;
+    ss << "k" << std::setw(5) << std::setfill('0') << i;
+    return ss.str();
+  };
+
+  auto rnd = Random::GetTLSInstance();
+  for (int i = 0; i < 100; ++i) {
+    ASSERT_OK(Put(key(i), rnd->RandomString(2 << 10)));
+  }
+  ASSERT_OK(Flush());
+
+  ASSERT_OK(db_->CompactRange({}, nullptr, nullptr));
+  ASSERT_EQ(2, NumTableFilesAtLevel(49));
+
+  int sort_count = 0;
+  SyncPoint::GetInstance()->SetCallBack(
+      "IODispatcherImpl::SubmitJob:SortBlockHandles",
+      [&](void* /*arg*/) { ++sort_count; });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  auto tracking_dispatcher = std::make_shared<TrackingIODispatcher>();
+  std::vector<std::string> key_ranges({key(10), key(90)});
+  MultiScanArgs scan_options(BytewiseComparator());
+  scan_options.io_dispatcher = tracking_dispatcher;
+  scan_options.use_async_io = false;
+  scan_options.insert(key_ranges[0], key_ranges[1]);
+
+  ReadOptions ro;
+  ro.fill_cache = GetParam();
+  ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
+  std::unique_ptr<MultiScan> iter =
+      dbfull()->NewMultiScan(ro, cfh, scan_options);
+
+  try {
+    int i = 10;
+    for (auto range : *iter) {
+      for (auto it : range) {
+        ASSERT_EQ(it.first.ToString(), key(i));
+        ++i;
+      }
+    }
+    ASSERT_EQ(i, 90);
+  } catch (MultiScanException& ex) {
+    ASSERT_NOK(ex.status());
+    std::cerr << "Iterator returned status " << ex.what();
+    abort();
+  } catch (std::logic_error& ex) {
+    std::cerr << "Iterator returned logic error " << ex.what();
+    abort();
+  }
+
+  ASSERT_GT(tracking_dispatcher->GetReadSets().size(), 0);
+  EXPECT_EQ(sort_count, 0);
+  iter.reset();
+}
+
 TEST_P(DBMultiScanIteratorTest, FailureTest) {
   auto options = CurrentOptions();
   options.compression = kNoCompression;
@@ -7181,6 +7246,52 @@ TEST_P(ReadPathRangeTombstoneTest,
   db_->ReleaseSnapshot(snap);
 }
 
+// SeekForPrev uses the reverse path: PrevInternal -> FindValueForCurrentKey.
+// When a key has more versions than max_sequential_skip_in_iterations,
+// FindValueForCurrentKey delegates to FindValueForCurrentKeyUsingSeek which
+// re-seeks forward to the newest visible version. That function must preserve
+// key pinning by passing the correct `copy` parameter to
+// saved_key_.SetUserKey().
+TEST_P(DBIteratorTest, SeekForPrevKeyPinnedWithManyVersions) {
+  Options options = CurrentOptions();
+  options.max_sequential_skip_in_iterations = 8;
+  options.statistics = CreateDBStatistics();
+  DestroyAndReopen(options);
+
+  // 20 versions > max_sequential_skip (8), forcing the reseek path.
+  // No flush: keeps all versions alive in the memtable.
+  for (int i = 0; i < 20; i++) {
+    ASSERT_OK(Put("key1", "value" + std::to_string(i)));
+  }
+
+  ReadOptions ro;
+  ro.pin_data = true;
+
+  std::unique_ptr<Iterator> iter(NewIterator(ro));
+  std::string prop_value;
+
+  // Seek (forward) correctly reports key as pinned.
+  iter->Seek("key1");
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+  ASSERT_EQ("1", prop_value);
+
+  uint64_t reseeks_before =
+      options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION);
+
+  iter->SeekForPrev("key1");
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ("key1", iter->key().ToString());
+
+  // Confirm FindValueForCurrentKeyUsingSeek was actually taken.
+  uint64_t reseeks_after =
+      options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION);
+  ASSERT_GT(reseeks_after, reseeks_before);
+
+  ASSERT_OK(iter->GetProperty("rocksdb.iterator.is-key-pinned", &prop_value));
+  ASSERT_EQ("1", prop_value);
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {

db/db_options_test.cc

@@ -102,6 +102,40 @@ TEST_F(DBOptionsTest, ImmutableTrackAndVerifyWalsInManifest) {
   ASSERT_FALSE(s.ok());
 }
 
+TEST_F(DBOptionsTest, ImmutableAsyncWalPrecreate) {
+  Options options;
+  options.env = env_;
+  options.async_wal_precreate = true;
+
+  ImmutableDBOptions db_options(options);
+  ASSERT_TRUE(db_options.async_wal_precreate);
+
+  Reopen(options);
+  ASSERT_TRUE(dbfull()->GetDBOptions().async_wal_precreate);
+
+  Status s = dbfull()->SetDBOptions({{"async_wal_precreate", "false"}});
+  ASSERT_FALSE(s.ok());
+}
+
+TEST_F(DBOptionsTest, SanitizeAsyncWalPrecreateWithWalRecycle) {
+  // This checks the option-level contract for the incompatible WAL paths:
+  // SanitizeOptions() preserves WAL recycling and disables only the
+  // opportunistic async precreation path, so the immutable options reflect
+  // effective behavior.
+  Options options;
+  options.env = env_;
+  options.async_wal_precreate = true;
+  options.recycle_log_file_num = 1;
+
+  Options sanitized_options = SanitizeOptions(dbname_, options);
+  ASSERT_FALSE(sanitized_options.async_wal_precreate);
+  ASSERT_EQ(1U, sanitized_options.recycle_log_file_num);
+
+  options.recycle_log_file_num = 0;
+  sanitized_options = SanitizeOptions(dbname_, options);
+  ASSERT_TRUE(sanitized_options.async_wal_precreate);
+}
+
 TEST_F(DBOptionsTest, ImmutableVerifySstUniqueIdInManifest) {
   Options options;
   options.env = env_;

db/db_secondary_test.cc

@@ -13,6 +13,7 @@
 #include "db/db_with_timestamp_test_util.h"
 #include "db/wide/wide_column_test_util.h"
 #include "db/write_batch_internal.h"
+#include "file/filename.h"
 #include "port/stack_trace.h"
 #include "rocksdb/utilities/transaction_db.h"
 #include "test_util/sync_point.h"
@@ -922,6 +923,48 @@ TEST_F(DBSecondaryTest, OpenAsSecondaryWALTailing) {
   verify_db_func("new_foo_value_1", "new_bar_value");
 }
 
+TEST_F(DBSecondaryTest, CatchUpTailsCurrentWalWhenFutureWalExists) {
+  // Goal: secondary catch-up must keep tailing the current WAL even when a
+  // higher-number empty WAL is present. This reproduces the async WAL
+  // precreation shape by creating a future WAL before opening the secondary,
+  // then appending another write to the current WAL and catching up again.
+  Options options;
+  options.env = env_;
+  Reopen(options);
+
+  ASSERT_OK(Put("foo", "value0"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Put("foo", "value1"));
+  ASSERT_OK(db_->FlushWAL(/*sync=*/true));
+
+  std::unique_ptr<WalFile> current_wal;
+  ASSERT_OK(db_->GetCurrentWalFile(&current_wal));
+  ASSERT_NE(nullptr, current_wal);
+
+  const uint64_t future_wal_number = current_wal->LogNumber() + 1000;
+  std::unique_ptr<WritableFile> future_wal_file;
+  ASSERT_OK(env_->NewWritableFile(LogFileName(dbname_, future_wal_number),
+                                  &future_wal_file, EnvOptions()));
+  ASSERT_OK(future_wal_file->Close());
+
+  Options secondary_options;
+  secondary_options.env = env_;
+  secondary_options.max_open_files = -1;
+  OpenSecondary(secondary_options);
+
+  ReadOptions read_options;
+  std::string value;
+  ASSERT_OK(db_secondary_->Get(read_options, "foo", &value));
+  ASSERT_EQ("value1", value);
+
+  ASSERT_OK(Put("foo", "value2"));
+  ASSERT_OK(db_->FlushWAL(/*sync=*/true));
+
+  ASSERT_OK(db_secondary_->TryCatchUpWithPrimary());
+  ASSERT_OK(db_secondary_->Get(read_options, "foo", &value));
+  ASSERT_EQ("value2", value);
+}
+
 TEST_F(DBSecondaryTest, SecondaryTailingBug_ISSUE_8467) {
   Options options;
   options.env = env_;

db/db_test.cc

@@ -8071,6 +8071,41 @@ INSTANTIATE_TEST_CASE_P(OpenFilesAsync, OpenFilesAsyncTest,
                                            ::testing::Values(-1, 10),
                                            ::testing::Bool()));
 
+TEST_F(DBTest, ReadOnlyCloseDoesNotDeleteWriterFiles) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.disable_auto_compactions = true;
+  DestroyAndReopen(options);
+
+  ASSERT_OK(Put("before", "value"));
+  ASSERT_OK(Flush());
+
+  std::unique_ptr<DB> read_only_db;
+  ASSERT_OK(DB::OpenForReadOnly(options, dbname_, &read_only_db));
+
+  ASSERT_OK(Put("after", "value"));
+  ASSERT_OK(Flush());
+
+  std::vector<LiveFileMetaData> live_files;
+  db_->GetLiveFilesMetaData(&live_files);
+  ASSERT_GE(live_files.size(), 2);
+
+  std::string newest_sst_path;
+  uint64_t newest_file_number = 0;
+  for (const auto& live_file : live_files) {
+    if (live_file.file_number > newest_file_number) {
+      newest_file_number = live_file.file_number;
+      newest_sst_path = live_file.directory + "/" + live_file.relative_filename;
+    }
+  }
+  ASSERT_FALSE(newest_sst_path.empty());
+  ASSERT_OK(env_->FileExists(newest_sst_path));
+
+  read_only_db.reset();
+
+  ASSERT_OK(env_->FileExists(newest_sst_path));
+}
+
 // Test mix of races with async file open, reads, compactions
 TEST_P(OpenFilesAsyncTest, ConcurrentFileAccess) {
   Options options = CurrentOptions();

db/db_test_util.cc

@@ -13,6 +13,7 @@
 #include "db/forward_iterator.h"
 #include "env/fs_readonly.h"
 #include "env/mock_env.h"
+#include "file/file_util.h"
 #include "port/lang.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/convenience.h"
@@ -90,6 +91,8 @@ DBTestBase::DBTestBase(const std::string path, bool env_do_fsync)
   dbname_ = test::PerThreadDBPath(env_, path);
   alternative_wal_dir_ = dbname_ + "/wal";
   alternative_db_log_dir_ = dbname_ + "/db_log_dir";
+  EXPECT_OK(DestroyDir(env_, alternative_wal_dir_));
+  EXPECT_OK(DestroyDir(env_, alternative_db_log_dir_));
   auto options = CurrentOptions();
   options.env = env_;
   auto delete_options = options;
@@ -117,6 +120,8 @@ DBTestBase::~DBTestBase() {
   if (getenv("KEEP_DB")) {
     printf("DB is still at %s\n", dbname_.c_str());
   } else {
+    EXPECT_OK(DestroyDir(env_, alternative_wal_dir_));
+    EXPECT_OK(DestroyDir(env_, alternative_db_log_dir_));
     EXPECT_OK(DestroyDB(dbname_, options));
   }
   // Ensure SstFileManager (and its DeleteScheduler background thread) is

db/db_wal_test.cc

@@ -7,6 +7,8 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
+#include <algorithm>
+
 #include "db/db_test_util.h"
 #include "db/db_with_timestamp_test_util.h"
 #include "options/options_helper.h"
@@ -19,12 +21,62 @@
 #include "utilities/fault_injection_env.h"
 #include "utilities/fault_injection_fs.h"
 
+#if defined(OS_LINUX)
+#include <sys/statfs.h>
+#endif
+
+#if defined(OS_LINUX) && !defined(BTRFS_SUPER_MAGIC)
+#define BTRFS_SUPER_MAGIC 0x9123683E
+#endif
+
+#if defined(OS_LINUX) && !defined(TMPFS_MAGIC)
+#define TMPFS_MAGIC 0x01021994
+#endif
+
+#if defined(OS_LINUX) && !defined(OVERLAYFS_SUPER_MAGIC)
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
+#endif
+
+#if defined(OS_LINUX) && !defined(ZFS_SUPER_MAGIC)
+#define ZFS_SUPER_MAGIC 0x2fc12fc1
+#endif
+
 namespace ROCKSDB_NAMESPACE {
 class DBWALTestBase : public DBTestBase {
  protected:
   explicit DBWALTestBase(const std::string& dir_name)
       : DBTestBase(dir_name, /*env_do_fsync=*/true) {}
 
+  std::vector<uint64_t> ListWalNumbers() {
+    std::vector<uint64_t> wal_numbers;
+    std::vector<std::string> files;
+    EXPECT_OK(env_->GetChildren(dbname_, &files));
+    for (const auto& file : files) {
+      uint64_t number = 0;
+      FileType type = kWalFile;
+      if (ParseFileName(file, &number, &type) && type == kWalFile) {
+        wal_numbers.push_back(number);
+      }
+    }
+    std::sort(wal_numbers.begin(), wal_numbers.end());
+    return wal_numbers;
+  }
+
+  void CreateEmptyWal(uint64_t wal_number) {
+    std::unique_ptr<WritableFile> file;
+    ASSERT_OK(env_->NewWritableFile(LogFileName(dbname_, wal_number), &file,
+                                    EnvOptions()));
+    ASSERT_OK(file->Close());
+  }
+
+  void CreateWalWithContents(uint64_t wal_number, const Slice& contents) {
+    std::unique_ptr<WritableFile> file;
+    ASSERT_OK(env_->NewWritableFile(LogFileName(dbname_, wal_number), &file,
+                                    EnvOptions()));
+    ASSERT_OK(file->Append(contents));
+    ASSERT_OK(file->Close());
+  }
+
 #if defined(ROCKSDB_PLATFORM_POSIX)
  public:
 #if defined(ROCKSDB_FALLOCATE_PRESENT)
@@ -57,6 +109,31 @@ class DBWALTestBase : public DBTestBase {
     assert(err == 0);
     return sbuf.st_blocks * 512;
   }
+
+#if defined(ROCKSDB_FALLOCATE_PRESENT)
+  bool ShouldSkipAllocationCheck(const std::string& file_name) {
+    (void)file_name;
+#if defined(OS_LINUX)
+    struct statfs fs_stat;
+    if (statfs(file_name.c_str(), &fs_stat) == 0) {
+      if (fs_stat.f_type ==
+          static_cast<decltype(fs_stat.f_type)>(BTRFS_SUPER_MAGIC)) {
+        return true;
+      } else if (fs_stat.f_type ==
+                 static_cast<decltype(fs_stat.f_type)>(ZFS_SUPER_MAGIC)) {
+        return true;
+      } else if (fs_stat.f_type ==
+                 static_cast<decltype(fs_stat.f_type)>(TMPFS_MAGIC)) {
+        return true;
+      } else if (fs_stat.f_type ==
+                 static_cast<decltype(fs_stat.f_type)>(OVERLAYFS_SUPER_MAGIC)) {
+        return true;
+      }
+    }
+#endif
+    return false;
+  }
+#endif  // ROCKSDB_FALLOCATE_PRESENT
 #endif  // ROCKSDB_PLATFORM_POSIX
 };
 
@@ -2752,16 +2829,35 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithoutFlush) {
   auto& file_before = log_files_before[0];
   ASSERT_LT(file_before->SizeFileBytes(), 1 * kKB);
   // The log file has preallocated space.
-  ASSERT_GE(GetAllocatedFileSize(dbname_ + file_before->PathName()),
-            preallocated_size);
+  {
+    std::string fname = dbname_ + file_before->PathName();
+    uint64_t allocated = GetAllocatedFileSize(fname);
+    if (ShouldSkipAllocationCheck(fname)) {
+      fprintf(stderr,
+              "Skipping preallocation check on this filesystem for %s\n",
+              fname.c_str());
+    } else if (allocated < preallocated_size) {
+      fprintf(stderr,
+              "Warning: allocated size (%lu) less than preallocated size (%lu) "
+              "for %s, skipping check. This may indicate the filesystem does "
+              "not support preallocation or does not report it.\n",
+              allocated, preallocated_size, fname.c_str());
+    } else {
+      ASSERT_GE(allocated, preallocated_size);
+    }
+  }
   Reopen(options);
   VectorLogPtr log_files_after;
   ASSERT_OK(dbfull()->GetSortedWalFiles(log_files_after));
   ASSERT_EQ(1, log_files_after.size());
   ASSERT_LT(log_files_after[0]->SizeFileBytes(), 1 * kKB);
   // The preallocated space should be truncated.
-  ASSERT_LT(GetAllocatedFileSize(dbname_ + file_before->PathName()),
-            preallocated_size);
+  {
+    std::string fname = dbname_ + file_before->PathName();
+    if (!ShouldSkipAllocationCheck(fname)) {
+      ASSERT_LT(GetAllocatedFileSize(fname), preallocated_size);
+    }
+  }
 }
 // Tests that we will truncate the preallocated space of the last log from
 // previous.
@@ -2788,8 +2884,23 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithFlush) {
   ASSERT_EQ(1, log_files_before.size());
   auto& file_before = log_files_before[0];
   ASSERT_LT(file_before->SizeFileBytes(), 1 * kKB);
-  ASSERT_GE(GetAllocatedFileSize(dbname_ + file_before->PathName()),
-            preallocated_size);
+  {
+    std::string fname = dbname_ + file_before->PathName();
+    uint64_t allocated = GetAllocatedFileSize(fname);
+    if (ShouldSkipAllocationCheck(fname)) {
+      fprintf(stderr,
+              "Skipping preallocation check on this filesystem for %s\n",
+              fname.c_str());
+    } else if (allocated < preallocated_size) {
+      fprintf(stderr,
+              "Warning: allocated size (%lu) less than preallocated size (%lu) "
+              "for %s, skipping check. This may indicate the filesystem does "
+              "not support preallocation or does not report it.\n",
+              allocated, preallocated_size, fname.c_str());
+    } else {
+      ASSERT_GE(allocated, preallocated_size);
+    }
+  }
   // The log file has preallocated space.
   Close();
 
@@ -2807,8 +2918,12 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithFlush) {
   // if  the process is in a crash loop, the log file may not get
   // deleted and thte preallocated space will keep accumulating. So we need
   // to ensure it gets trtuncated.
-  EXPECT_LT(GetAllocatedFileSize(dbname_ + file_before->PathName()),
-            preallocated_size);
+  {
+    std::string fname = dbname_ + file_before->PathName();
+    if (!ShouldSkipAllocationCheck(fname)) {
+      EXPECT_LT(GetAllocatedFileSize(fname), preallocated_size);
+    }
+  }
   TEST_SYNC_POINT(
       "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterTruncate");
   reopen_thread.join();
@@ -2863,14 +2978,31 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWALEmpty) {
   log_file->PrepareWrite(0, 4096);
   log_file.reset();
 
-  ASSERT_GE(GetAllocatedFileSize(last_log), preallocated_size);
+  {
+    uint64_t allocated = GetAllocatedFileSize(last_log);
+    if (ShouldSkipAllocationCheck(last_log)) {
+      fprintf(stderr,
+              "Skipping preallocation check on this filesystem for %s\n",
+              last_log.c_str());
+    } else if (allocated < preallocated_size) {
+      fprintf(stderr,
+              "Warning: allocated size (%lu) less than preallocated size (%lu) "
+              "for %s, skipping check. This may indicate the filesystem does "
+              "not support preallocation or does not report it.\n",
+              allocated, preallocated_size, last_log.c_str());
+    } else {
+      ASSERT_GE(allocated, preallocated_size);
+    }
+  }
 
   port::Thread reopen_thread([&]() { Reopen(options); });
 
   TEST_SYNC_POINT(
       "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterRecover");
   // The preallocated space should be truncated.
-  EXPECT_LT(GetAllocatedFileSize(last_log), preallocated_size);
+  if (!ShouldSkipAllocationCheck(last_log)) {
+    EXPECT_LT(GetAllocatedFileSize(last_log), preallocated_size);
+  }
   TEST_SYNC_POINT(
       "DBWALTest::TruncateLastLogAfterRecoverWithFlush:AfterTruncate");
   reopen_thread.join();
@@ -2912,8 +3044,23 @@ TEST_F(DBWALTest, ReadOnlyRecoveryNoTruncate) {
   auto& file_before = log_files_before[0];
   ASSERT_LT(file_before->SizeFileBytes(), 1 * kKB);
   // The log file has preallocated space.
-  auto db_size = GetAllocatedFileSize(dbname_ + file_before->PathName());
-  ASSERT_GE(db_size, preallocated_size);
+  std::string fname = dbname_ + file_before->PathName();
+  auto db_size = GetAllocatedFileSize(fname);
+  {
+    if (ShouldSkipAllocationCheck(fname)) {
+      fprintf(stderr,
+              "Skipping preallocation check on this filesystem for %s\n",
+              fname.c_str());
+    } else if (db_size < preallocated_size) {
+      fprintf(stderr,
+              "Warning: allocated size (%lu) less than preallocated size (%lu) "
+              "for %s, skipping check. This may indicate the filesystem does "
+              "not support preallocation or does not report it.\n",
+              db_size, preallocated_size, fname.c_str());
+    } else {
+      ASSERT_GE(db_size, preallocated_size);
+    }
+  }
   Close();
 
   // enable truncate and open DB as readonly, the file should not be truncated
@@ -2927,8 +3074,12 @@ TEST_F(DBWALTest, ReadOnlyRecoveryNoTruncate) {
   ASSERT_EQ(log_files_after[0]->PathName(), file_before->PathName());
   // The preallocated space should NOT be truncated.
   // the DB size is almost the same.
-  ASSERT_NEAR(GetAllocatedFileSize(dbname_ + file_before->PathName()), db_size,
-              db_size / 100);
+  {
+    std::string fname2 = dbname_ + file_before->PathName();
+    if (!ShouldSkipAllocationCheck(fname2)) {
+      ASSERT_NEAR(GetAllocatedFileSize(fname2), db_size, db_size / 100);
+    }
+  }
   SyncPoint::GetInstance()->DisableProcessing();
   SyncPoint::GetInstance()->ClearAllCallBacks();
 }
@@ -3071,6 +3222,284 @@ TEST_F(DBWALTest, EmptyWalReopenTest) {
   }
 }
 
+TEST_F(DBWALTest, AsyncWalPrecreateWaitsForPendingFile) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.statistics = CreateDBStatistics();
+  options.async_wal_precreate = true;
+  options.recycle_log_file_num = 0;
+  options.write_buffer_size = 1024;
+  options.max_write_buffer_number = 4;
+
+  // Goal: cover the race where foreground WAL rotation reaches the switch
+  // before the background precreate publishes its result. The sync points hold
+  // the async worker after it has created the file but before it marks it
+  // ready, then verify the foreground writer waits instead of allocating a
+  // higher WAL number.
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::BGWorkAsyncWALPrecreate:BeforePublish",
+       "DBWALTest::AsyncWalPrecreateWaitsForPendingFile:WorkerBlocked"},
+      {"DBWALTest::AsyncWalPrecreateWaitsForPendingFile:AllowPublish",
+       "DBImpl::BGWorkAsyncWALPrecreate:Publish"},
+      {"DBImpl::WaitForAsyncWALPrecreate:BeforeWait",
+       "DBWALTest::AsyncWalPrecreateWaitsForPendingFile:ForegroundWaiting"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  Defer cleanup_sync_point([] {
+    SyncPoint::GetInstance()->DisableProcessing();
+    SyncPoint::GetInstance()->ClearAllCallBacks();
+  });
+
+  Reopen(options);
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateWaitsForPendingFile:WorkerBlocked");
+
+  ASSERT_OK(Put("fill", "value"));
+  Status writer_status;
+  port::Thread writer(
+      [&]() { writer_status = dbfull()->TEST_SwitchMemtable(); });
+
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateWaitsForPendingFile:ForegroundWaiting");
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateWaitsForPendingFile:AllowPublish");
+  writer.join();
+  ASSERT_OK(writer_status);
+  ASSERT_OK(Put("trigger", "value"));
+  ASSERT_EQ("value", Get("trigger"));
+  ASSERT_EQ(1, options.statistics->getTickerCount(WAL_PRECREATE_HIT));
+  ASSERT_EQ(1, options.statistics->getTickerCount(WAL_PRECREATE_WAITED));
+  ASSERT_EQ(0, options.statistics->getTickerCount(WAL_PRECREATE_MISS));
+}
+
+TEST_F(DBWALTest, AsyncWalPrecreateConsumesReadyFile) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.statistics = CreateDBStatistics();
+  options.async_wal_precreate = true;
+  options.recycle_log_file_num = 0;
+  options.write_buffer_size = 1024;
+  options.max_write_buffer_number = 4;
+
+  // Goal: exercise the no-wait consumption path. The background task publishes
+  // a prepared future WAL before the foreground memtable switch, and the switch
+  // must install exactly that reserved WAL number instead of allocating
+  // another.
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::BGWorkAsyncWALPrecreate:Done",
+       "DBWALTest::AsyncWalPrecreateConsumesReadyFile:PrecreateDone"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  Defer cleanup_sync_point([] {
+    SyncPoint::GetInstance()->DisableProcessing();
+    SyncPoint::GetInstance()->ClearAllCallBacks();
+  });
+
+  Reopen(options);
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateConsumesReadyFile:PrecreateDone");
+
+  const std::vector<uint64_t> wal_numbers = ListWalNumbers();
+  ASSERT_GE(wal_numbers.size(), 2);
+  const uint64_t prepared_wal_number = wal_numbers.back();
+  ASSERT_NE(prepared_wal_number, dbfull()->TEST_GetCurrentLogNumber());
+
+  ASSERT_OK(Put("fill", "value"));
+  ASSERT_OK(dbfull()->TEST_SwitchMemtable());
+  ASSERT_EQ(prepared_wal_number, dbfull()->TEST_GetCurrentLogNumber());
+  ASSERT_EQ(1, options.statistics->getTickerCount(WAL_PRECREATE_HIT));
+  ASSERT_EQ(0, options.statistics->getTickerCount(WAL_PRECREATE_MISS));
+  ASSERT_EQ(0, options.statistics->getTickerCount(WAL_PRECREATE_WAITED));
+}
+
+TEST_F(DBWALTest, AsyncWalPrecreateRecoveryToleratesActualFutureWal) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.async_wal_precreate = true;
+  options.recycle_log_file_num = 0;
+  options.track_and_verify_wals = true;
+  options.track_and_verify_wals_in_manifest = true;
+  options.avoid_flush_during_shutdown = true;
+  options.avoid_flush_during_recovery = true;
+
+  // Goal: cover the actual async precreation path, not a hand-forged empty WAL.
+  // The background task opens the future WAL, clean close releases the
+  // unpublished writer and leaves the empty future WAL behind, and recovery
+  // must tolerate that file while replaying the preceding WAL with real user
+  // data.
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::BGWorkAsyncWALPrecreate:Done",
+       "DBWALTest::AsyncWalPrecreateRecoveryToleratesActualFutureWal:"
+       "PrecreateDone"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  Defer cleanup_sync_point([] {
+    SyncPoint::GetInstance()->DisableProcessing();
+    SyncPoint::GetInstance()->ClearAllCallBacks();
+  });
+
+  DestroyAndReopen(options);
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateRecoveryToleratesActualFutureWal:"
+      "PrecreateDone");
+
+  const std::vector<uint64_t> wal_numbers = ListWalNumbers();
+  ASSERT_GE(wal_numbers.size(), 2);
+  const uint64_t future_wal_number = wal_numbers.back();
+  uint64_t future_wal_size = 0;
+  ASSERT_OK(env_->GetFileSize(LogFileName(dbname_, future_wal_number),
+                              &future_wal_size));
+  ASSERT_EQ(0, future_wal_size);
+
+  ASSERT_OK(Put("key", "value"));
+  Close();
+
+  ASSERT_OK(TryReopen(options));
+  ASSERT_EQ("value", Get("key"));
+  ASSERT_OK(Put("after-recovery", "value2"));
+  ASSERT_EQ("value2", Get("after-recovery"));
+}
+
+TEST_F(DBWALTest, AsyncWalPrecreateDeletesFileOnStartFailure) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.statistics = CreateDBStatistics();
+  options.async_wal_precreate = true;
+  options.recycle_log_file_num = 0;
+  options.write_buffer_size = 1024;
+  options.max_write_buffer_number = 4;
+
+  // Goal: force failure after consuming a prepared WAL but before it becomes a
+  // logical WAL. The failed, unpublished file must be deleted and its writer
+  // destroyed outside mutex_.
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::BGWorkAsyncWALPrecreate:Done",
+       "DBWALTest::AsyncWalPrecreateDeletesFileOnStartFailure:PrecreateDone"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  Defer cleanup_sync_point([] {
+    SyncPoint::GetInstance()->DisableProcessing();
+    SyncPoint::GetInstance()->ClearAllCallBacks();
+  });
+
+  Reopen(options);
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateDeletesFileOnStartFailure:PrecreateDone");
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::StartWALFile:AfterCompressionTypeRecord", [](void* arg) {
+        *static_cast<IOStatus*>(arg) =
+            IOStatus::IOError("injected async WAL start failure");
+      });
+  const std::vector<uint64_t> wal_numbers = ListWalNumbers();
+  ASSERT_GE(wal_numbers.size(), 2);
+  const uint64_t prepared_wal_number = wal_numbers.back();
+
+  ASSERT_OK(Put("fill", "value"));
+  ASSERT_NOK(dbfull()->TEST_SwitchMemtable());
+  ASSERT_TRUE(
+      env_->FileExists(LogFileName(dbname_, prepared_wal_number)).IsNotFound());
+  ASSERT_EQ(1, options.statistics->getTickerCount(WAL_PRECREATE_HIT));
+}
+
+TEST_F(DBWALTest, AsyncWalPrecreateFailureFallsBackToSyncCreation) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.statistics = CreateDBStatistics();
+  options.async_wal_precreate = true;
+  options.recycle_log_file_num = 0;
+  options.write_buffer_size = 1024;
+  options.max_write_buffer_number = 4;
+
+  // Goal: fail the background precreate file open after normal DB open has
+  // created the current WAL. The foreground switch should observe no prepared
+  // WAL, create one synchronously, and expose both failure and miss counters.
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::BGWorkAsyncWALPrecreate:Done",
+       "DBWALTest::AsyncWalPrecreateFailureFallsBackToSyncCreation:"
+       "PrecreateDone"},
+  });
+  SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::Open:AfterDeleteFiles",
+      [&](void*) { env_->non_writable_count_ = 1; });
+  SyncPoint::GetInstance()->EnableProcessing();
+  Defer cleanup_sync_point([&] {
+    env_->non_writable_count_ = 0;
+    SyncPoint::GetInstance()->DisableProcessing();
+    SyncPoint::GetInstance()->ClearAllCallBacks();
+  });
+
+  Reopen(options);
+  TEST_SYNC_POINT(
+      "DBWALTest::AsyncWalPrecreateFailureFallsBackToSyncCreation:"
+      "PrecreateDone");
+  ASSERT_EQ(1, options.statistics->getTickerCount(WAL_PRECREATE_FAILED));
+
+  ASSERT_OK(Put("fill", "value"));
+  ASSERT_OK(dbfull()->TEST_SwitchMemtable());
+  ASSERT_EQ(1, options.statistics->getTickerCount(WAL_PRECREATE_MISS));
+}
+
+TEST_F(DBWALTest, ReadOnlyErrorIfWalFileExistsIgnoresEmptyWals) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  DestroyAndReopen(options);
+  Close();
+
+  // Goal: preserve error_if_wal_file_exists for WALs containing data while
+  // allowing empty future WALs left by async precreation. This creates empty
+  // WAL files directly so the test isolates the read-only open contract.
+  const std::vector<uint64_t> existing_wal_numbers = ListWalNumbers();
+  const uint64_t empty_wal_number =
+      existing_wal_numbers.empty() ? 1 : existing_wal_numbers.back() + 1;
+  CreateEmptyWal(empty_wal_number);
+
+  DBOptions db_options(options);
+  std::vector<ColumnFamilyDescriptor> column_families;
+  column_families.emplace_back(kDefaultColumnFamilyName,
+                               ColumnFamilyOptions(options));
+  std::vector<ColumnFamilyHandle*> handles;
+  std::unique_ptr<DB> read_only_db;
+  ASSERT_OK(DB::OpenForReadOnly(db_options, dbname_, column_families, &handles,
+                                &read_only_db,
+                                true /* error_if_wal_file_exists */));
+  for (ColumnFamilyHandle* handle : handles) {
+    ASSERT_OK(read_only_db->DestroyColumnFamilyHandle(handle));
+  }
+  read_only_db.reset();
+  handles.clear();
+
+  CreateWalWithContents(empty_wal_number + 1, Slice("not empty"));
+  ASSERT_NOK(DB::OpenForReadOnly(db_options, dbname_, column_families, &handles,
+                                 &read_only_db,
+                                 true /* error_if_wal_file_exists */));
+}
+
+TEST_F(DBWALTest, RecoveryToleratesEmptyFutureWal) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.track_and_verify_wals = true;
+  options.track_and_verify_wals_in_manifest = true;
+  options.avoid_flush_during_recovery = true;
+  DestroyAndReopen(options);
+
+  ASSERT_OK(Put("key", "value"));
+  Close();
+
+  const std::vector<uint64_t> wal_numbers = ListWalNumbers();
+  ASSERT_FALSE(wal_numbers.empty());
+  const uint64_t future_wal_number = wal_numbers.back() + 1;
+  CreateEmptyWal(future_wal_number);
+
+  // Goal: model a crash after async WAL precreation but before consumption.
+  // Recovery should process the zero-byte future WAL, mark its file number
+  // used, and keep replaying the real preceding WAL without reporting a WAL
+  // chain or MANIFEST-tracking error.
+  ASSERT_OK(TryReopen(options));
+  ASSERT_EQ("value", Get("key"));
+  ASSERT_OK(Put("after-recovery", "value2"));
+  ASSERT_EQ("value2", Get("after-recovery"));
+}
+
 TEST_F(DBWALTest, RecoveryFlushSwitchWALOnEmptyMemtable) {
   Options options = CurrentOptions();
   auto fault_fs = std::make_shared<FaultInjectionTestFS>(FileSystem::Default());

db/listener_test.cc

@@ -31,6 +31,7 @@
 #include "util/mutexlock.h"
 #include "util/rate_limiter_impl.h"
 #include "util/string_util.h"
+#include "utilities/fault_injection_fs.h"
 #include "utilities/merge_operators.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -201,6 +202,194 @@ TEST_F(EventListenerTest, OnSingleDBCompactionTest) {
   }
 }
 
