https://github.com/facebook/rocksdb
- HEAD
- refs/heads/2.2.fb.branch
- refs/heads/2.3.fb.branch
- refs/heads/2.4.fb.branch
- refs/heads/2.5.fb.branch
- refs/heads/2.6.fb.branch
- refs/heads/2.7
- refs/heads/2.7.fb.branch
- refs/heads/2.8.1.fb
- refs/heads/2.8.fb
- refs/heads/2.8.fb.trunk
- refs/heads/3.0.fb
- refs/heads/3.0.fb.branch
- refs/heads/3.1.fb
- refs/heads/3.10.fb
- refs/heads/3.11.fb
- refs/heads/3.12.fb
- refs/heads/3.13.fb
- refs/heads/3.2.fb
- refs/heads/3.3.fb
- refs/heads/3.4.fb
- refs/heads/3.5.fb
- refs/heads/3.6.fb
- refs/heads/3.7.fb
- refs/heads/3.8.fb
- refs/heads/3.9.fb
- refs/heads/4.0.fb
- refs/heads/4.1.fb
- refs/heads/4.10.fb
- refs/heads/4.11.fb
- refs/heads/4.12.fb
- refs/heads/4.13.fb
- refs/heads/4.2.fb
- refs/heads/4.3.fb
- refs/heads/4.4.fb
- refs/heads/4.5.fb
- refs/heads/4.6.fb
- refs/heads/4.7.fb
- refs/heads/4.8.fb
- refs/heads/4.9.fb
- refs/heads/5.0.fb
- refs/heads/5.1.fb
- refs/heads/5.10.fb
- refs/heads/5.11.fb
- refs/heads/5.12.fb
- refs/heads/5.13.fb
- refs/heads/5.13.fb.myrocks
- refs/heads/5.14.fb
- refs/heads/5.14.fb.myrocks
- refs/heads/5.15.fb
- refs/heads/5.16.fb
- refs/heads/5.17.fb
- refs/heads/5.17.fb.myrocks
- refs/heads/5.18.fb
- refs/heads/5.2.fb
- refs/heads/5.3.fb
- refs/heads/5.4.fb
- refs/heads/5.5.fb
- refs/heads/5.6.fb
- refs/heads/5.7.fb
- refs/heads/5.7.fb.myrocks
- refs/heads/5.8.3
- refs/heads/5.8.fb
- refs/heads/5.9.fb
- refs/heads/5.9.fb.myrocks
- refs/heads/6.0.fb
- refs/heads/6.0.fb.myrocks
- refs/heads/6.1.fb
- refs/heads/6.1.fb.myrocks
- refs/heads/6.1.fb.prod201905
- refs/heads/6.10.fb
- refs/heads/6.11.fb
- refs/heads/6.12.fb
- refs/heads/6.13.fb
- refs/heads/6.13.fb.laser
- refs/heads/6.14.fb
- refs/heads/6.14.fb.laser
- refs/heads/6.15.fb
- refs/heads/6.16.fb
- refs/heads/6.17.fb
- refs/heads/6.17.fb.laser
- refs/heads/6.18.fb
- refs/heads/6.19.fb
- refs/heads/6.2.fb
- refs/heads/6.20.fb
- refs/heads/6.21.fb
- refs/heads/6.22-history.md-fixup
- refs/heads/6.22.fb
- refs/heads/6.23.fb
- refs/heads/6.24.fb
- refs/heads/6.25.fb
- refs/heads/6.26.fb
- refs/heads/6.27.fb
- refs/heads/6.28.fb
- refs/heads/6.29.fb
- refs/heads/6.3.fb
- refs/heads/6.3.fb.myrocks
- refs/heads/6.3.fb.myrocks2
- refs/heads/6.3fb
- refs/heads/6.4.fb
- refs/heads/6.5.fb
- refs/heads/6.6.fb
- refs/heads/6.7.fb
- refs/heads/6.8.fb
- refs/heads/6.9.fb
- refs/heads/7.0.fb
- refs/heads/7.1.fb
- refs/heads/7.10.fb
- refs/heads/7.2.fb
- refs/heads/7.3.fb
- refs/heads/7.4.fb
- refs/heads/7.5.fb
- refs/heads/7.6.fb
- refs/heads/7.7.fb
- refs/heads/7.8.fb
- refs/heads/7.9.fb
- refs/heads/8.0.fb
- refs/heads/8.1.fb
- refs/heads/8.10.fb
- refs/heads/8.11.2_zippydb
- refs/heads/8.11.fb
- refs/heads/8.11.fb_zippydb
- refs/heads/8.2.fb
- refs/heads/8.3.fb
- refs/heads/8.4.fb
- refs/heads/8.5.fb
- refs/heads/8.6.fb
- refs/heads/8.7.fb
- refs/heads/8.8.fb
- refs/heads/8.9.fb
- refs/heads/9.0.fb
- refs/heads/9.1.fb
- refs/heads/9.1.fb.myrocks
- refs/heads/9.2.fb
- refs/heads/9.3.fb
- refs/heads/9.3.fb_exactly_at_hlc_testing
- refs/heads/9.4.fb
- refs/heads/9.5.fb
- refs/heads/9.6.fb
- refs/heads/adaptive
- refs/heads/ajkr-patch-1
- refs/heads/ajkr-patch-2
- refs/heads/blob_shadow
- refs/heads/bottom-pri-level
- refs/heads/bugfix-build-detect
- refs/heads/checksum_readahead_mmap_fix
- refs/heads/draft-myrocks-and-fbcode-8.0.fb
- refs/heads/feature/debug-rocksdbjavastatic
- refs/heads/feature/travis-arm64
- refs/heads/fix-release-notes
- refs/heads/fix-win2022-build
- refs/heads/fix-write-batch-comment
- refs/heads/format_compatible_4
- refs/heads/getmergeops
- refs/heads/gh-pages-old
- refs/heads/history-update
- refs/heads/hotfix/lambda-capture
- refs/heads/improve-support
- refs/heads/jijiew-patch-1
- refs/heads/katherinez-patch-1
- refs/heads/katherinez-patch-2
- refs/heads/main
- refs/heads/master
- refs/heads/mdcallag_benchmark_oct22
- refs/heads/nvm_cache_proto
- refs/heads/pr-sanity-check-as-GHAction
- refs/heads/pr/11267
- refs/heads/pr/6062
- refs/heads/ramvadiv-patch-1
- refs/heads/release_fix
- refs/heads/revert-10606-7.6.1
- refs/heads/ribbon_bloom_hybrid
- refs/heads/scaffold
- refs/heads/siying-patch-1
- refs/heads/siying-patch-10
- refs/heads/siying-patch-2
- refs/heads/siying-patch-3
- refs/heads/siying-patch-4
- refs/heads/siying-patch-5
- refs/heads/siying-patch-6
- refs/heads/siying-patch-7
- refs/heads/siying-patch-8
- refs/heads/skip_memtable_flush
- refs/heads/testing_ppc_build
- refs/heads/tests
- refs/heads/unschedule_issue_test_base
- refs/heads/unused-var
- refs/heads/v6.6.4
- refs/heads/xxhash_merge_base
- refs/heads/yiwu_stackable
- refs/heads/yuslepukhin
- refs/remotes/origin/5.13.fb
- refs/tags/2.5.fb
- refs/tags/2.6.fb
- refs/tags/3.0.fb
- refs/tags/do-not-use-me2
- refs/tags/rocksdb-3.1
- refs/tags/rocksdb-3.10.2
- refs/tags/rocksdb-3.11
- refs/tags/rocksdb-3.11.1
- refs/tags/rocksdb-3.11.2
- refs/tags/rocksdb-3.2
- refs/tags/rocksdb-3.3
- refs/tags/rocksdb-3.4
- refs/tags/rocksdb-3.5
- refs/tags/rocksdb-3.5.1
- refs/tags/rocksdb-3.6.1
- refs/tags/rocksdb-3.6.2
- refs/tags/rocksdb-3.7
- refs/tags/rocksdb-3.8
- refs/tags/rocksdb-3.9
- refs/tags/rocksdb-3.9.1
- refs/tags/rocksdb-4.1
- refs/tags/rocksdb-5.10.2
- refs/tags/rocksdb-5.10.3
- refs/tags/rocksdb-5.10.4
- refs/tags/rocksdb-5.11.2
- refs/tags/rocksdb-5.11.3
- refs/tags/rocksdb-5.14.3
- refs/tags/rocksdb-5.2.1
- refs/tags/rocksdb-5.3.3
- refs/tags/rocksdb-5.3.4
- refs/tags/rocksdb-5.3.5
- refs/tags/rocksdb-5.3.6
- refs/tags/rocksdb-5.4.10
- refs/tags/rocksdb-5.4.5
- refs/tags/rocksdb-5.4.6
- refs/tags/rocksdb-5.5.2
- refs/tags/rocksdb-5.5.3
- refs/tags/rocksdb-5.5.4
- refs/tags/rocksdb-5.5.5
- refs/tags/rocksdb-5.5.6
- refs/tags/rocksdb-5.6.1
- refs/tags/rocksdb-5.6.2
- refs/tags/rocksdb-5.7.1
- refs/tags/rocksdb-5.7.2
- refs/tags/rocksdb-5.7.3
- refs/tags/rocksdb-5.7.5
- refs/tags/rocksdb-5.8.6
- refs/tags/rocksdb-5.8.7
- refs/tags/rocksdb-5.8.8
- refs/tags/rocksdb-5.9.2
- refs/tags/v4.0
- refs/tags/v4.1
- refs/tags/v5.10.2
- refs/tags/v5.10.3
- refs/tags/v5.10.4
- refs/tags/v5.11.2
- refs/tags/v5.11.3
- refs/tags/v5.13.3
- refs/tags/v5.14.3
- refs/tags/v5.15.10
- refs/tags/v5.18.3
- refs/tags/v5.2.1
- refs/tags/v5.3.3
- refs/tags/v5.3.4
- refs/tags/v5.3.5
- refs/tags/v5.3.6
- refs/tags/v5.4.10
- refs/tags/v5.4.5
- refs/tags/v5.4.6
- refs/tags/v5.5.2
- refs/tags/v5.5.3
- refs/tags/v5.5.4
- refs/tags/v5.5.5
- refs/tags/v5.5.6
- refs/tags/v5.6.1
- refs/tags/v5.6.2
- refs/tags/v5.7.1
- refs/tags/v5.7.2
- refs/tags/v5.7.3
- refs/tags/v5.7.5
- refs/tags/v5.8.6
- refs/tags/v5.8.7
- refs/tags/v5.8.8
- refs/tags/v5.9.2
- refs/tags/v6.0.1
- refs/tags/v6.0.2
- refs/tags/v6.1.1
- refs/tags/v6.1.2
- refs/tags/v6.10.1
- refs/tags/v6.10.2
- refs/tags/v6.11.4
- refs/tags/v6.11.6
- refs/tags/v6.12.6
- refs/tags/v6.12.7
- refs/tags/v6.13.2
- refs/tags/v6.13.3
- refs/tags/v6.14.5
- refs/tags/v6.14.6
- refs/tags/v6.15.4
- refs/tags/v6.15.5
- refs/tags/v6.16.3
- refs/tags/v6.16.4
- refs/tags/v6.17.3
- refs/tags/v6.2.2
- refs/tags/v6.2.4
- refs/tags/v6.20.3
- refs/tags/v6.22.1
- refs/tags/v6.25.3
- refs/tags/v6.26.1
- refs/tags/v6.28.2
- refs/tags/v6.29.3
- refs/tags/v6.29.4
- refs/tags/v6.29.5
- refs/tags/v6.3.6
- refs/tags/v6.4.6
- refs/tags/v6.5.2
- refs/tags/v6.5.3
- refs/tags/v6.6.3
- refs/tags/v6.6.4
- refs/tags/v6.7.3
- refs/tags/v6.8.1
- refs/tags/v7.0.1
- refs/tags/v7.0.2
- refs/tags/v7.0.4
- refs/tags/v7.2.0
- refs/tags/v7.2.2
- refs/tags/v7.5.3
- refs/tags/v7.7.2
- refs/tags/v7.9.2
- refs/tags/v8.0.0
- refs/tags/v8.11.4
- refs/tags/v8.3.2
- refs/tags/v8.3.3
- refs/tags/v8.4.4
- refs/tags/v8.5.3
- refs/tags/v8.6.7
- refs/tags/v8.7.3
- refs/tags/v9.0.1
- refs/tags/v9.1.1
- refs/tags/v9.2.1
- refs/tags/v9.3.1
- refs/tags/v9.4.0
- v9.5.2
- v9.1.0
- v9.0.0
- v8.9.1
- v8.8.1
- v8.5.4
- v8.11.3
- v8.10.2
- v8.10.0
- v8.1.1
- v7.8.3
- v7.7.8
- v7.7.3
- v7.6.0
- v7.4.5
- v7.4.4
- v7.4.3
- v7.3.1
- v7.10.2
- v7.1.2
- v7.1.1
- v7.0.3
- v6.27.3
- v6.26.0
- v6.25.1
- v6.24.2
- v6.23.3
- v6.23.2
- v6.19.3
- v6.15.2
- v5.8
- v5.5.1
- v5.4.7
- v5.18.4
- v5.17.2
- v5.16.6
- v5.14.2
- v5.13.4
- v5.13.2
- v5.13.1
- v5.12.5
- v5.12.4
- v5.12.3
- v5.12.2
- v5.1.4
- v5.1.3
- v5.1.2
- v5.0.2
- v5.0.1
- v4.9
- v4.8
- v4.6.1
- v4.5.1
- v4.4.1
- v4.4
- v4.3.1
- v4.3
- v4.2
- v4.13.5
- v4.13
- v4.11.2
- v3.9
- v3.8
- v3.7
- v3.6.1
- v3.5
- v3.4
- v3.3
- v3.2
- v3.13.1
- v3.13
- v3.12.1
- v3.12
- v3.11
- v3.10
- v3.1
- v3.0
- v2.8
- v2.7
- v2.6
- v2.5
- v2.4
- v2.3
- v2.2
- v2.1
- v2.0
- v1.5.9.1
- v1.5.8.2
- v1.5.8.1
- v1.5.8
- v1.5.7
- rocksdb-5.8
- rocksdb-5.4.7
- rocksdb-5.1.4
- rocksdb-5.1.3
- rocksdb-5.1.2
- rocksdb-5.0.2
- rocksdb-5.0.1
- rocksdb-4.9
- rocksdb-4.8
- rocksdb-4.6.1
- rocksdb-4.5.1
- rocksdb-4.4.1
- rocksdb-4.4
- rocksdb-4.3.1
- rocksdb-4.3
- rocksdb-4.2
- rocksdb-4.13.5
- rocksdb-4.13
- rocksdb-4.11.2
- rocksdb-3.10.1
- blob_st_lvl-pre
- 2.8.fb
- 2.7.fb
- 2.4.fb
- 2.3.fb
- 2.2.fb
- 2.1.fb
- 2.0.fb
- 1.5.9.fb
- 1.5.9.2.fb
- 1.5.9.1.fb
- 1.5.8.fb
- 1.5.8.2.fb
- 1.5.8.1.fb
- 1.5.7.fb
Take a new snapshot of a software origin
If the archived software origin currently browsed is not synchronized with its upstream version (for instance when new commits have been issued), you can explicitly request Software Heritage to take a new snapshot of it.
Use the form below to proceed. Once a request has been submitted and accepted, it will be processed as soon as possible. You can then check its processing state by visiting this dedicated page.Processing "take a new snapshot" request ...
Permalinks
To reference or cite the objects present in the Software Heritage archive, permalinks based on SoftWare Hash IDentifiers (SWHIDs) must be used.
Select below a type of object currently browsed in order to display its associated SWHID and permalink.
Revision | Author | Date | Message | Commit Date |
---|---|---|---|---|
b7119ff | Peter Dillinger | 23 March 2022, 17:32:57 UTC | Update HISTORY.md and version.h for 7.0.3 Summary: Also clarified in HISTORY.md that this patch release breaks binary compatibility (because of FilterPolicy vtable) | 23 March 2022, 17:32:57 UTC |
418e58e | Peter Dillinger | 23 March 2022, 17:00:54 UTC | Fix a major performance bug in 7.0 re: filter compatibility (#9736) Summary: Bloom filters generated by pre-7.0 releases are not read by 7.0.x releases (and vice-versa) due to changes to FilterPolicy::Name() in https://github.com/facebook/rocksdb/issues/9590. This can severely impact read performance and read I/O on upgrade or downgrade with existing DB, but not data correctness. To fix, we go back using the old, unified name in SST metadata but (for a while anyway) recognize the aliases that could be generated by early 7.0.x releases. This unfortunately requires a public API change to avoid interfering with all the good changes from https://github.com/facebook/rocksdb/issues/9590, but the API change only affects users with custom FilterPolicy, which should be very few. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9736 Test Plan: manual Generate DBs with ``` ./db_bench.7.0 -db=/dev/shm/rocksdb.7.0 -bloom_bits=10 -cache_index_and_filter_blocks=1 -benchmarks=fillrandom -num=10000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 ``` and similar. Compare with ``` for IMPL in 6.29 7.0 fixed; do for DB in 6.29 7.0 fixed; do echo "Testing $IMPL on $DB:"; ./db_bench.$IMPL -db=/dev/shm/rocksdb.$DB -use_existing_db -readonly -bloom_bits=10 -benchmarks=readrandom -num=10000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -duration=10 2>&1 | grep micros/op; done; done ``` Results: ``` Testing 6.29 on 6.29: readrandom : 34.381 micros/op 29085 ops/sec; 3.2 MB/s (291999 of 291999 found) Testing 6.29 on 7.0: readrandom : 190.443 micros/op 5249 ops/sec; 0.6 MB/s (52999 of 52999 found) Testing 6.29 on fixed: readrandom : 40.148 micros/op 24907 ops/sec; 2.8 MB/s (249999 of 249999 found) Testing 7.0 on 6.29: readrandom : 229.430 micros/op 4357 ops/sec; 0.5 MB/s (43999 of 43999 found) Testing 7.0 on 7.0: readrandom : 33.348 micros/op 29986 ops/sec; 3.3 MB/s (299999 of 299999 found) Testing 7.0 on fixed: readrandom : 152.734 micros/op 6546 ops/sec; 0.7 MB/s (65999 of 65999 found) Testing fixed on 6.29: readrandom : 32.024 micros/op 31224 ops/sec; 3.5 MB/s (312999 of 312999 found) Testing fixed on 7.0: readrandom : 33.990 micros/op 29390 ops/sec; 3.3 MB/s (294999 of 294999 found) Testing fixed on fixed: readrandom : 28.714 micros/op 34825 ops/sec; 3.9 MB/s (348999 of 348999 found) ``` Just paying attention to order of magnitude of ops/sec (short test durations, lots of noise), it's clear that with the fix we can read <= 6.29 & >= 7.0 at full speed, where neither 6.29 nor 7.0 can on both. And 6.29 release can properly read fixed DB at full speed. Reviewed By: siying, ajkr Differential Revision: D35057844 Pulled By: pdillinger fbshipit-source-id: a46893a6af4bf084375ebe4728066d00eb08f050 | 23 March 2022, 17:10:56 UTC |
0e4c063 | gukaifeng | 15 March 2022, 16:55:49 UTC | fix a bug of the ticker NO_FILE_OPENS (#9677) Summary: In the original code, the value of `NO_FILE_OPENS` corresponding to the Ticker item will be increased regardless of whether the file is successfully opened or not. Even counts are repeated, which can lead to skewed counts. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9677 Reviewed By: jay-zhuang Differential Revision: D34725733 Pulled By: ajkr fbshipit-source-id: 841234ed03802c0105fd2107d82a740265ead576 | 15 March 2022, 17:47:44 UTC |
fddc1a7 | Jermy Li | 15 March 2022, 16:50:21 UTC | fix: Reusing-Iterator reads stale keys after DeleteRange() performed (#9258) Summary: fix https://github.com/facebook/rocksdb/issues/9255 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9258 Reviewed By: pdillinger Differential Revision: D34879684 Pulled By: ajkr fbshipit-source-id: 5934f4b7524dc27ecdf1430e0456a0fc02958fc7 | 15 March 2022, 17:46:54 UTC |
9db48d6 | Tomas Kolda | 14 March 2022, 21:12:30 UTC | NPE in Java_org_rocksdb_ColumnFamilyOptions_setSstPartitionerFactory (#9622) Summary: There was a mistake that incorrectly cast SstPartitionerFactory (missed shared pointer). It worked for database (correct cast), but not for family. Trying to set it in family has caused Access violation. I have also added test and improved it. Older version was passing even without sst partitioner which is weird, because on Level1 we had two SST files with same key "aaaa1". I was not sure if it is a new feature and changed it to overlaping keys "aaaa0" - "aaaa2" overlaps "aaaa1". Pull Request resolved: https://github.com/facebook/rocksdb/pull/9622 Reviewed By: ajkr Differential Revision: D34871968 Pulled By: pdillinger fbshipit-source-id: a08009766da49fc198692a610e8beb19caf737e6 | 15 March 2022, 17:42:49 UTC |
348414d | Yuriy Chernyshov | 14 March 2022, 00:01:21 UTC | #include <winioctl.h> as MSDN prescribes (#9612) Summary: The recommendation can be found e. g. [here](https://docs.microsoft.com/en-us/windows/win32/api/winioctl/ns-winioctl-storage_property_query). While `<windows.h>` transitively includes `<winioctl.h>` by default, this can be switched off by `/DWIN32_LEAN_AND_MEAN` which forces the user to include-what-you-use. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9612 Reviewed By: riversand963 Differential Revision: D34845629 Pulled By: ajkr fbshipit-source-id: 1ef9273074e3d84864c6833a7de6eb9df81e29d9 | 15 March 2022, 17:42:25 UTC |
7b6ca63 | Andrew Kryczka | 14 March 2022, 16:38:23 UTC | update HISTORY.md and version.h for 7.0.2 | 14 March 2022, 16:38:23 UTC |
9fe3a53 | Jay Zhuang | 13 March 2022, 04:07:04 UTC | DisableManualCompaction may fail to cancel an unscheduled task (#9659) Summary: https://github.com/facebook/rocksdb/issues/9625 didn't change the unschedule condition which was waiting for the background thread to clean-up the compaction. make sure we only unschedule the task when it's scheduled. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9659 Reviewed By: ajkr Differential Revision: D34651820 Pulled By: jay-zhuang fbshipit-source-id: 23f42081b15ec8886cd81cbf131b116e0c74dc2f | 13 March 2022, 06:17:59 UTC |
22e011f | Jay Zhuang | 12 March 2022, 19:45:56 UTC | Fix a timer crash caused by invalid memory management (#9656) Summary: Timer crash when multiple DB instances doing heavy DB open and close operations concurrently. Which is caused by adding a timer task with smaller timestamp than the current running task. Fix it by moving the getting new task timestamp part within timer mutex protection. And other fixes: - Disallow adding duplicated function name to timer - Fix a minor memory leak in timer when a running task is cancelled Pull Request resolved: https://github.com/facebook/rocksdb/pull/9656 Reviewed By: ajkr Differential Revision: D34626296 Pulled By: jay-zhuang fbshipit-source-id: 6b6d96a5149746bf503546244912a9e41a0c5f6b | 13 March 2022, 06:10:28 UTC |
bbae679 | Andrew Kryczka | 10 March 2022, 05:07:31 UTC | Avoid popcnt on Windows when unavailable and in portable builds (#9680) Summary: Fixes https://github.com/facebook/rocksdb/issues/9560. Only use popcnt intrinsic when HAVE_SSE42 is set. Also avoid setting it based on compiler test in portable builds because such test will pass on MSVC even without proper arch flags (ref: https://devblogs.microsoft.com/oldnewthing/20201026-00/?p=104397). Pull Request resolved: https://github.com/facebook/rocksdb/pull/9680 Test Plan: verified the combinations of -DPORTABLE and -DFORCE_SSE42 produce expected compiler flags on Linux. Verified MSVC build using PORTABLE=1 (in CircleCI) does not set HAVE_SSE42. Reviewed By: pdillinger Differential Revision: D34739033 Pulled By: ajkr fbshipit-source-id: d10456f3392945fc3e59430a1777840f7b60b276 | 10 March 2022, 06:51:01 UTC |
fe9e363 | Adam Retter | 07 March 2022, 18:50:52 UTC | Fix RocksJava releases for macOS (#9662) Summary: Addresses the problems described in https://github.com/facebook/rocksdb/pull/9254#issuecomment-1054598516 and https://github.com/facebook/rocksdb/pull/9254#issuecomment-1059574837 that have blocked a RocksJava release **NOTE** Also needs to be ported to 6.29.fb branch. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9662 Reviewed By: ajkr Differential Revision: D34689200 Pulled By: pdillinger fbshipit-source-id: c62fe34c54f05be5a00ee1daec8ec7454baa5eb8 | 07 March 2022, 23:29:08 UTC |
3a4d73d | Jonathan Albrecht | 01 March 2022, 21:50:41 UTC | Reenable s390x platform_dependent travis job (#9631) Summary: Fix g++ -march=native detection and reenable s390x in travis This PR fixes s390x assembler messages: ``` Error: invalid switch -march=z14 Error: unrecognized option -march=z14 ``` The s390x travis build was failing with gcc-7 because the assembler on ubuntu 16.04 is too old to recognize the z14 model so it doesn't work with -march=native on a z14 machine. It fixes the check for the -march=native flag so that the assembler will get called and correctly fail on ubuntu 16.04 which will cause the build to fall back to -march=z196 which works. The other changes are needed so builds work more consistently on s390x: 1. Set make parallelism to 1 for s390x: The default was 4 previously but I saw frequent internal compiler errors on travis probably due to low resources. The `platform_dependent` job works more consistently but is roughly 10 minutes slower although it varies. 2. Remove status_checked jobs, as we are relying on CircleCI for these now and do not really need platform coverage on them. Fixes https://github.com/facebook/rocksdb/issues/9524 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9631 Test Plan: CI Reviewed By: ajkr Differential Revision: D34553989 Pulled By: pdillinger fbshipit-source-id: a6e3a7276446721c4c0bebc4ed217c2ca2b53f11 | 07 March 2022, 18:32:43 UTC |
4ab2fe7 | Andrew Kryczka | 03 March 2022, 05:42:52 UTC | update HISTORY.md and version.h for 7.0.1 | 03 March 2022, 05:42:52 UTC |
596c606 | Yanqin Jin | 03 March 2022, 05:03:14 UTC | Fix bug causing incorrect data returned by snapshot read (#9648) Summary: This bug affects use cases that meet the following conditions - (has only the default column family or disables WAL) and - has at least one event listener - atomic flush is NOT affected. If the above conditions meet, then RocksDB can release the db mutex before picking all the existing memtables to flush. In the meantime, a snapshot can be created and db's sequence number can still be incremented. The upcoming flush will ignore this snapshot. A later read using this snapshot can return incorrect result. To fix this issue, we call the listeners callbacks after picking the memtables so that we avoid creating snapshots during this interval. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9648 Test Plan: make check Reviewed By: ajkr Differential Revision: D34555456 Pulled By: riversand963 fbshipit-source-id: 1438981e9f069a5916686b1a0ad7627f734cf0ee | 03 March 2022, 05:41:05 UTC |