+// Listener that asserts OnCompactionPreCommit fires strictly between
+// OnCompactionBegin and OnCompactionCompleted, and that input files'
+// being_compacted flag is still true at that point.
+class TestCompactionPreCommitListener : public EventListener {
+ public:
+  explicit TestCompactionPreCommitListener(EventListenerTest* test)
+      : test_(test) {}
+
+  void OnCompactionBegin(DB* /*db*/, const CompactionJobInfo& ci) override {
+    std::lock_guard<std::mutex> lock(mutex_);
+    ++begin_count_;
+    last_begin_job_id_ = ci.job_id;
+    EXPECT_EQ(begin_count_, pre_commit_count_ + 1);
+    EXPECT_EQ(begin_count_, completed_count_ + 1);
+  }
+
+  void OnCompactionPreCommit(DB* db, const CompactionJobInfo& ci) override {
+    std::lock_guard<std::mutex> lock(mutex_);
+    ++pre_commit_count_;
+    // Must fire after Begin and before Completed for this compaction.
+    EXPECT_EQ(pre_commit_count_, begin_count_);
+    EXPECT_EQ(pre_commit_count_, completed_count_ + 1);
+    EXPECT_EQ(ci.job_id, last_begin_job_id_);
+    EXPECT_GT(ci.input_files.size(), 0U);
+
+    // Verify input files are still marked being_compacted.
+    std::vector<std::vector<FileMetaData>> files_by_level;
+    test_->dbfull()->TEST_GetFilesMetaData(test_->handles_[ci.cf_id],
+                                           &files_by_level);
+    EXPECT_EQ(test_->db_.get(), db);
+    for (const auto& info : ci.input_file_infos) {
+      bool found = false;
+      for (const auto& level_files : files_by_level) {
+        for (const auto& meta : level_files) {
+          if (meta.fd.GetNumber() == info.file_number) {
+            found = true;
+            EXPECT_TRUE(meta.being_compacted)
+                << "input file " << info.file_number
+                << " should still be being_compacted in "
+                   "OnCompactionPreCommit";
+          }
+        }
+      }
+      EXPECT_TRUE(found) << "input file " << info.file_number
+                         << " not found in DB";
+    }
+  }
+
+  void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
+    std::lock_guard<std::mutex> lock(mutex_);
+    ++completed_count_;
+    // Must fire after the matching PreCommit.
+    EXPECT_EQ(completed_count_, pre_commit_count_);
+    EXPECT_EQ(completed_count_, begin_count_);
+    EXPECT_EQ(ci.job_id, last_begin_job_id_);
+  }
+
+  size_t BeginCount() {
+    std::lock_guard<std::mutex> lock(mutex_);
+    return begin_count_;
+  }
+  size_t PreCommitCount() {
+    std::lock_guard<std::mutex> lock(mutex_);
+    return pre_commit_count_;
+  }
+  size_t CompletedCount() {
+    std::lock_guard<std::mutex> lock(mutex_);
+    return completed_count_;
+  }
+
+ private:
+  EventListenerTest* test_;
+  std::mutex mutex_;
+  size_t begin_count_ = 0;
+  size_t pre_commit_count_ = 0;
+  size_t completed_count_ = 0;
+  int last_begin_job_id_ = -1;
+};
+
+TEST_F(EventListenerTest, OnCompactionPreCommitOrdering) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.compaction_style = kCompactionStyleLevel;
+  options.compression = kNoCompression;
+  options.level0_file_num_compaction_trigger = 4;
+  auto* listener = new TestCompactionPreCommitListener(this);
+  options.listeners.emplace_back(listener);
+
+  // Verify sync-point ordering: Begin -> PreCommit -> Completed.
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::NotifyOnCompactionBegin::UnlockMutex",
+        "DBImpl::NotifyOnCompactionPreCommit::UnlockMutex"},
+       {"DBImpl::NotifyOnCompactionPreCommit::UnlockMutex",
+        "DBImpl::NotifyOnCompactionCompleted::UnlockMutex"}});
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+
+  CreateAndReopenWithCF({"pikachu"}, options);
+
+  Random rnd(301);
+  for (int i = 0; i < 4; i++) {
+    for (int j = 0; j < 10; j++) {
+      ASSERT_OK(Put(1, rnd.RandomString(10), rnd.RandomString(10)));
+    }
+    ASSERT_OK(Flush(1));
+  }
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+
+  EXPECT_GT(listener->BeginCount(), 0U);
+  EXPECT_EQ(listener->PreCommitCount(), listener->BeginCount());
+  EXPECT_EQ(listener->CompletedCount(), listener->BeginCount());
+
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+class TestDBShutdownBeginListener : public EventListener {
+ public:
+  void OnDBShutdownBegin(DB* db) override {
+    std::lock_guard<std::mutex> lock(mutex_);
+    ++shutdown_count_;
+    last_db_ = db;
+  }
+
+  int ShutdownCount() const {
+    std::lock_guard<std::mutex> lock(mutex_);
+    return shutdown_count_;
+  }
+
+  DB* LastDB() const {
+    std::lock_guard<std::mutex> lock(mutex_);
+    return last_db_;
+  }
+
+ private:
+  mutable std::mutex mutex_;
+  int shutdown_count_ = 0;
+  DB* last_db_ = nullptr;
+};
+
+TEST_F(EventListenerTest, OnDBShutdownBeginOnceForCancelAndClose) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  auto listener = std::make_shared<TestDBShutdownBeginListener>();
+  options.listeners.emplace_back(listener);
+  DestroyAndReopen(options);
+
+  DB* db = db_.get();
+  dbfull()->CancelAllBackgroundWork(false);
+  EXPECT_EQ(1, listener->ShutdownCount());
+  EXPECT_EQ(db, listener->LastDB());
+
+  Close();
+  EXPECT_EQ(1, listener->ShutdownCount());
+}
+
+TEST_F(EventListenerTest, OnDBShutdownBeginOnFailedOpen) {
+  Close();
+
+  std::shared_ptr<FaultInjectionTestFS> fs(
+      new FaultInjectionTestFS(env_->GetFileSystem()));
+  std::unique_ptr<Env> env(NewCompositeEnv(fs));
+
+  Options options = CurrentOptions();
+  options.env = env.get();
+  options.create_if_missing = true;
+  auto listener = std::make_shared<TestDBShutdownBeginListener>();
+  options.listeners.emplace_back(listener);
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "PersistRocksDBOptions:create",
+      [&](void* /*arg*/) { fs->SetFilesystemActive(false); });
+  SyncPoint::GetInstance()->SetCallBack(
+      "PersistRocksDBOptions:written",
+      [&](void* /*arg*/) { fs->SetFilesystemActive(true); });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  std::unique_ptr<DB> db;
+  Status s = DB::Open(options, dbname_, &db);
+  ASSERT_TRUE(s.IsIOError()) << s.ToString();
+  EXPECT_EQ(1, listener->ShutdownCount());
+  EXPECT_NE(nullptr, listener->LastDB());
+  EXPECT_EQ(nullptr, db.get());
+
+  fs->SetFilesystemActive(true);
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
 // This simple Listener can only handle one flush at a time.
 class TestFlushListener : public EventListener {
  public:
@@ -1754,7 +1943,7 @@ TEST_F(EventListenerTest, BackgroundJobPressure) {
   listener->Reset();
   sleeping_task.WakeUp();
   sleeping_task.WaitUntilDone();
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  ASSERT_OK(dbfull()->TEST_WaitForBackgroundWork());
 
   snapshots = listener->GetSnapshots();
   CheckInvariants(snapshots);

db/version_edit.cc

@@ -240,6 +240,13 @@ bool VersionEdit::EncodeTo(std::string* dst,
     PutLengthPrefixedSlice(dst, progress_data);
   }
 
+  if (has_last_compacted_manifest_file_size_) {
+    PutVarint32(dst, kLastCompactedManifestFileSize);
+    std::string varint_size;
+    PutVarint64(&varint_size, last_compacted_manifest_file_size_);
+    PutLengthPrefixedSlice(dst, Slice(varint_size));
+  }
+
   return true;
 }
 
@@ -890,6 +897,17 @@ Status VersionEdit::DecodeFrom(const Slice& src) {
         break;
       }
 
+      case kLastCompactedManifestFileSize: {
+        Slice encoded;
+        if (GetLengthPrefixedSlice(&input, &encoded) &&
+            GetVarint64(&encoded, &last_compacted_manifest_file_size_)) {
+          has_last_compacted_manifest_file_size_ = true;
+        } else {
+          msg = "last compacted manifest file size";
+        }
+        break;
+      }
+
       default:
         if (tag & kTagSafeIgnoreMask) {
           // Tag from future which can be safely ignored.
@@ -1064,6 +1082,10 @@ std::string VersionEdit::DebugString(bool hex_key) const {
     r.append("\n SubcompactionProgress: ");
     r.append(subcompaction_progress_.ToString());
   }
+  if (has_last_compacted_manifest_file_size_) {
+    r.append("\n  LastCompactedManifestFileSize: ");
+    AppendNumberTo(&r, last_compacted_manifest_file_size_);
+  }
   r.append("\n}\n");
   return r;
 }
@@ -1220,6 +1242,10 @@ std::string VersionEdit::DebugJSON(int edit_num, bool hex_key) const {
     jw << "SubcompactionProgress" << subcompaction_progress_.ToString();
   }
 
+  if (has_last_compacted_manifest_file_size_) {
+    jw << "LastCompactedManifestFileSize" << last_compacted_manifest_file_size_;
+  }
+
   jw.EndObject();
 
   return jw.Get();

db/version_edit.h

@@ -74,6 +74,7 @@ enum Tag : uint32_t {
   kWalDeletion2,
   kPersistUserDefinedTimestamps,
   kSubcompactionProgress,
+  kLastCompactedManifestFileSize,
 };
 
 enum SubcompactionProgressPerLevelCustomTag : uint32_t {
@@ -977,6 +978,11 @@ class VersionEdit {
 
   bool IsColumnFamilyDrop() const { return is_column_family_drop_; }
 
+  void MarkForegroundOperation() { is_foreground_operation_ = true; }
+  bool IsForegroundOperation() const {
+    return is_foreground_operation_ || IsColumnFamilyManipulation();
+  }
+
   void MarkNoManifestWriteDummy() { is_no_manifest_write_dummy_ = true; }
   bool IsNoManifestWriteDummy() const { return is_no_manifest_write_dummy_; }
 
@@ -1016,6 +1022,17 @@ class VersionEdit {
     subcompaction_progress_.Clear();
   }
 
+  void SetLastCompactedManifestFileSize(uint64_t size) {
+    has_last_compacted_manifest_file_size_ = true;
+    last_compacted_manifest_file_size_ = size;
+  }
+  bool HasLastCompactedManifestFileSize() const {
+    return has_last_compacted_manifest_file_size_;
+  }
+  uint64_t GetLastCompactedManifestFileSize() const {
+    return last_compacted_manifest_file_size_;
+  }
+
   // Recovery-time per-column-family edits only need to be written when they
   // advance the CF's log number or carry some other manifest state.
   bool ShouldEmitPerColumnFamilyRecoveryEdit(uint64_t current_log_number) const;
@@ -1099,6 +1116,7 @@ class VersionEdit {
   // it also includes column family name.
   bool is_column_family_drop_ = false;
   bool is_column_family_add_ = false;
+  bool is_foreground_operation_ = false;
   std::string column_family_name_;
 
   uint32_t remaining_entries_ = 0;
@@ -1111,6 +1129,9 @@ class VersionEdit {
   bool has_subcompaction_progress_ = false;
   SubcompactionProgress subcompaction_progress_;
 
+  bool has_last_compacted_manifest_file_size_ = false;
+  uint64_t last_compacted_manifest_file_size_ = 0;
+
   // Newly created table files and blob files are eligible for deletion if they
   // are not registered as live files after the background jobs creating them
   // have finished. In case committing the VersionEdit containing such changes

db/version_edit_handler.cc

@@ -642,6 +642,11 @@ Status VersionEditHandler::ExtractInfoFromVersionEdit(ColumnFamilyData* cfd,
              version_edit_params_.GetLastSequence() <= edit.GetLastSequence());
       version_edit_params_.SetLastSequence(edit.GetLastSequence());
     }
+    if (edit.HasLastCompactedManifestFileSize()) {
+      version_set_->last_compacted_manifest_file_size_ =
+          edit.GetLastCompactedManifestFileSize();
+      version_set_->TuneMaxManifestFileSize();
+    }
     if (!version_edit_params_.HasPrevLogNumber()) {
       version_edit_params_.SetPrevLogNumber(0);
     }

db/version_set.cc

@@ -6111,9 +6111,32 @@ Status VersionSet::ProcessManifestWrites(
 
   uint64_t prev_manifest_file_size = manifest_file_size_;
   assert(pending_manifest_file_number_ == 0);
+  bool has_foreground_operation = false;
+  for (const VersionEdit* e : batch_edits) {
+    if (e->IsForegroundOperation()) {
+      has_foreground_operation = true;
+      break;
+    }
+  }
+  // For MANIFEST write batches with any foreground operation (external file
+  // ingestion/import, DeleteFilesInRange(s), and column family manipulations
+  // like CreateColumnFamily and DropColumnFamily), relax the size limit by 25%
+  // to reduce the likelihood of a user operation blocking on MANIFEST rotation.
+  // Background-only batches (flush/compaction) still rotate at the normal
+  // threshold.
+  // TODO/future: for workloads like atomic-replace ingestion-only, with zero
+  // or few flushes and compactions, it might be nice to trigger background
+  // manifest rotation if we are beyond the soft limit. But the vast majority
+  // of workloads should have plenty of background manifest ops to avoid
+  // foreground rotation.
+  uint64_t enforced_limit = tuned_max_manifest_file_size_;
+  if (has_foreground_operation) {
+    uint64_t new_limit = enforced_limit + enforced_limit / 4;
+    // don't keep in case of overflow
+    enforced_limit = std::max(enforced_limit, new_limit);
+  }
   if (!skip_manifest_write &&
-      (!descriptor_log_ ||
-       prev_manifest_file_size >= tuned_max_manifest_file_size_)) {
+      (!descriptor_log_ || prev_manifest_file_size >= enforced_limit)) {
     TEST_SYNC_POINT("VersionSet::ProcessManifestWrites:BeforeNewManifest");
     new_descriptor_log = true;
   } else {
@@ -6284,6 +6307,8 @@ Status VersionSet::ProcessManifestWrites(
       io_s = SetCurrentFile(
           write_options, fs_.get(), dbname_, pending_manifest_file_number_,
           file_options_.temperature, dir_contains_current_file);
+      TEST_SYNC_POINT_CALLBACK(
+          "VersionSet::ProcessManifestWrites:AfterSetCurrentFile", &io_s);
       if (!io_s.ok()) {
         s = io_s;
         // Quarantine old manifest file in case new manifest file's CURRENT
@@ -7496,6 +7521,28 @@ Status VersionSet::WriteCurrentStateToManifest(
       }
     }
   }
+
+  // Record the approximate compacted manifest size so it's available at
+  // recovery time for TuneMaxManifestFileSize(). This record must come last
+  // in WriteCurrentStateToManifest for an accurate size estimate.
+  {
+    // Include a rough estimate of this record's own size (~15 bytes for the
+    // VersionEdit payload + log record header).
+    constexpr uint64_t kEstimatedRecordOverhead = 15;
+    VersionEdit edit;
+    edit.SetLastCompactedManifestFileSize(log->file()->GetFileSize() +
+                                          kEstimatedRecordOverhead);
+    std::string record;
+    if (!edit.EncodeTo(&record)) {
+      return Status::Corruption("Unable to Encode VersionEdit:" +
+                                edit.DebugString(true));
+    }
+    io_s = log->AddRecord(write_options, record);
+    if (!io_s.ok()) {
+      return io_s;
+    }
+  }
+
   return Status::OK();
 }
 

db_stress_tool/batched_ops_stress.cc

@@ -13,7 +13,9 @@
 namespace ROCKSDB_NAMESPACE {
 class BatchedOpsStressTest : public StressTest {
  public:
-  BatchedOpsStressTest() = default;
+  BatchedOpsStressTest(int db_index, const std::string& db_path,
+                       const std::string& ev_path, const std::string& sec_path)
+      : StressTest(db_index, db_path, ev_path, sec_path) {}
   virtual ~BatchedOpsStressTest() = default;
 
   bool IsStateTracked() const override { return false; }
@@ -722,7 +724,11 @@ class BatchedOpsStressTest : public StressTest {
   }
 };
 
-StressTest* CreateBatchedOpsStressTest() { return new BatchedOpsStressTest(); }
+StressTest* CreateBatchedOpsStressTest(int db_index, const std::string& db_path,
+                                       const std::string& ev_path,
+                                       const std::string& sec_path) {
+  return new BatchedOpsStressTest(db_index, db_path, ev_path, sec_path);
+}
 
 }  // namespace ROCKSDB_NAMESPACE
 #endif  // GFLAGS

db_stress_tool/cf_consistency_stress.cc

@@ -21,7 +21,10 @@
 namespace ROCKSDB_NAMESPACE {
 class CfConsistencyStressTest : public StressTest {
  public:
-  CfConsistencyStressTest() : batch_id_(0) {}
+  CfConsistencyStressTest(int db_index, const std::string& db_path,
+                          const std::string& ev_path,
+                          const std::string& sec_path)
+      : StressTest(db_index, db_path, ev_path, sec_path), batch_id_(0) {}
 
   ~CfConsistencyStressTest() override = default;
 
@@ -227,10 +230,10 @@ class CfConsistencyStressTest : public StressTest {
                    key, &value0);
 
       // Temporarily disable error injection for verification
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
 
@@ -279,10 +282,10 @@ class CfConsistencyStressTest : public StressTest {
       }
 
       //  Enable back error injection disabled for verification
-      if (fault_fs_guard) {
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
       db_->ReleaseSnapshot(snapshot);
@@ -397,10 +400,10 @@ class CfConsistencyStressTest : public StressTest {
                          &cmp_result);
 
       //  Temporarily disable error injection for verification
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
 
@@ -559,10 +562,10 @@ class CfConsistencyStressTest : public StressTest {
       }
 
       //  Enable back error injection disabled for verification
-      if (fault_fs_guard) {
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
     }
@@ -1543,8 +1546,11 @@ class CfConsistencyStressTest : public StressTest {
   std::deque<DebugEvent> recent_debug_events_;
 };
 
-StressTest* CreateCfConsistencyStressTest() {
-  return new CfConsistencyStressTest();
+StressTest* CreateCfConsistencyStressTest(int db_index,
+                                          const std::string& db_path,
+                                          const std::string& ev_path,
+                                          const std::string& sec_path) {
+  return new CfConsistencyStressTest(db_index, db_path, ev_path, sec_path);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db_stress_tool/db_stress_common.cc

@@ -13,16 +13,17 @@
 
 #include <cmath>
 
+#include "db_stress_tool/db_stress_test_base.h"
 #include "file/file_util.h"
 #include "rocksdb/secondary_cache.h"
 #include "util/file_checksum_helper.h"
 #include "util/xxhash.h"
 
-ROCKSDB_NAMESPACE::Env* db_stress_listener_env = nullptr;
-ROCKSDB_NAMESPACE::Env* db_stress_env = nullptr;
-std::shared_ptr<ROCKSDB_NAMESPACE::FaultInjectionTestFS> fault_fs_guard;
+ROCKSDB_NAMESPACE::Env* raw_env = nullptr;
 std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache> compressed_secondary_cache;
 std::shared_ptr<ROCKSDB_NAMESPACE::Cache> block_cache;
+std::shared_ptr<ROCKSDB_NAMESPACE::WriteBufferManager> wbm;
+std::shared_ptr<ROCKSDB_NAMESPACE::RateLimiter> rate_limiter;
 enum ROCKSDB_NAMESPACE::CompressionType compression_type_e =
     ROCKSDB_NAMESPACE::kSnappyCompression;
 enum ROCKSDB_NAMESPACE::CompressionType bottommost_compression_type_e =
@@ -114,10 +115,10 @@ void PoolSizeChangeThread(void* v) {
     if (new_thread_pool_size < 1) {
       new_thread_pool_size = 1;
     }
-    db_stress_env->SetBackgroundThreads(new_thread_pool_size,
-                                        ROCKSDB_NAMESPACE::Env::Priority::LOW);
+    raw_env->SetBackgroundThreads(new_thread_pool_size,
+                                  ROCKSDB_NAMESPACE::Env::Priority::LOW);
     // Sleep up to 3 seconds
-    db_stress_env->SleepForMicroseconds(
+    raw_env->SleepForMicroseconds(
         thread->rand.Next() % FLAGS_compaction_thread_pool_adjust_interval *
             1000 +
         1);
@@ -144,7 +145,7 @@ void DbVerificationThread(void* v) {
     if (!shared->HasVerificationFailedYet()) {
       stress_test->ContinuouslyVerifyDb(thread);
     }
-    db_stress_env->SleepForMicroseconds(
+    raw_env->SleepForMicroseconds(
         thread->rand.Next() % FLAGS_continuous_verification_interval * 1000 +
         1);
   }
@@ -166,7 +167,7 @@ void CompressedCacheSetCapacityThread(void* v) {
         return;
       }
     }
-    db_stress_env->SleepForMicroseconds(FLAGS_secondary_cache_update_interval);
+    raw_env->SleepForMicroseconds(FLAGS_secondary_cache_update_interval);
     if (FLAGS_compressed_secondary_cache_size > 0) {
       Status s = compressed_secondary_cache->SetCapacity(0);
       size_t capacity;
@@ -174,7 +175,7 @@ void CompressedCacheSetCapacityThread(void* v) {
         s = compressed_secondary_cache->GetCapacity(capacity);
         assert(capacity == 0);
       }
-      db_stress_env->SleepForMicroseconds(10 * 1000 * 1000);
+      raw_env->SleepForMicroseconds(10 * 1000 * 1000);
       if (s.ok()) {
         s = compressed_secondary_cache->SetCapacity(
             FLAGS_compressed_secondary_cache_size);
@@ -201,7 +202,7 @@ void CompressedCacheSetCapacityThread(void* v) {
         block_cache->SetCapacity(capacity - adjustment);
         fprintf(stdout, "New cache capacity = %zu\n",
                 block_cache->GetCapacity());
-        db_stress_env->SleepForMicroseconds(10 * 1000 * 1000);
+        raw_env->SleepForMicroseconds(10 * 1000 * 1000);
         block_cache->SetCapacity(capacity);
       } else {
         Status s;
@@ -214,7 +215,7 @@ void CompressedCacheSetCapacityThread(void* v) {
         s = UpdateTieredCache(block_cache, /*capacity*/ -1,
                               new_comp_cache_ratio);
         if (s.ok()) {
-          db_stress_env->SleepForMicroseconds(10 * 1000 * 1000);
+          raw_env->SleepForMicroseconds(10 * 1000 * 1000);
         }
         if (s.ok()) {
           s = UpdateTieredCache(block_cache, /*capacity*/ -1,
@@ -231,36 +232,37 @@ void CompressedCacheSetCapacityThread(void* v) {
 
 #ifndef NDEBUG
 static void SetupFaultInjectionForRemoteCompaction(SharedState* shared) {
-  if (!fault_fs_guard) {
+  auto fault_fs = shared->GetStressTest()->GetDbFaultInjectionFs();
+  if (!fault_fs) {
     return;
   }
 
-  fault_fs_guard->SetThreadLocalErrorContext(
+  fault_fs->SetThreadLocalErrorContext(
       FaultInjectionIOType::kRead, shared->GetSeed(), FLAGS_read_fault_one_in,
       FLAGS_inject_error_severity == 1 /* retryable */,
       FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-  fault_fs_guard->EnableThreadLocalErrorInjection(FaultInjectionIOType::kRead);
+  fault_fs->EnableThreadLocalErrorInjection(FaultInjectionIOType::kRead);
 
-  fault_fs_guard->SetThreadLocalErrorContext(
+  fault_fs->SetThreadLocalErrorContext(
       FaultInjectionIOType::kWrite, shared->GetSeed(), FLAGS_write_fault_one_in,
       FLAGS_inject_error_severity == 1 /* retryable */,
       FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-  fault_fs_guard->EnableThreadLocalErrorInjection(FaultInjectionIOType::kWrite);
+  fault_fs->EnableThreadLocalErrorInjection(FaultInjectionIOType::kWrite);
 
-  fault_fs_guard->SetThreadLocalErrorContext(
+  fault_fs->SetThreadLocalErrorContext(
       FaultInjectionIOType::kMetadataRead, shared->GetSeed(),
       FLAGS_metadata_read_fault_one_in,
       FLAGS_inject_error_severity == 1 /* retryable */,
       FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-  fault_fs_guard->EnableThreadLocalErrorInjection(
+  fault_fs->EnableThreadLocalErrorInjection(
       FaultInjectionIOType::kMetadataRead);
 
-  fault_fs_guard->SetThreadLocalErrorContext(
+  fault_fs->SetThreadLocalErrorContext(
       FaultInjectionIOType::kMetadataWrite, shared->GetSeed(),
       FLAGS_metadata_write_fault_one_in,
       FLAGS_inject_error_severity == 1 /* retryable */,
       FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-  fault_fs_guard->EnableThreadLocalErrorInjection(
+  fault_fs->EnableThreadLocalErrorInjection(
       FaultInjectionIOType::kMetadataWrite);
 }
 #endif  // NDEBUG
@@ -268,7 +270,7 @@ static void SetupFaultInjectionForRemoteCompaction(SharedState* shared) {
 static CompactionServiceOptionsOverride CreateOverrideOptions(
     const Options& options, const CompactionServiceJobInfo& job_info) {
   CompactionServiceOptionsOverride override_options{
-      .env = db_stress_env,
+      .env = options.env,
       .file_checksum_gen_factory = options.file_checksum_gen_factory,
       .merge_operator = options.merge_operator,
       .compaction_filter = options.compaction_filter,
@@ -311,14 +313,8 @@ static CompactionServiceOptionsOverride CreateOverrideOptions(
 }
 
 static Status CleanupOutputDirectory(const std::string& output_directory) {
-#ifndef NDEBUG
-  // Temporarily disable fault injection to ensure deletion always succeeds
-  if (fault_fs_guard) {
-    fault_fs_guard->DisableAllThreadLocalErrorInjection();
-  }
-#endif  // NDEBUG
-
-  Status s = DestroyDir(db_stress_env, output_directory);
+  // Uses raw_env (no fault injection); cleanup must always succeed.
+  Status s = DestroyDir(raw_env, output_directory);
   if (!s.ok()) {
     fprintf(stderr,
             "Failed to destroy output directory %s when allow_resumption is "
@@ -327,7 +323,7 @@ static Status CleanupOutputDirectory(const std::string& output_directory) {
   }
 
   if (s.ok()) {
-    s = db_stress_env->CreateDir(output_directory);
+    s = raw_env->CreateDir(output_directory);
     if (!s.ok()) {
       fprintf(stderr,
               "Failed to recreate output directory %s when allow_resumption is "
@@ -336,13 +332,6 @@ static Status CleanupOutputDirectory(const std::string& output_directory) {
     }
   }
 
-#ifndef NDEBUG
-  // Re-enable fault injection after deletion
-  if (fault_fs_guard) {
-    fault_fs_guard->EnableAllThreadLocalErrorInjection();
-  }
-#endif  // NDEBUG
-
   return s;
 }
 
@@ -497,7 +486,7 @@ void RemoteCompactionWorkerThread(void* v) {
           shared, stress_test, rand, successful_compaction_end_to_end_micros);
     }
 
-    db_stress_env->SleepForMicroseconds(
+    raw_env->SleepForMicroseconds(
         thread->rand.Next() % FLAGS_remote_compaction_worker_interval * 1000 +
         1);
   }
@@ -679,7 +668,7 @@ bool VerifyIteratorAttributeGroups(
 }
 
 std::string GetNowNanos() {
-  uint64_t t = db_stress_env->NowNanos();
+  uint64_t t = raw_env->NowNanos();
   std::string ret;
   PutFixed64(&ret, t);
   return ret;
@@ -691,7 +680,7 @@ uint64_t GetWriteUnixTime(ThreadState* thread) {
                FLAGS_preclude_last_level_data_seconds);
   static uint64_t kFallbackTime = std::numeric_limits<uint64_t>::max();
   int64_t write_time = 0;
-  Status s = db_stress_env->GetCurrentTime(&write_time);
+  Status s = raw_env->GetCurrentTime(&write_time);
   uint32_t write_time_mode = thread->rand.Uniform(3);
   if (write_time_mode == 0 || !s.ok()) {
     return kFallbackTime;
@@ -806,6 +795,8 @@ std::shared_ptr<FileChecksumGenFactory> GetFileChecksumImpl(
   return std::make_shared<DbStressChecksumGenFactory>(internal_name);
 }
 
+// Expected values state files are always on local filesystem (Python owns
+// this dir), so use Env::Default() (PosixEnv) even when raw_env is remote.
 Status DeleteFilesInDirectory(const std::string& dirname) {
   std::vector<std::string> filenames;
   Status s = Env::Default()->GetChildren(dirname, &filenames);
@@ -880,8 +871,12 @@ Status DestroyUnverifiedSubdir(const std::string& dirname) {
 Status DbStressDestroyDb(const std::string& db_path) {
   Status s;
   Options options;
-  // NOTE: using db_stress_listener_env in order to see obsolete MANIFEST files
-  options.env = db_stress_listener_env;
+  // Use raw_env (no DbStressFSWrapper) because DbStressFSWrapper renames
+  // MANIFEST files to MANIFEST-xxx_renamed_ instead of deleting them during
+  // normal DB operation (to preserve history for debugging). Using raw_env
+  // here ensures DestroyDB actually deletes these files. DestroyDir below
+  // catches any remaining files not known to DestroyDB.
+  options.env = raw_env;
   // Remove DB files in a principled way to avoid issues
   if (FLAGS_use_blob_db) {
     s = blob_db::DestroyBlobDB(db_path, options, blob_db::BlobDBOptions());
@@ -891,9 +886,8 @@ Status DbStressDestroyDb(const std::string& db_path) {
   if (!s.ok()) {
     return s;
   }
-  // Remove everything else recursively, only reporting success if able to
-  // delete everything
-  return DestroyDir(db_stress_listener_env, db_path);
+  // Remove everything else recursively (catches MANIFEST_renamed_ files)
+  return DestroyDir(raw_env, db_path);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db_stress_tool/db_stress_common.h

@@ -49,6 +49,7 @@
 #include "rocksdb/advanced_options.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/env.h"
+#include "rocksdb/rate_limiter.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/slice_transform.h"
 #include "rocksdb/statistics.h"
@@ -61,6 +62,7 @@
 #include "rocksdb/utilities/transaction.h"
 #include "rocksdb/utilities/transaction_db.h"
 #include "rocksdb/write_batch.h"
+#include "rocksdb/write_buffer_manager.h"
 #include "test_util/testutil.h"
 #include "util/coding.h"
 #include "util/compression.h"
@@ -114,6 +116,7 @@ DECLARE_double(memtable_prefix_bloom_size_ratio);
 DECLARE_bool(memtable_whole_key_filtering);
 DECLARE_int32(open_files);
 DECLARE_bool(open_files_async);
+DECLARE_bool(async_wal_precreate);
 DECLARE_uint64(compressed_secondary_cache_size);
 DECLARE_int32(compressed_secondary_cache_numshardbits);
 DECLARE_int32(secondary_cache_update_interval);
@@ -190,6 +193,7 @@ DECLARE_string(db);
 DECLARE_string(secondaries_base);
 DECLARE_bool(test_secondary);
 DECLARE_string(expected_values_dir);
+DECLARE_int32(num_dbs);
 DECLARE_bool(expected_state_trace_debug);
 DECLARE_int64(expected_state_trace_debug_key);
 DECLARE_int32(expected_state_trace_debug_max_logs);
@@ -462,6 +466,7 @@ DECLARE_uint32(ingest_wbwi_one_in);
 DECLARE_bool(universal_reduce_file_locking);
 DECLARE_bool(use_multiscan);
 DECLARE_bool(multiscan_use_async_io);
+DECLARE_bool(read_scoped_block_buffer_provider);
 DECLARE_uint64(multiscan_max_prefetch_memory_bytes);
 
 // Compaction deletion trigger declarations for stress testing
@@ -472,18 +477,23 @@ DECLARE_int32(compaction_on_deletion_window_size);
 DECLARE_double(compaction_on_deletion_ratio);
 DECLARE_double(read_triggered_compaction_threshold);
 
+DECLARE_string(listener_uri);
+
 constexpr long KB = 1024;
 constexpr int kRandomValueMaxFactor = 3;
 constexpr int kValueMaxLen = 100;
 constexpr uint32_t kLargePrimeForCommonFactorSkew = 1872439133;
 
-// wrapped posix environment
-extern ROCKSDB_NAMESPACE::Env* db_stress_env;
-extern ROCKSDB_NAMESPACE::Env* db_stress_listener_env;
-extern std::shared_ptr<ROCKSDB_NAMESPACE::FaultInjectionTestFS> fault_fs_guard;
+// Base env from --env_uri/--fs_uri. No wrappers (no DbStressFSWrapper, no
+// fault injection). Could be PosixEnv or remote. Used for infrastructure ops
+// (threads, time, dirs, cleanup). Per-StressTest env adds fault injection +
+// DbStressFSWrapper on top for DB I/O.
+extern ROCKSDB_NAMESPACE::Env* raw_env;
 extern std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache>
     compressed_secondary_cache;
 extern std::shared_ptr<ROCKSDB_NAMESPACE::Cache> block_cache;
+extern std::shared_ptr<ROCKSDB_NAMESPACE::WriteBufferManager> wbm;
+extern std::shared_ptr<ROCKSDB_NAMESPACE::RateLimiter> rate_limiter;
 
 extern enum ROCKSDB_NAMESPACE::CompressionType compression_type_e;
 extern enum ROCKSDB_NAMESPACE::CompressionType bottommost_compression_type_e;
@@ -828,10 +838,21 @@ AttributeGroups GenerateAttributeGroups(
     const std::vector<ColumnFamilyHandle*>& cfhs, uint32_t value_base,
     const Slice& slice);
 
-StressTest* CreateCfConsistencyStressTest();
-StressTest* CreateBatchedOpsStressTest();
-StressTest* CreateNonBatchedOpsStressTest();
-StressTest* CreateMultiOpsTxnsStressTest();
+StressTest* CreateCfConsistencyStressTest(int db_index,
+                                          const std::string& db_path,
+                                          const std::string& ev_path,
+                                          const std::string& sec_path);
+StressTest* CreateBatchedOpsStressTest(int db_index, const std::string& db_path,
+                                       const std::string& ev_path,
+                                       const std::string& sec_path);
+StressTest* CreateNonBatchedOpsStressTest(int db_index,
+                                          const std::string& db_path,
+                                          const std::string& ev_path,
+                                          const std::string& sec_path);
+StressTest* CreateMultiOpsTxnsStressTest(int db_index,
+                                         const std::string& db_path,
+                                         const std::string& ev_path,
+                                         const std::string& sec_path);
 void CheckAndSetOptionsForMultiOpsTxnStressTest();
 void InitializeHotKeyGenerator(double alpha);
 int64_t GetOneHotKeyID(double rand_seed, int64_t max_key);

db_stress_tool/db_stress_compaction_service.cc

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) Meta Platforms, Inc. and affiliates.
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

db_stress_tool/db_stress_driver.cc

@@ -10,12 +10,14 @@
 
 #include "db_stress_tool/db_stress_shared_state.h"
 #ifdef GFLAGS
+#include <mutex>
+
 #include "db_stress_tool/db_stress_common.h"
 #include "utilities/fault_injection_fs.h"
 
 namespace ROCKSDB_NAMESPACE {
 void ThreadBody(void* v) {
-  ThreadStatusUtil::RegisterThread(db_stress_env, ThreadStatus::USER);
+  ThreadStatusUtil::RegisterThread(raw_env, ThreadStatus::USER);
   ThreadState* thread = static_cast<ThreadState*>(v);
   SharedState* shared = thread->shared;
 
@@ -64,17 +66,21 @@ void ThreadBody(void* v) {
   ThreadStatusUtil::UnregisterThread();
 }
 bool RunStressTestImpl(SharedState* shared) {
-  SystemClock* clock = db_stress_env->GetSystemClock().get();
+  SystemClock* clock = raw_env->GetSystemClock().get();
   StressTest* stress = shared->GetStressTest();
+  const std::string db_label =
+      (FLAGS_num_dbs > 1) ? "[" + stress->GetDbLabel() + "] " : "";
 
   if (shared->ShouldVerifyAtBeginning() && FLAGS_preserve_unverified_changes) {
-    Status s = InitUnverifiedSubdir(FLAGS_db);
-    if (s.ok() && !FLAGS_expected_values_dir.empty()) {
-      s = InitUnverifiedSubdir(FLAGS_expected_values_dir);
+    const auto& db_path = stress->GetDbPath();
+    const auto& ev_dir = stress->GetExpectedValuesDir();
+    Status s = InitUnverifiedSubdir(db_path);
+    if (s.ok() && !ev_dir.empty()) {
+      s = InitUnverifiedSubdir(ev_dir);
     }
     if (!s.ok()) {
-      fprintf(stderr, "Failed to setup unverified state dir: %s\n",
-              s.ToString().c_str());
+      fprintf(stderr, "%sFailed to setup unverified state dir: %s\n",
+              db_label.c_str(), s.ToString().c_str());
       exit(1);
     }
   }
@@ -84,24 +90,15 @@ bool RunStressTestImpl(SharedState* shared) {
 
   uint32_t n = FLAGS_threads;
   uint64_t now = clock->NowMicros();
-  fprintf(stdout, "%s Initializing worker threads\n",
-          clock->TimeToString(now / 1000000).c_str());
+  fprintf(stdout, "%s %sInitializing worker threads\n",
+          clock->TimeToString(now / 1000000).c_str(), db_label.c_str());
 
   shared->SetThreads(n);
 
-  if (FLAGS_compaction_thread_pool_adjust_interval > 0) {
-    shared->IncBgThreads();
-  }
-
   if (FLAGS_continuous_verification_interval > 0) {
     shared->IncBgThreads();
   }
 
-  if (FLAGS_compressed_secondary_cache_size > 0 ||
-      FLAGS_compressed_secondary_cache_ratio > 0.0) {
-    shared->IncBgThreads();
-  }
-
   uint32_t remote_compaction_worker_thread_count =
       FLAGS_remote_compaction_worker_threads;
   if (remote_compaction_worker_thread_count > 0) {
@@ -113,25 +110,39 @@ bool RunStressTestImpl(SharedState* shared) {
   std::vector<ThreadState*> threads(n);
   for (uint32_t i = 0; i < n; i++) {
     threads[i] = new ThreadState(i, shared);
-    db_stress_env->StartThread(ThreadBody, threads[i]);
+    raw_env->StartThread(ThreadBody, threads[i]);
   }
 
+  // Spawn at most one PoolSizeChangeThread globally. All DBs share the
+  // same raw_env, so one thread resizing the pool is sufficient.
+  // IncBgThreads inside call_once so only the launching DB's SharedState
+  // tracks this thread (avoids deadlock for non-first DBs).
   ThreadState bg_thread(0, shared);
+  static std::once_flag pool_size_thread_flag;
   if (FLAGS_compaction_thread_pool_adjust_interval > 0) {
-    db_stress_env->StartThread(PoolSizeChangeThread, &bg_thread);
+    std::call_once(pool_size_thread_flag, [&]() {
+      shared->IncBgThreads();
+      raw_env->StartThread(PoolSizeChangeThread, &bg_thread);
+    });
   }
 
   ThreadState continuous_verification_thread(0, shared);
   if (FLAGS_continuous_verification_interval > 0) {
-    db_stress_env->StartThread(DbVerificationThread,
-                               &continuous_verification_thread);
+    raw_env->StartThread(DbVerificationThread, &continuous_verification_thread);
   }
 
+  // Spawn at most one CompressedCacheSetCapacityThread globally. The cache
+  // is shared across all DBs, and the thread's SetCapacity(0)/assert(==0)
+  // sequence would race if multiple DBs each spawned their own copy.
   ThreadState compressed_cache_set_capacity_thread(0, shared);
+  static std::once_flag compressed_cache_thread_flag;
   if (FLAGS_compressed_secondary_cache_size > 0 ||
       FLAGS_compressed_secondary_cache_ratio > 0.0) {
-    db_stress_env->StartThread(CompressedCacheSetCapacityThread,
-                               &compressed_cache_set_capacity_thread);
+    std::call_once(compressed_cache_thread_flag, [&]() {
+      shared->IncBgThreads();
+      raw_env->StartThread(CompressedCacheSetCapacityThread,
+                           &compressed_cache_set_capacity_thread);
+    });
   }
 
   std::vector<ThreadState*> remote_compaction_worker_threads;
@@ -141,7 +152,7 @@ bool RunStressTestImpl(SharedState* shared) {
     for (uint32_t i = 0; i < remote_compaction_worker_thread_count; i++) {
       ThreadState* ts = new ThreadState(i, shared);
       remote_compaction_worker_threads.push_back(ts);
-      db_stress_env->StartThread(RemoteCompactionWorkerThread, ts);
+      raw_env->StartThread(RemoteCompactionWorkerThread, ts);
     }
   }
 
@@ -156,16 +167,19 @@ bool RunStressTestImpl(SharedState* shared) {
     }
     if (shared->ShouldVerifyAtBeginning()) {
       if (shared->HasVerificationFailedYet()) {
-        fprintf(stderr, "Crash-recovery verification failed :(\n");
+        fprintf(stderr, "%sCrash-recovery verification failed :(\n",
+                db_label.c_str());
       } else {
-        fprintf(stdout, "Crash-recovery verification passed :)\n");
-        Status s = DestroyUnverifiedSubdir(FLAGS_db);
-        if (s.ok() && !FLAGS_expected_values_dir.empty()) {
-          s = DestroyUnverifiedSubdir(FLAGS_expected_values_dir);
+        fprintf(stdout, "%sCrash-recovery verification passed :)\n",
+                db_label.c_str());
+        const auto& ev_dir = stress->GetExpectedValuesDir();
+        Status s = DestroyUnverifiedSubdir(stress->GetDbPath());
+        if (s.ok() && !ev_dir.empty()) {
+          s = DestroyUnverifiedSubdir(ev_dir);
         }
         if (!s.ok()) {
-          fprintf(stderr, "Failed to cleanup unverified state dir: %s\n",
-                  s.ToString().c_str());
+          fprintf(stderr, "%sFailed to cleanup unverified state dir: %s\n",
+                  db_label.c_str(), s.ToString().c_str());
           exit(1);
         }
       }
@@ -174,15 +188,16 @@ bool RunStressTestImpl(SharedState* shared) {
     if (!FLAGS_verification_only) {
       // This is after the verification step to avoid making all those `Get()`s
       // and `MultiGet()`s contend on the DB-wide trace mutex.
-      if (!FLAGS_expected_values_dir.empty()) {
+      if (!stress->GetExpectedValuesDir().empty()) {
         stress->TrackExpectedState(shared);
       }
 
       if (FLAGS_sync_fault_injection || FLAGS_write_fault_one_in > 0) {
-        fault_fs_guard->SetFilesystemDirectWritable(false);
-        fault_fs_guard->SetInjectUnsyncedDataLoss(FLAGS_sync_fault_injection);
+        auto fault_fs = stress->GetDbFaultInjectionFs();
+        fault_fs->SetFilesystemDirectWritable(false);
+        fault_fs->SetInjectUnsyncedDataLoss(FLAGS_sync_fault_injection);
         if (FLAGS_exclude_wal_from_write_fault_injection) {
-          fault_fs_guard->SetFileTypesExcludedFromWriteFaultInjection(
+          fault_fs->SetFileTypesExcludedFromWriteFaultInjection(
               {FileType::kWalFile});
         }
       }
@@ -190,8 +205,8 @@ bool RunStressTestImpl(SharedState* shared) {
         Status s = stress->EnableAutoCompaction();
         assert(s.ok());
       }
-      fprintf(stdout, "%s Starting database operations\n",
-              clock->TimeToString(now / 1000000).c_str());
+      fprintf(stdout, "%s %sStarting database operations\n",
+              clock->TimeToString(now / 1000000).c_str(), db_label.c_str());
 
       shared->SetStart();
       shared->GetCondVar()->SignalAll();
@@ -201,14 +216,17 @@ bool RunStressTestImpl(SharedState* shared) {
 
       now = clock->NowMicros();
       if (FLAGS_test_batches_snapshots) {
-        fprintf(stdout, "%s Limited verification already done during gets\n",
-                clock->TimeToString((uint64_t)now / 1000000).c_str());
+        fprintf(stdout, "%s %sLimited verification already done during gets\n",
+                clock->TimeToString((uint64_t)now / 1000000).c_str(),
+                db_label.c_str());
       } else if (FLAGS_skip_verifydb) {
-        fprintf(stdout, "%s Verification skipped\n",
-                clock->TimeToString((uint64_t)now / 1000000).c_str());
+        fprintf(stdout, "%s %sVerification skipped\n",
+                clock->TimeToString((uint64_t)now / 1000000).c_str(),
+                db_label.c_str());
       } else {
-        fprintf(stdout, "%s Starting verification\n",
-                clock->TimeToString((uint64_t)now / 1000000).c_str());
+        fprintf(stdout, "%s %sStarting verification\n",
+                clock->TimeToString((uint64_t)now / 1000000).c_str(),
+                db_label.c_str());
       }
 
       shared->SetStartVerify();
@@ -230,7 +248,7 @@ bool RunStressTestImpl(SharedState* shared) {
     for (unsigned int i = 1; i < n; i++) {
       threads[0]->stats.Merge(threads[i]->stats);
     }
-    threads[0]->stats.Report("Stress Test");
+    threads[0]->stats.Report((db_label + "Stress Test").c_str());
   }
 
   for (unsigned int i = 0; i < n; i++) {
@@ -241,8 +259,8 @@ bool RunStressTestImpl(SharedState* shared) {
   now = clock->NowMicros();
   if (!FLAGS_skip_verifydb && !FLAGS_test_batches_snapshots &&
       !shared->HasVerificationFailedYet()) {
-    fprintf(stdout, "%s Verification successful\n",
-            clock->TimeToString(now / 1000000).c_str());
+    fprintf(stdout, "%s %sVerification successful\n",
+            clock->TimeToString(now / 1000000).c_str(), db_label.c_str());
   }
 
   if (!FLAGS_verification_only) {
@@ -260,6 +278,9 @@ bool RunStressTestImpl(SharedState* shared) {
       shared->GetCondVar()->Wait();
     }
   }
+  now = clock->NowMicros();
+  fprintf(stdout, "%s %sStress test bg threads finished\n",
+          clock->TimeToString(now / 1000000).c_str(), db_label.c_str());
 
   assert(remote_compaction_worker_threads.size() ==
          remote_compaction_worker_thread_count);
@@ -271,13 +292,13 @@ bool RunStressTestImpl(SharedState* shared) {
   }
 
   if (shared->HasVerificationFailedYet()) {
-    fprintf(stderr, "Verification failed :(\n");
+    fprintf(stderr, "%sVerification failed :(\n", db_label.c_str());
     return false;
   }
   return true;
 }
 bool RunStressTest(SharedState* shared) {
-  ThreadStatusUtil::RegisterThread(db_stress_env, ThreadStatus::USER);
+  ThreadStatusUtil::RegisterThread(raw_env, ThreadStatus::USER);
   bool result = RunStressTestImpl(shared);
   ThreadStatusUtil::UnregisterThread();
   return result;

db_stress_tool/db_stress_gflags.cc

@@ -206,6 +206,10 @@ DEFINE_int32(open_files, ROCKSDB_NAMESPACE::Options().max_open_files,
 DEFINE_bool(open_files_async, ROCKSDB_NAMESPACE::Options().open_files_async,
             "Options.open_files_async");
 
+DEFINE_bool(async_wal_precreate,
+            ROCKSDB_NAMESPACE::Options().async_wal_precreate,
+            "Options.async_wal_precreate");
+
 DEFINE_uint64(compressed_secondary_cache_size, 0,
               "Number of bytes to use as a cache of compressed data."
               " 0 means use default settings.");
@@ -1664,6 +1668,10 @@ DEFINE_double(read_triggered_compaction_threshold,
               ROCKSDB_NAMESPACE::Options().read_triggered_compaction_threshold,
               "Sets CF option read_triggered_compaction_threshold.");
 
+DEFINE_string(listener_uri, "",
+              "URI for an additional EventListener to attach (e.g. "
+              "auto_tuner://). Empty means none.");
+
 DEFINE_bool(
     auto_refresh_iterator_with_snapshot,
     ROCKSDB_NAMESPACE::ReadOptions().auto_refresh_iterator_with_snapshot,
@@ -1697,10 +1705,27 @@ DEFINE_bool(use_multiscan, false,
 DEFINE_bool(multiscan_use_async_io, false,
             "If set, enable async_io for MultiScan operations.");
 
+DEFINE_bool(read_scoped_block_buffer_provider, false,
+            "If set, configure ReadOptions::read_scoped_block_buffer_provider "
+            "with a stress-test provider for supported scan reads.");
+
 DEFINE_uint64(multiscan_max_prefetch_memory_bytes, 0,
               "If non-zero, sets the max_prefetch_memory_bytes on the "
               "IODispatcher used for MultiScan. This limits the total memory "
               "used for prefetching data blocks across all concurrent "
               "MultiScan ReadSets.");
 
+DEFINE_int32(num_dbs, 1,
+             "Number of DB instances to run in parallel. "
+             "For num_dbs=1: --db is the DB path directly (default). "
+             "For num_dbs>1: --db is a parent directory; db_stress "
+             "auto-creates db_0/, db_1/, ... subdirs underneath "
+             "(same for --expected_values_dir and secondaries). "
+             "Per-DB flags: threads, max_key, ops_per_thread, reopen, "
+             "column_families, and all DB options. "
+             "Shared across all instances: background env threads "
+             "(compaction, flush pool), cache, write_buffer_manager, "
+             "compressed_secondary_cache, rate_limiter, and "
+             "compaction_thread_pool_adjust_interval.");
+
 #endif  // GFLAGS

db_stress_tool/db_stress_listener.cc

@@ -7,6 +7,7 @@
 
 #include <cstdint>
 
+#include "db_stress_tool/db_stress_test_base.h"
 #include "file/file_util.h"
 #include "rocksdb/file_system.h"
 #include "util/coding_lean.h"
@@ -15,6 +16,21 @@ namespace ROCKSDB_NAMESPACE {
 
 #ifdef GFLAGS
 
+DbStressListener::DbStressListener(
+    const std::string& db_name, const std::vector<DbPath>& db_paths,
+    const std::vector<ColumnFamilyDescriptor>& column_families,
+    SharedState* shared)
+    : db_name_(db_name),
+      db_paths_(db_paths),
+      column_families_(column_families),
+      num_pending_file_creations_(0),
+      unique_ids_(shared->GetStressTest()->GetExpectedValuesDir().empty()
+                      ? db_name
+                      : shared->GetStressTest()->GetExpectedValuesDir()),
+      shared_(shared),
+      db_fault_injection_fs_(shared->GetStressTest()->GetDbFaultInjectionFs()) {
+}
+
 UniqueIdVerifier::UniqueIdVerifier(const std::string& dir)
     : path_(dir + "/.unique_ids") {
   // We expect such a small number of files generated during this test

db_stress_tool/db_stress_listener.h

@@ -6,7 +6,9 @@
 #ifdef GFLAGS
 #pragma once
 
+#include <cinttypes>
 #include <mutex>
+#include <unordered_map>
 #include <unordered_set>
 
 #include "db_stress_tool/db_stress_compaction_service.h"
@@ -19,13 +21,12 @@
 #include "rocksdb/listener.h"
 #include "rocksdb/table_properties.h"
 #include "rocksdb/unique_id.h"
+#include "util/atomic.h"
 #include "util/gflags_compat.h"
 #include "util/random.h"
 #include "utilities/fault_injection_fs.h"
 DECLARE_int32(compact_files_one_in);
 
-extern std::shared_ptr<ROCKSDB_NAMESPACE::FaultInjectionTestFS> fault_fs_guard;
-
 namespace ROCKSDB_NAMESPACE {
 
 // Verify across process executions that all seen IDs are unique
@@ -55,27 +56,22 @@ class DbStressListener : public EventListener {
   DbStressListener(const std::string& db_name,
                    const std::vector<DbPath>& db_paths,
                    const std::vector<ColumnFamilyDescriptor>& column_families,
-                   SharedState* shared)
-      : db_name_(db_name),
-        db_paths_(db_paths),
-        column_families_(column_families),
-        num_pending_file_creations_(0),
-        unique_ids_(FLAGS_expected_values_dir.empty()
-                        ? db_name
-                        : FLAGS_expected_values_dir),
-        shared_(shared) {}
+                   SharedState* shared);
 
   const char* Name() const override { return kClassName(); }
   static const char* kClassName() { return "DBStressListener"; }
 
   ~DbStressListener() override { assert(num_pending_file_creations_ == 0); }
+
+  void OnDBShutdownBegin(DB* /*db*/) override { shutting_down_.Store(true); }
+
   void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
     assert(IsValidColumnFamilyName(info.cf_name));
     VerifyFilePath(info.file_path);
     // pretending doing some work here
     RandomSleep();
-    if (fault_fs_guard) {
-      fault_fs_guard->DisableAllThreadLocalErrorInjection();
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->DisableAllThreadLocalErrorInjection();
     }
     shared_->SetPersistedSeqno(info.largest_seqno);
   }
@@ -83,46 +79,118 @@ class DbStressListener : public EventListener {
   void OnFlushBegin(DB* /*db*/,
                     const FlushJobInfo& /*flush_job_info*/) override {
     RandomSleep();
-    if (fault_fs_guard) {
-      fault_fs_guard->SetThreadLocalErrorContext(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kRead, static_cast<uint32_t>(FLAGS_seed),
           FLAGS_read_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kRead);
 
-      fault_fs_guard->SetThreadLocalErrorContext(
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kWrite, static_cast<uint32_t>(FLAGS_seed),
           FLAGS_write_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kWrite);
 
-      fault_fs_guard->SetThreadLocalErrorContext(
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kMetadataRead,
           static_cast<uint32_t>(FLAGS_seed), FLAGS_metadata_read_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataRead);
 
-      fault_fs_guard->SetThreadLocalErrorContext(
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kMetadataWrite,
           static_cast<uint32_t>(FLAGS_seed), FLAGS_metadata_write_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataWrite);
     }
   }
 
-  void OnTableFileDeleted(const TableFileDeletionInfo& /*info*/) override {
+  void OnTableFileDeleted(const TableFileDeletionInfo& info) override {
+    // A file must not be deleted while it is still between
+    // OnCompactionBegin and OnCompactionPreCommit (i.e. actively being
+    // compacted with being_compacted == true). (Perhaps more realistically,
+    // this is checking for failure to call OnCompactionPreCommit.)
+    //
+    // During shutdown, compaction notifications are skipped so tracking
+    // state may be stale -- skip the check.
+    if (!shutting_down_.Load()) {
+      std::lock_guard<std::mutex> lock(compacting_files_mu_);
+      uint64_t file_number = FileNumberFromPath(info.file_path);
+      if (file_number != 0 &&
+          compacting_files_.find(file_number) != compacting_files_.end()) {
+        fprintf(stderr,
+                "OnTableFileDeleted for file tracked as being compacted "
+                "(between Begin and PreCommit): file_number=%" PRIu64 "\n",
+                file_number);
+        fflush(stderr);
+        std::abort();
+      }
+    }
     RandomSleep();
   }
 
-  void OnCompactionBegin(DB* /*db*/, const CompactionJobInfo& /*ci*/) override {
+  void OnCompactionBegin(DB* /*db*/, const CompactionJobInfo& ci) override {
+    // Sanity check inspired by a Meta-internal check: the same input file must
+    // not be in two concurrent compactions. Inserting input file numbers into a
+    // shared set on Begin and removing them on PreCommit (rather than on
+    // Completed) is what exercises the new OnCompactionPreCommit
+    // callback. Removing on Completed would race with another picker that
+    // grabs the same file as soon as ReleaseCompactionFiles flips
+    // FileMetaData::being_compacted back to false; PreCommit runs
+    // while being_compacted is still true and so closes that race.
+    {
+      std::lock_guard<std::mutex> lock(compacting_files_mu_);
+      for (const auto& info : ci.input_file_infos) {
+        auto [_, inserted] = compacting_files_.insert(info.file_number);
+        if (!inserted) {
+          fprintf(stderr,
+                  "Concurrent compaction of SST file detected: cf=%s "
+                  "file_number=%" PRIu64 "\n",
+                  ci.cf_name.c_str(), info.file_number);
+          fflush(stderr);
+          std::abort();
+        }
+      }
+    }
+    RandomSleep();
+  }
+
+  void OnCompactionPreCommit(DB* /*db*/, const CompactionJobInfo& ci) override {
+    // Pair with OnCompactionBegin's bookkeeping: move files from
+    // compacting_files_ and record the job for Completed verification.
+    {
+      std::lock_guard<std::mutex> lock(compacting_files_mu_);
+      std::unordered_set<uint64_t> job_files;
+      for (const auto& info : ci.input_file_infos) {
+        size_t erased = compacting_files_.erase(info.file_number);
+        if (erased != 1) {
+          fprintf(stderr,
+                  "OnCompactionPreCommit for file not in tracking set: "
+                  "cf=%s file_number=%" PRIu64 "\n",
+                  ci.cf_name.c_str(), info.file_number);
+          fflush(stderr);
+          std::abort();
+        }
+        job_files.insert(info.file_number);
+      }
+      auto [_, inserted] =
+          precommitted_jobs_.emplace(ci.job_id, std::move(job_files));
+      if (!inserted) {
+        fprintf(stderr, "OnCompactionPreCommit: duplicate job_id %d\n",
+                ci.job_id);
+        fflush(stderr);
+        std::abort();
+      }
+    }
     RandomSleep();
   }
 
@@ -135,49 +203,77 @@ class DbStressListener : public EventListener {
     for (const auto& file_path : ci.output_files) {
       VerifyFilePath(file_path);
     }
+
+    // Verify that OnCompactionPreCommit fired before OnCompactionCompleted
+    // for the same job, with matching input files.
+    {
+      std::lock_guard<std::mutex> lock(compacting_files_mu_);
+      auto it = precommitted_jobs_.find(ci.job_id);
+      if (it == precommitted_jobs_.end()) {
+        fprintf(stderr,
+                "OnCompactionCompleted without prior OnCompactionPreCommit: "
+                "cf=%s job_id=%d\n",
+                ci.cf_name.c_str(), ci.job_id);
+        fflush(stderr);
+        std::abort();
+      }
+      // Verify input file sets match between PreCommit and Completed.
+      for (const auto& info : ci.input_file_infos) {
+        if (it->second.find(info.file_number) == it->second.end()) {
+          fprintf(stderr,
+                  "OnCompactionCompleted: input file %" PRIu64
+                  " not in PreCommit set for job_id=%d\n",
+                  info.file_number, ci.job_id);
+          fflush(stderr);
+          std::abort();
+        }
+      }
+      precommitted_jobs_.erase(it);
+    }
+
     // pretending doing some work here
     RandomSleep();
   }
 
   void OnSubcompactionBegin(const SubcompactionJobInfo& /* si */) override {
-    if (fault_fs_guard) {
-      fault_fs_guard->SetThreadLocalErrorContext(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kRead, static_cast<uint32_t>(FLAGS_seed),
           FLAGS_read_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kRead);
 
-      fault_fs_guard->SetThreadLocalErrorContext(
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kWrite, static_cast<uint32_t>(FLAGS_seed),
           FLAGS_write_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kWrite);
 
-      fault_fs_guard->SetThreadLocalErrorContext(
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kMetadataRead,
           static_cast<uint32_t>(FLAGS_seed), FLAGS_metadata_read_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataRead);
 
-      fault_fs_guard->SetThreadLocalErrorContext(
+      db_fault_injection_fs_->SetThreadLocalErrorContext(
           FaultInjectionIOType::kMetadataWrite,
           static_cast<uint32_t>(FLAGS_seed), FLAGS_metadata_write_fault_one_in,
           FLAGS_inject_error_severity == 1 /* retryable */,
           FLAGS_inject_error_severity == 2 /* has_data_loss*/);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataWrite);
     }
   }
 
   void OnSubcompactionCompleted(const SubcompactionJobInfo& /* si */) override {
-    if (fault_fs_guard) {
-      fault_fs_guard->DisableAllThreadLocalErrorInjection();
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->DisableAllThreadLocalErrorInjection();
     }
   }
 