a6fd333 | jingkai.yuan | 03 March 2022, 00:35:21 UTC | Fix corruption error when compressing blob data with zlib. (#9572) Summary: The plain data length may not be big enough if the compression actually expands data. So use deflateBound() to get the upper limit on the compressed output before deflate(). Pull Request resolved: https://github.com/facebook/rocksdb/pull/9572 Reviewed By: riversand963 Differential Revision: D34326475 Pulled By: ajkr fbshipit-source-id: 4b679cb7a83a62782a127785b4d5eb9aa4646449 | 03 March 2022, 05:39:21 UTC |
f278e0e | Hui Xiao | 25 February 2022, 22:44:46 UTC | Deflake DBErrorHandlingFSTest.MultiCFWALWriteError (#9496) Summary: **Context:** As part of https://github.com/facebook/rocksdb/pull/6949, file deletion is disabled for faulty database on the IOError of MANIFEST write/sync and [re-enabled again during `DBImpl::Resume()` if all recovery is completed](https://github.com/facebook/rocksdb/commit/e66199d848cd484b816d07359f1dc0f0b99e5351#diff-d9341fbe2a5d4089b93b22c5ed7f666bc311b378c26d0786f4b50c290e460187R396). Before re-enabling file deletion, it `assert(versions_->io_status().ok());`, which IMO assumes `versions_` is **the** `version_` in the recovery process. However, this is not necessarily true due to `s = error_handler_.ClearBGError();` happening before that assertion can unblock some foreground thread by [`EventHelpers::NotifyOnErrorRecoveryEnd()`](https://github.com/facebook/rocksdb/blob/3122cb435875d720fc3d23a48eb7c0fa89d869aa/db/error_handler.cc#L552-L553) as part of the `ClearBGError()`. That foreground thread can do whatever it wants including closing/reopening the db and clean up that same `versions_`. As a consequence, `assert(versions_->io_status().ok());`, will access `io_status()` of a nullptr and test like `DBErrorHandlingFSTest.MultiCFWALWriteError` becomes flaky. The unblocked foreground thread (in this case, the testing thread) proceeds to [reopen the db](https://github.com/facebook/rocksdb/blob/6.29.fb/db/error_handler_fs_test.cc?fbclid=IwAR1kQOxSbTUmaHQPAGz5jdMHXtDsDFKiFl8rifX-vIz4B23Y0S9jBkssSCg#L1494), where [`versions_` gets reset to nullptr](https://github.com/facebook/rocksdb/blob/6.29.fb/db/db_impl/db_impl.cc?fbclid=IwAR2uRhwBiPKgmE9q_6CM2mzbfwjoRgsGpXOrHruSJUDcAKc9rYZtVSvKdOY#L678) as part of the old db clean-up. If this happens right before `assert(versions_->io_status().ok()); ` gets excuted in the background thread, then we can see error like ``` db/db_impl/db_impl.cc:420:5: runtime error: member call on null pointer of type 'rocksdb::VersionSet' assert(versions_->io_status().ok()); ``` **Summary:** - I proposed to call `s = error_handler_.ClearBGError();` after we know it's fine to wake up foreground, which I think is right before we LOG `ROCKS_LOG_INFO(immutable_db_options_.info_log, "Successfully resumed DB");` - As the context, the orignal https://github.com/facebook/rocksdb/pull/3997 introducing `DBImpl::Resume()` calls `s = error_handler_.ClearBGError();` very close to calling `ROCKS_LOG_INFO(immutable_db_options_.info_log, "Successfully resumed DB");` while the later https://github.com/facebook/rocksdb/pull/6949 distances these two calls a bit. - And it seems fine to me that `s = error_handler_.ClearBGError();` happens after `EnableFileDeletions(/*force=*/true);` at least syntax-wise since these two functions are orthogonal. And it also seems okay to me that we re-enable file deletion before `s = error_handler_.ClearBGError();`, which basically is resetting some state variables. - In addition, to preserve the previous behavior of https://github.com/facebook/rocksdb/pull/6949 where status of re-enabling file deletion is not taken account into the general status of resuming the db, I separated `enable_file_deletion_s` from the general `s` - In addition, to make `ROCKS_LOG_INFO(immutable_db_options_.info_log, "Successfully resumed DB");` more clear, I separated it into its own if-block. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9496 Test Plan: - Manually reproduce the assertion failure in`DBErrorHandlingFSTest.MultiCFWALWriteError` by injecting sleep like below so that it's more likely for `assert(versions_->io_status().ok());` to execute after [reopening the db](https://github.com/facebook/rocksdb/blob/6.29.fb/db/error_handler_fs_test.cc?fbclid=IwAR1kQOxSbTUmaHQPAGz5jdMHXtDsDFKiFl8rifX-vIz4B23Y0S9jBkssSCg#L1494) in the foreground (i.e, testing) thread ``` sleep(1); assert(versions_->io_status().ok()); ``` `python3 gtest-parallel/gtest_parallel.py -r 100 -w 100 rocksdb/error_handler_fs_test --gtest_filter=DBErrorHandlingFSTest.MultiCFWALWriteError` ``` [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from DBErrorHandlingFSTest [ RUN ] DBErrorHandlingFSTest.MultiCFWALWriteError Received signal 11 (Segmentation fault) #0 rocksdb/error_handler_fs_test() [0x5818a4] rocksdb::DBImpl::ResumeImpl(rocksdb::DBRecoverContext) /data/users/huixiao/rocksdb/db/db_impl/db_impl.cc:421 https://github.com/facebook/rocksdb/issues/1 rocksdb/error_handler_fs_test() [0x6379ff] rocksdb::ErrorHandler::RecoverFromBGError(bool) /data/users/huixiao/rocksdb/db/error_handler.cc:600 https://github.com/facebook/rocksdb/issues/2 rocksdb/error_handler_fs_test() [0x7c5362] rocksdb::SstFileManagerImpl::ClearError() /data/users/huixiao/rocksdb/file/sst_file_manager_impl.cc:310 https://github.com/facebook/rocksdb/issues/3 rocksdb/error_handler_fs_test() ``` - The assertion failure does not happen with PR `python3 gtest-parallel/gtest_parallel.py -r 100 -w 100 rocksdb/error_handler_fs_test --gtest_filter=DBErrorHandlingFSTest.MultiCFWALWriteError` `[100/100] DBErrorHandlingFSTest.MultiCFWALWriteError (43785 ms) ` Reviewed By: riversand963, anand1976 Differential Revision: D33990099 Pulled By: hx235 fbshipit-source-id: 2e0259a471fa8892ff177da91b3e1c0792dd7bab | 03 March 2022, 05:38:50 UTC |
0344b1d | Jay Zhuang | 02 March 2022, 21:43:00 UTC | Unschedule manual compaction from thread-pool queue (#9625) Summary: PR https://github.com/facebook/rocksdb/issues/9557 introduced a race condition between manual compaction foreground thread and background compaction thread. This PR adds the ability to really unschedule manual compaction from thread-pool queue by differentiate tag name for manual compaction and other tasks. Also fix an issue that db `close()` didn't cancel the manual compaction thread. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9625 Test Plan: unittest not hang Reviewed By: ajkr Differential Revision: D34410811 Pulled By: jay-zhuang fbshipit-source-id: cb14065eabb8cf1345fa042b5652d4f788c0c40c | 03 March 2022, 05:37:10 UTC |
a4bf931 | Andrew Kryczka | 01 March 2022, 07:45:08 UTC | Handle failures in block-based table size/offset approximation (#9615) Summary: In crash test with fault injection, we were seeing stack traces like the following: ``` https://github.com/facebook/rocksdb/issues/3 0x00007f75f763c533 in __GI___assert_fail (assertion=assertion@entry=0x1c5b2a0 "end_offset >= start_offset", file=file@entry=0x1c580a0 "table/block_based/block_based_table_reader.cc", line=line@entry=3245, function=function@entry=0x1c60e60 "virtual uint64_t rocksdb::BlockBasedTable::ApproximateSize(const rocksdb::Slice&, const rocksdb::Slice&, rocksdb::TableReaderCaller)") at assert.c:101 https://github.com/facebook/rocksdb/issues/4 0x00000000010ea9b4 in rocksdb::BlockBasedTable::ApproximateSize (this=<optimized out>, start=..., end=..., caller=<optimized out>) at table/block_based/block_based_table_reader.cc:3224 https://github.com/facebook/rocksdb/issues/5 0x0000000000be61fb in rocksdb::TableCache::ApproximateSize (this=0x60f0000161b0, start=..., end=..., fd=..., caller=caller@entry=rocksdb::kCompaction, internal_comparator=..., prefix_extractor=...) at db/table_cache.cc:719 https://github.com/facebook/rocksdb/issues/6 0x0000000000c3eaec in rocksdb::VersionSet::ApproximateSize (this=<optimized out>, v=<optimized out>, f=..., start=..., end=..., caller=<optimized out>) at ./db/version_set.h:850 https://github.com/facebook/rocksdb/issues/7 0x0000000000c6ebc3 in rocksdb::VersionSet::ApproximateSize (this=<optimized out>, options=..., v=v@entry=0x621000047500, start=..., end=..., start_level=start_level@entry=0, end_level=<optimized out>, caller=<optimized out>) at db/version_set.cc:5657 https://github.com/facebook/rocksdb/issues/8 0x000000000166e894 in rocksdb::CompactionJob::GenSubcompactionBoundaries (this=<optimized out>) at ./include/rocksdb/options.h:1869 https://github.com/facebook/rocksdb/issues/9 0x000000000168c526 in rocksdb::CompactionJob::Prepare (this=this@entry=0x7f75f3ffcf00) at db/compaction/compaction_job.cc:546 ``` The problem occurred in `ApproximateSize()` when the index `Seek()` for the first `ApproximateDataOffsetOf()` encountered an I/O error, while the second `Seek()` did not. In the old code that scenario caused `start_offset == data_size` , thus it was easy to trip the assertion that `end_offset >= start_offset`. The fix is to set `start_offset == 0` when the first index `Seek()` fails, and `end_offset == data_size` when the second index `Seek()` fails. I doubt these give an "on average correct" answer for how this function is used, but I/O errors in index seeks are hopefully rare, it looked consistent with what was already there, and it was easier to calculate. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9615 Test Plan: run the repro command for a while and stopped seeing coredumps - ``` $ while ! ./db_stress --block_size=128 --cache_size=32768 --clear_column_family_one_in=0 --column_families=1 --continuous_verification_interval=0 --db=/dev/shm/rocksdb_crashtest --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --expected_values_dir=/dev/shm/rocksdb_crashtest_expected --index_type=2 --iterpercent=10 --kill_random_test=18887 --max_key=1000000 --max_bytes_for_level_base=2048576 --nooverwritepercent=1 --open_files=-1 --open_read_fault_one_in=32 --ops_per_thread=1000000 --prefixpercent=5 --read_fault_one_in=0 --readpercent=45 --reopen=0 --skip_verifydb=1 --subcompactions=2 --target_file_size_base=524288 --test_batches_snapshots=0 --value_size_mult=32 --write_buffer_size=524288 --writepercent=35 ; do : ; done ``` Reviewed By: pdillinger Differential Revision: D34383069 Pulled By: ajkr fbshipit-source-id: fac26c3b20ea962e75387515ba5f2724dc48719f | 03 March 2022, 05:35:15 UTC |
b251c4f | Andrew Kryczka | 27 February 2022, 19:36:54 UTC | Dedicate cacheline for DB mutex (#9637) Summary: We found a case of cacheline bouncing due to writers locking/unlocking `mutex_` and readers accessing `block_cache_tracer_`. We discovered it only after the issue was fixed by https://github.com/facebook/rocksdb/issues/9462 shifting the `DBImpl` members such that `mutex_` and `block_cache_tracer_` were naturally placed in separate cachelines in our regression testing setup. This PR forces the cacheline alignment of `mutex_` so we don't accidentally reintroduce the problem. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9637 Reviewed By: riversand963 Differential Revision: D34502233 Pulled By: ajkr fbshipit-source-id: 46aa313b7fe83e80c3de254e332b6fb242434c07 | 03 March 2022, 05:33:07 UTC |
a12be56 | Andrew Kryczka | 20 February 2022, 22:33:37 UTC | Update HISTORY.md and version.h for 7.0 release (#9609) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9609 Reviewed By: riversand963 Differential Revision: D34370309 Pulled By: ajkr fbshipit-source-id: 5fc9306439aefa4b2d61d847534ea6758c30b6a5 | 21 February 2022, 00:40:15 UTC |
3699b17 | Akanksha Mahajan | 19 February 2022, 04:13:41 UTC | Change enum SizeApproximationFlags to enum class (#9604) Summary: Change enum SizeApproximationFlags to enum and class and add overloaded operators for the transition between enum class and uint8_t Pull Request resolved: https://github.com/facebook/rocksdb/pull/9604 Test Plan: Circle CI jobs Reviewed By: riversand963 Differential Revision: D34360281 Pulled By: akankshamahajan15 fbshipit-source-id: 6351dfdb717ae3c4530d324c3d37a8ecb01dd1ef | 19 February 2022, 04:22:57 UTC |
d3a2f28 | Jay Zhuang | 19 February 2022, 02:18:49 UTC | Add Temperature info in `NewSequentialFile()` (#9499) Summary: Add Temperature hints information from RocksDB in API `NewSequentialFile()`. backup and checkpoint operations need to open the source files with `NewSequentialFile()`, which will have the temperature hints. Other operations are not covered. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9499 Test Plan: Added unittest Reviewed By: pdillinger Differential Revision: D34006115 Pulled By: jay-zhuang fbshipit-source-id: 568b34602b76520e53128672bd07e9d886786a2f | 19 February 2022, 02:23:07 UTC |
559525d | Akanksha Mahajan | 19 February 2022, 00:37:24 UTC | Add Async Read and Poll APIs in FileSystem (#9564) Summary: This PR adds support for new APIs Async Read that reads the data asynchronously and Poll API that checks if requested read request has completed or not. Usage: In RocksDB, we are currently planning to prefetch data asynchronously during sequential scanning and RocksDB will call these APIs to prefetch more data in advanced. Design: - ReadAsync API submits the read request to underlying FileSystem in order to read data asynchronously. When read request is completed, callback function will be called. cb_arg is used by RocksDB to track the original request submitted and IOHandle is used by FileSystem to keep track of IO requests at their level. - The Poll API is added in FileSystem because the call could end up handling completions for multiple different files which is not specific to a FSRandomAccessFile instance. There could be multiple outstanding file reads from different files in future and they can complete in any order. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9564 Test Plan: Test will be added in separate PR. Reviewed By: anand1976 Differential Revision: D34226216 Pulled By: akankshamahajan15 fbshipit-source-id: 95e64edafb17f543f7232421d51e2665a3267f69 | 19 February 2022, 01:23:18 UTC |
67f071f | Bo Wang | 18 February 2022, 22:10:25 UTC | Fixes #9565 (#9586) Summary: [Compaction::IsTrivialMove](https://github.com/facebook/rocksdb/blob/a2b9be42b6d5ac4d44bcc6a9451a825440000769/db/compaction/compaction.cc#L318) checks whether allow_trivial_move is set, and if so it returns the value of is_trivial_move_. The allow_trivial_move option is there for universal compaction. So when this is set and leveled compaction is enabled, then useful code that follows this block never gets a chance to run. A check that [compaction_style == kCompactionStyleUniversal](https://github.com/facebook/rocksdb/blob/320d9a8e8a1b6998f92934f87fc71ad8bd6d4596/db/db_impl/db_impl_compaction_flush.cc#L1030) should be added to avoid doing the wrong thing for leveled. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9586 Test Plan: To reproduce this: First edit db/compaction/compaction.cc with ``` diff --git a/db/compaction/compaction.cc b/db/compaction/compaction.cc index 7ae50b91e..52dd489b1 100644 --- a/db/compaction/compaction.cc +++ b/db/compaction/compaction.cc @@ -319,6 +319,8 @@ bool Compaction::IsTrivialMove() const { // input files are non overlapping if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) && (output_level_ != 0)) { + printf("IsTrivialMove:: return %d because universal allow_trivial_move\n", (int) is_trivial_move_); + // abort(); return is_trivial_move_; } ``` And then run ``` ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/m/rx --wal_dir=/data/m/rx --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --seed=1641328309 --universal_allow_trivial_move=1 ``` Example output with the debug code added ``` IsTrivialMove:: return 0 because universal allow_trivial_move IsTrivialMove:: return 0 because universal allow_trivial_move ``` After this PR, the bug is fixed. Reviewed By: ajkr Differential Revision: D34350451 Pulled By: gitbw95 fbshipit-source-id: 3232005cc47c40a7e75d316cfc7960beb5bdff3a | 18 February 2022, 22:23:07 UTC |
736bc83 | pat somaru | 18 February 2022, 21:59:23 UTC | fix issue with buckifier update (#9602) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9602 Reviewed By: jay-zhuang Differential Revision: D34350406 Pulled By: likewhatevs fbshipit-source-id: caa81f272a429fbf7293f0588ea24cc53b29ee98 | 18 February 2022, 22:23:07 UTC |
f4b2500 | Jay Zhuang | 18 February 2022, 21:35:36 UTC | Add last level and non-last level read statistics (#9519) Summary: Add last level and non-last level read statistics: ``` LAST_LEVEL_READ_BYTES, LAST_LEVEL_READ_COUNT, NON_LAST_LEVEL_READ_BYTES, NON_LAST_LEVEL_READ_COUNT, ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9519 Test Plan: added unittest Reviewed By: siying Differential Revision: D34062539 Pulled By: jay-zhuang fbshipit-source-id: 908644c3050878b4234febdc72e3e19d89af38cd | 18 February 2022, 22:23:07 UTC |
30b0887 | mrambacher | 18 February 2022, 20:23:48 UTC | Make FilterPolicy Customizable (#9590) Summary: Make FilterPolicy into a Customizable class. Allow new FilterPolicy to be discovered through the ObjectRegistry Pull Request resolved: https://github.com/facebook/rocksdb/pull/9590 Reviewed By: pdillinger Differential Revision: D34327367 Pulled By: mrambacher fbshipit-source-id: 37e7edac90ec9457422b72f359ab8ef48829c190 | 18 February 2022, 21:22:31 UTC |
f066b5c | Patrick Somaru | 18 February 2022, 18:59:57 UTC | update buckifier, add support for microbenchmarks (#9598) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9598 Reviewed By: jay-zhuang, hodgesds Differential Revision: D34130191 fbshipit-source-id: e5413f7d6af70a66940022d153b64a3383eccff1 | 18 February 2022, 19:23:18 UTC |
2fbc672 | Jay Zhuang | 18 February 2022, 18:26:45 UTC | Add temperature information to the event listener callbacks (#9591) Summary: RocksDB try to provide temperature information in the event listener callbacks. The information is not guaranteed, as some operation like backup won't have these information. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9591 Test Plan: Added unittest Reviewed By: siying, pdillinger Differential Revision: D34309339 Pulled By: jay-zhuang fbshipit-source-id: 4aca4f270f99fa49186d85d300da42594663d6d7 | 18 February 2022, 19:23:18 UTC |
54fb2a8 | Andrew Kryczka | 18 February 2022, 05:08:59 UTC | Change type of cache buffer passed to `Cache::CreateCallback()` to `const void*` (#9595) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9595 Reviewed By: riversand963 Differential Revision: D34329906 Pulled By: ajkr fbshipit-source-id: 508601856fa9bee4d40f4a68d14d333ef2143d40 | 18 February 2022, 05:09:56 UTC |
48b9de4 | Peter Dillinger | 18 February 2022, 04:27:07 UTC | Mark more OldDefaults as deprecated (#9594) Summary: `ColumnFamilyOptions::OldDefaults` and `DBOptions::OldDefaults` now deprecated. Were previously overlooked with `Options::OldDefaults` in https://github.com/facebook/rocksdb/issues/9363 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9594 Test Plan: comments only Reviewed By: jay-zhuang Differential Revision: D34318592 Pulled By: pdillinger fbshipit-source-id: 773c97a61e2a8290ae154f363dd61c1f35a9dd16 | 18 February 2022, 04:28:10 UTC |
ce84e50 | Alan Paxton | 18 February 2022, 03:38:23 UTC | Plugin java jni support (#9575) Summary: Extend the plugin architecture to allow for the inclusion, building and testing of Java and JNI components of a plugin. This will cause the JAR built by `$ make rocksdbjava` to include the extra functionality provided by the plugin, and will cause `$ make jtest` to add the java tests provided by the plugin to the tests built and run by Java testing. The plugin's `<plugin>.mk` file can define: ``` <plugin>_JNI_NATIVE_SOURCES <plugin>_NATIVE_JAVA_CLASSES <plugin>_JAVA_TESTS ``` The plugin should provide java/src, java/test and java/rocksjni directories. When a plugin is required to be build it must be named in the ROCKSDB_PLUGINS environment variable (as per the plugin architecture). This now has the effect of adding the files specified by the above definitions to the appropriate parts of the build. An example of a plugin with a Java component can be found as part of the hdfs plugin in https://github.com/riversand963/rocksdb-hdfs-env - at the time of writing the Java part of this fails tests, and needs a little work to complete, but it builds correctly under the plugin model. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9575 Reviewed By: hx235 Differential Revision: D34253948 Pulled By: riversand963 fbshipit-source-id: b3dde5da06f3d3c25c54246892097ae2a369b42d | 18 February 2022, 03:39:23 UTC |
561be00 | Peter Dillinger | 18 February 2022, 02:50:09 UTC | Some better API and other comments (#9533) Summary: Various comments, mostly about SliceTransform + prefix extractors. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9533 Test Plan: comments only Reviewed By: ajkr Differential Revision: D34094367 Pulled By: pdillinger fbshipit-source-id: 9742ce3b89ef7fd5c5e748fec862e6361ed44e95 | 18 February 2022, 02:51:08 UTC |
8d9c203 | Alan Paxton | 18 February 2022, 01:23:31 UTC | Remove previously deprecated Java where RocksDB also removed it, or where no direct equivalent existed. (#9576) Summary: For RocksDB v7 major release. Remove previously deprecated Java API methods and associated tests - where equivalent/alternative functionality exists and is already tested AND - where the core RocksDB function/feature has also been removed - OR the functionality exists only in Java so the previous deprecation only affected Java methods RETAIN deprecated Java which reflects functionality which is deprecated by, but also still supported by, the core of RocksDB. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9576 Reviewed By: ajkr Differential Revision: D34314983 Pulled By: jay-zhuang fbshipit-source-id: 7cf9c17e3e07be9d289beb99f81b71e8e09ac403 | 18 February 2022, 01:29:35 UTC |
725833a | Peter Dillinger | 18 February 2022, 00:33:39 UTC | Hide FilterBits{Builder,Reader} from public API (#9592) Summary: We don't have any evidence of people using these to build custom filters. The recommended way of customizing filter handling is to defer to various built-in policies based on FilterBuildingContext (e.g. to build Monkey filtering policy). With old API, we have evidence of people modifying keys going into filter, but most cases of that can be handled with prefix_extractor. Having FilterBitsBuilder+Reader in the public API is an ogoing hinderance to code evolution (e.g. recent new Finish and MaybePostVerify), and so this change removes them from the public API for 7.0. Maybe they will come back in some form later, but lacking evidence of them providing value in the public API, we want to take back more freedom to evolve these. With this moved to internal-only, there is no rush to clean up the complex Finish signatures, or add memory allocator support, but doing so is much easier with them out of public API, for example to use CacheAllocationPtr without exposing it in the public API. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9592 Test Plan: cosmetic changes only Reviewed By: hx235 Differential Revision: D34315470 Pulled By: pdillinger fbshipit-source-id: 03e03bb66a72c73df2c464d2dbbbae906dd8f99b | 18 February 2022, 00:34:46 UTC |
627deb7 | anand76 | 18 February 2022, 00:30:40 UTC | Fix some MultiGet batching stats (#9583) Summary: The NUM_INDEX_AND_FILTER_BLOCKS_READ_PER_LEVEL, NUM_DATA_BLOCKS_READ_PER_LEVEL, and NUM_SST_READ_PER_LEVEL stats were being recorded only when the last file in a level happened to have hits. They are supposed to be updated for every level. Also, there was some overcounting of GetContextStats. This PR fixes both the problems. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9583 Test Plan: Update the unit test in db_basic_test Reviewed By: akankshamahajan15 Differential Revision: D34308044 Pulled By: anand1976 fbshipit-source-id: b3b36020fda26ba91bc6e0e47d52d58f4d7f656e | 18 February 2022, 00:31:41 UTC |