@@ -270,11 +366,12 @@ class DbStressListener : public EventListener {
                             Status /* bg_error */,
                             bool* /* auto_recovery */) override {
     RandomSleep();
-    if (FLAGS_error_recovery_with_no_fault_injection && fault_fs_guard) {
-      fault_fs_guard->DisableAllThreadLocalErrorInjection();
+    if (FLAGS_error_recovery_with_no_fault_injection &&
+        db_fault_injection_fs_) {
+      db_fault_injection_fs_->DisableAllThreadLocalErrorInjection();
       // TODO(hx235): only exempt the flush thread during error recovery instead
       // of all the flush threads from error injection
-      fault_fs_guard->SetIOActivitiesExcludedFromFaultInjection(
+      db_fault_injection_fs_->SetIOActivitiesExcludedFromFaultInjection(
           {Env::IOActivity::kFlush});
     }
   }
@@ -282,9 +379,10 @@ class DbStressListener : public EventListener {
   void OnErrorRecoveryEnd(
       const BackgroundErrorRecoveryInfo& /*info*/) override {
     RandomSleep();
-    if (FLAGS_error_recovery_with_no_fault_injection && fault_fs_guard) {
-      fault_fs_guard->EnableAllThreadLocalErrorInjection();
-      fault_fs_guard->SetIOActivitiesExcludedFromFaultInjection({});
+    if (FLAGS_error_recovery_with_no_fault_injection &&
+        db_fault_injection_fs_) {
+      db_fault_injection_fs_->EnableAllThreadLocalErrorInjection();
+      db_fault_injection_fs_->SetIOActivitiesExcludedFromFaultInjection({});
     }
   }
 
@@ -375,8 +473,43 @@ class DbStressListener : public EventListener {
   std::atomic<int> num_pending_file_creations_;
   UniqueIdVerifier unique_ids_;
   SharedState* shared_;
+  std::shared_ptr<FaultInjectionTestFS> db_fault_injection_fs_;
   mutable std::mutex bg_pressure_mu_;
   BackgroundJobPressure last_bg_pressure_;
+  // Files (by file_number) currently in flight from OnCompactionBegin to
+  // OnCompactionPreCommit. Used to detect concurrent compaction of
+  // the same SST file -- the bug fixed by the OnCompactionPreCommit
+  // callback. Protected by compacting_files_mu_.
+  std::mutex compacting_files_mu_;
+  std::unordered_set<uint64_t> compacting_files_;
+  // Set when DBImpl begins shutdown to suppress false positives from stale
+  // tracking when compaction callbacks are skipped during shutdown.
+  Atomic<bool> shutting_down_{false};
+  // Jobs that have passed OnCompactionPreCommit but not yet
+  // OnCompactionCompleted. Maps job_id -> input file numbers.
+  // Used to verify Begin -> PreCommit -> Completed ordering per job.
+  // Protected by compacting_files_mu_.
+  std::unordered_map<int, std::unordered_set<uint64_t>> precommitted_jobs_;
+
+  // Extract file number from a file path like "/path/to/000123.sst".
+  // Returns 0 if the path cannot be parsed.
+  static uint64_t FileNumberFromPath(const std::string& file_path) {
+    size_t pos = file_path.find_last_of('/');
+    // Avoid copying file_path when no '/' separator is found
+    std::string file_name_buf;
+    if (pos != std::string::npos) {
+      file_name_buf = file_path.substr(pos + 1);
+    }
+    const std::string& file_name =
+        (pos == std::string::npos) ? file_path : file_name_buf;
+    uint64_t file_number = 0;
+    FileType file_type;
+    if (ParseFileName(file_name, &file_number, &file_type) &&
+        file_type == kTableFile) {
+      return file_number;
+    }
+    return 0;
+  }
 };
 }  // namespace ROCKSDB_NAMESPACE
 #endif  // GFLAGS

db_stress_tool/db_stress_shared_state.cc

@@ -11,7 +11,109 @@
 #ifdef GFLAGS
 #include "db_stress_tool/db_stress_shared_state.h"
 
+#include "db_stress_tool/db_stress_test_base.h"
+
 namespace ROCKSDB_NAMESPACE {
 thread_local bool SharedState::ignore_read_error;
+
+SharedState::SharedState(Env* /*env*/, StressTest* stress_test)
+    : cv_(&mu_),
+      seed_(static_cast<uint32_t>(FLAGS_seed)),
+      max_key_(FLAGS_max_key),
+      log2_keys_per_lock_(static_cast<uint32_t>(FLAGS_log2_keys_per_lock)),
+      num_threads_(0),
+      num_initialized_(0),
+      num_populated_(0),
+      vote_reopen_(0),
+      num_done_(0),
+      start_(false),
+      start_verify_(false),
+      num_bg_threads_(0),
+      should_stop_bg_thread_(false),
+      bg_thread_finished_(0),
+      stress_test_(stress_test),
+      verification_failure_(false),
+      should_stop_test_(false),
+      no_overwrite_ids_(GenerateNoOverwriteIds()),
+      expected_state_manager_(nullptr),
+      printing_verification_results_(false),
+      start_timestamp_(Env::Default()->NowNanos()) {
+  Status status;
+  // TODO: We should introduce a way to explicitly disable verification
+  // during shutdown. When that is disabled and FLAGS_expected_values_dir
+  // is empty (disabling verification at startup), we can skip tracking
+  // expected state. Only then should we permit bypassing the below feature
+  // compatibility checks.
+  const auto& expected_values_dir = stress_test_->GetExpectedValuesDir();
+  if (!expected_values_dir.empty()) {
+    if (!std::atomic<uint32_t>{}.is_lock_free() ||
+        !std::atomic<uint64_t>{}.is_lock_free()) {
+      std::ostringstream status_s;
+      status_s << "Cannot use --expected_values_dir on platforms without "
+                  "lock-free "
+               << (!std::atomic<uint32_t>{}.is_lock_free()
+                       ? "std::atomic<uint32_t>"
+                       : "std::atomic<uint64_t>");
+      status = Status::InvalidArgument(status_s.str());
+    }
+
+    if (status.ok() && FLAGS_clear_column_family_one_in > 0) {
+      status = Status::InvalidArgument(
+          "Cannot use --expected_values_dir on when "
+          "--clear_column_family_one_in is greater than zero.");
+    }
+  }
+  if (status.ok()) {
+    if (expected_values_dir.empty()) {
+      expected_state_manager_.reset(
+          new AnonExpectedStateManager(FLAGS_max_key, FLAGS_column_families));
+    } else {
+      expected_state_manager_.reset(new FileExpectedStateManager(
+          FLAGS_max_key, FLAGS_column_families, expected_values_dir));
+    }
+    status = expected_state_manager_->Open();
+  }
+  if (!status.ok()) {
+    fprintf(stderr, "Failed setting up expected state with error: %s\n",
+            status.ToString().c_str());
+    exit(1);  // NOLINT(concurrency-mt-unsafe)
+  }
+
+  if (FLAGS_test_batches_snapshots) {
+    fprintf(stdout, "No lock creation because test_batches_snapshots set\n");
+    return;
+  }
+
+  long num_locks = static_cast<long>(max_key_ >> log2_keys_per_lock_);
+  if (max_key_ & ((1 << log2_keys_per_lock_) - 1)) {
+    num_locks++;
+  }
+  fprintf(stdout, "Creating %ld locks\n", num_locks * FLAGS_column_families);
+  key_locks_.resize(FLAGS_column_families);
+
+  for (int i = 0; i < FLAGS_column_families; ++i) {
+    key_locks_[i].reset(new port::Mutex[num_locks]);
+  }
+  if (FLAGS_read_fault_one_in || FLAGS_metadata_read_fault_one_in) {
+#ifdef NDEBUG
+    // Unsupported in release mode because it relies on
+    // `IGNORE_STATUS_IF_ERROR` to distinguish faults not expected to lead to
+    // failure.
+    fprintf(stderr,
+            "Cannot set nonzero value for --read_fault_one_in in "
+            "release mode.");
+    exit(1);  // NOLINT(concurrency-mt-unsafe)
+#else         // NDEBUG
+    SyncPoint::GetInstance()->SetCallBack("FaultInjectionIgnoreError",
+                                          IgnoreReadErrorCallback);
+    SyncPoint::GetInstance()->EnableProcessing();
+#endif        // NDEBUG
+  }
+}
+
+bool SharedState::ShouldVerifyAtBeginning() const {
+  return !stress_test_->GetExpectedValuesDir().empty();
+}
+
 }  // namespace ROCKSDB_NAMESPACE
 #endif  // GFLAGS

db_stress_tool/db_stress_shared_state.h

@@ -24,7 +24,6 @@ DECLARE_uint64(log2_keys_per_lock);
 DECLARE_int32(threads);
 DECLARE_int32(column_families);
 DECLARE_int32(nooverwritepercent);
-DECLARE_string(expected_values_dir);
 DECLARE_int32(clear_column_family_one_in);
 DECLARE_bool(test_batches_snapshots);
 DECLARE_int32(compaction_thread_pool_adjust_interval);
@@ -78,99 +77,7 @@ class SharedState {
   // for those calls
   static thread_local bool ignore_read_error;
 
-  SharedState(Env* /*env*/, StressTest* stress_test)
-      : cv_(&mu_),
-        seed_(static_cast<uint32_t>(FLAGS_seed)),
-        max_key_(FLAGS_max_key),
-        log2_keys_per_lock_(static_cast<uint32_t>(FLAGS_log2_keys_per_lock)),
-        num_threads_(0),
-        num_initialized_(0),
-        num_populated_(0),
-        vote_reopen_(0),
-        num_done_(0),
-        start_(false),
-        start_verify_(false),
-        num_bg_threads_(0),
-        should_stop_bg_thread_(false),
-        bg_thread_finished_(0),
-        stress_test_(stress_test),
-        verification_failure_(false),
-        should_stop_test_(false),
-        no_overwrite_ids_(GenerateNoOverwriteIds()),
-        expected_state_manager_(nullptr),
-        printing_verification_results_(false),
-        start_timestamp_(Env::Default()->NowNanos()) {
-    Status status;
-    // TODO: We should introduce a way to explicitly disable verification
-    // during shutdown. When that is disabled and FLAGS_expected_values_dir
-    // is empty (disabling verification at startup), we can skip tracking
-    // expected state. Only then should we permit bypassing the below feature
-    // compatibility checks.
-    if (!FLAGS_expected_values_dir.empty()) {
-      if (!std::atomic<uint32_t>{}.is_lock_free() ||
-          !std::atomic<uint64_t>{}.is_lock_free()) {
-        std::ostringstream status_s;
-        status_s << "Cannot use --expected_values_dir on platforms without "
-                    "lock-free "
-                 << (!std::atomic<uint32_t>{}.is_lock_free()
-                         ? "std::atomic<uint32_t>"
-                         : "std::atomic<uint64_t>");
-        status = Status::InvalidArgument(status_s.str());
-      }
-
-      if (status.ok() && FLAGS_clear_column_family_one_in > 0) {
-        status = Status::InvalidArgument(
-            "Cannot use --expected_values_dir on when "
-            "--clear_column_family_one_in is greater than zero.");
-      }
-    }
-    if (status.ok()) {
-      if (FLAGS_expected_values_dir.empty()) {
-        expected_state_manager_.reset(
-            new AnonExpectedStateManager(FLAGS_max_key, FLAGS_column_families));
-      } else {
-        expected_state_manager_.reset(new FileExpectedStateManager(
-            FLAGS_max_key, FLAGS_column_families, FLAGS_expected_values_dir));
-      }
-      status = expected_state_manager_->Open();
-    }
-    if (!status.ok()) {
-      fprintf(stderr, "Failed setting up expected state with error: %s\n",
-              status.ToString().c_str());
-      exit(1);
-    }
-
-    if (FLAGS_test_batches_snapshots) {
-      fprintf(stdout, "No lock creation because test_batches_snapshots set\n");
-      return;
-    }
-
-    long num_locks = static_cast<long>(max_key_ >> log2_keys_per_lock_);
-    if (max_key_ & ((1 << log2_keys_per_lock_) - 1)) {
-      num_locks++;
-    }
-    fprintf(stdout, "Creating %ld locks\n", num_locks * FLAGS_column_families);
-    key_locks_.resize(FLAGS_column_families);
-
-    for (int i = 0; i < FLAGS_column_families; ++i) {
-      key_locks_[i].reset(new port::Mutex[num_locks]);
-    }
-    if (FLAGS_read_fault_one_in || FLAGS_metadata_read_fault_one_in) {
-#ifdef NDEBUG
-      // Unsupported in release mode because it relies on
-      // `IGNORE_STATUS_IF_ERROR` to distinguish faults not expected to lead to
-      // failure.
-      fprintf(stderr,
-              "Cannot set nonzero value for --read_fault_one_in in "
-              "release mode.");
-      exit(1);
-#else   // NDEBUG
-      SyncPoint::GetInstance()->SetCallBack("FaultInjectionIgnoreError",
-                                            IgnoreReadErrorCallback);
-      SyncPoint::GetInstance()->EnableProcessing();
-#endif  // NDEBUG
-    }
-  }
+  SharedState(Env* env, StressTest* stress_test);
 
   ~SharedState() {
 #ifndef NDEBUG
@@ -430,9 +337,7 @@ class SharedState {
     return bg_thread_finished_ == num_bg_threads_;
   }
 
-  bool ShouldVerifyAtBeginning() const {
-    return !FLAGS_expected_values_dir.empty();
-  }
+  bool ShouldVerifyAtBeginning() const;
 
   bool PrintingVerificationResults() {
     bool tmp = false;

db_stress_tool/db_stress_stat.h

@@ -15,6 +15,7 @@
 #include "rocksdb/statistics.h"
 #include "rocksdb/system_clock.h"
 #include "util/gflags_compat.h"
+#include "util/mutexlock.h"
 #include "util/random.h"
 
 DECLARE_bool(histogram);
@@ -181,6 +182,9 @@ class Stats {
     double rate = bytes_mb / elapsed;
     double throughput = (double)done_ / elapsed;
 
+    // Lock stdout so multi-DB reports don't interleave.
+    static port::Mutex report_mutex;
+    MutexLock l(&report_mutex);
     fprintf(stdout, "%-12s: ", name);
     fprintf(stdout, "%.3f micros/op %ld ops/sec\n", seconds_ * 1e6 / done_,
             (long)throughput);

db_stress_tool/db_stress_test_base.h

@@ -13,6 +13,7 @@
 
 #include "db_stress_tool/db_stress_common.h"
 #include "db_stress_tool/db_stress_shared_state.h"
+#include "env/composite_env_wrapper.h"
 #include "rocksdb/experimental.h"
 #include "rocksdb/user_defined_index.h"
 #include "utilities/fault_injection_fs.h"
@@ -22,6 +23,7 @@ class SystemClock;
 class Transaction;
 class TransactionDB;
 class OptimisticTransactionDB;
+class DbStressFSWrapper;
 struct TransactionDBOptions;
 using experimental::SstQueryFilterConfigsManager;
 
@@ -40,11 +42,26 @@ class StressTest {
   // from optimistic transactions when conflict detection retries are exhausted.
   static bool IsExpectedTxnError(const Status& s);
 
-  StressTest();
+  StressTest(int db_index, const std::string& db_path,
+             const std::string& ev_path, const std::string& sec_path);
 
   virtual ~StressTest() {}
 
-  std::shared_ptr<Cache> NewCache(size_t capacity, int32_t num_shard_bits);
+  const std::string& GetDbLabel() const;
+  const std::string& GetDbPath() const;
+  const std::string& GetExpectedValuesDir() const;
+  const std::string& GetSecondariesBase() const;
+
+  // See db_fault_injection_fs_ member.
+  std::shared_ptr<FaultInjectionTestFS> GetDbFaultInjectionFs() const {
+    return db_fault_injection_fs_;
+  }
+
+  // See db_env_ member.
+  Env* GetDbEnv() const;
+
+  static std::shared_ptr<Cache> NewCache(size_t capacity,
+                                         int32_t num_shard_bits);
 
   static std::vector<std::string> GetBlobCompressionTags();
 
@@ -71,6 +88,11 @@ class StressTest {
   Options GetOptions(int cf_id);
   void CleanUp();
 
+ private:
+  void InitializeListenersForOpen(
+      SharedState* shared,
+      const std::vector<ColumnFamilyDescriptor>& cf_descriptors);
+
  protected:
   static int GetMinInjectedErrorCount(int error_count_1, int error_count_2) {
     if (error_count_1 > 0 && error_count_2 > 0) {
@@ -84,39 +106,34 @@ class StressTest {
     }
   }
 
-  void UpdateIfInitialWriteFails(Env* db_stress_env, const Status& write_s,
+  void UpdateIfInitialWriteFails(Env* env, const Status& write_s,
                                  Status* initial_write_s,
                                  bool* initial_wal_write_may_succeed,
                                  uint64_t* wait_for_recover_start_time,
                                  bool commit_bypass_memtable = false) {
-    assert(db_stress_env && initial_write_s && initial_wal_write_may_succeed &&
+    assert(env && initial_write_s && initial_wal_write_may_succeed &&
            wait_for_recover_start_time);
-    // Only update `initial_write_s`, `initial_wal_write_may_succeed` when the
-    // first write fails
     if (!write_s.ok() && (*initial_write_s).ok()) {
       *initial_write_s = write_s;
-      // With commit_bypass_memtable, we create a new WAL after WAL write
-      // succeeds, that wal creation may fail due to injected error. So the
-      // initial wal write may succeed even if status is failed to write to wal
       *initial_wal_write_may_succeed =
           commit_bypass_memtable ||
           !FaultInjectionTestFS::IsFailedToWriteToWALError(*initial_write_s);
-      *wait_for_recover_start_time = db_stress_env->NowMicros();
+      *wait_for_recover_start_time = env->NowMicros();
     }
   }
 
-  void PrintWriteRecoveryWaitTimeIfNeeded(Env* db_stress_env,
+  void PrintWriteRecoveryWaitTimeIfNeeded(Env* env,
                                           const Status& initial_write_s,
                                           bool initial_wal_write_may_succeed,
                                           uint64_t wait_for_recover_start_time,
                                           const std::string& thread_name) {
-    assert(db_stress_env);
+    assert(env);
     bool waited_for_recovery = !initial_write_s.ok() &&
                                IsErrorInjectedAndRetryable(initial_write_s) &&
                                initial_wal_write_may_succeed;
     if (waited_for_recovery) {
       uint64_t elapsed_sec =
-          (db_stress_env->NowMicros() - wait_for_recover_start_time) / 1000000;
+          (env->NowMicros() - wait_for_recover_start_time) / 1000000;
       if (elapsed_sec > 10) {
         fprintf(stdout,
                 "%s thread slept to wait for write recovery for "
@@ -303,6 +320,35 @@ class StressTest {
     kLastOpSeekToLast
   };
 
+  // Enum used to track MANIFEST verification mode during DB reopen
+  enum ManifestVerifyMode {
+    MANIFEST_VERIFY_NONE,
+    // MANIFEST file should be reused (same file number), CURRENT should not
+    // change. Used when reuse_manifest_on_open=1. Warnings are logged on
+    // failure but test continues.
+    MANIFEST_VERIFY_REUSE,
+    // MANIFEST file should be reused AND no recovery writes should occur.
+    // Used when both reuse_manifest_on_open=1 and
+    // optimize_manifest_for_recovery=1. Warnings are logged on failure but test
+    // continues.
+    MANIFEST_VERIFY_NO_WRITE,
+    // Strict verification: MANIFEST file must be reused with ZERO writes
+    // (complete avoidance). Used when ALL conditions for complete avoidance
+    // are met. Failures are FATAL and will terminate the test.
+    // Conditions for STRICT mode:
+    // - Both reuse_manifest_on_open=1 and optimize_manifest_for_recovery=1
+    // - Not in best_efforts_recovery mode
+    // - avoid_flush_during_recovery=true (no flush during recovery)
+    // - write_dbid_to_manifest=0 (no DB_ID write on open)
+    // - metadata_write_fault_one_in=0 (no fault injection)
+    // - open_metadata_write_fault_one_in=0 (no fault injection)
+    // - MANIFEST not corrupted, not at size limit
+    // Note: avoid_flush_during_shutdown is NOT required. If it leaves data
+    // in WAL but avoid_flush_during_recovery=true prevents flushing it,
+    // MANIFEST still won't be written.
+    MANIFEST_VERIFY_STRICT
+  };
+
   // Compare the two iterator, iter and cmp_iter are in the same position,
   // unless iter might be made invalidate or undefined because of
   // upper or lower bounds, or prefix extractor.
@@ -413,7 +459,20 @@ class StressTest {
 
   void CleanUpColumnFamilies();
 
-  std::shared_ptr<Cache> cache_;
+  void RecordManifestStateBeforeReopen();
+  void VerifyManifestNotRewritten();
+
+  int db_index_;
+  std::string db_label_;
+  std::string db_path_;
+  std::string expected_values_path_;
+  std::string secondaries_path_;
+  // Wraps raw_env->GetFileSystem(). See DbStressFSWrapper.
+  std::shared_ptr<DbStressFSWrapper> db_stress_fs_;
+  // Wraps db_stress_fs_ when NeedsFaultInjection(). Null otherwise.
+  std::shared_ptr<FaultInjectionTestFS> db_fault_injection_fs_;
+  // Wraps the outermost FS above. Set as options_.env for all DB I/O.
+  std::unique_ptr<CompositeEnvWrapper> db_env_;
   std::shared_ptr<Cache> compressed_cache_;
   std::shared_ptr<const FilterPolicy> filter_policy_;
   std::unique_ptr<DB> db_owner_;
@@ -439,6 +498,12 @@ class StressTest {
   std::unique_ptr<DB> secondary_db_;
   std::vector<ColumnFamilyHandle*> secondary_cfhs_;
   bool is_db_stopped_;
+
+  // MANIFEST verification state for reopen
+  ManifestVerifyMode manifest_verify_mode_;
+  uint64_t manifest_file_number_before_reopen_;
+  uint64_t manifest_file_size_before_reopen_;
+  std::string current_file_content_before_reopen_;
 };
 
 // Load options from OPTIONS file and populate `options`.

db_stress_tool/db_stress_tool.cc

@@ -22,6 +22,7 @@
 
 #ifdef GFLAGS
 #include <iostream>
+#include <thread>
 
 #include "db_stress_tool/db_stress_common.h"
 #include "db_stress_tool/db_stress_driver.h"
@@ -33,11 +34,79 @@
 namespace ROCKSDB_NAMESPACE {
 namespace {
 static std::shared_ptr<ROCKSDB_NAMESPACE::Env> env_guard;
-static std::shared_ptr<ROCKSDB_NAMESPACE::Env> env_wrapper_guard;
 static std::shared_ptr<ROCKSDB_NAMESPACE::Env> legacy_env_wrapper_guard;
-static std::shared_ptr<ROCKSDB_NAMESPACE::CompositeEnvWrapper>
-    dbsl_env_wrapper_guard;
-static std::shared_ptr<CompositeEnvWrapper> fault_env_guard;
+// Raw pointers for signal-safe crash callback. Signal handlers can only
+// access file-static/global variables; can't capture StressTest instances.
+static std::vector<ROCKSDB_NAMESPACE::FaultInjectionTestFS*>
+    fault_fs_for_crash_report;
+
+int ValidateNumDbsFlags() {
+  if (FLAGS_num_dbs < 1) {
+    fprintf(stderr, "Error: --num_dbs must be >= 1\n");
+    return 1;
+  }
+  if (FLAGS_num_dbs > 1) {
+    if (FLAGS_clear_column_family_one_in > 0) {
+      fprintf(stderr,
+              "Error: --num_dbs > 1 incompatible with "
+              "--clear_column_family_one_in\n");
+      return 1;
+    }
+    if (FLAGS_test_multi_ops_txns) {
+      fprintf(stderr,
+              "Error: --num_dbs > 1 incompatible with "
+              "--test_multi_ops_txns\n");
+      return 1;
+    }
+  }
+  return 0;
+}
+
+int DestroyAllDbs() {
+  bool all_ok = true;
+  const int num_dbs = FLAGS_num_dbs;
+  auto destroy_one = [&](const std::string& db_path) {
+    Status s = DbStressDestroyDb(db_path);
+    if (s.ok()) {
+      fprintf(stdout, "Successfully destroyed db at %s\n", db_path.c_str());
+    } else {
+      fprintf(stderr, "Failed to destroy db at %s: %s\n", db_path.c_str(),
+              s.ToString().c_str());
+      all_ok = false;
+    }
+  };
+  if (num_dbs == 1) {
+    destroy_one(FLAGS_db);
+  } else {
+    for (int i = 0; i < num_dbs; i++) {
+      destroy_one(FLAGS_db + "/db_" + std::to_string(i));
+    }
+    DestroyDir(raw_env, FLAGS_db);
+  }
+  return all_ok ? 0 : 1;
+}
+
+void RegisterCrashCallbacks(
+    const std::vector<std::unique_ptr<StressTest>>& stress_tests, int num_dbs) {
+  fault_fs_for_crash_report.resize(num_dbs, nullptr);
+  bool any_fault_fs = false;
+  for (int i = 0; i < num_dbs; i++) {
+    fault_fs_for_crash_report[i] =
+        stress_tests[i]->GetDbFaultInjectionFs().get();
+    if (fault_fs_for_crash_report[i]) {
+      any_fault_fs = true;
+    }
+  }
+  if (any_fault_fs) {
+    port::RegisterCrashCallback([]() {
+      for (auto* fs : fault_fs_for_crash_report) {
+        if (fs) {
+          fs->PrintRecentInjectedErrors();
+        }
+      }
+    });
+  }
+}
 
 int ReturnFlagValidationError(const char* message) {
   std::cerr << "Error: " << message << '\n';
@@ -67,8 +136,6 @@ int db_stress_tool(int argc, char** argv) {
       StringToCompressionType(FLAGS_bottommost_compression_type.c_str());
   checksum_type_e = StringToChecksumType(FLAGS_checksum_type.c_str());
 
-  Env* raw_env;
-
   int env_opts = !FLAGS_env_uri.empty() + !FLAGS_fs_uri.empty();
   if (env_opts > 1) {
     fprintf(stderr, "Error: --env_uri and --fs_uri are mutually exclusive\n");
@@ -82,57 +149,10 @@ int db_stress_tool(int argc, char** argv) {
             s.ToString().c_str());
     exit(1);
   }
-  dbsl_env_wrapper_guard = std::make_shared<CompositeEnvWrapper>(raw_env);
-  db_stress_listener_env = dbsl_env_wrapper_guard.get();
 
-  if (FLAGS_open_metadata_read_fault_one_in ||
-      FLAGS_open_metadata_write_fault_one_in || FLAGS_open_read_fault_one_in ||
-      FLAGS_open_write_fault_one_in || FLAGS_metadata_read_fault_one_in ||
-      FLAGS_metadata_write_fault_one_in || FLAGS_read_fault_one_in ||
-      FLAGS_write_fault_one_in || FLAGS_sync_fault_injection) {
-    FaultInjectionTestFS* fs =
-        new FaultInjectionTestFS(raw_env->GetFileSystem());
-    fault_fs_guard.reset(fs);
-    // Info logs are debugging artifacts, so exclude them from fault injection
-    // and keep error accounting focused on DB data and metadata.
-    fault_fs_guard->SetFileTypesExcludedFromFaultInjection(
-        {FileType::kInfoLogFile});
-    // Set it to direct writable here to initially bypass any fault injection
-    // during DB open This will correspondingly be overwritten in
-    // StressTest::Open() for open fault injection and in RunStressTestImpl()
-    // for proper fault injection setup.
-    fault_fs_guard->SetFilesystemDirectWritable(true);
-    fault_env_guard =
-        std::make_shared<CompositeEnvWrapper>(raw_env, fault_fs_guard);
-    raw_env = fault_env_guard.get();
-
-    // Register a crash callback so that recently injected errors are
-    // printed to stderr when the process crashes (SIGABRT, SIGSEGV, etc.).
-    // This helps diagnose stress test failures caused by fault injection.
-    port::RegisterCrashCallback([]() {
-      if (fault_fs_guard) {
-        fault_fs_guard->PrintRecentInjectedErrors();
-      }
-    });
-  }
-
-  auto db_stress_fs =
-      std::make_shared<DbStressFSWrapper>(raw_env->GetFileSystem());
-  env_wrapper_guard =
-      std::make_shared<CompositeEnvWrapper>(raw_env, db_stress_fs);
-  db_stress_env = env_wrapper_guard.get();
-
-  // Handle --destroy_db_and_exit early, before other option validation
+  // Handle --destroy_db_and_exit early
   if (FLAGS_destroy_db_and_exit) {
-    s = DbStressDestroyDb(FLAGS_db);
-    if (s.ok()) {
-      fprintf(stdout, "Successfully destroyed db at %s\n", FLAGS_db.c_str());
-      return 0;
-    } else {
-      fprintf(stderr, "Failed to destroy db at %s: %s\n", FLAGS_db.c_str(),
-              s.ToString().c_str());
-      return 1;
-    }
+    return DestroyAllDbs();
   }
 
   // Handle --delete_dir_and_exit early, before other option validation
@@ -149,14 +169,21 @@ int db_stress_tool(int argc, char** argv) {
     }
   }
 
+  {
+    int rc = ValidateNumDbsFlags();
+    if (rc != 0) {
+      return rc;
+    }
+  }
+
   FLAGS_rep_factory = StringToRepFactory(FLAGS_memtablerep.c_str());
 
   // The number of background threads should be at least as much the
   // max number of concurrent compactions.
-  db_stress_env->SetBackgroundThreads(FLAGS_max_background_compactions,
-                                      ROCKSDB_NAMESPACE::Env::Priority::LOW);
-  db_stress_env->SetBackgroundThreads(FLAGS_num_bottom_pri_threads,
-                                      ROCKSDB_NAMESPACE::Env::Priority::BOTTOM);
+  raw_env->SetBackgroundThreads(FLAGS_max_background_compactions,
+                                ROCKSDB_NAMESPACE::Env::Priority::LOW);
+  raw_env->SetBackgroundThreads(FLAGS_num_bottom_pri_threads,
+                                ROCKSDB_NAMESPACE::Env::Priority::BOTTOM);
   if (FLAGS_prefixpercent > 0 && FLAGS_prefix_size < 0) {
     fprintf(stderr,
             "Error: prefixpercent is non-zero while prefix_size is "
@@ -356,42 +383,75 @@ int db_stress_tool(int argc, char** argv) {
   // Choose a location for the test database if none given with --db=<path>
   if (FLAGS_db.empty()) {
     std::string default_db_path;
-    db_stress_env->GetTestDirectory(&default_db_path);
+    raw_env->GetTestDirectory(&default_db_path);
     default_db_path += "/dbstress";
     FLAGS_db = default_db_path;
   }
 