39b0d92 | Siddhartha Roychowdhury | 18 February 2022, 00:18:01 UTC | Add record to set WAL compression type if enabled (#9556) Summary: When WAL compression is enabled, add a record (new record type) to store the compression type to indicate that all subsequent records are compressed. The log reader will store the compression type when this record is encountered and use the type to uncompress the subsequent records. Compress and uncompress to be implemented in subsequent diffs. Enabled WAL compression in some WAL tests to check for regressions. Some tests that rely on offsets have been disabled. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9556 Reviewed By: anand1976 Differential Revision: D34308216 Pulled By: sidroyc fbshipit-source-id: 7f10595e46f3277f1ea2d309fbf95e2e935a8705 | 18 February 2022, 00:19:31 UTC |
f092f0f | Jay Zhuang | 17 February 2022, 23:46:16 UTC | Add subcompaction event API (#9311) Summary: Add event callback for subcompaction and adds a sub_job_id to identify it. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9311 Reviewed By: ajkr Differential Revision: D33892707 Pulled By: jay-zhuang fbshipit-source-id: 57b5e5e594d61b2112d480c18a79a36751f65a4e | 17 February 2022, 23:47:10 UTC |
a86ee02 | Peter Dillinger | 17 February 2022, 23:38:06 UTC | Clarify compiler support release note (#9593) Summary: in HISTORY.md Pull Request resolved: https://github.com/facebook/rocksdb/pull/9593 Test Plan: release note only Reviewed By: siying Differential Revision: D34318189 Pulled By: pdillinger fbshipit-source-id: ba2eca8bede2d42a3fefd10b954b92cb54f831f2 | 17 February 2022, 23:39:17 UTC |
36ce2e2 | Alan Paxton | 17 February 2022, 21:28:09 UTC | Update build files for java8 build (#9541) Summary: For RocksJava 7 we will move from requiring Java 7 to Java 8. * This simplifies the `Makefile` as we no longer need to deal with Java 7; so we no longer use `javah`. * Added a java-version target which is invoked by the java target, and which exits if the version of java being used is not 8 or greater. * Enforces java 8 as a minimum. * Fixed CMake build. * Fixed broken java event listener test, as the test was broken and the assertions in the callbacks were not causing assertions in the tests. The callbacks now queue up assertion errors for the main thread of the tests to check. * Fixed C++ dangling pointers in the test code. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9541 Reviewed By: pdillinger Differential Revision: D34214929 Pulled By: jay-zhuang fbshipit-source-id: fdff348758d0a23a742e83c87d5f54073ce16ca6 | 17 February 2022, 21:29:21 UTC |
5e64407 | Adam Retter | 17 February 2022, 20:47:45 UTC | Support C++17 Docker build environments for RocksJava (#9500) Summary: See https://github.com/facebook/rocksdb/issues/9388#issuecomment-1029583789 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9500 Reviewed By: pdillinger Differential Revision: D34114687 Pulled By: jay-zhuang fbshipit-source-id: 22129d99ccd0dba7e8f1b263ddc5520d939641bf | 17 February 2022, 20:48:38 UTC |
babe56d | Andrew Kryczka | 17 February 2022, 07:17:03 UTC | Add rate limiter priority to ReadOptions (#9424) Summary: Users can set the priority for file reads associated with their operation by setting `ReadOptions::rate_limiter_priority` to something other than `Env::IO_TOTAL`. Rate limiting `VerifyChecksum()` and `VerifyFileChecksums()` is the motivation for this PR, so it also includes benchmarks and minor bug fixes to get that working. `RandomAccessFileReader::Read()` already had support for rate limiting compaction reads. I changed that rate limiting to be non-specific to compaction, but rather performed according to the passed in `Env::IOPriority`. Now the compaction read rate limiting is supported by setting `rate_limiter_priority = Env::IO_LOW` on its `ReadOptions`. There is no default value for the new `Env::IOPriority` parameter to `RandomAccessFileReader::Read()`. That means this PR goes through all callers (in some cases multiple layers up the call stack) to find a `ReadOptions` to provide the priority. There are TODOs for cases I believe it would be good to let user control the priority some day (e.g., file footer reads), and no TODO in cases I believe it doesn't matter (e.g., trace file reads). The API doc only lists the missing cases where a file read associated with a provided `ReadOptions` cannot be rate limited. For cases like file ingestion checksum calculation, there is no API to provide `ReadOptions` or `Env::IOPriority`, so I didn't count that as missing. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9424 Test Plan: - new unit tests - new benchmarks on ~50MB database with 1MB/s read rate limit and 100ms refill interval; verified with strace reads are chunked (at 0.1MB per chunk) and spaced roughly 100ms apart. - setup command: `./db_bench -benchmarks=fillrandom,compact -db=/tmp/testdb -target_file_size_base=1048576 -disable_auto_compactions=true -file_checksum=true` - benchmarks command: `strace -ttfe pread64 ./db_bench -benchmarks=verifychecksum,verifyfilechecksums -use_existing_db=true -db=/tmp/testdb -rate_limiter_bytes_per_sec=1048576 -rate_limit_bg_reads=1 -rate_limit_user_ops=true -file_checksum=true` - crash test using IO_USER priority on non-validation reads with https://github.com/facebook/rocksdb/issues/9567 reverted: `python3 tools/db_crashtest.py blackbox --max_key=1000000 --write_buffer_size=524288 --target_file_size_base=524288 --level_compaction_dynamic_level_bytes=true --duration=3600 --rate_limit_bg_reads=true --rate_limit_user_ops=true --rate_limiter_bytes_per_sec=10485760 --interval=10` Reviewed By: hx235 Differential Revision: D33747386 Pulled By: ajkr fbshipit-source-id: a2d985e97912fba8c54763798e04f006ccc56e0c | 17 February 2022, 07:18:14 UTC |
1cda273 | Yanqin Jin | 17 February 2022, 07:07:48 UTC | Fix a silent data loss for write-committed txn (#9571) Summary: The following sequence of events can cause silent data loss for write-committed transactions. ``` Time thread 1 bg flush | db->Put("a") | txn = NewTxn() | txn->Put("b", "v") | txn->Prepare() // writes only to 5.log | db->SwitchMemtable() // memtable 1 has "a" | // close 5.log, | // creates 8.log | trigger flush | pick memtable 1 | unlock db mutex | write new sst | txn->ctwb->Put("gtid", "1") // writes 8.log | txn->Commit() // writes to 8.log | // writes to memtable 2 | compute min_log_number_to_keep_2pc, this | will be 8 (incorrect). | | Purge obsolete wals, including 5.log | V ``` At this point, writes of txn exists only in memtable. Close db without flush because db thinks the data in memtable are backed by log. Then reopen, the writes are lost except key-value pair {"gtid"->"1"}, only the commit marker of txn is in 8.log The reason lies in `PrecomputeMinLogNumberToKeep2PC()` which calls `FindMinPrepLogReferencedByMemTable()`. In the above example, when bg flush thread tries to find obsolete wals, it uses the information computed by `PrecomputeMinLogNumberToKeep2PC()`. The return value of `PrecomputeMinLogNumberToKeep2PC()` depends on three components - `PrecomputeMinLogNumberToKeepNon2PC()`. This represents the WAL that has unflushed data. As the name of this method suggests, it does not account for 2PC. Although the keys reside in the prepare section of a previous WAL, the column family references the current WAL when they are actually inserted into the memtable during txn commit. - `prep_tracker->FindMinLogContainingOutstandingPrep()`. This represents the WAL with a prepare section but the txn hasn't committed. - `FindMinPrepLogReferencedByMemTable()`. This represents the WAL on which some memtables (mutable and immutable) depend for their unflushed data. The bug lies in `FindMinPrepLogReferencedByMemTable()`. Originally, this function skips checking the column families that are being flushed, but the unit test added in this PR shows that they should not be. In this unit test, there is only the default column family, and one of its memtables has unflushed data backed by a prepare section in 5.log. We should return this information via `FindMinPrepLogReferencedByMemTable()`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9571 Test Plan: ``` ./transaction_test --gtest_filter=*/TransactionTest.SwitchMemtableDuringPrepareAndCommit_WC/* make check ``` Reviewed By: siying Differential Revision: D34235236 Pulled By: riversand963 fbshipit-source-id: 120eb21a666728a38dda77b96276c6af72b008b1 | 17 February 2022, 07:08:58 UTC |
1e403a0 | Peter Dillinger | 17 February 2022, 06:42:28 UTC | Fix assertion failure in FastLocalBloomBitsBuilder (#9585) Summary: As in ``` db_stress: table/block_based/filter_policy.cc:316: rocksdb::{anonymous}::FastLocalBloomBitsBuilder::FastLocalBloomBitsBuilder(int, std::atomic<long int>*, std::shared_ptr<rocksdb::CacheReservationManager>, bool): Assertion `millibits_per_key >= 1000' failed. ``` This assertion failure was actually happening with our RibbonFilterPolicy which falls back to Bloom for some cases, often for flush, but was missing new special logic to skip generating filter for 0 bits per key case. Fixed by adding the logic in other builtin FilterPolicy implementations. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9585 Test Plan: Updated db_bloom_filter_test to do more integration testing of the RibbonFilterPolicy ("auto Ribbon") class, incl regression test this with SkipFilterOnEssentiallyZeroBpk Reviewed By: ajkr Differential Revision: D34295101 Pulled By: pdillinger fbshipit-source-id: 3488eb207fc1d67bbbd1301313714aa1b6406e6e | 17 February 2022, 06:43:34 UTC |
8286469 | sdong | 17 February 2022, 01:06:33 UTC | LDB to add --secondary_path to help (#9582) Summary: Opening DB as seconeary instance has been supported in ldb but it is not mentioned in --help. Mention it there. The part of the help message after the modification: ``` commands MUST specify --db=<full_path_to_db_directory> when necessary commands can optionally specify --env_uri=<uri_of_environment> or --fs_uri=<uri_of_filesystem> if necessary --secondary_path=<secondary_path> to open DB as secondary instance. Operations not supported in secondary instance will fail. ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9582 Test Plan: Build and run ldb --help Reviewed By: riversand963 Differential Revision: D34286427 fbshipit-source-id: e56c5290d0548098ab6acc6dde2167f5a64f34f3 | 17 February 2022, 01:07:37 UTC |
31031c0 | Jay Zhuang | 16 February 2022, 21:24:43 UTC | Remove deprecated RemoteCompaction API (#9570) Summary: Remove deprecated remote compaction APIs `CompactionService::Start()` and `CompactionService::WaitForComplete()`. Please use `CompactionService::StartV2()`, `CompactionService::WaitForCompleteV2()` instead, which provides the same information plus extra data like priority, db_id, etc. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9570 Test Plan: CI Reviewed By: riversand963 Differential Revision: D34255969 Pulled By: jay-zhuang fbshipit-source-id: c6376eccdd1123f1c42ab53771b5f65f8160c325 | 16 February 2022, 21:25:28 UTC |
c42d0cf | mrambacher | 16 February 2022, 19:11:55 UTC | Add support for decimals to PatternEntry (#9577) Summary: Add support for doubles to ObjectLibrary::PatternEntry. This support will allow patterns containing a non-integer number to be parsed correctly. Added appropriate test cases to cover this new option. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9577 Reviewed By: pdillinger Differential Revision: D34269763 Pulled By: mrambacher fbshipit-source-id: b5ce16cbd3665c2974ec0f3412ef2b403ef8b155 | 16 February 2022, 19:15:19 UTC |
48f6c2a | Yueh-Hsuan Chiang | 16 February 2022, 16:52:07 UTC | Add Solana's RocksDB use case in USERS.md (#9558) Summary: Add Solana's RocksDB use case in USERS.md. Solana is a fast, secure, scalable, and decentralized blockchain. It uses RocksDB as the underlying storage for its ledger store. github: https://github.com/solana-labs/solana Pull Request resolved: https://github.com/facebook/rocksdb/pull/9558 Reviewed By: jay-zhuang Differential Revision: D34249087 Pulled By: riversand963 fbshipit-source-id: 7524eff4952e2676e8520ac491ffb6a686fb4d7e | 16 February 2022, 17:23:01 UTC |
8c68108 | Peter Dillinger | 16 February 2022, 16:27:37 UTC | Refactor FilterPolicies toward Customizable (#9567) Summary: Some changes to make it easier to make FilterPolicy customizable. Especially, create distinct classes for the different testing-only and user-facing built-in FilterPolicy modes. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9567 Test Plan: tests updated, with no intended difference in functionality tested. No difference in test performance seen as a result of moving to string-based filter type configuration. Reviewed By: mrambacher Differential Revision: D34234694 Pulled By: pdillinger fbshipit-source-id: 8a94931a9e04c3bcca863a4f524cfd064aaf0122 | 16 February 2022, 16:30:03 UTC |
a0c569e | Jay Zhuang | 16 February 2022, 01:59:31 UTC | Cancel manual compaction in thread-pool queue (#9557) Summary: Fix `DisableManualCompaction()` has to wait scheduled manual compaction to start the execution to cancel the job. When a manual compaction in thread-pool queue is cancel, set the job is_canceled to true and clean the resource. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9557 Test Plan: added unittest that will hang without the change Reviewed By: ajkr Differential Revision: D34214910 Pulled By: jay-zhuang fbshipit-source-id: 89dbaee78ddf26eb13ce862c2b15f4a098b36a78 | 16 February 2022, 03:23:01 UTC |
ad2cab8 | Andrew Kryczka | 15 February 2022, 21:55:22 UTC | minor tweaks to db_crashtest.py settings (#9483) Summary: I did another pass through running CI jobs. It is uncommon now to see `db_stress` stuck in the setup phase but still happen. One reason was repeatedly reading/verifying checksum on filter blocks when `-cache_index_and_filter_blocks=1` and `-cache_size=1048576`. To address that I increased the cache size. Another reason was having a WAL with many range tombstones and every `db_stress` run using `-avoid_flush_during_recovery=1` (in that scenario, the setup phase spent too much CPU in `rocksdb::MemTable::NewRangeTombstoneIteratorInternal()`). To address that I fixed the `-avoid_flush_during_recovery` setting so it is reevaluated for every `db_stress` run. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9483 Reviewed By: riversand963 Differential Revision: D33922929 Pulled By: ajkr fbshipit-source-id: 0a298ec7c4df6f6b44620233996047a2dc7ee5f3 | 15 February 2022, 21:56:27 UTC |
57418ab | Hui Xiao | 15 February 2022, 20:30:19 UTC | Fix a typo in HISTORY.md for 7.0 (#9574) Summary: See PR Pull Request resolved: https://github.com/facebook/rocksdb/pull/9574 Reviewed By: ajkr, mrambacher Differential Revision: D34239184 Pulled By: hx235 fbshipit-source-id: 6b5cc70d86b804ab4645bc2cd0243961c2fb00ee | 15 February 2022, 20:31:16 UTC |
443d8ef | Hui Xiao | 15 February 2022, 20:24:05 UTC | Fix PinSelf() read-after-free in DB::GetMergeOperands() (#9507) Summary: **Context:** Running the new test `DBMergeOperandTest.MergeOperandReadAfterFreeBug` prior to this fix surfaces the read-after-free bug of PinSef() as below: ``` READ of size 8 at 0x60400002529d thread T0 https://github.com/facebook/rocksdb/issues/5 0x7f199a in rocksdb::PinnableSlice::PinSelf(rocksdb::Slice const&) include/rocksdb/slice.h:171 https://github.com/facebook/rocksdb/issues/6 0x7f199a in rocksdb::DBImpl::GetImpl(rocksdb::ReadOptions const&, rocksdb::Slice const&, rocksdb::DBImpl::GetImplOptions&) db/db_impl/db_impl.cc:1919 https://github.com/facebook/rocksdb/issues/7 0x540d63 in rocksdb::DBImpl::GetMergeOperands(rocksdb::ReadOptions const&, rocksdb::ColumnFamilyHandle*, rocksdb::Slice const&, rocksdb::PinnableSlice*, rocksdb::GetMergeOperandsOptions*, int*) db/db_impl/db_impl.h:203 freed by thread T0 here: https://github.com/facebook/rocksdb/issues/3 0x1191399 in rocksdb::cache_entry_roles_detail::RegisteredDeleter<rocksdb::Block, (rocksdb::CacheEntryRole)0>::Delete(rocksdb::Slice const&, void*) cache/cache_entry_roles.h:99 https://github.com/facebook/rocksdb/issues/4 0x719348 in rocksdb::LRUHandle::Free() cache/lru_cache.h:205 https://github.com/facebook/rocksdb/issues/5 0x71047f in rocksdb::LRUCacheShard::Release(rocksdb::Cache::Handle*, bool) cache/lru_cache.cc:547 https://github.com/facebook/rocksdb/issues/6 0xa78f0a in rocksdb::Cleanable::DoCleanup() include/rocksdb/cleanable.h:60 https://github.com/facebook/rocksdb/issues/7 0xa78f0a in rocksdb::Cleanable::Reset() include/rocksdb/cleanable.h:38 https://github.com/facebook/rocksdb/issues/8 0xa78f0a in rocksdb::PinnedIteratorsManager::ReleasePinnedData() db/pinned_iterators_manager.h:71 https://github.com/facebook/rocksdb/issues/9 0xd0c21b in rocksdb::PinnedIteratorsManager::~PinnedIteratorsManager() db/pinned_iterators_manager.h:24 https://github.com/facebook/rocksdb/issues/10 0xd0c21b in rocksdb::Version::Get(rocksdb::ReadOptions const&, rocksdb::LookupKey const&, rocksdb::PinnableSlice*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >*, rocksdb::Status*, rocksdb::MergeContext*, unsigned long*, bool*, bool*, unsigned long*, rocksdb::ReadCallback*, bool*, bool) db/pinned_iterators_manager.h:22 https://github.com/facebook/rocksdb/issues/11 0x7f0fdf in rocksdb::DBImpl::GetImpl(rocksdb::ReadOptions const&, rocksdb::Slice const&, rocksdb::DBImpl::GetImplOptions&) db/db_impl/db_impl.cc:1886 https://github.com/facebook/rocksdb/issues/12 0x540d63 in rocksdb::DBImpl::GetMergeOperands(rocksdb::ReadOptions const&, rocksdb::ColumnFamilyHandle*, rocksdb::Slice const&, rocksdb::PinnableSlice*, rocksdb::GetMergeOperandsOptions*, int*) db/db_impl/db_impl.h:203 previously allocated by thread T0 here: https://github.com/facebook/rocksdb/issues/1 0x1239896 in rocksdb::AllocateBlock(unsigned long, **rocksdb::MemoryAllocator*)** memory/memory_allocator.h:35 https://github.com/facebook/rocksdb/issues/2 0x1239896 in rocksdb::BlockFetcher::CopyBufferToHeapBuf() table/block_fetcher.cc:171 https://github.com/facebook/rocksdb/issues/3 0x1239896 in rocksdb::BlockFetcher::GetBlockContents() table/block_fetcher.cc:206 https://github.com/facebook/rocksdb/issues/4 0x122eae5 in rocksdb::BlockFetcher::ReadBlockContents() table/block_fetcher.cc:325 https://github.com/facebook/rocksdb/issues/5 0x11b1f45 in rocksdb::Status rocksdb::BlockBasedTable::MaybeReadBlockAndLoadToCache<rocksdb::Block>(rocksdb::FilePrefetchBuffer*, rocksdb::ReadOptions const&, rocksdb::BlockHandle const&, rocksdb::UncompressionDict const&, bool, rocksdb::CachableEntry<rocksdb::Block>*, rocksdb::BlockType, rocksdb::GetContext*, rocksdb::BlockCacheLookupContext*, rocksdb::BlockContents*) const table/block_based/block_based_table_reader.cc:1503 ``` Here is the analysis: - We have [PinnedIteratorsManager](https://github.com/facebook/rocksdb/blob/6.28.fb/db/version_set.cc#L1980) with `Cleanable` capability in our `Version::Get()` path. It's responsible for managing the life-time of pinned iterator and invoking registered cleanup functions during its own destruction. - For example in case above, the merge operands's clean-up gets associated with this manger in [GetContext::push_operand](https://github.com/facebook/rocksdb/blob/6.28.fb/table/get_context.cc#L405). During PinnedIteratorsManager's [destruction](https://github.com/facebook/rocksdb/blob/6.28.fb/db/pinned_iterators_manager.h#L67), the release function associated with those merge operand data is invoked. **And that's what we see in "freed by thread T955 here" in ASAN.** - Bug 🐛: `PinnedIteratorsManager` is local to `Version::Get()` while the data of merge operands need to outlive `Version::Get` and stay till they get [PinSelf()](https://github.com/facebook/rocksdb/blob/6.28.fb/db/db_impl/db_impl.cc#L1905), **which is the read-after-free in ASAN.** - This bug is likely to be an overlook of `PinnedIteratorsManager` when developing the API `DB::GetMergeOperands` cuz the current logic works fine with the existing case of getting the *merged value* where the operands do not need to live that long. - This bug was not surfaced much (even in its unit test) due to the release function associated with the merge operands (which are actually blocks put in cache as you can see in `BlockBasedTable::MaybeReadBlockAndLoadToCache` **in "previously allocated by" in ASAN report**) is a cache entry deleter. The deleter will call `Cache::Release()` which, for LRU cache, won't immediately deallocate the block based on LRU policy [unless the cache is full or being instructed to force erase](https://github.com/facebook/rocksdb/blob/6.28.fb/cache/lru_cache.cc#L521-L531) - `DBMergeOperandTest.MergeOperandReadAfterFreeBug` makes the cache extremely small to force cache full. **Summary:** - Fix the bug by align `PinnedIteratorsManager`'s lifetime with the merge operands Pull Request resolved: https://github.com/facebook/rocksdb/pull/9507 Test Plan: - New test `DBMergeOperandTest.MergeOperandReadAfterFreeBug` - db bench on read path - Setup (LSM tree with several levels, cache the whole db to avoid read IO, warm cache with readseq to avoid read IO): `TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks="fillrandom,readseq -num=1000000 -cache_size=100000000 -write_buffer_size=10000 -statistics=1 -max_bytes_for_level_base=10000 -level0_file_num_compaction_trigger=1``TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks="readrandom" -num=1000000 -cache_size=100000000 ` - Actual command run (run 20-run for 20 times and then average the 20-run's average micros/op) - `for j in {1..20}; do (for i in {1..20}; do rm -rf /dev/shm/rocksdb/ && TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks="fillrandom,readseq,readrandom" -num=1000000 -cache_size=100000000 -write_buffer_size=10000 -statistics=1 -max_bytes_for_level_base=10000 -level0_file_num_compaction_trigger=1 | egrep 'readrandom'; done > rr_output_pre.txt && (awk '{sum+=$3; sum_sqrt+=$3^2}END{print sum/20, sqrt(sum_sqrt/20-(sum/20)^2)}' rr_output_pre.txt) >> rr_output_pre_2.txt); done` - **Result: Pre-change: 3.79193 micros/op; Post-change: 3.79528 micros/op (+0.09%)** (pre-change)sorted avg micros/op of each 20-run | std of micros/op of each 20-run | (post-change) sorted avg micros/op of each 20-run | std of micros/op of each 20-run -- | -- | -- | -- 3.58355 | 0.265209 | 3.48715 | 0.382076 3.58845 | 0.519927 | 3.5832 | 0.382726 3.66415 | 0.452097 | 3.677 | 0.563831 3.68495 | 0.430897 | 3.68405 | 0.495355 3.70295 | 0.482893 | 3.68465 | 0.431438 3.719 | 0.463806 | 3.71945 | 0.457157 3.7393 | 0.453423 | 3.72795 | 0.538604 3.7806 | 0.527613 | 3.75075 | 0.444509 3.7817 | 0.426704 | 3.7683 | 0.468065 3.809 | 0.381033 | 3.8086 | 0.557378 3.80985 | 0.466011 | 3.81805 | 0.524833 3.8165 | 0.500351 | 3.83405 | 0.529339 3.8479 | 0.430326 | 3.86285 | 0.44831 3.85125 | 0.434108 | 3.8717 | 0.544098 3.8556 | 0.524602 | 3.895 | 0.411679 3.8656 | 0.476383 | 3.90965 | 0.566636 3.8911 | 0.488477 | 3.92735 | 0.608038 3.898 | 0.493978 | 3.9439 | 0.524511 3.97235 | 0.515008 | 3.9623 | 0.477416 3.9768 | 0.519993 | 3.98965 | 0.521481 - CI Reviewed By: ajkr Differential Revision: D34030519 Pulled By: hx235 fbshipit-source-id: a99ac585c11704c5ed93af033cb29ba0a7b16ae8 | 15 February 2022, 20:25:18 UTC |