-  // Now that FLAGS_db is resolved, set the fault injection log file path
-  // so that PrintAll() writes to a file instead of stderr (signal-safe).
-  // Store the log in TEST_TMPDIR (outside the DB directory) so it survives
-  // DB reopen (which cleans untracked files) and gets included in the
-  // sandcastle db.tar.gz artifact for post-failure analysis.
-  if (fault_fs_guard) {
-    std::string log_dir;
-    const char* test_tmpdir = getenv("TEST_TMPDIR");
-    if (test_tmpdir && test_tmpdir[0] != '\0') {
-      log_dir = test_tmpdir;
-    } else {
-      log_dir = "/tmp";
-    }
-    std::string log_path = log_dir + "/fault_injection_" +
-                           std::to_string(getpid()) + "_" +
-                           std::to_string(time(nullptr)) + ".log";
-    fault_fs_guard->SetInjectedErrorLogPath(log_path);
-  }
-
-  if ((FLAGS_test_secondary || FLAGS_continuous_verification_interval > 0) &&
-      FLAGS_secondaries_base.empty()) {
-    std::string default_secondaries_path;
-    db_stress_env->GetTestDirectory(&default_secondaries_path);
-    default_secondaries_path += "/dbstress_secondaries";
-    s = db_stress_env->CreateDirIfMissing(default_secondaries_path);
+  // For num_dbs=1: --db and --expected_values_dir are paths used as-is.
+  // For num_dbs>1: they are parent directories; C++ creates db_0/, db_1/, ...
+  // subdirs underneath. DB::Open(create_if_missing) creates each DB dir.
+  // Python (db_crashtest.py) also creates EV dirs; C++ creates them here as a
+  // fallback for direct CLI usage.
+  const int num_dbs = FLAGS_num_dbs;
+  if (num_dbs > 1) {
+    s = raw_env->CreateDirIfMissing(FLAGS_db);
     if (!s.ok()) {
-      fprintf(stderr, "Failed to create directory %s: %s\n",
-              default_secondaries_path.c_str(), s.ToString().c_str());
+      fprintf(stderr, "Failed to create directory %s: %s\n", FLAGS_db.c_str(),
+              s.ToString().c_str());
       exit(1);
     }
-    FLAGS_secondaries_base = default_secondaries_path;
+  }
+  std::vector<std::string> db_paths;
+  std::vector<std::string> ev_paths;
+  for (int i = 0; i < num_dbs; i++) {
+    std::string suffix = (num_dbs == 1) ? "" : "/db_" + std::to_string(i);
+    db_paths.push_back(FLAGS_db + suffix);
+    if (!FLAGS_expected_values_dir.empty()) {
+      std::string ep = FLAGS_expected_values_dir + suffix;
+      s = Env::Default()->CreateDirIfMissing(ep);
+      if (!s.ok()) {
+        fprintf(stderr, "Failed to create directory %s: %s\n", ep.c_str(),
+                s.ToString().c_str());
+        exit(1);
+      }
+      ev_paths.push_back(std::move(ep));
+    }
+  }
+  if (ev_paths.empty()) {
+    ev_paths.resize(num_dbs);
+  }
+
+  // Secondary paths: C++ owns creation entirely.
+  std::vector<std::string> sec_paths;
+  if (FLAGS_test_secondary || FLAGS_continuous_verification_interval > 0) {
+    std::string sec_parent;
+    if (!FLAGS_secondaries_base.empty()) {
+      sec_parent = FLAGS_secondaries_base;
+    } else {
+      raw_env->GetTestDirectory(&sec_parent);
+      sec_parent += "/dbstress_secondaries";
+    }
+    s = raw_env->CreateDirIfMissing(sec_parent);
+    if (!s.ok()) {
+      fprintf(stderr, "Failed to create directory %s: %s\n", sec_parent.c_str(),
+              s.ToString().c_str());
+      exit(1);
+    }
+    for (int i = 0; i < num_dbs; i++) {
+      std::string suffix = (num_dbs == 1) ? "" : "/db_" + std::to_string(i);
+      std::string sec_path = sec_parent + suffix;
+      s = raw_env->CreateDirIfMissing(sec_path);
+      if (!s.ok()) {
+        fprintf(stderr, "Failed to create directory %s: %s\n", sec_path.c_str(),
+                s.ToString().c_str());
+        exit(1);
+      }
+      sec_paths.push_back(std::move(sec_path));
+    }
+  }
+  if (sec_paths.empty()) {
+    sec_paths.resize(num_dbs);
   }
 
   if (FLAGS_best_efforts_recovery &&
@@ -511,25 +571,72 @@ int db_stress_tool(int argc, char** argv) {
     key_gen_ctx.weights.emplace_back(key_gen_ctx.window -
                                      keys_per_level * (levels - 1));
   }
-  std::unique_ptr<ROCKSDB_NAMESPACE::SharedState> shared;
-  std::unique_ptr<ROCKSDB_NAMESPACE::StressTest> stress;
-  if (FLAGS_test_cf_consistency) {
-    stress.reset(CreateCfConsistencyStressTest());
-  } else if (FLAGS_test_batches_snapshots) {
-    stress.reset(CreateBatchedOpsStressTest());
-  } else if (FLAGS_test_multi_ops_txns) {
-    stress.reset(CreateMultiOpsTxnsStressTest());
-  } else {
-    stress.reset(CreateNonBatchedOpsStressTest());
-  }
-  // Initialize the Zipfian pre-calculated array
+  // Initialize shared resources (hot-key generator, block cache, WBM,
+  // rate limiter) once so that all DB instances share them.
   InitializeHotKeyGenerator(FLAGS_hot_key_alpha);
-  shared.reset(new SharedState(db_stress_env, stress.get()));
-  bool run_stress_test = RunStressTest(shared.get());
-  // Close DB in CleanUp() before destructor to prevent race between destructor
-  // and operations in listener callbacks (e.g. MultiOpsTxnsStressListener).
-  stress->CleanUp();
-  return run_stress_test ? 0 : 1;
+  block_cache =
+      StressTest::NewCache(FLAGS_cache_size, FLAGS_cache_numshardbits);
+  if (FLAGS_use_write_buffer_manager) {
+    wbm = std::make_shared<WriteBufferManager>(FLAGS_db_write_buffer_size,
+                                               block_cache);
+  }
+  if (FLAGS_rate_limiter_bytes_per_sec > 0) {
+    rate_limiter.reset(NewGenericRateLimiter(
+        FLAGS_rate_limiter_bytes_per_sec, 1000 /* refill_period_us */,
+        10 /* fairness */,
+        FLAGS_rate_limit_bg_reads ? RateLimiter::Mode::kReadsOnly
+                                  : RateLimiter::Mode::kWritesOnly));
+  }
+
+  // Phase 1: Create StressTest instances (one per DB).
+  std::vector<std::unique_ptr<StressTest>> stress_tests(num_dbs);
+  for (int i = 0; i < num_dbs; i++) {
+    if (FLAGS_test_cf_consistency) {
+      stress_tests[i].reset(CreateCfConsistencyStressTest(
+          i, db_paths[i], ev_paths[i], sec_paths[i]));
+    } else if (FLAGS_test_batches_snapshots) {
+      stress_tests[i].reset(CreateBatchedOpsStressTest(
+          i, db_paths[i], ev_paths[i], sec_paths[i]));
+    } else if (FLAGS_test_multi_ops_txns) {
+      stress_tests[i].reset(CreateMultiOpsTxnsStressTest(
+          i, db_paths[i], ev_paths[i], sec_paths[i]));
+    } else {
+      stress_tests[i].reset(CreateNonBatchedOpsStressTest(
+          i, db_paths[i], ev_paths[i], sec_paths[i]));
+    }
+  }
+
+  RegisterCrashCallbacks(stress_tests, num_dbs);
+
+  // Phase 2: Create SharedState for every DB before any worker thread starts.
+  std::vector<std::unique_ptr<SharedState>> shared_states(num_dbs);
+  for (int i = 0; i < num_dbs; i++) {
+    shared_states[i].reset(new SharedState(raw_env, stress_tests[i].get()));
+  }
+
+  // Phase 3: Launch each DB's stress test on its own thread.
+  std::vector<int> results(num_dbs, 0);
+  std::vector<std::thread> stress_test_runners;
+  stress_test_runners.reserve(num_dbs);
+  for (int i = 0; i < num_dbs; i++) {
+    stress_test_runners.emplace_back([i, &results, &shared_states]() {
+      results[i] = RunStressTest(shared_states[i].get()) ? 1 : 0;
+    });
+  }
+
+  // Phase 4: Wait for all DB threads, collect results, clean up.
+  bool all_passed = true;
+  for (int i = 0; i < num_dbs; i++) {
+    stress_test_runners[i].join();
+    if (!results[i]) {
+      all_passed = false;
+    }
+    stress_tests[i]->CleanUp();
+  }
+  for (auto& fs : fault_fs_for_crash_report) {
+    fs = nullptr;
+  }
+  return all_passed ? 0 : 1;
 }
 
 }  // namespace ROCKSDB_NAMESPACE

db_stress_tool/multi_ops_txns_stress.cc

@@ -40,7 +40,7 @@ DEFINE_int32(clear_wp_commit_cache_one_in, 0,
              "write-unprepared transactions.");
 
 extern "C" bool rocksdb_write_prepared_TEST_ShouldClearCommitCache(void) {
-  static Random rand(static_cast<uint32_t>(db_stress_env->NowMicros()));
+  static Random rand(static_cast<uint32_t>(raw_env->NowMicros()));
   return FLAGS_clear_wp_commit_cache_one_in > 0 &&
          rand.OneIn(FLAGS_clear_wp_commit_cache_one_in);
 }
@@ -1413,7 +1413,7 @@ Status MultiOpsTxnsStressTest::CommitAndCreateTimestampedSnapshotIfNeeded(
   Status s;
   if (FLAGS_create_timestamped_snapshot_one_in > 0 &&
       thread->rand.OneInOpt(FLAGS_create_timestamped_snapshot_one_in)) {
-    uint64_t ts = db_stress_env->NowNanos();
+    uint64_t ts = raw_env->NowNanos();
     std::shared_ptr<const Snapshot> snapshot;
     s = txn.CommitAndTryCreateSnapshot(/*notifier=*/nullptr, ts, &snapshot);
   } else {
@@ -1428,7 +1428,7 @@ Status MultiOpsTxnsStressTest::CommitAndCreateTimestampedSnapshotIfNeeded(
   assert(txn_db_);
   if (FLAGS_create_timestamped_snapshot_one_in > 0 &&
       thread->rand.OneInOpt(50000)) {
-    uint64_t now = db_stress_env->NowNanos();
+    uint64_t now = raw_env->NowNanos();
     constexpr uint64_t time_diff = static_cast<uint64_t>(1000) * 1000 * 1000;
     txn_db_->ReleaseTimestampedSnapshotsOlderThan(now - time_diff);
   }
@@ -1767,8 +1767,11 @@ void MultiOpsTxnsStressTest::ScanExistingDb(SharedState* shared, int threads) {
   }
 }
 
-StressTest* CreateMultiOpsTxnsStressTest() {
-  return new MultiOpsTxnsStressTest();
+StressTest* CreateMultiOpsTxnsStressTest(int db_index,
+                                         const std::string& db_path,
+                                         const std::string& ev_path,
+                                         const std::string& sec_path) {
+  return new MultiOpsTxnsStressTest(db_index, db_path, ev_path, sec_path);
 }
 
 void CheckAndSetOptionsForMultiOpsTxnStressTest() {

db_stress_tool/multi_ops_txns_stress.h

@@ -9,6 +9,7 @@
 
 #ifdef GFLAGS
 #include "db_stress_tool/db_stress_common.h"
+#include "util/atomic.h"
 
 namespace ROCKSDB_NAMESPACE {
 
@@ -191,7 +192,10 @@ class MultiOpsTxnsStressTest : public StressTest {
     uint32_t c_{0};
   };
 
-  MultiOpsTxnsStressTest() {}
+  MultiOpsTxnsStressTest(int db_index, const std::string& db_path,
+                         const std::string& ev_path,
+                         const std::string& sec_path)
+      : StressTest(db_index, db_path, ev_path, sec_path) {}
 
   ~MultiOpsTxnsStressTest() override {}
 
@@ -423,11 +427,16 @@ class MultiOpsTxnsStressListener : public EventListener {
 
   ~MultiOpsTxnsStressListener() override {}
 
+  void OnDBShutdownBegin(DB* /*db*/) override { shutting_down_.Store(true); }
+
   void OnFlushCompleted(DB* db, const FlushJobInfo& info) override {
     assert(db);
 #ifdef NDEBUG
     (void)db;
 #endif
+    if (shutting_down_.Load()) {
+      return;
+    }
     assert(info.cf_id == 0);
     const ReadOptions read_options(Env::IOActivity::kFlush);
     stress_test_->VerifyPkSkFast(read_options, info.job_id);
@@ -438,6 +447,9 @@ class MultiOpsTxnsStressListener : public EventListener {
 #ifdef NDEBUG
     (void)db;
 #endif
+    if (shutting_down_.Load()) {
+      return;
+    }
     assert(info.cf_id == 0);
     const ReadOptions read_options(Env::IOActivity::kCompaction);
     stress_test_->VerifyPkSkFast(read_options, info.job_id);
@@ -445,6 +457,7 @@ class MultiOpsTxnsStressListener : public EventListener {
 
  private:
   MultiOpsTxnsStressTest* const stress_test_ = nullptr;
+  Atomic<bool> shutting_down_{false};
 };
 
 }  // namespace ROCKSDB_NAMESPACE

db_stress_tool/no_batched_ops_stress.cc

@@ -24,7 +24,10 @@
 namespace ROCKSDB_NAMESPACE {
 class NonBatchedOpsStressTest : public StressTest {
  public:
-  NonBatchedOpsStressTest() = default;
+  NonBatchedOpsStressTest(int db_index, const std::string& db_path,
+                          const std::string& ev_path,
+                          const std::string& sec_path)
+      : StressTest(db_index, db_path, ev_path, sec_path) {}
 
   virtual ~NonBatchedOpsStressTest() = default;
 
@@ -265,20 +268,20 @@ class NonBatchedOpsStressTest : public StressTest {
             std::string from_db;
 
             // Temporarily disable error injection to verify the secondary
-            if (fault_fs_guard) {
-              fault_fs_guard->DisableThreadLocalErrorInjection(
+            if (db_fault_injection_fs_) {
+              db_fault_injection_fs_->DisableThreadLocalErrorInjection(
                   FaultInjectionIOType::kRead);
-              fault_fs_guard->DisableThreadLocalErrorInjection(
+              db_fault_injection_fs_->DisableThreadLocalErrorInjection(
                   FaultInjectionIOType::kMetadataRead);
             }
 
             s = secondary_db_->Get(options, secondary_cfhs_[cf], key, &from_db);
 
             // Re-enable error injection after verifying the secondary
-            if (fault_fs_guard) {
-              fault_fs_guard->EnableThreadLocalErrorInjection(
+            if (db_fault_injection_fs_) {
+              db_fault_injection_fs_->EnableThreadLocalErrorInjection(
                   FaultInjectionIOType::kRead);
-              fault_fs_guard->EnableThreadLocalErrorInjection(
+              db_fault_injection_fs_->EnableThreadLocalErrorInjection(
                   FaultInjectionIOType::kMetadataRead);
             }
 
@@ -688,10 +691,10 @@ class NonBatchedOpsStressTest : public StressTest {
     bool read_older_ts = MaybeUseOlderTimestampForPointLookup(
         thread, read_ts_str, read_ts_slice, read_opts_copy);
 
-    if (fault_fs_guard) {
-      fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
           FaultInjectionIOType::kRead);
-      fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+      db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
           FaultInjectionIOType::kMetadataRead);
       SharedState::ignore_read_error = false;
     }
@@ -703,11 +706,11 @@ class NonBatchedOpsStressTest : public StressTest {
         thread->shared->Get(rand_column_families[0], rand_keys[0]);
 
     int injected_error_count = 0;
-    if (fault_fs_guard) {
+    if (db_fault_injection_fs_) {
       injected_error_count = GetMinInjectedErrorCount(
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kRead),
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kMetadataRead));
       if (!SharedState::ignore_read_error && injected_error_count > 0 &&
           (s.ok() || s.IsNotFound())) {
@@ -716,9 +719,9 @@ class NonBatchedOpsStressTest : public StressTest {
         MutexLock l(thread->shared->GetMutex());
         fprintf(stderr, "Didn't get expected error from Get\n");
         fprintf(stderr, "Callstack that injected the fault\n");
-        fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+        db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+        db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
             FaultInjectionIOType::kMetadataRead);
         std::terminate();
       }
@@ -821,10 +824,10 @@ class NonBatchedOpsStressTest : public StressTest {
     std::unique_ptr<Transaction> txn;
     if (use_txn) {
       // TODO(hx235): test fault injection with MultiGet() with transactions
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
       WriteOptions wo;
@@ -850,20 +853,20 @@ class NonBatchedOpsStressTest : public StressTest {
     int injected_error_count = 0;
 
     if (!use_txn) {
-      if (fault_fs_guard) {
-        fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+        db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
             FaultInjectionIOType::kMetadataRead);
         SharedState::ignore_read_error = false;
       }
       db_->MultiGet(readoptionscopy, cfh, num_keys, keys.data(), values.data(),
                     statuses.data());
-      if (fault_fs_guard) {
+      if (db_fault_injection_fs_) {
         injected_error_count = GetMinInjectedErrorCount(
-            fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+            db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
                 FaultInjectionIOType::kRead),
-            fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+            db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
                 FaultInjectionIOType::kMetadataRead));
 
         if (injected_error_count > 0) {
@@ -883,9 +886,9 @@ class NonBatchedOpsStressTest : public StressTest {
                     "num_keys %zu Expected %d errors, seen at least %d\n",
                     num_keys, injected_error_count, stat_nok_nfound);
             fprintf(stderr, "Callstack that injected the fault\n");
-            fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+            db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
                 FaultInjectionIOType::kRead);
-            fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+            db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
                 FaultInjectionIOType::kMetadataRead);
             std::terminate();
           }
@@ -952,10 +955,10 @@ class NonBatchedOpsStressTest : public StressTest {
             const Status& s,
             const std::optional<ExpectedValue>& ryw_expected_value) -> bool {
       //  Temporarily disable error injection for verification
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
 
@@ -1049,10 +1052,10 @@ class NonBatchedOpsStressTest : public StressTest {
       }
 
       // Enable back error injection disbled for checking results
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
       return check_multiget_res;
@@ -1091,10 +1094,10 @@ class NonBatchedOpsStressTest : public StressTest {
     if (use_txn) {
       txn->Rollback().PermitUncheckedError();
       // Enable back error injection disbled for transactions
-      if (fault_fs_guard) {
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
     }
@@ -1141,10 +1144,10 @@ class NonBatchedOpsStressTest : public StressTest {
     const ExpectedValue pre_read_expected_value =
         thread->shared->Get(column_family, key);
 
-    if (fault_fs_guard) {
-      fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
           FaultInjectionIOType::kRead);
-      fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+      db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
           FaultInjectionIOType::kMetadataRead);
       SharedState::ignore_read_error = false;
     }
@@ -1164,11 +1167,11 @@ class NonBatchedOpsStressTest : public StressTest {
         thread->shared->Get(column_family, key);
 
     int injected_error_count = 0;
-    if (fault_fs_guard) {
+    if (db_fault_injection_fs_) {
       injected_error_count = GetMinInjectedErrorCount(
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kRead),
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kMetadataRead));
       if (!SharedState::ignore_read_error && injected_error_count > 0 &&
           (s.ok() || s.IsNotFound())) {
@@ -1177,9 +1180,9 @@ class NonBatchedOpsStressTest : public StressTest {
         MutexLock l(thread->shared->GetMutex());
         fprintf(stderr, "Didn't get expected error from GetEntity\n");
         fprintf(stderr, "Callstack that injected the fault\n");
-        fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+        db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+        db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
             FaultInjectionIOType::kMetadataRead);
         std::terminate();
       }
@@ -1281,10 +1284,10 @@ class NonBatchedOpsStressTest : public StressTest {
     if (FLAGS_use_txn) {
       // TODO(hx235): test fault injection with MultiGetEntity() with
       // transactions
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
       WriteOptions write_options;
@@ -1318,11 +1321,11 @@ class NonBatchedOpsStressTest : public StressTest {
     int injected_error_count = 0;
 
     auto verify_expected_errors = [&](auto get_status) {
-      assert(fault_fs_guard);
+      assert(db_fault_injection_fs_);
       injected_error_count = GetMinInjectedErrorCount(
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kRead),
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kMetadataRead));
       if (injected_error_count) {
         int stat_nok_nfound = 0;
@@ -1344,9 +1347,9 @@ class NonBatchedOpsStressTest : public StressTest {
           fprintf(stderr, "num_keys %zu Expected %d errors, seen %d\n",
                   num_keys, injected_error_count, stat_nok_nfound);
           fprintf(stderr, "Call stack that injected the fault\n");
-          fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+          db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
               FaultInjectionIOType::kRead);
-          fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+          db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
               FaultInjectionIOType::kMetadataRead);
           std::terminate();
         }
@@ -1356,10 +1359,10 @@ class NonBatchedOpsStressTest : public StressTest {
     auto check_results = [&](auto get_columns, auto get_status,
                              auto do_extra_check, auto call_get_entity) {
       // Temporarily disable error injection for checking results
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
       const bool check_get_entity =
@@ -1538,10 +1541,10 @@ class NonBatchedOpsStressTest : public StressTest {
         }
       }
       // Enable back error injection disbled for checking results
-      if (fault_fs_guard) {
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
     };
@@ -1624,19 +1627,19 @@ class NonBatchedOpsStressTest : public StressTest {
 
       txn->Rollback().PermitUncheckedError();
       // Enable back error injection disbled for transactions
-      if (fault_fs_guard) {
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
     } else if (FLAGS_use_attribute_group) {
       // AttributeGroup MultiGetEntity verification
 
-      if (fault_fs_guard) {
-        fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+        db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
             FaultInjectionIOType::kMetadataRead);
         SharedState::ignore_read_error = false;
       }
@@ -1652,7 +1655,7 @@ class NonBatchedOpsStressTest : public StressTest {
       db_->MultiGetEntity(read_opts_copy, num_keys, key_slices.data(),
                           results.data());
 
-      if (fault_fs_guard) {
+      if (db_fault_injection_fs_) {
         verify_expected_errors(
             [&](size_t i) { return results[i][0].status(); });
       }
@@ -1668,10 +1671,10 @@ class NonBatchedOpsStressTest : public StressTest {
     } else {
       // Non-AttributeGroup MultiGetEntity verification
 
-      if (fault_fs_guard) {
-        fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+        db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
             FaultInjectionIOType::kMetadataRead);
         SharedState::ignore_read_error = false;
       }
@@ -1682,7 +1685,7 @@ class NonBatchedOpsStressTest : public StressTest {
       db_->MultiGetEntity(read_opts_copy, cfh, num_keys, key_slices.data(),
                           results.data(), statuses.data());
 
-      if (fault_fs_guard) {
+      if (db_fault_injection_fs_) {
         verify_expected_errors([&](size_t i) { return statuses[i]; });
       }
 
@@ -1733,10 +1736,10 @@ class NonBatchedOpsStressTest : public StressTest {
     MaybeUseOlderTimestampForRangeScan(thread, read_ts_str, read_ts_slice,
                                        ro_copy);
 
-    if (fault_fs_guard) {
-      fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
           FaultInjectionIOType::kRead);
-      fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+      db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
           FaultInjectionIOType::kMetadataRead);
       SharedState::ignore_read_error = false;
     }
@@ -1798,11 +1801,11 @@ class NonBatchedOpsStressTest : public StressTest {
     }
 
     int injected_error_count = 0;
-    if (fault_fs_guard) {
+    if (db_fault_injection_fs_) {
       injected_error_count = GetMinInjectedErrorCount(
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kRead),
-          fault_fs_guard->GetAndResetInjectedThreadLocalErrorCount(
+          db_fault_injection_fs_->GetAndResetInjectedThreadLocalErrorCount(
               FaultInjectionIOType::kMetadataRead));
       if (!SharedState::ignore_read_error && injected_error_count > 0 &&
           s.ok()) {
@@ -1811,9 +1814,9 @@ class NonBatchedOpsStressTest : public StressTest {
         MutexLock l(thread->shared->GetMutex());
         fprintf(stderr, "Didn't get expected error from PrefixScan\n");
         fprintf(stderr, "Callstack that injected the fault\n");
-        fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+        db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->PrintInjectedThreadLocalErrorBacktrace(
+        db_fault_injection_fs_->PrintInjectedThreadLocalErrorBacktrace(
             FaultInjectionIOType::kMetadataRead);
         std::terminate();
       }
@@ -1880,10 +1883,10 @@ class NonBatchedOpsStressTest : public StressTest {
 
     if (FLAGS_verify_before_write) {
       // Temporarily disable error injection for preparation
-      if (fault_fs_guard) {
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->DisableThreadLocalErrorInjection(
+        db_fault_injection_fs_->DisableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
 
@@ -1894,10 +1897,10 @@ class NonBatchedOpsStressTest : public StressTest {
           /* msg_prefix */ "Pre-Put Get verification", from_db, s);
 
       // Enable back error injection disabled for preparation
-      if (fault_fs_guard) {
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+      if (db_fault_injection_fs_) {
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kRead);
-        fault_fs_guard->EnableThreadLocalErrorInjection(
+        db_fault_injection_fs_->EnableThreadLocalErrorInjection(
             FaultInjectionIOType::kMetadataRead);
       }
       if (!res) {
@@ -2000,7 +2003,7 @@ class NonBatchedOpsStressTest : public StressTest {
               &commit_bypass_memtable);
         }
       }
-      UpdateIfInitialWriteFails(db_stress_env, s, &initial_write_s,
+      UpdateIfInitialWriteFails(raw_env, s, &initial_write_s,
                                 &initial_wal_write_may_succeed,
                                 &wait_for_recover_start_time);
 
@@ -2031,7 +2034,7 @@ class NonBatchedOpsStressTest : public StressTest {
       }
     } else {
       PrintWriteRecoveryWaitTimeIfNeeded(
-          db_stress_env, initial_write_s, initial_wal_write_may_succeed,
+          raw_env, initial_write_s, initial_wal_write_may_succeed,
           wait_for_recover_start_time, "TestPut");
       pending_expected_value.Commit();
       thread->stats.AddBytesForWrites(1, sz);
@@ -2107,7 +2110,7 @@ class NonBatchedOpsStressTest : public StressTest {
               &commit_bypass_memtable);
         }
         UpdateIfInitialWriteFails(
-            db_stress_env, s, &initial_write_s, &initial_wal_write_may_succeed,
+            raw_env, s, &initial_write_s, &initial_wal_write_may_succeed,
             &wait_for_recover_start_time, commit_bypass_memtable);
       } while (!s.ok() && IsErrorInjectedAndRetryable(s) &&
                initial_wal_write_may_succeed);
@@ -2137,7 +2140,7 @@ class NonBatchedOpsStressTest : public StressTest {
         }
       } else {
         PrintWriteRecoveryWaitTimeIfNeeded(
-            db_stress_env, initial_write_s, initial_wal_write_may_succeed,
+            raw_env, initial_write_s, initial_wal_write_may_succeed,
             wait_for_recover_start_time, "TestDelete");
         pending_expected_value.Commit();
         thread->stats.AddDeletes(1);
@@ -2179,7 +2182,7 @@ class NonBatchedOpsStressTest : public StressTest {
               &commit_bypass_memtable);
         }
         UpdateIfInitialWriteFails(
-            db_stress_env, s, &initial_write_s, &initial_wal_write_may_succeed,
+            raw_env, s, &initial_write_s, &initial_wal_write_may_succeed,
             &wait_for_recover_start_time, commit_bypass_memtable);
       } while (!s.ok() && IsErrorInjectedAndRetryable(s) &&
                initial_wal_write_may_succeed);
@@ -2209,7 +2212,7 @@ class NonBatchedOpsStressTest : public StressTest {
         }
       } else {
         PrintWriteRecoveryWaitTimeIfNeeded(
-            db_stress_env, initial_write_s, initial_wal_write_may_succeed,
+            raw_env, initial_write_s, initial_wal_write_may_succeed,
             wait_for_recover_start_time, "TestDelete");
         pending_expected_value.Commit();
         thread->stats.AddSingleDeletes(1);
@@ -2274,7 +2277,7 @@ class NonBatchedOpsStressTest : public StressTest {
       } else {
         s = db_->DeleteRange(write_opts, cfh, key, end_key);
       }
-      UpdateIfInitialWriteFails(db_stress_env, s, &initial_write_s,
+      UpdateIfInitialWriteFails(raw_env, s, &initial_write_s,
                                 &initial_wal_write_may_succeed,
                                 &wait_for_recover_start_time);
     } while (!s.ok() && IsErrorInjectedAndRetryable(s) &&
@@ -2302,7 +2305,7 @@ class NonBatchedOpsStressTest : public StressTest {
       }
     } else {
       PrintWriteRecoveryWaitTimeIfNeeded(
-          db_stress_env, initial_write_s, initial_wal_write_may_succeed,
+          raw_env, initial_write_s, initial_wal_write_may_succeed,
           wait_for_recover_start_time, "TestDeleteRange");
       for (PendingExpectedValue& pending_expected_value :
            pending_expected_values) {
@@ -2325,11 +2328,11 @@ class NonBatchedOpsStressTest : public StressTest {
         FLAGS_test_ingest_standalone_range_deletion_one_in);
     std::vector<std::string> external_files;
     const std::string sst_filename =
-        FLAGS_db + "/." + std::to_string(thread->tid) + ".sst";
+        GetDbPath() + "/." + std::to_string(thread->tid) + ".sst";
     external_files.push_back(sst_filename);
     std::string standalone_rangedel_filename;
     if (test_standalone_range_deletion) {
-      standalone_rangedel_filename = FLAGS_db + "/." +
+      standalone_rangedel_filename = GetDbPath() + "/." +
                                      std::to_string(thread->tid) +
                                      "_standalone_rangedel.sst";
       external_files.push_back(standalone_rangedel_filename);
@@ -2338,28 +2341,28 @@ class NonBatchedOpsStressTest : public StressTest {
     std::ostringstream ingest_options_oss;
 
     // Temporarily disable error injection for preparation
-    if (fault_fs_guard) {
-      fault_fs_guard->DisableThreadLocalErrorInjection(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->DisableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataRead);
-      fault_fs_guard->DisableThreadLocalErrorInjection(
+      db_fault_injection_fs_->DisableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataWrite);
     }
 
     for (const auto& filename : external_files) {
-      if (db_stress_env->FileExists(filename).ok()) {
+      if (raw_env->FileExists(filename).ok()) {
         // Maybe we terminated abnormally before, so cleanup to give this file
         // ingestion a clean slate
-        s = db_stress_env->DeleteFile(filename);
+        s = raw_env->DeleteFile(filename);
       }
       if (!s.ok()) {
         return;
       }
     }
 
-    if (fault_fs_guard) {
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+    if (db_fault_injection_fs_) {
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataRead);
-      fault_fs_guard->EnableThreadLocalErrorInjection(
+      db_fault_injection_fs_->EnableThreadLocalErrorInjection(
           FaultInjectionIOType::kMetadataWrite);
     }
 
@@ -3485,8 +3488,11 @@ class NonBatchedOpsStressTest : public StressTest {
   }
 };
 
-StressTest* CreateNonBatchedOpsStressTest() {
-  return new NonBatchedOpsStressTest();
+StressTest* CreateNonBatchedOpsStressTest(int db_index,
+                                          const std::string& db_path,
+                                          const std::string& ev_path,
+                                          const std::string& sec_path) {
+  return new NonBatchedOpsStressTest(db_index, db_path, ev_path, sec_path);
 }
 
 }  // namespace ROCKSDB_NAMESPACE

docs/_posts/2026-05-19-resumable-remote-compaction.markdown

@@ -0,0 +1,55 @@
+---
+title: Resumable Remote Compaction
+layout: post
+author: hx235
+category: blog
+---
+
+## Background
+
+RocksDB can offload compaction work to remote workers through the `CompactionService` API. In this model, the **primary RocksDB instance** selects the input files and sends a serialized `CompactionServiceInput` to a worker; the **remote worker** runs `DB::OpenAndCompact()`, writes output SSTs to `output_directory`, and returns a serialized `CompactionServiceResult` that the primary RocksDB instance installs into its LSM tree. See the [Remote Compaction wiki](https://github.com/facebook/rocksdb/wiki/Remote-Compaction) for the full architecture. This lets operators scale compaction throughput with stateless workers while keeping the primary RocksDB instance's CPU and I/O available for serving reads and writes. However, remote compaction jobs can be long-running—sometimes processing hundreds of gigabytes of input. When a worker crashes, gets preempted, or times out, the entire compaction must restart from scratch, wasting all output produced before the interruption and increasing compaction debt on the primary RocksDB instance.
+
+## How Resumable Remote Compaction Works
+
+Resumable remote compaction introduces a **checkpoint-and-resume** mechanism. During a compaction, the worker periodically saves its progress to the `output_directory`. If the compaction is interrupted, a subsequent call to `OpenAndCompact()` with the same output directory can pick up from the last checkpoint rather than starting over.
+
+### Checkpointing
+
+After each output SST file is completed, the worker persists a progress checkpoint to a **compaction progress file** in the output directory `output_directory`. The checkpoint records which internal key to resume from and the metadata of all completed output files. Progress records use **delta encoding**—each record only contains files completed since the last checkpoint—to keep serialization cost linear.
+
+![Checkpointing overview](/static/images/resumable-remote-compaction/checkpointing-overview.svg)
+
+The worker skips checkpointing at boundaries where resuming could be unsafe or requires complicated handling: when range deletions span the file boundary or when adjacent output files share the same user key. These constraints ensure that resuming produces the same results as if the compaction was not interrupted.
+
+### Resuming
+
+When `OpenAndCompact()` is called with `allow_resumption = true`, it scans the output directory for a valid progress file. If one is found, it loads the checkpointed state, seeks the input iterator to the recorded resume key, restores the output file state, and continues compaction from that point. If the progress file is corrupted or missing, the system falls back to a fresh compaction by cleaning the directory.
+
+![Resume flow](/static/images/resumable-remote-compaction/resume-flow.svg)
+
+## How to Enable It
+
+On the primary RocksDB instance, set a `CompactionService` implementation on the DB options. On the remote worker, pass `allow_resumption = true` in `OpenAndCompactOptions` when calling `DB::OpenAndCompact()`. The `output_directory` must be the same across retries for resumption to work—each retry call with the same directory will automatically detect and resume from the previous checkpoint. The `REMOTE_COMPACT_RESUMED_BYTES` statistics ticker tracks the total bytes of output files reused from a previous interrupted run, giving visibility into how much work resumption saved.
+
+```cpp
+// Primary RocksDB instance
+DBOptions db_options;
+db_options.compaction_service = std::make_shared<MyCompactionService>();
+
+// Remote worker
+OpenAndCompactOptions options;
+options.allow_resumption = true;
+
+std::string result;
+Status s = DB::OpenAndCompact(
+    options,
+    db_path,             // source database path
+    output_directory,    // where output SSTs and progress are stored
+    compaction_input,    // serialized CompactionServiceInput
+    &result,             // serialized CompactionServiceResult
+    override_options);
+```
+
+## Future Work
+
+Today this feature targets remote compaction. The same checkpoint-and-resume mechanism could also support **local compaction** after a crash. The core persistence and resume logic is already in `CompactionJob`; the remaining work is to integrate it with local compaction scheduling and recovery.

docs/components/write_flow/03_wal.md

@@ -94,11 +94,23 @@ Step 3 - **Synced**: `fsync()` is called when `WriteOptions::sync` is true, or w
 
 Step 4 - **Obsolete**: After all memtables referencing this WAL are flushed, the WAL becomes obsolete and is either recycled or deleted.
 