420d51b | Peter Dillinger | 15 February 2022, 20:17:45 UTC | Update Java API for FilterPolicy changes (#9569) Summary: Obsolete block-based filter no longer in public API, from https://github.com/facebook/rocksdb/issues/9535 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9569 Test Plan: existing tests Reviewed By: jay-zhuang Differential Revision: D34243579 Pulled By: pdillinger fbshipit-source-id: ec5127d9bb9cc3f70501c531829a735bffdd1418 | 15 February 2022, 20:18:52 UTC |
e24734f | Peter Dillinger | 15 February 2022, 17:18:08 UTC | Use -Wno-invalid-offsetof instead of dangerous offset_of hack (#9563) Summary: After https://github.com/facebook/rocksdb/issues/9515 added a unique_ptr to Status, we see some warnings-as-error in some internal builds like this: ``` stderr: rocksdb/src/db/compaction/compaction_job.cc:2839:7: error: offset of on non-standard-layout type 'struct CompactionServiceResult' [-Werror,-Winvalid-offsetof] {offsetof(struct CompactionServiceResult, status), ^ ~~~~~~ ``` I see three potential solutions to resolving this: * Expand our use of an idiom that works around the warning (see offset_of functions removed in this change, inspired by https://gist.github.com/graphitemaster/494f21190bb2c63c5516) However, this construction is invoking undefined behavior that assumes consistent layout with no compiler-introduced indirection. A compiler incompatible with our assumptions will likely compile the code and exhibit undefined behavior. * Migrate to something in place of offset, like a function mapping CompactionServiceResult* to Status* (for the `status` field). This might be required in the long term. * **Selected:** Use our new C++17 dependency to use offsetof in a well-defined way when the compiler allows it. From a comment on https://gist.github.com/graphitemaster/494f21190bb2c63c5516: > A final note: in C++17, offsetof is conditionally supported, which > means that you can use it on any type (not just standard layout > types) and the compiler will error if it can't compile it correctly. > That appears to be the best option if you can live with C++17 and > don't need constexpr support. The C++17 semantics are confirmed on https://en.cppreference.com/w/cpp/types/offsetof, so we can suppress the warning as long as we accept that we might run into a compiler that rejects the code, and at that point we will find a solution, such as the more intrusive "migrate" solution above. Although this is currently only showing in our buck build, it will surely show up also with make and cmake, so I have updated those configurations as well. Also in the buck build, -Wno-expansion-to-defined does not appear to be needed anymore (both current compiler configurations) so I removed it. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9563 Test Plan: Tried out buck builds with both current compiler configurations Reviewed By: riversand963 Differential Revision: D34220931 Pulled By: pdillinger fbshipit-source-id: d39436008259bd1eaaa87c77be69fb2a5b559e1f | 15 February 2022, 17:19:19 UTC |
241b5aa | Yanqin Jin | 15 February 2022, 01:31:41 UTC | Timestamp-based validation for pessimistic txn (#9562) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9562 With per-transaction `read_timestamp_`, it is possible to perform transaction validation after locking a key in addition to sequence-based validation. Specifically, if a transaction has a read_timestamp, then we perform timestamp-based validation as well after the key is locked via `GetForUpdate()`. This is to make sure that no other transaction has modified the key and committed successfully since the read timestamp (but before the locking operation) which represents a consistent view of the database. Reviewed By: ltamasi Differential Revision: D31822034 fbshipit-source-id: c6f1828b7fc23e4f85e2d1ed73ff51464a058d91 | 15 February 2022, 01:32:47 UTC |
ec0b1ff | Levi Tamasi | 14 February 2022, 23:37:20 UTC | Add blob compaction readahead size to the BlobDB benchmark script (#9566) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9566 Reviewed By: riversand963 Differential Revision: D34226256 Pulled By: ltamasi fbshipit-source-id: 4374b819e937c35e3a866ba5b5eafba87ff20af3 | 14 February 2022, 23:38:32 UTC |
ac251aa | Levi Tamasi | 14 February 2022, 17:11:59 UTC | Add Java bindings for blob compaction readahead size (#9554) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9554 Test Plan: Added new unit tests. Reviewed By: mrambacher Differential Revision: D34197121 Pulled By: ltamasi fbshipit-source-id: 15056e26d632057a7c052a5024a560ba0eac554c | 14 February 2022, 17:15:42 UTC |
5cdc8af | Peter Dillinger | 14 February 2022, 16:53:29 UTC | Fix parallel test updates in CI; fbcode LIB_MODE=shared (#9553) Summary: * Fix LIB_MODE=shared for Meta-internal builds (use PIC libraries appropriately) * Fix gnu_parallel to recognize CircleCI and Travis builds as not connected to a terminal (was previously relying on the `| cat_ignore_eagain` stuff for Ubuntu 16). This problem could cause timeouts that should be 10m to balloon to 5h. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9553 Test Plan: manual and CI Reviewed By: jay-zhuang Differential Revision: D34182886 Pulled By: pdillinger fbshipit-source-id: e95fd8002d94c8dc414bae1975e4fd348589f2b5 | 14 February 2022, 17:07:03 UTC |
eed71df | Alan Paxton | 14 February 2022, 16:30:00 UTC | Transaction multiGet convert to list-based (#9522) Summary: Transaction multiGet convert to list-based. RocksDB Java (non-transactional) has multiGetAsList() methods to expose multiGet(). These return a list of results. These methods replaced multiGet() methods returning an array of results, which were deprecated in Rocks 6 and are being removed in Rocks 7. The transactional API still presents multiGet() methods returning arrays, so in Rocks 7 we replace these with multiGetAsList()methods and deprecate the multiGet() methods. This does not require any changes to the supporting JNI/C++ code, only to the wrappers which present the Java API. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9522 Reviewed By: mrambacher Differential Revision: D34114373 Pulled By: jay-zhuang fbshipit-source-id: cb22d6095934d951b6aee4aed3e07923d3c18007 | 14 February 2022, 16:33:02 UTC |
479eb1a | Peter Dillinger | 12 February 2022, 15:04:09 UTC | Hide deprecated, inefficient block-based filter from public API (#9535) Summary: This change removes the ability to configure the deprecated, inefficient block-based filter in the public API. Options that would have enabled it now use "full" (and optionally partitioned) filters. Existing block-based filters can still be read and used, and a "back door" way to build them still exists, for testing and in case of trouble. About the only way this removal would cause an issue for users is if temporary memory for filter construction greatly increases. In HISTORY.md we suggest a few possible mitigations: partitioned filters, smaller SST files, or setting reserve_table_builder_memory=true. Or users who have customized a FilterPolicy using the CreateFilter/KeyMayMatch mechanism removed in https://github.com/facebook/rocksdb/issues/9501 will have to upgrade their code. (It's long past time for people to move to the new builder/reader customization interface.) This change also introduces some internal-use-only configuration strings for testing specific filter implementations while bypassing some compatibility / intelligence logic. This is intended to hint at a path toward making FilterPolicy Customizable, but it also gives us a "back door" way to configure block-based filter. Aside: updated db_bench so that -readonly implies -use_existing_db Pull Request resolved: https://github.com/facebook/rocksdb/pull/9535 Test Plan: Unit tests updated. Specifically, * BlockBasedTableTest.BlockReadCountTest is tweaked to validate the back door configuration interface and ignoring of `use_block_based_builder`. * BlockBasedTableTest.TracingGetTest is migrated from testing block-based filter access pattern to full filter access patter, by re-ordering some things. * Options test (pretty self-explanatory) Performance test - create with `./db_bench -db=/dev/shm/rocksdb1 -bloom_bits=10 -cache_index_and_filter_blocks=1 -benchmarks=fillrandom -num=10000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0` with and without `-use_block_based_filter`, which creates a DB with 21 SST files in L0. Read with `./db_bench -db=/dev/shm/rocksdb1 -readonly -bloom_bits=10 -cache_index_and_filter_blocks=1 -benchmarks=readrandom -num=10000000 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -duration=30` Without -use_block_based_filter: readrandom 464 ops/sec, 689280 KB DB With -use_block_based_filter: readrandom 169 ops/sec, 690996 KB DB No consistent difference with fillrandom Reviewed By: jay-zhuang Differential Revision: D34153871 Pulled By: pdillinger fbshipit-source-id: 31f4a933c542f8f09aca47fa64aec67832a69738 | 12 February 2022, 15:05:57 UTC |
d6e1e6f | Yanqin Jin | 12 February 2022, 04:18:06 UTC | Add commit_timestamp and read_timestamp to Pessimistic transaction (#9537) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9537 Add `Transaction::SetReadTimestampForValidation()` and `Transaction::SetCommitTimestamp()` APIs with default implementation returning `Status::NotSupported()`. Currently, calling these two APIs do not have any effect. Also add checks to `PessimisticTransactionDB` to enforce that column families in the same db either - disable user-defined timestamp - enable 64-bit timestamp Just to clarify, a `PessimisticTransactionDB` can have some column families without timestamps as well as column families that enable timestamp. Each `PessimisticTransaction` can have two optional timestamps, `read_timestamp_` used for additional validation and `commit_timestamp_` which denotes when the transaction commits. For now, we are going to support `WriteCommittedTxn` (in a series of subsequent PRs) Once set, we do not allow decreasing `read_timestamp_`. The `commit_timestamp_` must be greater than `read_timestamp_` for each transaction and must be set before commit, unless the transaction does not involve any column family that enables user-defined timestamp. TransactionDB builds on top of RocksDB core `DB` layer. Though `DB` layer assumes that user-defined timestamps are byte arrays, `TransactionDB` uses uint64_t to store timestamps. When they are passed down, they are still interpreted as byte-arrays by `DB`. Reviewed By: ltamasi Differential Revision: D31567959 fbshipit-source-id: b0b6b69acab5d8e340cf174f33e8b09f1c3d3502 | 12 February 2022, 04:19:15 UTC |
81ada95 | mrambacher | 11 February 2022, 21:19:34 UTC | Add STATIC_AVOID_DESTRUCTION for ObjectLibrary/Registry (#9464) Summary: This change should guarantee that the default ObjectLibrary/Registry are long-lived and not destroyed while the process is running. This will prevent some issues of them being referenced after they were destroyed via the static destruction. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9464 Reviewed By: pdillinger Differential Revision: D33849876 Pulled By: mrambacher fbshipit-source-id: 7a69177d7c58c81be293fc7ef8e600d47ddbc14b | 11 February 2022, 21:20:41 UTC |
5c53b90 | Akanksha Mahajan | 11 February 2022, 18:22:22 UTC | Fix failure in c_test (#9547) Summary: When tests are run with TMPD, c_test may fail because TMPD is not created by the test. It results in IO error: No such file or directory: While mkdir if missing: /tmp/rocksdb_test_tmp/rocksdb_c_test-0: No such file or directory Pull Request resolved: https://github.com/facebook/rocksdb/pull/9547 Test Plan: make -j32 c_test; TEST_TMPDIR=/tmp/rocksdb_test ./c_test Reviewed By: riversand963 Differential Revision: D34173298 Pulled By: akankshamahajan15 fbshipit-source-id: 5b5a01f5b842c2487b05b0708c8e9532241db7f8 | 11 February 2022, 18:31:41 UTC |