+## Async WAL Precreation
+
+When `DBOptions::async_wal_precreate` is enabled, RocksDB keeps at most one future WAL file precreated in the background. RocksDB reserves a file number before scheduling the background task; the task opens the file/writer, but deliberately leaves the file as reserved empty storage:
+
+- It does not write compression metadata.
+- It does not write predecessor WAL info.
+- It does not add the file to `logs_`, `alive_wal_files_`, or MANIFEST WAL tracking.
+
+The file becomes a logical WAL only when foreground `SwitchMemtable()` consumes it. At that point RocksDB writes the normal WAL metadata, flushes the previous WAL writer buffer, and installs the new WAL in the same order as synchronous WAL creation. If foreground rotation reaches the switch while the background task is still running, the writer waits for the reserved file number instead of allocating a higher numbered WAL. This avoids a late lower-numbered WAL appearing after a newer WAL has become live. If background precreation fails, the background task logs the failure and foreground rotation falls back to normal synchronous WAL creation.
+
+Unused precreated WALs are safe across crashes and clean shutdowns because they are zero-record future WAL files. Recovery processes WAL files by log number, marks every observed WAL number as used, and treats an empty future WAL as EOF. On clean close, RocksDB releases the unpublished WAL writer but does not need to delete the empty file. The option is sanitized to false when `recycle_log_file_num > 0`.
+
 ## WAL Tracking in MANIFEST
 
 `WalSet` (see `db/wal_edit.h`, tracked in `VersionSet`) manages WAL metadata in the MANIFEST:
 
-- `WalAddition` records are written when a WAL is created or when a closed/inactive WAL's synced size is finalized
+- `WalAddition` records are written when a closed/inactive WAL's synced size is finalized
 - `WalDeletion` records are written when a WAL becomes obsolete after flush
 - Live-WAL syncs (via `DB::SyncWAL()` or `WriteOptions::sync`) are intentionally not tracked in MANIFEST
 

docs/components/write_flow/04_memtable_insert.md

@@ -103,7 +103,7 @@ When a flush is triggered, `DBImpl::SwitchMemtable()` (see `db/db_impl/db_impl_w
 
 Step 1 - Writes any recoverable state to the current memtable.
 
-Step 2 - Creates a new WAL file (unless the current WAL is empty) with the next file number from `VersionSet::NewFileNumber()`.
+Step 2 - Creates a new WAL file (unless the current WAL is empty) with the next file number from `VersionSet::NewFileNumber()`. If `DBOptions::async_wal_precreate` has prepared a future WAL, this step consumes that reserved file number and finalizes the WAL metadata instead of creating the file synchronously.
 
 Step 3 - Constructs a new `MemTable` with `earliest_seq` set to the current last sequence.
 

docs/static/images/resumable-remote-compaction/checkpointing-overview.svg

@@ -0,0 +1,65 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1000 390" style="background-color: #fafafa;">
+  <defs>
+    <marker id="cp-arrowhead" markerWidth="10" markerHeight="7" refX="10" refY="3.5" orient="auto">
+      <polygon points="0 0, 10 3.5, 0 7" fill="#355070" />
+    </marker>
+    <filter id="cp-shadow" x="-20%" y="-20%" width="140%" height="140%">
+      <feDropShadow dx="2" dy="2" stdDeviation="2" flood-color="#00000020"/>
+    </filter>
+  </defs>
+
+  <text x="500" y="36" font-family="Arial, sans-serif" font-size="22" font-weight="bold" text-anchor="middle" fill="#25364d">
+    Checkpointing
+  </text>
+
+  <g transform="translate(50,80)">
+    <rect x="0" y="0" width="360" height="220" rx="18" fill="#eef5ff" stroke="#9cb9dd" stroke-width="2" filter="url(#cp-shadow)"/>
+    <text x="180" y="38" font-family="Arial, sans-serif" font-size="18" font-weight="bold" text-anchor="middle" fill="#25364d">
+      During DB::OpenAndCompact()
+    </text>
+
+    <g transform="translate(28,86)">
+      <rect x="0" y="0" width="90" height="72" rx="12" fill="#daf3e5" stroke="#4f9d69" stroke-width="2"/>
+      <text x="45" y="30" font-family="Arial, sans-serif" font-size="15" font-weight="bold" text-anchor="middle" fill="#214e32">1.sst</text>
+      <text x="45" y="51" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#214e32">complete</text>
+    </g>
+
+    <g transform="translate(136,86)">
+      <rect x="0" y="0" width="90" height="72" rx="12" fill="#daf3e5" stroke="#4f9d69" stroke-width="2"/>
+      <text x="45" y="30" font-family="Arial, sans-serif" font-size="15" font-weight="bold" text-anchor="middle" fill="#214e32">2.sst</text>
+      <text x="45" y="51" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#214e32">complete</text>
+    </g>
+
+    <g transform="translate(244,86)">
+      <rect x="0" y="0" width="90" height="72" rx="12" fill="#fff1d6" stroke="#d08a2e" stroke-width="2" stroke-dasharray="6 4"/>
+      <text x="45" y="28" font-family="Arial, sans-serif" font-size="15" font-weight="bold" text-anchor="middle" fill="#7a5015">3.sst</text>
+      <text x="45" y="49" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#7a5015">in progress</text>
+    </g>
+  </g>
+
+  <line x1="432" y1="190" x2="558" y2="190" stroke="#355070" stroke-width="3" marker-end="url(#cp-arrowhead)"/>
+  <text x="495" y="168" font-family="Arial, sans-serif" font-size="13" font-weight="bold" text-anchor="middle" fill="#25364d">
+    After each completed SST
+  </text>
+
+  <g transform="translate(590,80)">
+    <rect x="0" y="0" width="360" height="240" rx="18" fill="#fff8e8" stroke="#d4a24a" stroke-width="2" filter="url(#cp-shadow)"/>
+    <text x="180" y="38" font-family="Arial, sans-serif" font-size="18" font-weight="bold" text-anchor="middle" fill="#6e4a16">
+      Compaction Progress File
+    </text>
+    <g transform="translate(26,76)">
+      <rect x="0" y="0" width="308" height="72" rx="12" fill="#fffdf8" stroke="#d4a24a" stroke-width="1.5"/>
+      <text x="154" y="20" font-family="Courier New, monospace" font-size="12" text-anchor="middle" fill="#4e3a19">record 1</text>
+      <text x="154" y="38" font-family="Courier New, monospace" font-size="12" text-anchor="middle" fill="#4e3a19">resume_from = key_after_1.sst</text>
+      <text x="154" y="56" font-family="Courier New, monospace" font-size="12" text-anchor="middle" fill="#4e3a19">new_files += [1.sst metadata]</text>
+    </g>
+
+    <g transform="translate(26,158)">
+      <rect x="0" y="0" width="308" height="72" rx="12" fill="#fffdf8" stroke="#d4a24a" stroke-width="1.5"/>
+      <text x="154" y="20" font-family="Courier New, monospace" font-size="12" text-anchor="middle" fill="#4e3a19">record 2</text>
+      <text x="154" y="38" font-family="Courier New, monospace" font-size="12" text-anchor="middle" fill="#4e3a19">resume_from = key_after_2.sst</text>
+      <text x="154" y="56" font-family="Courier New, monospace" font-size="12" text-anchor="middle" fill="#4e3a19">new_files += [2.sst metadata]</text>
+    </g>
+  </g>
+</svg>

docs/static/images/resumable-remote-compaction/resume-flow.svg

@@ -0,0 +1,97 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1000 720" style="background-color: #fafafa;">
+  <defs>
+    <marker id="rf-arrowhead" markerWidth="10" markerHeight="7" refX="10" refY="3.5" orient="auto">
+      <polygon points="0 0, 10 3.5, 0 7" fill="#355070" />
+    </marker>
+    <filter id="rf-shadow" x="-20%" y="-20%" width="140%" height="140%">
+      <feDropShadow dx="2" dy="2" stdDeviation="2" flood-color="#00000020"/>
+    </filter>
+  </defs>
+
+  <text x="500" y="36" font-family="Arial, sans-serif" font-size="22" font-weight="bold" text-anchor="middle" fill="#25364d">
+    Resuming a Remote Compaction
+  </text>
+
+  <g transform="translate(275,70)">
+    <rect x="0" y="0" width="450" height="64" rx="18" fill="#edf4ff" stroke="#9cb9dd" stroke-width="2" filter="url(#rf-shadow)"/>
+    <text x="225" y="28" font-family="Arial, sans-serif" font-size="18" font-weight="bold" text-anchor="middle" fill="#25364d">
+      OpenAndCompact(allow_resumption = true)
+    </text>
+    <text x="225" y="48" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#5b6573">
+      Retry with the same output_directory
+    </text>
+  </g>
+
+  <line x1="500" y1="134" x2="500" y2="180" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+
+  <g transform="translate(275,190)">
+    <rect x="0" y="0" width="450" height="78" rx="18" fill="#edf4ff" stroke="#9cb9dd" stroke-width="2" filter="url(#rf-shadow)"/>
+    <text x="225" y="30" font-family="Arial, sans-serif" font-size="18" font-weight="bold" text-anchor="middle" fill="#25364d">
+      Scan output_directory
+    </text>
+    <text x="225" y="52" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#5b6573">
+      Inspect the progress file and any existing SST files
+    </text>
+  </g>
+
+  <line x1="500" y1="268" x2="500" y2="316" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+
+  <polygon points="500,316 650,386 500,456 350,386" fill="#fff8e8" stroke="#d4a24a" stroke-width="2" filter="url(#rf-shadow)"/>
+  <text x="500" y="392" font-family="Arial, sans-serif" font-size="18" font-weight="bold" text-anchor="middle" fill="#6e4a16">
+    Valid progress file?
+  </text>
+
+  <line x1="350" y1="386" x2="220" y2="386" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+  <text x="308" y="372" font-family="Arial, sans-serif" font-size="13" font-weight="bold" text-anchor="middle" fill="#25364d">No</text>
+
+  <g transform="translate(40,344)">
+    <rect x="0" y="0" width="240" height="72" rx="18" fill="#fff0f0" stroke="#d97070" stroke-width="2" filter="url(#rf-shadow)"/>
+    <text x="120" y="30" font-family="Arial, sans-serif" font-size="17" font-weight="bold" text-anchor="middle" fill="#7f2323">
+      Start fresh
+    </text>
+    <text x="120" y="50" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#7f2323">
+      Clean output_directory
+    </text>
+  </g>
+
+  <line x1="650" y1="386" x2="780" y2="386" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+  <text x="694" y="372" font-family="Arial, sans-serif" font-size="13" font-weight="bold" text-anchor="middle" fill="#25364d">Yes</text>
+
+  <g transform="translate(720,310)">
+    <rect x="0" y="0" width="230" height="106" rx="18" fill="#eef8ef" stroke="#7db28e" stroke-width="2" filter="url(#rf-shadow)"/>
+    <text x="115" y="30" font-family="Arial, sans-serif" font-size="17" font-weight="bold" text-anchor="middle" fill="#24503a">
+      Resume from checkpoint
+    </text>
+    <text x="115" y="52" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#24503a">
+      Load progress state
+    </text>
+    <text x="115" y="70" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#24503a">
+      Seek the iterator to the resume key
+    </text>
+    <text x="115" y="88" font-family="Arial, sans-serif" font-size="12" text-anchor="middle" fill="#24503a">
+      Restore output file state
+    </text>
+  </g>
+
+  <line x1="160" y1="416" x2="160" y2="560" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+  <line x1="835" y1="416" x2="835" y2="560" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+  <line x1="160" y1="560" x2="355" y2="560" stroke="#355070" stroke-width="3"/>
+  <line x1="835" y1="560" x2="645" y2="560" stroke="#355070" stroke-width="3"/>
+
+  <g transform="translate(355,526)">
+    <rect x="0" y="0" width="290" height="50" rx="18" fill="#edf4ff" stroke="#9cb9dd" stroke-width="2" filter="url(#rf-shadow)"/>
+    <text x="145" y="31" font-family="Arial, sans-serif" font-size="18" font-weight="bold" text-anchor="middle" fill="#25364d">
+      Continue compaction
+    </text>
+  </g>
+
+  <line x1="500" y1="576" x2="500" y2="646" stroke="#355070" stroke-width="3" marker-end="url(#rf-arrowhead)"/>
+
+  <g transform="translate(310,656)">
+    <rect x="0" y="0" width="380" height="44" rx="16" fill="#eef8ef" stroke="#7db28e" stroke-width="2" filter="url(#rf-shadow)"/>
+    <text x="190" y="28" font-family="Arial, sans-serif" font-size="17" font-weight="bold" text-anchor="middle" fill="#24503a">
+      Return CompactionServiceResult
+    </text>
+  </g>
+</svg>

env/env_test.cc

@@ -38,6 +38,18 @@
 #define BTRFS_SUPER_MAGIC 0x9123683E
 #endif
 
+#if !defined(TMPFS_MAGIC)
+#define TMPFS_MAGIC 0x01021994
+#endif
+
+#if !defined(OVERLAYFS_SUPER_MAGIC)
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
+#endif
+
+#if !defined(ZFS_SUPER_MAGIC)
+#define ZFS_SUPER_MAGIC 0x2fc12fc1
+#endif
+
 #ifdef ROCKSDB_FALLOCATE_PRESENT
 #include <cerrno>
 #endif
@@ -283,6 +295,46 @@ class EnvPosixTestWithParam
     }
   }
 
+  // ReserveThreads() returns the number of threads observed waiting at that
+  // instant. When this test runs in parallel with many other CPU-heavy tests,
+  // worker-thread scheduling can vary enough that the sync points prove key
+  // transitions were reached before waiting-thread accounting has fully
+  // settled. Use this helper only for positive exact-reservation checks; it
+  // releases any partial reservation before retrying so the retry does not
+  // perturb test state.
+  testing::AssertionResult ReserveThreadsEventually(int expected, int requested,
+                                                    Env::Priority priority,
+                                                    int wait_micros) {
+    constexpr int kRetryMicros = 1000;
+    int last_reserved = -1;
+    for (int waited_micros = 0; waited_micros <= wait_micros;
+         waited_micros += kRetryMicros) {
+      int reserved = env_->ReserveThreads(requested, priority);
+      if (reserved == expected) {
+        return testing::AssertionSuccess();
+      }
+      if (reserved > 0) {
+        int released = env_->ReleaseThreads(reserved, priority);
+        if (released != reserved) {
+          return testing::AssertionFailure()
+                 << "ReserveThreads(" << requested << ") returned " << reserved
+                 << ", but ReleaseThreads(" << reserved << ") released "
+                 << released;
+        }
+      }
+      if (reserved > expected) {
+        return testing::AssertionFailure()
+               << "ReserveThreads(" << requested << ") returned " << reserved
+               << ", more than expected " << expected;
+      }
+      last_reserved = reserved;
+      Env::Default()->SleepForMicroseconds(kRetryMicros);
+    }
+    return testing::AssertionFailure()
+           << "ReserveThreads(" << requested << ") returned " << last_reserved
+           << " after waiting " << wait_micros << "us, expected " << expected;
+  }
+
   ~EnvPosixTestWithParam() override { WaitThreadPoolsEmpty(); }
 };
 
@@ -1010,7 +1062,7 @@ TEST_P(EnvPosixTestWithParam, ReserveThreads) {
   TEST_SYNC_POINT("EnvTest::ReserveThreads:2");
   TEST_SYNC_POINT("EnvTest::ReserveThreads:3");
   // Reserve 2 threads
-  ASSERT_EQ(2, env_->ReserveThreads(2, Env::Priority::HIGH));
+  ASSERT_TRUE(ReserveThreadsEventually(2, 2, Env::Priority::HIGH, kWaitMicros));
 
   // Schedule 3 tasks. Task 0 running (in this context, doing
   // SleepingBackgroundTask); Task 1, 2 waiting; 3 reserved threads.
@@ -1039,7 +1091,7 @@ TEST_P(EnvPosixTestWithParam, ReserveThreads) {
   // Add sync point to ensure the 4th thread starts
   TEST_SYNC_POINT("EnvTest::ReserveThreads:4");
   // As the thread pool is expanded, we can reserve one more thread
-  ASSERT_EQ(1, env_->ReserveThreads(3, Env::Priority::HIGH));
+  ASSERT_TRUE(ReserveThreadsEventually(1, 3, Env::Priority::HIGH, kWaitMicros));
   // No more threads can be reserved
   ASSERT_EQ(0, env_->ReserveThreads(3, Env::Priority::HIGH));
 
@@ -1058,7 +1110,7 @@ TEST_P(EnvPosixTestWithParam, ReserveThreads) {
   // Add sync point to ensure the number of waiting threads increases
   TEST_SYNC_POINT("EnvTest::ReserveThreads:5");
   // 1 more thread can be reserved
-  ASSERT_EQ(1, env_->ReserveThreads(3, Env::Priority::HIGH));
+  ASSERT_TRUE(ReserveThreadsEventually(1, 3, Env::Priority::HIGH, kWaitMicros));
   // 2 reserved threads now
 
   // Currently, two threads are blocked since the number of waiting
@@ -1384,16 +1436,34 @@ TEST_P(EnvPosixTestWithParam, AllocateTest) {
     struct stat f_stat;
     ASSERT_EQ(stat(fname.c_str(), &f_stat), 0);
     ASSERT_EQ((unsigned int)kDataSize, f_stat.st_size);
-    // btrfs accepts fallocate but uses copy-on-write, so preallocated extents
-    // are not reflected in st_blocks. Skip block-count verification there.
+    // btrfs (and other CoW filesystems) accept fallocate but use
+    // copy-on-write, so preallocated extents are not reliably reflected in
+    // st_blocks (especially under load). Skip block-count verification on
+    // those filesystems.
+    // Also skip on tmpfs and overlayfs, which may not report preallocated
+    // blocks in st_blocks reliably.
     bool skip_block_checks = false;
 #ifdef OS_LINUX
     struct statfs fs_stat;
-    if (statfs(fname.c_str(), &fs_stat) == 0 &&
-        fs_stat.f_type ==
-            static_cast<decltype(fs_stat.f_type)>(BTRFS_SUPER_MAGIC)) {
-      fprintf(stderr, "Skipping preallocation block count checks on btrfs\n");
-      skip_block_checks = true;
+    if (statfs(fname.c_str(), &fs_stat) == 0) {
+      if (fs_stat.f_type ==
+          static_cast<decltype(fs_stat.f_type)>(BTRFS_SUPER_MAGIC)) {
+        fprintf(stderr, "Skipping preallocation block count checks on btrfs\n");
+        skip_block_checks = true;
+      } else if (fs_stat.f_type ==
+                 static_cast<decltype(fs_stat.f_type)>(ZFS_SUPER_MAGIC)) {
+        fprintf(stderr, "Skipping preallocation block count checks on zfs\n");
+        skip_block_checks = true;
+      } else if (fs_stat.f_type ==
+                 static_cast<decltype(fs_stat.f_type)>(TMPFS_MAGIC)) {
+        fprintf(stderr, "Skipping preallocation block count checks on tmpfs\n");
+        skip_block_checks = true;
+      } else if (fs_stat.f_type ==
+                 static_cast<decltype(fs_stat.f_type)>(OVERLAYFS_SUPER_MAGIC)) {
+        fprintf(stderr,
+                "Skipping preallocation block count checks on overlayfs\n");
+        skip_block_checks = true;
+      }
     }
 #endif
     if (!skip_block_checks) {
@@ -1403,8 +1473,20 @@ TEST_P(EnvPosixTestWithParam, AllocateTest) {
       // expect.
       // It looks like some FS give us more blocks that we asked for. That's
       // fine. It might be worth investigating further.
-      ASSERT_LE((unsigned int)(kPreallocateSize / kBlockSize),
-                f_stat.st_blocks);
+      if ((unsigned int)(kPreallocateSize / kBlockSize) > f_stat.st_blocks) {
+        // Preallocation may not be supported or reflected in st_blocks on this
+        // filesystem. Print a warning and skip the check rather than failing.
+        fprintf(stderr,
+                "Warning: preallocated blocks (%u) less than expected (%u), "
+                "skipping block count check. This may indicate the filesystem "
+                "does not support preallocation or does not report it in "
+                "st_blocks.\n",
+                (unsigned int)f_stat.st_blocks,
+                (unsigned int)(kPreallocateSize / kBlockSize));
+      } else {
+        ASSERT_LE((unsigned int)(kPreallocateSize / kBlockSize),
+                  f_stat.st_blocks);
+      }
     }
 
     // close the file, should deallocate the blocks

env/fs_posix.cc

@@ -1114,10 +1114,10 @@ class PosixFileSystem : public FileSystem {
         struct io_uring_cqe* cqe = nullptr;
         ssize_t ret = io_uring_wait_cqe(iu, &cqe);
         if (ret) {
-          fprintf(stderr, "Poll: io_uring_wait_cqe failed: %ld", (long)ret);
           if (ret == -EINTR || ret == -EAGAIN) {
             continue;  // Retry
           }
+          fprintf(stderr, "Poll: io_uring_wait_cqe failed: %ld\n", (long)ret);
           abort();
         }
 
@@ -1207,10 +1207,11 @@ class PosixFileSystem : public FileSystem {
         struct io_uring_cqe* cqe = nullptr;
         ssize_t ret = io_uring_wait_cqe(iu, &cqe);
         if (ret) {
-          fprintf(stderr, "AbortIO: io_uring_wait_cqe failed: %ld", (long)ret);
           if (ret == -EINTR || ret == -EAGAIN) {
             continue;  // Retry
           }
+          fprintf(stderr, "AbortIO: io_uring_wait_cqe failed: %ld\n",
+                  (long)ret);
           abort();
         }
         assert(cqe != nullptr);

file/file_prefetch_buffer.cc

@@ -103,7 +103,7 @@ Status FilePrefetchBuffer::Read(BufferInfo* buf, const IOOptions& opts,
   } else {
     to_buf = buf->buffer_.BufferStart() + aligned_useful_len;
     s = reader->Read(opts, start_offset + aligned_useful_len, read_len, &result,
-                     to_buf, /*aligned_buf=*/nullptr);
+                     to_buf);
   }
 
 #ifndef NDEBUG
@@ -165,7 +165,7 @@ Status FilePrefetchBuffer::ReadAsync(BufferInfo* buf, const IOOptions& opts,
     // Fall back to synchronous read so the buffer is populated inline
     // and callers proceed transparently.
     s = reader->Read(opts, start_offset, read_len, &result,
-                     buf->buffer_.BufferStart(), /*aligned_buf=*/nullptr);
+                     buf->buffer_.BufferStart());
     if (s.ok()) {
       buf->buffer_.Size(buf->CurrentSize() + result.size());
       if (usage_ == FilePrefetchBufferUsage::kUserScanPrefetch) {

file/file_prefetch_buffer.h

@@ -527,7 +527,9 @@ class FilePrefetchBuffer {
     read_req.offset = offset;
     read_req.len = n;
     read_req.scratch = nullptr;
-    IOStatus s = reader->MultiRead(opts, &read_req, 1, nullptr);
+    AlignedBuffer direct_io_buffer;
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
+    IOStatus s = reader->MultiRead(opts, &read_req, 1, &direct_io_context);
     if (!s.ok()) {
       return s;
     }

file/random_access_file_reader.cc

@@ -16,6 +16,7 @@
 #include "monitoring/histogram.h"
 #include "monitoring/iostats_context_imp.h"
 #include "port/port.h"
+#include "rocksdb/io_status.h"
 #include "table/format.h"
 #include "test_util/sync_point.h"
 #include "util/random.h"
@@ -128,11 +129,17 @@ IOStatus RandomAccessFileReader::Create(
   return io_s;
 }
 
-IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
-                                      size_t n, Slice* result, char* scratch,
-                                      AlignedBuf* aligned_buf,
-                                      IODebugContext* dbg) const {
-  (void)aligned_buf;
+IOStatus RandomAccessFileReader::Read(
+    const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
+    char* scratch, AlignedBufferAllocationContext* direct_io_buffer_context,
+    IODebugContext* dbg) const {
+  AlignedBuffer* direct_io_buffer = direct_io_buffer_context != nullptr
+                                        ? direct_io_buffer_context->buffer
+                                        : nullptr;
+  const AlignedBuffer::Allocator* direct_io_allocator =
+      direct_io_buffer_context != nullptr ? direct_io_buffer_context->allocator
+                                          : nullptr;
+  assert(direct_io_buffer_context == nullptr || direct_io_buffer != nullptr);
   const Env::IOPriority rate_limiter_priority = opts.rate_limiter_priority;
 
   TEST_SYNC_POINT_CALLBACK("RandomAccessFileReader::Read", nullptr);
@@ -151,7 +158,7 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
   uint64_t elapsed = 0;
   size_t alignment = file_->GetRequiredBufferAlignment();
   bool is_aligned = false;
-  if (scratch != nullptr) {
+  if (direct_io_buffer == nullptr && scratch != nullptr) {
     // Check if offset, length and buffer are aligned.
     is_aligned = (offset & (alignment - 1)) == 0 &&
                  (n & (alignment - 1)) == 0 &&
@@ -172,17 +179,25 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
       size_t read_size =
           Roundup(static_cast<size_t>(offset + n), alignment) - aligned_offset;
       AlignedBuffer buf;
-      buf.Alignment(alignment);
-      buf.AllocateNewBuffer(read_size);
-      while (buf.CurrentSize() < read_size) {
+      AlignedBuffer* aligned_read_buffer =
+          direct_io_buffer != nullptr ? direct_io_buffer : &buf;
+      aligned_read_buffer->Alignment(alignment);
+      Status allocate_status = aligned_read_buffer->AllocateNewBuffer(
+          read_size, direct_io_allocator);
+      if (!allocate_status.ok()) {
+        io_s = status_to_io_status(std::move(allocate_status));
+      }
+      char* aligned_scratch = aligned_read_buffer->BufferStart();
+      size_t current_size = 0;
+      while (io_s.ok() && current_size < read_size) {
         size_t allowed;
         if (rate_limiter_priority != Env::IO_TOTAL &&
             rate_limiter_ != nullptr) {
           allowed = rate_limiter_->RequestToken(
-              buf.Capacity() - buf.CurrentSize(), buf.Alignment(),
-              rate_limiter_priority, stats_, RateLimiter::OpType::kRead);
+              read_size - current_size, alignment, rate_limiter_priority,
+              stats_, RateLimiter::OpType::kRead);
         } else {
-          assert(buf.CurrentSize() == 0);
+          assert(current_size == 0);
           allowed = read_size;
         }
         Slice tmp;
@@ -191,7 +206,7 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
         uint64_t orig_offset = 0;
         if (ShouldNotifyListeners()) {
           start_ts = FileOperationInfo::StartNow();
-          orig_offset = aligned_offset + buf.CurrentSize();
+          orig_offset = aligned_offset + current_size;
         }
 
         {
@@ -201,8 +216,8 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
           // one iteration of this loop, so we don't need to check and adjust
           // the opts.timeout before calling file_->Read
           assert(!opts.timeout.count() || allowed == read_size);
-          io_s = file_->Read(aligned_offset + buf.CurrentSize(), allowed, opts,
-                             &tmp, buf.Destination(), dbg);
+          io_s = file_->Read(aligned_offset + current_size, allowed, opts, &tmp,
+                             aligned_scratch + current_size, dbg);
         }
         if (ShouldNotifyListeners()) {
           auto finish_ts = FileOperationInfo::FinishNow();
@@ -214,19 +229,22 @@ IOStatus RandomAccessFileReader::Read(const IOOptions& opts, uint64_t offset,
           }
         }
 
-        buf.Size(buf.CurrentSize() + tmp.size());
+        current_size += tmp.size();
+        if (direct_io_buffer == nullptr) {
+          buf.Size(current_size);
+        }
         if (!io_s.ok() || tmp.size() < allowed) {
           break;
         }
       }
       size_t res_len = 0;
-      if (io_s.ok() && offset_advance < buf.CurrentSize()) {
-        res_len = std::min(buf.CurrentSize() - offset_advance, n);
-        if (aligned_buf == nullptr) {
-          buf.Read(scratch, offset_advance, res_len);
+      if (io_s.ok() && offset_advance < current_size) {
+        res_len = std::min(current_size - offset_advance, n);
+        if (direct_io_buffer != nullptr) {
+          scratch = aligned_scratch + offset_advance;
         } else {
-          scratch = buf.BufferStart() + offset_advance;
-          *aligned_buf = buf.Release();
+          assert(scratch != nullptr);
+          buf.Read(scratch, offset_advance, res_len);
         }
       }
       *result = Slice(scratch, res_len);
@@ -335,13 +353,18 @@ bool TryMerge(FSReadRequest* dest, const FSReadRequest& src) {
   return true;
 }
 
-IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
-                                           FSReadRequest* read_reqs,
-                                           size_t num_reqs,
-                                           AlignedBuf* aligned_buf,
-                                           IODebugContext* dbg) const {
-  (void)aligned_buf;  // suppress warning of unused variable in LITE mode
+IOStatus RandomAccessFileReader::MultiRead(
+    const IOOptions& opts, FSReadRequest* read_reqs, size_t num_reqs,
+    AlignedBufferAllocationContext* direct_io_buffer_context,
+    IODebugContext* dbg) const {
   assert(num_reqs > 0);
+  AlignedBuffer* direct_io_buffer = direct_io_buffer_context != nullptr
+                                        ? direct_io_buffer_context->buffer
+                                        : nullptr;
+  const AlignedBuffer::Allocator* direct_io_allocator =
+      direct_io_buffer_context != nullptr ? direct_io_buffer_context->allocator
+                                          : nullptr;
+  assert(direct_io_buffer != nullptr);
 
 #ifndef NDEBUG
   for (size_t i = 0; i < num_reqs - 1; ++i) {
@@ -403,16 +426,20 @@ IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
       for (const auto& r : aligned_reqs) {
         total_len += r.len;
       }
-      AlignedBuffer buf;
-      buf.Alignment(alignment);
-      buf.AllocateNewBuffer(total_len);
-      char* scratch = buf.BufferStart();
-      for (auto& r : aligned_reqs) {
-        r.scratch = scratch;
-        scratch += r.len;
+      direct_io_buffer->Alignment(alignment);
+      Status allocate_status =
+          direct_io_buffer->AllocateNewBuffer(total_len, direct_io_allocator);
+      if (!allocate_status.ok()) {
+        io_s = status_to_io_status(std::move(allocate_status));
+      }
+      if (io_s.ok()) {
+        char* scratch = direct_io_buffer->BufferStart();
+        for (auto& r : aligned_reqs) {
+          r.scratch = scratch;
+          scratch += r.len;
+        }
       }
 
-      *aligned_buf = buf.Release();
       fs_reqs = aligned_reqs.data();
       num_fs_reqs = aligned_reqs.size();
     }
@@ -422,7 +449,7 @@ IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
       start_ts = FileOperationInfo::StartNow();
     }
 
-    {
+    if (io_s.ok()) {
       IOSTATS_CPU_TIMER_GUARD(cpu_read_nanos, clock_);
       if (rate_limiter_priority != Env::IO_TOTAL && rate_limiter_ != nullptr) {
         // TODO: ideally we should call `RateLimiter::RequestToken()` for
@@ -455,7 +482,7 @@ IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
       RecordInHistogram(stats_, MULTIGET_IO_BATCH_SIZE, num_fs_reqs);
     }
 
-    if (use_direct_io()) {
+    if (use_direct_io() && io_s.ok()) {
       // Populate results in the unaligned read requests.
       size_t aligned_i = 0;
       for (size_t i = 0; i < num_reqs; i++) {
@@ -481,19 +508,20 @@ IOStatus RandomAccessFileReader::MultiRead(const IOOptions& opts,
       }
     }
 
+    const bool overall_io_ok = io_s.ok();
     for (size_t i = 0; i < num_reqs; ++i) {
+      const IOStatus& req_status = overall_io_ok ? read_reqs[i].status : io_s;
+      const size_t result_size = overall_io_ok ? read_reqs[i].result.size() : 0;
       if (ShouldNotifyListeners()) {
         auto finish_ts = FileOperationInfo::FinishNow();
-        NotifyOnFileReadFinish(read_reqs[i].offset, read_reqs[i].result.size(),
-                               start_ts, finish_ts, read_reqs[i].status);
+        NotifyOnFileReadFinish(read_reqs[i].offset, result_size, start_ts,
+                               finish_ts, req_status);
       }
-      if (!read_reqs[i].status.ok()) {
-        NotifyOnIOError(read_reqs[i].status, FileOperationType::kRead,
-                        file_name(), read_reqs[i].result.size(),
-                        read_reqs[i].offset);
+      if (!req_status.ok()) {
+        NotifyOnIOError(req_status, FileOperationType::kRead, file_name(),
+                        result_size, read_reqs[i].offset);
       }
-      RecordIOStats(stats_, file_temperature_, is_last_level_,
-                    read_reqs[i].result.size());
+      RecordIOStats(stats_, file_temperature_, is_last_level_, result_size);
     }
     SetPerfLevel(prev_perf_level);
   }
@@ -517,16 +545,26 @@ IOStatus RandomAccessFileReader::PrepareIOOptions(const ReadOptions& ro,
 
 // Notes for when direct_io is enabled:
 // Unless req.offset, req.len, req.scratch are all already aligned,
-// RandomAccessFileReader will creats aligned requests and aligned buffer for
-// the request. User should only provide either req.scratch or aligned_buf. If
-// only req.scratch is provided, result will be copied from allocated aligned
-// buffer to req.scratch. If only alignd_buf is provided, it will be set to
-// the ailgned buf allocated by RandomAccessFileReader and saves a copy.
+// RandomAccessFileReader creates an aligned request and aligned buffer for the
+// request. If direct_io_buffer_context is provided, its buffer owns the aligned
+// backing storage and its optional allocator is used only for this allocation.
+// Otherwise, callers should provide either req.scratch or aligned_buf. If only
+// req.scratch is provided, the result is copied from the allocated aligned
+// buffer to req.scratch. If only aligned_buf is provided, it is set to the
+// aligned buffer allocated by RandomAccessFileReader and saves a copy.
 IOStatus RandomAccessFileReader::ReadAsync(
     FSReadRequest& req, const IOOptions& opts,
     std::function<void(FSReadRequest&, void*)> cb, void* cb_arg,
     void** io_handle, IOHandleDeleter* del_fn, AlignedBuf* aligned_buf,
-    IODebugContext* dbg) {
+    IODebugContext* dbg,
+    AlignedBufferAllocationContext* direct_io_buffer_context) {
+  AlignedBuffer* direct_io_buffer = direct_io_buffer_context != nullptr
+                                        ? direct_io_buffer_context->buffer
+                                        : nullptr;
+  const AlignedBuffer::Allocator* direct_io_allocator =
+      direct_io_buffer_context != nullptr ? direct_io_buffer_context->allocator
+                                          : nullptr;
+  assert(direct_io_buffer_context == nullptr || direct_io_buffer != nullptr);
   IOStatus s;
   TEST_SYNC_POINT_CALLBACK("RandomAccessFileReader::ReadAsync:InjectStatus",
                            &s);
@@ -546,7 +584,8 @@ IOStatus RandomAccessFileReader::ReadAsync(
   }
 
   size_t alignment = file_->GetRequiredBufferAlignment();
-  bool is_aligned = (req.offset & (alignment - 1)) == 0 &&
+  bool is_aligned = direct_io_buffer == nullptr &&
+                    (req.offset & (alignment - 1)) == 0 &&
                     (req.len & (alignment - 1)) == 0 &&
                     (uintptr_t(req.scratch) & (alignment - 1)) == 0;
   read_async_info->is_aligned_ = is_aligned;
@@ -556,21 +595,27 @@ IOStatus RandomAccessFileReader::ReadAsync(
     FSReadRequest aligned_req = Align(req, alignment);
     aligned_req.status.PermitUncheckedError();
 
-    // Allocate aligned buffer.
-    read_async_info->buf_.Alignment(alignment);
-    read_async_info->buf_.AllocateNewBuffer(aligned_req.len);
-
-    // Set rem fields in aligned FSReadRequest.
-    aligned_req.scratch = read_async_info->buf_.BufferStart();
+    AlignedBuffer* aligned_read_buffer =
+        direct_io_buffer != nullptr ? direct_io_buffer : &read_async_info->buf_;
+    aligned_read_buffer->Alignment(alignment);
+    Status allocate_status = aligned_read_buffer->AllocateNewBuffer(
+        aligned_req.len, direct_io_allocator);
+    if (!allocate_status.ok()) {
+      delete read_async_info;
+      return status_to_io_status(std::move(allocate_status));
+    }
+    aligned_req.scratch = aligned_read_buffer->BufferStart();
 
     // Set user provided fields to populate back in callback.
     read_async_info->user_scratch_ = req.scratch;
     read_async_info->user_aligned_buf_ = aligned_buf;
+    read_async_info->direct_io_buffer_ = direct_io_buffer;
     read_async_info->user_len_ = req.len;
     read_async_info->user_offset_ = req.offset;
     read_async_info->user_result_ = req.result;
 
-    assert(read_async_info->buf_.CurrentSize() == 0);
+    assert(direct_io_buffer != nullptr ||
+           read_async_info->buf_.CurrentSize() == 0);
 
     StopWatch sw(clock_, stats_, hist_type_,
                  GetFileReadHistograms(stats_, opts.io_activity),
@@ -618,20 +663,25 @@ void RandomAccessFileReader::ReadAsyncCallback(FSReadRequest& req,
     user_req.result = req.result;
     user_req.status = req.status;
 
-    read_async_info->buf_.Size(read_async_info->buf_.CurrentSize() +
-                               req.result.size());
+    size_t current_size = req.result.size();
+    if (read_async_info->direct_io_buffer_ == nullptr) {
+      read_async_info->buf_.Size(read_async_info->buf_.CurrentSize() +
+                                 req.result.size());
+      current_size = read_async_info->buf_.CurrentSize();
+    }
 
     size_t offset_advance_len = static_cast<size_t>(
         /*offset_passed_by_user=*/read_async_info->user_offset_ -
         /*aligned_offset=*/req.offset);
 
     size_t res_len = 0;
-    if (req.status.ok() &&
-        offset_advance_len < read_async_info->buf_.CurrentSize()) {
-      res_len =
-          std::min(read_async_info->buf_.CurrentSize() - offset_advance_len,
-                   read_async_info->user_len_);
-      if (read_async_info->user_aligned_buf_ == nullptr) {
+    if (req.status.ok() && offset_advance_len < current_size) {
+      res_len = std::min(current_size - offset_advance_len,
+                         read_async_info->user_len_);
+      if (read_async_info->direct_io_buffer_ != nullptr) {
+        user_req.scratch = read_async_info->direct_io_buffer_->BufferStart() +
+                           offset_advance_len;
+      } else if (read_async_info->user_aligned_buf_ == nullptr) {
         // Copy the data into user's scratch.
 // Clang analyzer assumes that it will take use_direct_io() == false in
 // ReadAsync and use_direct_io() == true in Callback which cannot be true.

file/random_access_file_reader.h

@@ -9,6 +9,7 @@
 
 #pragma once
 #include <atomic>
+#include <functional>
 #include <sstream>
 #include <string>
 
@@ -27,6 +28,15 @@ class SystemClock;
 
 using AlignedBuf = FSAllocationPtr;
 
+struct AlignedBufferAllocationContext {
+  // `allocator` is intentionally not owned. RandomAccessFileReader invokes it
+  // only while allocating `buffer`, before Read/ReadAsync/MultiRead returns.
+  // For ReadAsync, `buffer` is still referenced by the completion callback and
+  // must outlive the async operation.
+  AlignedBuffer* buffer = nullptr;
+  const AlignedBuffer::Allocator* allocator = nullptr;
+};
+
 // Align the request r according to alignment and return the aligned result.
 FSReadRequest Align(const FSReadRequest& r, size_t alignment);
 
@@ -97,6 +107,7 @@ class RandomAccessFileReader {
           start_time_(start_time),
           user_scratch_(nullptr),
           user_aligned_buf_(nullptr),
+          direct_io_buffer_(nullptr),
           user_offset_(0),
           user_len_(0),
           is_aligned_(false) {}
@@ -108,6 +119,10 @@ class RandomAccessFileReader {
     // Below fields stores the parameters passed by caller in case of direct_io.
     char* user_scratch_;
     AlignedBuf* user_aligned_buf_;
+    // Raw pointer to caller-owned direct-I/O storage used when forming the
+    // user-visible result in ReadAsyncCallback. The caller must keep it alive
+    // until the async operation completes or is cancelled.
+    AlignedBuffer* direct_io_buffer_;
     uint64_t user_offset_;
     size_t user_len_;
     Slice user_result_;
@@ -157,23 +172,28 @@ class RandomAccessFileReader {
   // 1. if using mmap, result is stored in a buffer other than scratch;
   // 2. if not using mmap, result is stored in the buffer starting from scratch.
   //
-  // In direct IO mode, an aligned buffer is allocated internally.
-  // 1. If aligned_buf is null, then results are copied to the buffer
-  // starting from scratch;
-  // 2. Otherwise, scratch is not used and can be null, the aligned_buf owns
-  // the internally allocated buffer on return, and the result refers to a
-  // region in aligned_buf.
-  IOStatus Read(const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
-                char* scratch, AlignedBuf* aligned_buf,
-                IODebugContext* dbg = nullptr) const;
+  // In direct IO mode, if direct_io_buffer_context is provided then it
+  // allocates the aligned buffer and the result refers to a region in
+  // direct_io_buffer_context->buffer. Otherwise, results are returned in
+  // scratch; unaligned reads use an internal aligned buffer and copy the
+  // requested subrange to scratch.
+  IOStatus Read(
+      const IOOptions& opts, uint64_t offset, size_t n, Slice* result,
+      char* scratch,
+      AlignedBufferAllocationContext* direct_io_buffer_context = nullptr,
+      IODebugContext* dbg = nullptr) const;
 
   // REQUIRES:
   // num_reqs > 0, reqs do not overlap, and offsets in reqs are increasing.
-  // In non-direct IO mode, aligned_buf should be null;
-  // In direct IO mode, aligned_buf stores the aligned buffer allocated inside
-  // MultiRead, the result Slices in reqs refer to aligned_buf.
+  // MultiRead uses direct_io_buffer_context to allocate the aligned buffer in
+  // direct IO mode. The result Slices in reqs refer to
+  // direct_io_buffer_context->buffer, so callers must keep it alive while those
+  // Slices are used. Callers should pass a default-constructed AlignedBuffer
+  // when default heap-backed allocation is sufficient. direct_io_buffer_context
+  // is ignored in non-direct IO mode.
   IOStatus MultiRead(const IOOptions& opts, FSReadRequest* reqs,
-                     size_t num_reqs, AlignedBuf* aligned_buf,
+                     size_t num_reqs,
+                     AlignedBufferAllocationContext* direct_io_buffer_context,
                      IODebugContext* dbg = nullptr) const;
 
   IOStatus Prefetch(const IOOptions& opts, uint64_t offset, size_t n,
@@ -190,10 +210,12 @@ class RandomAccessFileReader {
   IOStatus PrepareIOOptions(const ReadOptions& ro, IOOptions& opts,
                             IODebugContext* dbg = nullptr) const;
 
-  IOStatus ReadAsync(FSReadRequest& req, const IOOptions& opts,
-                     std::function<void(FSReadRequest&, void*)> cb,
-                     void* cb_arg, void** io_handle, IOHandleDeleter* del_fn,
-                     AlignedBuf* aligned_buf, IODebugContext* dbg = nullptr);
+  IOStatus ReadAsync(
+      FSReadRequest& req, const IOOptions& opts,
+      std::function<void(FSReadRequest&, void*)> cb, void* cb_arg,
+      void** io_handle, IOHandleDeleter* del_fn, AlignedBuf* aligned_buf,
+      IODebugContext* dbg = nullptr,
+      AlignedBufferAllocationContext* direct_io_buffer_context = nullptr);
 
   void ReadAsyncCallback(FSReadRequest& req, void* cb_arg);
 };

file/random_access_file_reader_test.cc

@@ -81,15 +81,91 @@ TEST_F(RandomAccessFileReaderTest, ReadDirectIO) {
   size_t offset = page_size / 2;
   size_t len = page_size / 3;
   Slice result;
-  AlignedBuf buf;
   for (Env::IOPriority rate_limiter_priority : {Env::IO_LOW, Env::IO_TOTAL}) {
     IOOptions io_opts;
     io_opts.rate_limiter_priority = rate_limiter_priority;
-    ASSERT_OK(r->Read(io_opts, offset, len, &result, nullptr, &buf));
+    AlignedBuffer direct_io_buffer;
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
+    ASSERT_OK(r->Read(io_opts, offset, len, &result, nullptr,
+                      &direct_io_context,
+                      /*dbg=*/nullptr));
     ASSERT_EQ(result.ToString(), content.substr(offset, len));
   }
 }
 
+TEST_F(RandomAccessFileReaderTest, ReadDirectIOCopiesToScratch) {
+  std::string fname = "read-direct-io-copies-to-scratch";
+  Random rand(0);
+  std::string content = rand.RandomString(kDefaultPageSize);
+  Write(fname, content);
+
+  FileOptions opts;
+  opts.use_direct_reads = true;
+  std::unique_ptr<RandomAccessFileReader> r;
+  Read(fname, opts, &r);
+  ASSERT_TRUE(r->use_direct_io());
+
+  const size_t page_size = r->file()->GetRequiredBufferAlignment();
+  size_t offset = page_size / 2;
+  size_t len = page_size / 3;
+  std::string scratch(len, '\0');
+  Slice result;
+  ASSERT_OK(r->Read(IOOptions(), offset, len, &result, scratch.data(),
+                    /*direct_io_buffer=*/nullptr, /*dbg=*/nullptr));
+  ASSERT_EQ(result.data(), scratch.data());
+  ASSERT_EQ(result.ToString(), content.substr(offset, len));
+}
+
+TEST_F(RandomAccessFileReaderTest, ReadDirectIOUsesExternalBuffer) {
+  std::string fname = "read-direct-io-external-buffer";
+  Random rand(0);
+  std::string content = rand.RandomString(kDefaultPageSize);
+  Write(fname, content);
+
+  FileOptions opts;
+  opts.use_direct_reads = true;
+  std::unique_ptr<RandomAccessFileReader> r;
+  Read(fname, opts, &r);
+  ASSERT_TRUE(r->use_direct_io());
+
+  const size_t page_size = r->file()->GetRequiredBufferAlignment();
+  const size_t offset = page_size / 4;
+  const size_t len = page_size / 2;
+
+  AlignedBuffer external_storage;
+  int allocations = 0;
+  size_t requested_size = 0;
+  size_t requested_alignment = 0;
+  AlignedBuffer::Allocator allocator =
+      [&](size_t size, size_t alignment,
+          AlignedBuffer::ExternalAllocation* out) {
+        ++allocations;
+        requested_size = size;
+        requested_alignment = alignment;
+        external_storage.Alignment(alignment);
+        external_storage.AllocateNewBuffer(size);
+        out->data = external_storage.BufferStart();
+        out->size = external_storage.Capacity();
+        out->owner =
+            FSAllocationPtr(external_storage.BufferStart(), [](void*) {});
+        return Status::OK();
+      };
+
+  AlignedBuffer direct_io_buffer;
+  AlignedBufferAllocationContext direct_io_context{&direct_io_buffer,
+                                                   &allocator};
+  Slice result;
+  ASSERT_OK(r->Read(IOOptions(), offset, len, &result, /*scratch=*/nullptr,
+                    &direct_io_context, /*dbg=*/nullptr));
+  ASSERT_EQ(result.ToString(), content.substr(offset, len));
+
+  ASSERT_EQ(allocations, 1);
+  ASSERT_EQ(requested_alignment, page_size);
+  ASSERT_EQ(requested_size, page_size);
+  ASSERT_EQ(direct_io_buffer.BufferStart(), external_storage.BufferStart());
+  ASSERT_EQ(result.data(), external_storage.BufferStart() + offset);
+}
+
 TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
   std::vector<FSReadRequest> aligned_reqs;
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
@@ -146,10 +222,11 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     std::vector<FSReadRequest> reqs;
     reqs.push_back(std::move(r0));
     reqs.push_back(std::move(r1));
-    AlignedBuf aligned_buf;
+    AlignedBuffer direct_io_buffer;
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
     IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(),
+                           &direct_io_context, &dbg));
 
     AssertResult(content, reqs);
 
@@ -192,10 +269,11 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     reqs.push_back(std::move(r0));
     reqs.push_back(std::move(r1));
     reqs.push_back(std::move(r2));
-    AlignedBuf aligned_buf;
+    AlignedBuffer direct_io_buffer;
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
     IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(),
+                           &direct_io_context, &dbg));
 
     AssertResult(content, reqs);
 
@@ -238,10 +316,11 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     reqs.push_back(std::move(r0));
     reqs.push_back(std::move(r1));
     reqs.push_back(std::move(r2));
-    AlignedBuf aligned_buf;
+    AlignedBuffer direct_io_buffer;
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
     IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(),
+                           &direct_io_context, &dbg));
 
     AssertResult(content, reqs);
 
@@ -276,10 +355,11 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
     std::vector<FSReadRequest> reqs;
     reqs.push_back(std::move(r0));
     reqs.push_back(std::move(r1));
-    AlignedBuf aligned_buf;
+    AlignedBuffer direct_io_buffer;
+    AlignedBufferAllocationContext direct_io_context{&direct_io_buffer};
     IODebugContext dbg;
-    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(), &aligned_buf,
-                           &dbg));
+    ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(),
+                           &direct_io_context, &dbg));
 
     AssertResult(content, reqs);
 
@@ -299,6 +379,71 @@ TEST_F(RandomAccessFileReaderTest, MultiReadDirectIO) {
   ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
+TEST_F(RandomAccessFileReaderTest, MultiReadDirectIOUsesExternalBuffer) {
+  std::string fname = "multi-read-direct-io-external-buffer";
+  Random rand(0);
+  std::string content = rand.RandomString(3 * kDefaultPageSize);
+  Write(fname, content);
+
+  FileOptions opts;
+  opts.use_direct_reads = true;
+  std::unique_ptr<RandomAccessFileReader> r;
+  Read(fname, opts, &r);
+  ASSERT_TRUE(r->use_direct_io());
+
+  const size_t page_size = r->file()->GetRequiredBufferAlignment();
+  FSReadRequest r0;
+  r0.offset = page_size / 4;
+  r0.len = page_size / 2;
+  r0.scratch = nullptr;
+
+  FSReadRequest r1;
+  r1.offset = 2 * page_size + page_size / 4;
+  r1.len = page_size / 2;
+  r1.scratch = nullptr;
+
+  std::vector<FSReadRequest> reqs;
+  reqs.push_back(std::move(r0));
+  reqs.push_back(std::move(r1));
+
+  AlignedBuffer external_storage;
+  int allocations = 0;
+  size_t requested_size = 0;
+  size_t requested_alignment = 0;
+  AlignedBuffer::Allocator allocator =
+      [&](size_t size, size_t alignment,
+          AlignedBuffer::ExternalAllocation* out) {
+        ++allocations;
+        requested_size = size;
+        requested_alignment = alignment;
+        external_storage.Alignment(alignment);
+        external_storage.AllocateNewBuffer(size);
+        out->data = external_storage.BufferStart();
+        out->size = external_storage.Capacity();
+        out->owner =
+            FSAllocationPtr(external_storage.BufferStart(), [](void*) {});
+        return Status::OK();
+      };
+
+  AlignedBuffer direct_io_buffer;
+  AlignedBufferAllocationContext direct_io_context{&direct_io_buffer,
+                                                   &allocator};
+  ASSERT_OK(r->MultiRead(IOOptions(), reqs.data(), reqs.size(),
+                         &direct_io_context, /*dbg=*/nullptr));
+  AssertResult(content, reqs);
+
+  ASSERT_EQ(allocations, 1);
+  ASSERT_EQ(requested_alignment, page_size);
+  ASSERT_EQ(requested_size, 2 * page_size);
+  ASSERT_EQ(direct_io_buffer.BufferStart(), external_storage.BufferStart());
+  const char* storage_begin = external_storage.BufferStart();
+  const char* storage_end = storage_begin + external_storage.Capacity();
+  for (const auto& req : reqs) {
+    ASSERT_GE(req.result.data(), storage_begin);
+    ASSERT_LE(req.result.data() + req.result.size(), storage_end);
+  }
+}
+
 TEST(FSReadRequest, Align) {
   FSReadRequest r;
   r.offset = 2000;

folly.mk

@@ -98,7 +98,31 @@ endif  # FMT_SOURCE_PATH
 	PLATFORM_LDFLAGS += -lglog
 endif
 
-FOLLY_COMMIT_HASH = 3b0eed0a128c484a2b077546c3e08c824a311357
+FOLLY_COMMIT_HASH = 548b16da0b3cc887d69cdb6ae06496ad8a2a9276
+FOLLY_GETDEPS_CACHE_DIR = /tmp/rocksdb-getdeps-cache
+
+define restore_folly_getdeps_downloads
+	@cd third-party/folly && \
+		DOWNLOAD_DIR=`$(PYTHON) build/fbcode_builder/getdeps.py show-inst-dir | sed 's|/installed/.*|/downloads|'` && \
+		mkdir -p "$$DOWNLOAD_DIR" && \
+		CACHE_DIR="$(FOLLY_GETDEPS_CACHE_DIR)" && \
+		mkdir -p "$$CACHE_DIR" && \
+		echo "Restoring cached downloads..." && \
+		if ls "$$CACHE_DIR"/*.tar.gz "$$CACHE_DIR"/*.tar.xz "$$CACHE_DIR"/*.zip >/dev/null 2>&1; then \
+			cp -n "$$CACHE_DIR"/*.tar.gz "$$CACHE_DIR"/*.tar.xz "$$CACHE_DIR"/*.zip "$$DOWNLOAD_DIR/" 2>/dev/null || true; \
+		fi && \
+		echo "Handling known unreliable downloads with fallback mirrors..." && \
+		$(PYTHON) ../../build_tools/getdeps_fallback_mirror.py "$$DOWNLOAD_DIR" "$$CACHE_DIR" build/fbcode_builder/manifests
+endef
+
+define cache_folly_getdeps_downloads
+	@cd third-party/folly && \
+		DOWNLOAD_DIR=`$(PYTHON) build/fbcode_builder/getdeps.py show-inst-dir | sed 's|/installed/.*|/downloads|'` && \
+		CACHE_DIR="$(FOLLY_GETDEPS_CACHE_DIR)" && \
+		if ls "$$DOWNLOAD_DIR"/*.tar.gz "$$DOWNLOAD_DIR"/*.tar.xz "$$DOWNLOAD_DIR"/*.zip >/dev/null 2>&1; then \
+			cp -n "$$DOWNLOAD_DIR"/*.tar.gz "$$DOWNLOAD_DIR"/*.tar.xz "$$DOWNLOAD_DIR"/*.zip "$$CACHE_DIR/" 2>/dev/null || true; \
+		fi
+endef
 
 # For public CI runs, checkout folly in a way that can build with RocksDB.
 # This is mostly intended as a test-only simulation of Meta-internal folly
@@ -117,26 +141,11 @@ checkout_folly:
 	@# const mismatch
 	perl -pi -e 's/: environ/: (const char**)(environ)/' third-party/folly/folly/Subprocess.cpp
 	@# Restore cached downloads and handle unreliable mirrors with fallback
-	@cd third-party/folly && \
-		DOWNLOAD_DIR=`$(PYTHON) build/fbcode_builder/getdeps.py show-inst-dir | sed 's|/installed/.*|/downloads|'` && \
-		mkdir -p "$$DOWNLOAD_DIR" && \
-		CACHE_DIR="/tmp/rocksdb-getdeps-cache" && \
-		mkdir -p "$$CACHE_DIR" && \
-		echo "Restoring cached downloads..." && \
-		if ls "$$CACHE_DIR"/*.tar.gz "$$CACHE_DIR"/*.tar.xz "$$CACHE_DIR"/*.zip >/dev/null 2>&1; then \
-			cp -n "$$CACHE_DIR"/*.tar.gz "$$CACHE_DIR"/*.tar.xz "$$CACHE_DIR"/*.zip "$$DOWNLOAD_DIR/" 2>/dev/null || true; \
-		fi && \
-		echo "Handling known unreliable downloads with fallback mirrors..." && \
-		$(PYTHON) ../../build_tools/getdeps_fallback_mirror.py "$$DOWNLOAD_DIR" "$$CACHE_DIR" build/fbcode_builder/manifests
+	$(restore_folly_getdeps_downloads)
 	@# NOTE: boost and fmt source will be needed for any build including `USE_FOLLY_LITE` builds as those depend on those headers
 	cd third-party/folly && GETDEPS_USE_WGET=1 $(PYTHON) build/fbcode_builder/getdeps.py fetch boost && GETDEPS_USE_WGET=1 $(PYTHON) build/fbcode_builder/getdeps.py fetch fmt
 	@# Update cache with any new downloads
-	@cd third-party/folly && \
-		DOWNLOAD_DIR=`$(PYTHON) build/fbcode_builder/getdeps.py show-inst-dir | sed 's|/installed/.*|/downloads|'` && \
-		CACHE_DIR="/tmp/rocksdb-getdeps-cache" && \
-		if ls "$$DOWNLOAD_DIR"/*.tar.gz "$$DOWNLOAD_DIR"/*.tar.xz "$$DOWNLOAD_DIR"/*.zip >/dev/null 2>&1; then \
-			cp -n "$$DOWNLOAD_DIR"/*.tar.gz "$$DOWNLOAD_DIR"/*.tar.xz "$$DOWNLOAD_DIR"/*.zip "$$CACHE_DIR/" 2>/dev/null || true; \
-		fi
+	$(cache_folly_getdeps_downloads)
 
 CXX_M_FLAGS = $(filter -m%, $(CXXFLAGS))
 
@@ -155,6 +164,8 @@ build_folly:
 		echo "Please run checkout_folly first"; \
 		false; \
 	fi
+	@# Restore fallback archives after the cleanup above removes downloads.
+	$(restore_folly_getdeps_downloads)
 	cd third-party/folly && \
 		CXXFLAGS=" $(CXX_M_FLAGS) -DHAVE_CXX11_ATOMIC " GETDEPS_USE_WGET=1 $(PYTHON) build/fbcode_builder/getdeps.py build $(FOLLY_BUILD_FLAGS)
 	@# In the folly build, glog and gflags are only built as dynamic libraries,

include/rocksdb/blob_file_partition_strategy.h

@@ -1,7 +1,8 @@
-// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) Meta Platforms, Inc. and affiliates.
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
+
 // Copyright (c) 2011 The LevelDB Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

include/rocksdb/c.h

@@ -205,6 +205,8 @@ extern ROCKSDB_LIBRARY_API rocksdb_t* rocksdb_open(
 extern ROCKSDB_LIBRARY_API rocksdb_t* rocksdb_open_with_ttl(
     const rocksdb_options_t* options, const char* name, int ttl, char** errptr);
 
+/* If error_if_wal_file_exists is non-zero, returns an error when a non-empty
+ * WAL file exists. Empty WAL files are tolerated. */
 extern ROCKSDB_LIBRARY_API rocksdb_t* rocksdb_open_for_read_only(
     const rocksdb_options_t* options, const char* name,
     unsigned char error_if_wal_file_exists, char** errptr);
@@ -450,6 +452,8 @@ extern ROCKSDB_LIBRARY_API rocksdb_t* rocksdb_open_column_families_with_ttl(
     rocksdb_column_family_handle_t** column_family_handles, const int* ttls,
     char** errptr);
 
+/* If error_if_wal_file_exists is non-zero, returns an error when a non-empty
+ * WAL file exists. Empty WAL files are tolerated. */
 extern ROCKSDB_LIBRARY_API rocksdb_t*
 rocksdb_open_for_read_only_column_families(
     const rocksdb_options_t* options, const char* name, int num_column_families,
@@ -1216,11 +1220,15 @@ rocksdb_block_based_options_set_data_block_index_type(
 enum {
   rocksdb_block_based_table_index_block_search_type_binary = 0,
   rocksdb_block_based_table_index_block_search_type_interpolation = 1,
+  rocksdb_block_based_table_index_block_search_type_auto = 2,
 };
 extern ROCKSDB_LIBRARY_API void
 rocksdb_block_based_options_set_index_block_search_type(
     rocksdb_block_based_table_options_t*, int);  // uses one of the above enums
 extern ROCKSDB_LIBRARY_API void
+rocksdb_block_based_options_set_uniform_cv_threshold(
+    rocksdb_block_based_table_options_t*, double);
+extern ROCKSDB_LIBRARY_API void
 rocksdb_block_based_options_set_data_block_hash_ratio(
     rocksdb_block_based_table_options_t* options, double v);
 // rocksdb_block_based_options_set_hash_index_allow_collision()
@@ -1818,6 +1826,11 @@ extern ROCKSDB_LIBRARY_API void rocksdb_options_set_recycle_log_file_num(
     rocksdb_options_t*, size_t);
 extern ROCKSDB_LIBRARY_API size_t
 rocksdb_options_get_recycle_log_file_num(rocksdb_options_t*);
+// Set/get DBOptions::async_wal_precreate.
+extern ROCKSDB_LIBRARY_API void rocksdb_options_set_async_wal_precreate(
+    rocksdb_options_t*, unsigned char);
+extern ROCKSDB_LIBRARY_API unsigned char
+rocksdb_options_get_async_wal_precreate(rocksdb_options_t*);
 extern ROCKSDB_LIBRARY_API void
 rocksdb_options_set_soft_pending_compaction_bytes_limit(rocksdb_options_t* opt,
                                                         size_t v);
@@ -1981,6 +1994,12 @@ extern ROCKSDB_LIBRARY_API void rocksdb_options_set_memtable_huge_page_size(
 extern ROCKSDB_LIBRARY_API size_t
 rocksdb_options_get_memtable_huge_page_size(rocksdb_options_t*);
 
+extern ROCKSDB_LIBRARY_API void
+rocksdb_options_set_memtable_batch_lookup_optimization(rocksdb_options_t*,
+                                                       unsigned char);
+extern ROCKSDB_LIBRARY_API unsigned char
+rocksdb_options_get_memtable_batch_lookup_optimization(rocksdb_options_t*);
+
 extern ROCKSDB_LIBRARY_API void rocksdb_options_set_max_successive_merges(
     rocksdb_options_t*, size_t);
 extern ROCKSDB_LIBRARY_API size_t
@@ -2206,7 +2225,8 @@ enum {
   rocksdb_filter_block_read_byte,
   rocksdb_compression_dict_block_read_byte,
   rocksdb_metadata_block_read_byte,
-  rocksdb_total_metric_count = 85
+  rocksdb_blob_cache_read_byte,
+  rocksdb_total_metric_count = 86
 };
 
 extern ROCKSDB_LIBRARY_API void rocksdb_set_perf_level(int);
@@ -2386,6 +2406,11 @@ extern ROCKSDB_LIBRARY_API void rocksdb_readoptions_set_async_io(
     rocksdb_readoptions_t*, unsigned char);
 extern ROCKSDB_LIBRARY_API unsigned char rocksdb_readoptions_get_async_io(
     rocksdb_readoptions_t*);
+extern ROCKSDB_LIBRARY_API void
+rocksdb_readoptions_set_optimize_multiget_for_io(rocksdb_readoptions_t*,
+                                                 unsigned char);
+extern ROCKSDB_LIBRARY_API unsigned char
+rocksdb_readoptions_get_optimize_multiget_for_io(rocksdb_readoptions_t*);
 extern ROCKSDB_LIBRARY_API void rocksdb_readoptions_set_timestamp(
     rocksdb_readoptions_t*, const char* ts, size_t tslen);
 extern ROCKSDB_LIBRARY_API void rocksdb_readoptions_set_iter_start_ts(

include/rocksdb/cleanable.h

@@ -107,6 +107,7 @@ class SharedCleanablePtr {
   Cleanable* operator->();
   // Get as raw pointer to Cleanable
   Cleanable* get();
+  const Cleanable* get() const;
 
   // Creates a (virtual) copy of this SharedCleanablePtr and registers its
   // destruction with target, so that the cleanups registered with the

include/rocksdb/convenience.h

@@ -432,9 +432,33 @@ Status GetOptionsFromString(const ConfigOptions& config_options,
                             const Options& base_options,
                             const std::string& opts_str, Options* new_options);
 
+// StringToMap parses a serialized options string into a map. Each
+// resulting map value is in a self-contained form (it can be embedded
+// directly in a `key=value;` context -- e.g. SetOptions -- without further
+// escaping). Specifically: nested braced values from the input are
+// preserved with their outer braces. Permissive: accepts both braced and
+// unbraced forms; values not requiring braces are returned as-is.
+// Example:
+//   "filter_policy={id=ribbonfilter:10;bloom_before_level=-1};block_size=4096"
+// produces:
+//   {filter_policy -> "{id=ribbonfilter:10;bloom_before_level=-1}",
+//    block_size    -> "4096"}
 Status StringToMap(const std::string& opts_str,
                    std::unordered_map<std::string, std::string>* opts_map);
 
+// MapToString is the inverse of StringToMap: a naive `key=value;` join.
+// Each map value must already be in self-contained form (as returned by
+// StringToMap) -- i.e. simple text or a single balanced `{...}` block.
+// Values from StringToMap satisfy this property, so the round-trip
+//
+//   StringToMap(MapToString(StringToMap(s))) == StringToMap(s)
+//
+// holds. Callers building a map by hand are responsible for ensuring
+// values are self-contained; raw values containing `;` or starting with
+// `{` without matching `}` won't round-trip.
+Status MapToString(const std::unordered_map<std::string, std::string>& opts_map,
+                   std::string* opts_str);
+
 // Request stopping background work, if wait is true wait until it's done
 void CancelAllBackgroundWork(DB* db, bool wait = false);
 

include/rocksdb/db.h

@@ -172,6 +172,10 @@ class DB {
 
   // Open the database for read only.
   //
+  // If error_if_wal_file_exists is true, returns an error when a non-empty
+  // WAL file exists. Empty WAL files can be left behind by features such as
+  // async WAL precreation and are tolerated.
+  //
   static Status OpenForReadOnly(const Options& options, const std::string& name,
                                 std::unique_ptr<DB>* dbptr,
                                 bool error_if_wal_file_exists = false);
@@ -183,6 +187,10 @@ class DB {
   // to specify default column family. The default column family name is
   // 'default' and it's stored in ROCKSDB_NAMESPACE::kDefaultColumnFamilyName
   //
+  // If error_if_wal_file_exists is true, returns an error when a non-empty
+  // WAL file exists. Empty WAL files can be left behind by features such as
+  // async WAL precreation and are tolerated.
+  //
   static Status OpenForReadOnly(
       const DBOptions& db_options, const std::string& name,
       const std::vector<ColumnFamilyDescriptor>& column_families,

include/rocksdb/io_dispatcher.h

@@ -152,6 +152,11 @@ class BlockBasedTable;
 struct JobOptions {
   uint64_t io_coalesce_threshold = 16 * 1024;
   ReadOptions read_options;
+
+  // True when IOJob::block_handles is already sorted by file offset. Callers
+  // that can guarantee sorted order may set this to let IODispatcher skip
+  // defensive sorting before cache lookup and coalescing.
+  bool block_handles_are_sorted = false;
 };
 
 class IOJob {
@@ -255,6 +260,17 @@ class ReadSet {
   Status PollAndProcessAsyncIO(
       const std::shared_ptr<AsyncIOState>& async_state);
 
+  // Release memory budget acquired for a prefetched block.
+  void ReleasePrefetchMemory(size_t block_index);
+
+  // Stop tracking one block from an in-flight async IO request. If this was
+  // the last block using the request, abort and delete the IO handle before the
+  // async state is released.
+  void ReleaseAsyncIOForBlock(size_t block_index);
+
+  // Delete a completed or aborted async IO handle exactly once.
+  void DeleteAsyncIOHandle(const std::shared_ptr<AsyncIOState>& async_state);
+
   // Perform synchronous read for a specific block
   Status SyncRead(size_t block_index);
 

include/rocksdb/listener.h

@@ -674,16 +674,69 @@ class EventListener : public Customizable {
   // Note that the this function must be implemented in a way such that
   // it should not run for an extended period of time before the function
   // returns.  Otherwise, RocksDB may be blocked.
+  //
+  // WART: this callback is skipped during DB shutdown, so a compaction
+  // that commits during shutdown may never be observed by listeners.
   virtual void OnCompactionBegin(DB* /*db*/, const CompactionJobInfo& /*ci*/) {}
 
+  // A callback function for RocksDB which will be called when a registered
+  // RocksDB has finished writing a compaction job's output files, but
+  // *before* the manifest write commits the new Version (i.e. before
+  // input files are released and output files become visible to readers
+  // and the compaction picker). At this point the input files in
+  // `ci.input_files` still have `FileMetaData::being_compacted == true`,
+  // so no other thread can pick them up for a new compaction.
+  //
+  // This callback fires strictly between `OnCompactionBegin` and
+  // `OnCompactionCompleted` for the same compaction. It is the right
+  // place for listeners to clean up their own bookkeeping of which input
+  // files they think are being compacted: doing it here, rather than in
+  // `OnCompactionCompleted`, avoids a race where `OnCompactionBegin` for
+  // the same file fires before `OnCompactionCompleted` for the previous
+  // compaction. The default implementation is a no-op.
+  //
+  // Unlike `OnCompactionCompleted`, `ci.status` does not reflect the
+  // final outcome: the manifest commit has not yet occurred, so it
+  // does not capture commit failures. Other `CompactionJobInfo` quirks
+  // that also apply to `OnCompactionCompleted`: for trivial moves and
+  // FIFO deletion-only compactions, `ci.stats` is minimal (no
+  // `CompactionJob` runs), and FIFO deletions have no output files.
+  //
+  // As with `OnCompactionCompleted`, the DB mutex is released for the
+  // duration of this callback, but other manifest writers may be waiting,
+  // so cheap implementations are strongly preferred.
+  //
+  // WART: this callback is skipped during DB shutdown, so a compaction
+  // that commits during shutdown may never be observed by listeners.
+  //
+  // @param db a pointer to the rocksdb instance which just compacted a file.
+  // @param ci a reference to a CompactionJobInfo struct. 'ci' is released
+  //  after this function is returned, and must be copied if it is needed
+  //  outside of this function.
+  virtual void OnCompactionPreCommit(DB* /*db*/,
+                                     const CompactionJobInfo& /*ci*/) {}
+
   // A callback function for RocksDB which will be called whenever
   // a registered RocksDB compacts a file. The default implementation
   // is a no-op.
   //
+  // At the time this callback fires, the manifest commit has applied:
+  // output files in `ci.output_files` are live in the DB (visible to
+  // readers and the compaction picker, and possibly already picked up
+  // by another compaction), and input files in `ci.input_files` have
+  // been removed from the live Version with `being_compacted == false`
+  // (their on-disk files may still exist if held by snapshots / iterators
+  // / pending physical deletion; see `OnTableFileDeleted`). To observe
+  // state *before* input files are released, use
+  // `OnCompactionPreCommit` instead.
+  //
   // Note that this function must be implemented in a way such that
   // it should not run for an extended period of time before the function
   // returns. Otherwise, RocksDB may be blocked.
   //
+  // WART: this callback is skipped during DB shutdown, so a compaction
+  // that commits during shutdown may never be observed by listeners.
+  //
   // @param db a pointer to the rocksdb instance which just compacted
   //   a file.
   // @param ci a reference to a CompactionJobInfo struct. 'ci' is released
@@ -911,6 +964,17 @@ class EventListener : public Customizable {
   virtual void OnBackgroundJobPressureChanged(
       DB* /*db*/, const BackgroundJobPressure& /*pressure*/) {}
 
+  // A callback function for RocksDB which will be called once when a DB begins
+  // shutting down, before background work cancellation publishes the DB's
+  // shutdown state. This callback can also fire during cleanup of a failed
+  // DB::Open() attempt, in which case the DB pointer refers to the DB instance
+  // that failed to open and was never returned to the application.
+  //
+  // Background work may still be running when this callback fires, and other
+  // listener callbacks may still run concurrently or afterward. Implementations
+  // should not call blocking DB APIs or run for an extended period of time.
+  virtual void OnDBShutdownBegin(DB* /*db*/) {}
+
   ~EventListener() override {}
 };
 

include/rocksdb/options.h

@@ -52,6 +52,7 @@ class MergeOperator;
 class Snapshot;
 class MemTableRepFactory;
 class RateLimiter;
+class ReadScopedBlockBufferProvider;
 class Slice;
 class Statistics;
 class InternalKeyComparator;
@@ -975,6 +976,17 @@ struct DBOptions {
   // Default: 0
   size_t recycle_log_file_num = 0;
 
+  // EXPERIMENTAL: If true, RocksDB asynchronously precreates the next WAL file
+  // so foreground memtable switching can usually avoid the filesystem latency
+  // of creating a new WAL. The precreated file is only reserved empty storage;
+  // it does not become a logical WAL and is not added to WAL tracking until it
+  // is consumed by a foreground WAL rotation.
+  //
+  // The option is sanitized to false when recycle_log_file_num is non-zero.
+  //
+  // Default: false
+  bool async_wal_precreate = false;
+
   // The manifest file is rolled over on reaching this limit AND the
   // space amp limit described in max_manifest_space_amp_pct. More trade-off
   // details there.
@@ -992,6 +1004,13 @@ struct DBOptions {
   //
   // This option is mutable with SetDBOptions(), taking effect on the next
   // manifest write (e.g. completed DB compaction or flush).
+  //
+  // For MANIFEST write batches containing foreground operations like external
+  // file ingestion/import, DeleteFilesInRange, CreateColumnFamily, and
+  // DropColumnFamily, the effective limit is relaxed by 25% to reduce the
+  // likelihood of user operations blocking on MANIFEST rotation.
+  // Background-only batches (flush and compaction) use the configured or
+  // auto-tuned limit directly.
   uint64_t max_manifest_file_size = 1024 * 1024 * 1024;
 
   // If true, on DB close, read back the entire MANIFEST file and validate
@@ -2368,6 +2387,30 @@ struct ReadOptions {
   // reads.
   const UserDefinedIndexFactory* table_index_factory = nullptr;
 
+  // EXPERIMENTAL: Optional non-owning provider for data-block storage pinned by
+  // scans using this ReadOptions. Applications that set it are attempting
+  // advanced performance optimizations and are responsible for ensuring the
+  // provider outlives the iterator/read scope and any provider-backed data that
+  // can remain pinned by that scope.
+  //
+  // This is a raw pointer rather than a shared_ptr because ReadOptions is
+  // copied through stack frames and iterator internals; a shared_ptr would add
+  // refcount overhead to those copies. An internal shadow ReadOptions that
+  // strips ownership would add maintenance overhead for this advanced option.
+  //
+  // Current support is limited to block-based table iterators and MultiScan
+  // data-block reads, and is ignored when mmap reads are enabled. When set,
+  // supported scan reads bypass the data-block cache and use provider-backed
+  // final data-block memory. RocksDB may still use ordinary temporary scratch
+  // for serialized block bytes, such as when a block may be compressed. When
+  // unset, scans use the normal RocksDB data-block backing for the table: use
+  // the configured block cache when present, otherwise use RocksDB-owned block
+  // memory. Index/filter blocks keep their normal block-cache behavior.
+  //
+  // TODO: Extend support to point lookups (Get/MultiGet) once those paths can
+  // preserve provider-backed block ownership.
+  ReadScopedBlockBufferProvider* read_scoped_block_buffer_provider = nullptr;
+
   // *** END options only relevant to iterators or scans ***
 
   // *** BEGIN options for RocksDB internal use only ***

include/rocksdb/perf_context.h

@@ -106,7 +106,7 @@ struct PerfContextBase {
   uint64_t compressed_sec_cache_compressed_bytes;
 
   uint64_t block_checksum_time;    // total nanos spent on block checksum
-  uint64_t block_decompress_time;   // total nanos spent on block decompression
+  uint64_t block_decompress_time;  // total nanos spent on block decompression
   uint64_t block_decompress_count;  // total number of block decompressions
 
   uint64_t get_read_bytes;       // bytes for vals returned by Get
@@ -114,6 +114,7 @@ struct PerfContextBase {
   uint64_t iter_read_bytes;      // bytes for keys/vals decoded by iterator
 
   uint64_t blob_cache_hit_count;  // total number of blob cache hits
+  uint64_t blob_cache_read_byte;  // total bytes read from blob cache
   uint64_t blob_read_count;       // total number of blob reads (with IO)
   uint64_t blob_read_byte;        // total number of bytes from blob reads
   uint64_t blob_read_time;        // total nanos spent on blob reads

include/rocksdb/statistics.h

@@ -223,6 +223,16 @@ enum Tickers : uint32_t {
   GET_UPDATES_SINCE_CALLS,
   WAL_FILE_SYNCED,  // Number of times WAL sync is done
   WAL_FILE_BYTES,   // Number of bytes written to WAL
+  // Number of WAL rotations that consumed an async precreated WAL.
+  WAL_PRECREATE_HIT,
+  // Number of WAL rotations that found no async precreated WAL to consume.
+  WAL_PRECREATE_MISS,
+  // Number of WAL rotations that waited for an in-flight WAL precreation.
+  WAL_PRECREATE_WAITED,
+  // Total foreground wait time for in-flight WAL precreation.
+  WAL_PRECREATE_WAIT_MICROS,
+  // Number of async WAL precreation attempts that failed.
+  WAL_PRECREATE_FAILED,
 
   // Writes can be processed by requesting thread or by the thread at the
   // head of the writers queue.

include/rocksdb/table.h

@@ -23,6 +23,7 @@
 #include <unordered_map>
 
 #include "rocksdb/cache.h"
+#include "rocksdb/cleanable.h"
 #include "rocksdb/customizable.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
@@ -46,6 +47,67 @@ struct ConfigOptions;
 struct EnvOptions;
 class UserDefinedIndexFactory;
 
+// Hook for providing read-scoped storage for data blocks read from SST files.
+// This is configured through C++ options rather than OPTIONS files.
+//
+// Current support is limited to block-based table iterator scans and MultiScan
+// data-block reads. Reads using mmap ignore this provider and use normal
+// RocksDB block backing.
+//
+// The provider backs final data-block contents pinned by the scan. RocksDB may
+// still use ordinary temporary scratch for serialized block bytes, such as when
+// reading a block that may be compressed before decompressing or copying the
+// final data block into provider-backed storage.
+//
+// This is separate from MemoryAllocator because each allocation needs a
+// per-lease cleanup handle that RocksDB can attach to pinned blocks/slices, and
+// direct-I/O reads that use provider-backed read buffers need the requested
+// alignment to be passed to the provider.
+//
+// TODO: Extend support to point lookups (Get/MultiGet) once those paths can
+// preserve provider-backed block ownership.
+//
+// Requirements:
+// - If the same provider instance is shared by multiple concurrently active
+//   readers, `Allocate()` must be safe to call concurrently.
+// - `Lease::data` must point to at least `size` bytes of writable contiguous
+//   memory that remains valid until every copy of `Lease::cleanup` is reset.
+// - `Lease::data` must be aligned to `alignment` bytes, where `alignment` is a
+//   power of two and `1` means no special alignment requirement.
+// - When `alignment` is greater than 1, `Lease::size` must also be a multiple
+//   of `alignment` so it can be used as direct-I/O backing storage.
+// - `Lease::cleanup` must be non-null on success. Its cleanup may run on any
+//   thread that releases the last RocksDB reference. If the cleanup touches
+//   provider or other shared state, it must synchronize with Allocate() and
+//   other provider cleanup callbacks.
+// - After `Allocate()` succeeds, RocksDB releases `Lease::cleanup` on all
+//   paths, including later I/O or decompression failure.
+class ReadScopedBlockBufferProvider {
+ public:
+  // A Lease hands one writable backing allocation from the provider to
+  // RocksDB. For a provider-backed block, the final BlockContents data points
+  // into this allocation and RocksDB attaches `cleanup` to the resulting Blocks
+  // and any slices pinned from them. File-read scratch, copying, and
+  // decompression choices are implementation details outside this contract.
+  //
+  // The provider controls allocation reclamation. RocksDB keeps the data valid
+  // by copying `cleanup`; the provider must not reuse or release `data` until
+  // every copy of `cleanup` has been reset. `size` is the usable backing
+  // allocation size and may be larger than the requested allocation size. For
+  // direct-I/O reads, `size` must be a multiple of the requested alignment.
+  struct Lease {
+    // Writable contiguous memory for the loaded block.
+    char* data = nullptr;
+    size_t size = 0;
+    // Reclaims `data` after all derived pinned key/value slices are released.
+    SharedCleanablePtr cleanup;
+  };
+
+  virtual ~ReadScopedBlockBufferProvider() = default;
+
+  virtual Status Allocate(size_t size, size_t alignment, Lease* out) = 0;
+};
+
 // Types of checksums to use for checking integrity of logical blocks within
 // files. All checksums currently use 32 bits of checking power (1 in 4B
 // chance of failing to detect random corruption). Traditionally, the actual

include/rocksdb/utilities/options_type.h

@@ -453,11 +453,13 @@ class OptionTypeInfo {
                                        const std::string& value, void* addr) {
           std::map<std::string, std::string> map;
           Status s;
+          // Permit `{k1=v1;k2=v2}` (as serialized) or bare `k1=v1;k2=v2`.
+          std::string stripped = OptionTypeInfo::StripOuterBraces(value);
           for (size_t start = 0, end = 0;
-               s.ok() && start < value.size() && end != std::string::npos;
+               s.ok() && start < stripped.size() && end != std::string::npos;
                start = end + 1) {
             std::string token;
-            s = OptionTypeInfo::NextToken(value, item_separator, start, &end,
+            s = OptionTypeInfo::NextToken(stripped, item_separator, start, &end,
                                           &token);
             if (s.ok() && !token.empty()) {
               size_t pos = token.find(kv_separator);
@@ -947,6 +949,14 @@ class OptionTypeInfo {
   static Status NextToken(const std::string& opts, char delimiter, size_t start,
                           size_t* end, std::string* token);
 
+  // Strips a single layer of outer "{" / "}" wrapping iff the leading '{'
+  // pairs with the trailing '}'. This permissively unwraps values that
+  // could legitimately be either braced or bare (e.g. `{a:b:c}` and
+  // `a:b:c` are accepted equivalently by list-style parsers). The check
+  // is done at brace depth: `{a}:{b}` is left as-is because the leading
+  // '{' closes before the end of the string.
+  static std::string StripOuterBraces(const std::string& value);
+
   constexpr static const char* kIdPropName() { return "id"; }
   constexpr static const char* kIdPropSuffix() { return ".id"; }
 
@@ -995,12 +1005,16 @@ Status ParseArray(const ConfigOptions& config_options,
 
   ConfigOptions copy = config_options;
   copy.ignore_unsupported_options = false;
+  // Permit the caller to pass either bare `item1:item2` or wrapped
+  // `{item1:item2}`. Either form parses identically.
+  std::string stripped = OptionTypeInfo::StripOuterBraces(value);
   size_t i = 0, start = 0, end = 0;
-  for (; status.ok() && i < kSize && start < value.size() &&
+  for (; status.ok() && i < kSize && start < stripped.size() &&
          end != std::string::npos;
        i++, start = end + 1) {
     std::string token;
-    status = OptionTypeInfo::NextToken(value, separator, start, &end, &token);
+    status =
+        OptionTypeInfo::NextToken(stripped, separator, start, &end, &token);
     if (status.ok()) {
       status = elem_info.Parse(copy, name, token, &((*result)[i]));
       if (config_options.ignore_unsupported_options &&
@@ -1137,11 +1151,15 @@ Status ParseVector(const ConfigOptions& config_options,
   // object is valid or not.
   ConfigOptions copy = config_options;
   copy.ignore_unsupported_options = false;
+  // Permit the caller to pass either bare `item1:item2` or wrapped
+  // `{item1:item2}`. Either form parses identically.
+  std::string stripped = OptionTypeInfo::StripOuterBraces(value);
   for (size_t start = 0, end = 0;
-       status.ok() && start < value.size() && end != std::string::npos;
+       status.ok() && start < stripped.size() && end != std::string::npos;
        start = end + 1) {
     std::string token;
-    status = OptionTypeInfo::NextToken(value, separator, start, &end, &token);
+    status =
+        OptionTypeInfo::NextToken(stripped, separator, start, &end, &token);
     if (status.ok()) {
       T elem;
       status = elem_info.Parse(copy, name, token, &elem);

include/rocksdb/utilities/sorted_run_builder.h

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) Meta Platforms, Inc. and affiliates.
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).

include/rocksdb/utilities/transaction.h

@@ -234,6 +234,11 @@ class Transaction {
   // TransactionOptions.expiration. Status::TxnNotPrepared() may be returned if
   // TransactionOptions.skip_prepare is false and Prepare is not called on this
   // transaction before Commit.
+  //
+  // For TransactionDB transactions using 2PC, if Commit() returns non-OK after
+  // Prepare() succeeds, the transaction may still need to be resolved. Unless
+  // the application resolves it another way, call Rollback() before destroying
+  // the transaction or closing the DB.
   virtual Status Commit() = 0;
 
   // In addition to Commit(), also creates a snapshot of the db after all
@@ -259,7 +264,16 @@ class Transaction {
       std::shared_ptr<const Snapshot>* snapshot = nullptr);
 
   // Discard all batched writes in this transaction.
-  // FIXME: what happens if this isn't called before destruction?
+  //
+  // Transactions should normally be completed with Commit() or Rollback()
+  // before destruction and before closing the DB. Destroying a Transaction
+  // object releases its in-memory resources, but it is not a substitute for
+  // resolving a prepared transaction.
+  //
+  // Rollback() can return write errors when it needs to write rollback state,
+  // such as for prepared transactions. If it returns a retryable I/O error,
+  // recover the DB (for example by calling DB::Resume() when applicable) and
+  // retry Rollback() before closing the DB.
   virtual Status Rollback() = 0;
 
   // Records the state of the transaction for future calls to

include/rocksdb/version.h

@@ -12,8 +12,8 @@
 // NOTE: in 'main' development branch, this should be the *next*
 // minor or major version number planned for release.
 #define ROCKSDB_MAJOR 11
-#define ROCKSDB_MINOR 3
-#define ROCKSDB_PATCH 0
+#define ROCKSDB_MINOR 4
+#define ROCKSDB_PATCH 3
 
 // Make it easy to do conditional compilation based on version checks, i.e.
 // #if ROCKSDB_VERSION_GE(4, 5, 6)

java/Makefile

@@ -332,10 +332,7 @@ endif
 clean: clean-not-downloaded clean-downloaded
 
 clean-not-downloaded:
-	$(AM_V_at)rm -rf $(NATIVE_INCLUDE)
-	$(AM_V_at)rm -rf $(OUTPUT)
-	$(AM_V_at)rm -rf $(BENCHMARK_OUTPUT)
-	$(AM_V_at)rm -rf $(SAMPLES_OUTPUT)
+	$(AM_V_at)rm -rf $(NATIVE_INCLUDE) $(OUTPUT) $(BENCHMARK_OUTPUT) $(SAMPLES_OUTPUT)
 
 clean-downloaded:
 	$(AM_V_at)rm -rf $(JAVA_TEST_LIBDIR)

java/rocksjni/jni_perf_context.cc

@@ -348,6 +348,18 @@ jlong Java_org_rocksdb_PerfContext_getBlobCacheHitCount(JNIEnv*, jobject,
   return perf_context->blob_cache_hit_count;
 }
 
+/*
+ * Class:     org_rocksdb_PerfContext
+ * Method:    getBlobCacheReadByte
+ * Signature: (J)J
+ */
+jlong Java_org_rocksdb_PerfContext_getBlobCacheReadByte(JNIEnv*, jobject,
+                                                        jlong jpc_handle) {
+  ROCKSDB_NAMESPACE::PerfContext* perf_context =
+      reinterpret_cast<ROCKSDB_NAMESPACE::PerfContext*>(jpc_handle);
+  return perf_context->blob_cache_read_byte;
+}
+
 /*
  * Class:     org_rocksdb_PerfContext
  * Method:    getBlobReadCount

java/rocksjni/portal.h

@@ -5011,6 +5011,16 @@ class TickerTypeJni {
         return 0x53;
       case ROCKSDB_NAMESPACE::Tickers::WAL_FILE_BYTES:
         return 0x54;
+      case ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_HIT:
+        return -0x6C;
+      case ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_MISS:
+        return -0x6D;
+      case ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_WAITED:
+        return -0x6E;
+      case ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_WAIT_MICROS:
+        return -0x6F;
+      case ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_FAILED:
+        return -0x70;
       case ROCKSDB_NAMESPACE::Tickers::WRITE_DONE_BY_SELF:
         return 0x55;
       case ROCKSDB_NAMESPACE::Tickers::WRITE_DONE_BY_OTHER:
@@ -5509,6 +5519,16 @@ class TickerTypeJni {
         return ROCKSDB_NAMESPACE::Tickers::WAL_FILE_SYNCED;
       case 0x54:
         return ROCKSDB_NAMESPACE::Tickers::WAL_FILE_BYTES;
+      case -0x6C:
+        return ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_HIT;
+      case -0x6D:
+        return ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_MISS;
+      case -0x6E:
+        return ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_WAITED;
+      case -0x6F:
+        return ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_WAIT_MICROS;
+      case -0x70:
+        return ROCKSDB_NAMESPACE::Tickers::WAL_PRECREATE_FAILED;
       case 0x55:
         return ROCKSDB_NAMESPACE::Tickers::WRITE_DONE_BY_SELF;
       case 0x56:

java/src/main/java/org/rocksdb/PerfContext.java

@@ -184,6 +184,13 @@ public class PerfContext extends RocksObject {
     return getBlobCacheHitCount(nativeHandle_);
   }
 
+  /**
+   * @return total number of bytes read from blob cache
+   */
+  public long getBlobCacheReadByte() {
+    return getBlobCacheReadByte(nativeHandle_);
+  }
+
   /**
    * @return total number of blob reads (with IO)
    */
@@ -693,6 +700,7 @@ public class PerfContext extends RocksObject {
   private native long getMultigetReadBytes(final long handle);
   private native long getIterReadBytes(final long handle);
   private native long getBlobCacheHitCount(final long handle);
+  private native long getBlobCacheReadByte(final long handle);
   private native long getBlobReadCount(final long handle);
   private native long getBlobReadByte(final long handle);
   private native long getBlobReadTime(final long handle);

java/src/main/java/org/rocksdb/RocksDB.java

@@ -404,7 +404,7 @@ public class RocksDB extends RocksObject {
    * @param options {@link Options} instance.
    * @param path the path to the RocksDB.
    * @param errorIfWalFileExists true to raise an error when opening the db
-   *            if a Write Ahead Log file exists, false otherwise.
+   *            if a non-empty Write Ahead Log file exists, false otherwise.
    * @return a {@link RocksDB} instance on success, null if the specified
    *     {@link RocksDB} can not be opened.
    *
@@ -493,7 +493,7 @@ public class RocksDB extends RocksObject {
    * @param columnFamilyHandles will be filled with ColumnFamilyHandle instances
    *     on open.
    * @param errorIfWalFileExists true to raise an error when opening the db
-   *            if a Write Ahead Log file exists, false otherwise.
+   *            if a non-empty Write Ahead Log file exists, false otherwise.
    * @return a {@link RocksDB} instance on success, null if the specified
    *     {@link RocksDB} can not be opened.
    *

java/src/main/java/org/rocksdb/TickerType.java

@@ -394,6 +394,31 @@ public enum TickerType {
      */
     WAL_FILE_BYTES((byte) 0x54),
 
+    /**
+     * Number of WAL rotations that consumed an async precreated WAL.
+     */
+    WAL_PRECREATE_HIT((byte) -0x6C),
+
+    /**
+     * Number of WAL rotations that found no async precreated WAL to consume.
+     */
+    WAL_PRECREATE_MISS((byte) -0x6D),
+
+    /**
+     * Number of WAL rotations that waited for an in-flight WAL precreation.
+     */
+    WAL_PRECREATE_WAITED((byte) -0x6E),
+
+    /**
+     * Total foreground wait time for in-flight WAL precreation.
+     */
+    WAL_PRECREATE_WAIT_MICROS((byte) -0x6F),
+
+    /**
+     * Number of async WAL precreation attempts that failed.
+     */
+    WAL_PRECREATE_FAILED((byte) -0x70),
+
     /**
      * Writes can be processed by requesting thread or by the thread at the
      * head of the writers queue.

java/src/test/java/org/rocksdb/ReadOnlyTest.java

@@ -6,6 +6,8 @@ package org.rocksdb;
 
 import static org.assertj.core.api.Assertions.assertThat;
 
+import java.io.IOException;
+import java.nio.file.Files;
 import java.util.ArrayList;
 import java.util.Collections;
 import java.util.List;
@@ -200,11 +202,12 @@ public class ReadOnlyTest {
   }
 
   @Test(expected = RocksDBException.class)
-  public void errorIfWalFileExists() throws RocksDBException {
+  public void errorIfWalFileExists() throws RocksDBException, IOException {
     try (final Options options = new Options().setCreateIfMissing(true);
          final RocksDB ignored = RocksDB.open(options, dbFolder.getRoot().getAbsolutePath())) {
       // no-op
     }
+    Files.write(dbFolder.getRoot().toPath().resolve("999999.log"), new byte[] {1});
 
     try (final ColumnFamilyOptions cfOpts = new ColumnFamilyOptions()) {
       final List<ColumnFamilyDescriptor> cfDescriptors = Collections.singletonList(

java/src/test/java/org/rocksdb/RocksDBTest.java

@@ -1631,7 +1631,8 @@ public class RocksDBTest {
       try (final RocksDB db = RocksDB.open(options, dbPath)) {
         final RocksDB.LiveFiles livefiles = db.getLiveFiles(true);
         assertThat(livefiles).isNotNull();
-        assertThat(livefiles.manifestFileSize).isEqualTo(116);
+        assertThat(livefiles.manifestFileSize).isGreaterThanOrEqualTo(100L);
+        assertThat(livefiles.manifestFileSize).isLessThanOrEqualTo(300L);
         assertThat(livefiles.files.size()).isEqualTo(3);
         assertThat(livefiles.files.get(0)).isEqualTo("/CURRENT");
         assertThat(livefiles.files.get(1)).isEqualTo("/MANIFEST-000005");