95d9cb8 | Ezgi Çiçek | 11 February 2022, 17:14:30 UTC | Avoid unnecessary copy of sample_slice map (#9551) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9551 Reviewed By: riversand963 Differential Revision: D34169574 Pulled By: ezgicicek fbshipit-source-id: 2e88db59b65bda269917a9b0bed17181a4afd281 | 11 February 2022, 17:15:27 UTC |
a1203ed | Levi Tamasi | 11 February 2022, 16:24:44 UTC | Rework VersionStorageInfo::ComputeFilesMarkedForForcedBlobGC a bit (#9548) Summary: We had a bug in `VersionStorageInfo::ComputeFilesMarkedForForcedBlobGC` related to the edge case where all blob files are part of the "oldest batch", i.e. where only the very oldest file has any linked SSTs. (See https://github.com/facebook/rocksdb/issues/9542) This PR tries to make the logic in this method clearer and also adds a unit test for the problematic case. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9548 Test Plan: `make check` Reviewed By: akankshamahajan15 Differential Revision: D34158959 Pulled By: ltamasi fbshipit-source-id: fbab6d749c569728382aa04f7b7c60c92cca7650 | 11 February 2022, 16:41:41 UTC |
fe9d495 | mrambacher | 11 February 2022, 13:10:10 UTC | Return different Status based on ObjectRegistry::NewObject calls (#9333) Summary: This fix addresses https://github.com/facebook/rocksdb/issues/9299. If attempting to create a new object via the ObjectRegistry and a factory is not found, the ObjectRegistry will return a "NotSupported" status. This is the same behavior as previously. If the factory is found but could not successfully create the object, an "InvalidArgument" status is returned. If the factory returned a reason why (in the errmsg), this message will be in the returned status. In practice, there are two options in the ConfigOptions that control how these errors are propagated: - If "ignore_unknown_options=true", then both InvalidArgument and NotSupported status codes will be swallowed internally. Both cases will return success - If "ignore_unsupported_options=true", then having no factory will return success but a failing factory will return an error - If both options are false, both cases (no and failing factory) will return errors. In practice this likely only changes Customizable that may be partially available. For example, the JEMallocMemoryAllocator is a built-in allocator that is registered with the system but may not be compiled in. In this case, the status code for this allocator changed from NotSupported("JEMalloc not available") to InvalidArgumen("JEMalloc not available"). Other Customizable builtins/plugins would have the same semantics. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9333 Reviewed By: pdillinger Differential Revision: D33517681 Pulled By: mrambacher fbshipit-source-id: 8033052d4a4a7b88c2d9f90147b1b4467e51f6fd | 11 February 2022, 13:11:24 UTC |
073ac54 | Levi Tamasi | 10 February 2022, 20:41:19 UTC | Log blob file space amp and expose it via the rocksdb.blob-stats DB property (#9538) Summary: Extend the periodic statistics in the info log with the total amount of garbage in blob files and the space amplification pertaining to blob files, where the latter is defined as `total_blob_file_size / (total_blob_file_size - total_blob_garbage_size)`. Also expose the space amp via the `rocksdb.blob-stats` DB property. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9538 Test Plan: `make check` Reviewed By: riversand963 Differential Revision: D34126855 Pulled By: ltamasi fbshipit-source-id: 3153e7a0fe0eca440322db273f4deaabaccc51b2 | 10 February 2022, 20:42:11 UTC |
b2423f8 | Levi Tamasi | 10 February 2022, 19:12:18 UTC | Fix off-by-one bug in VersionStorageInfo::ComputeFilesMarkedForForcedBlobGC (#9542) Summary: Fixes a bug introduced in https://github.com/facebook/rocksdb/issues/9526 where we index one position past the end of a `vector`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9542 Test Plan: `make asan_check` Will add a unit test in a separate PR. Reviewed By: akankshamahajan15 Differential Revision: D34145825 Pulled By: ltamasi fbshipit-source-id: 4e87c948407dee489d669a3e41f59e2fcc1228d8 | 10 February 2022, 19:13:25 UTC |
c5cd31c | Hui Xiao | 10 February 2022, 18:17:53 UTC | Fix TSAN data race in EventListenerTest.MultiCF (#9528) Summary: **Context:** `EventListenerTest.MultiCF` occasionally failed on TSAN data race as below: ``` WARNING: ThreadSanitizer: data race (pid=2047633) Read of size 8 at 0x7b6000001440 by main thread: #0 std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> >::size() const /usr/bin/../lib/gcc/x86_64-linux-gnu/9/../../../../include/c++/9/bits/stl_vector.h:916:40 (listener_test+0x52337c) https://github.com/facebook/rocksdb/issues/1 rocksdb::EventListenerTest_MultiCF_Test::TestBody() /home/circleci/project/db/listener_test.cc:384:7 (listener_test+0x52337c) Previous write of size 8 at 0x7b6000001440 by thread T2: #0 void std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> >::_M_realloc_insert<rocksdb::DB* const&>(__gnu_cxx::__normal_iterator<rocksdb::DB**, std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> > >, rocksdb::DB* const&) /usr/bin/../lib/gcc/x86_64-linux-gnu/9/../../../../include/c++/9/bits/vector.tcc:503:31 (listener_test+0x550654) https://github.com/facebook/rocksdb/issues/1 std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> >::push_back(rocksdb::DB* const&) /usr/bin/../lib/gcc/x86_64-linux-gnu/9/../../../../include/c++/9/bits/stl_vector.h:1195:4 (listener_test+0x550654) https://github.com/facebook/rocksdb/issues/2 rocksdb::TestFlushListener::OnFlushCompleted(rocksdb::DB*, rocksdb::FlushJobInfo const&) /home/circleci/project/db/listener_test.cc:255:18 (listener_test+0x550654) ``` After investigation, it is due to the following: (1) `ASSERT_OK(Flush(i));` before the read `std::vector::size()` is supposed to be [blocked on `DB::Impl::bg_cv_` for memtable flush to finish](https://github.com/facebook/rocksdb/blob/320d9a8e8a1b6998f92934f87fc71ad8bd6d4596/db/db_impl/db_impl_compaction_flush.cc#L2319) and get signaled [at the end of background flush ](https://github.com/facebook/rocksdb/blob/320d9a8e8a1b6998f92934f87fc71ad8bd6d4596/db/db_impl/db_impl_compaction_flush.cc#L2830), which happens after the write `std::vector::push_back()` . So the sequence of execution should have been synchronized as `call flush() -> write -> return from flush() -> read` and would not cause any TSAN data race. - The subsequent `ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());` serves a similar purpose based on [the previous attempt to deflake the test.](https://github.com/facebook/rocksdb/pull/9084) (2) However, there are multiple places in the code can signal this `DB::Impl::bg_cv_` and mistakenly wake up `ASSERT_OK(Flush(i));` (or `ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());`) too early (and with the lock available to them), resulting in non-synchronized read and write thus a TSAN data race. - Reproduced by the following, suggested by ajkr: ``` diff --git a/db/db_impl/db_impl_compaction_flush.cc b/db/db_impl/db_impl_compaction_flush.cc index 4ff87c1e4..52492e9cf 100644 --- a/db/db_impl/db_impl_compaction_flush.cc +++ b/db/db_impl/db_impl_compaction_flush.cc @@ -22,7 +22,7 @@ #include "test_util/sync_point.h" #include "util/cast_util.h" #include "util/concurrent_task_limiter_impl.h" namespace ROCKSDB_NAMESPACE { bool DBImpl::EnoughRoomForCompaction( @@ -855,6 +855,7 @@ void DBImpl::NotifyOnFlushCompleted( mutable_cf_options.level0_stop_writes_trigger); // release lock while notifying events mutex_.Unlock(); + bg_cv_.SignalAll(); ``` **Summary:** - Added synchornization between read and write by ` ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency()` mechanism Pull Request resolved: https://github.com/facebook/rocksdb/pull/9528 Test Plan: `./listener_test --gtest_filter=EventListenerTest.MultiCF --gtest_repeat=10` - pre-fix: ``` Repeating all tests (iteration 3) Note: Google Test filter = EventListenerTest.MultiCF [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from EventListenerTest [ RUN ] EventListenerTest.MultiCF ================== WARNING: ThreadSanitizer: data race (pid=3377137) Read of size 8 at 0x7b6000000840 by main thread: #0 std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> >::size() https://github.com/facebook/rocksdb/issues/1 rocksdb::EventListenerTest_MultiCF_Test::TestBody() db/listener_test.cc:384 (listener_test+0x4bb300) Previous write of size 8 at 0x7b6000000840 by thread T2: #0 void std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> >::_M_realloc_insert<rocksdb::DB* const&>(__gnu_cxx::__normal_iterator<rocksdb::DB**, std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> > >, rocksdb::DB* const&) https://github.com/facebook/rocksdb/issues/1 std::vector<rocksdb::DB*, std::allocator<rocksdb::DB*> >::push_back(rocksdb::DB* const&) https://github.com/facebook/rocksdb/issues/2 rocksdb::TestFlushListener::OnFlushCompleted(rocksdb::DB*, rocksdb::FlushJobInfo const&) db/listener_test.cc:255 (listener_test+0x4e820f) ``` - post-fix: `All passed` Reviewed By: ajkr Differential Revision: D34085791 Pulled By: hx235 fbshipit-source-id: f877aa687ea1d5cb6f31ef8c4772625d22868e8b | 10 February 2022, 18:21:25 UTC |
320d9a8 | Levi Tamasi | 09 February 2022, 20:35:39 UTC | Use a sorted vector instead of a map to store blob file metadata (#9526) Summary: The patch replaces `std::map` with a sorted `std::vector` for `VersionStorageInfo::blob_files_` and preallocates the space for the `vector` before saving the `BlobFileMetaData` into the new `VersionStorageInfo` in `VersionBuilder::Rep::SaveBlobFilesTo`. These changes reduce the time the DB mutex is held while saving new `Version`s, and using a sorted `vector` also makes lookups faster thanks to better memory locality. In addition, the patch introduces helper methods `VersionStorageInfo::GetBlobFileMetaData` and `VersionStorageInfo::GetBlobFileMetaDataLB` that can be used by clients to perform lookups in the `vector`, and does some general cleanup in the parts of code where blob file metadata are used. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9526 Test Plan: Ran `make check` and the crash test script for a while. Performance was tested using a load-optimized benchmark (`fillseq` with vector memtable, no WAL) and small file sizes so that a significant number of files are produced: ``` numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --memtablerep=skip_list --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --min_level_to_compress=3 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --allow_concurrent_memtable_write=false --disable_wal=1 --enable_blob_files=1 --blob_file_size=16777216 --min_blob_size=0 --blob_compression_type=lz4 --enable_blob_garbage_collection=1 --seed=<some value> ``` Final statistics before the patch: ``` Cumulative writes: 0 writes, 700M keys, 0 commit groups, 0.0 writes per commit group, ingest: 284.62 GB, 121.27 MB/s Interval writes: 0 writes, 334K keys, 0 commit groups, 0.0 writes per commit group, ingest: 139.28 MB, 72.46 MB/s ``` With the patch: ``` Cumulative writes: 0 writes, 760M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.66 GB, 131.52 MB/s Interval writes: 0 writes, 445K keys, 0 commit groups, 0.0 writes per commit group, ingest: 185.35 MB, 93.15 MB/s ``` Total time to complete the benchmark is 2611 seconds with the patch, down from 2986 secs. Reviewed By: riversand963 Differential Revision: D34082728 Pulled By: ltamasi fbshipit-source-id: fc598abf676dce436734d06bb9d2d99a26a004fc | 09 February 2022, 20:36:43 UTC |
99d8625 | Alan Paxton | 09 February 2022, 19:31:41 UTC | remove deprecated dispose() for Rocks JNI interface Java objects. (#9523) Summary: For RocksDB 7. Remove deprecated dispose() And as a consequence remove finalize(), which is good Modern Java hygiene. It is extremely non-deterministic when `finalize()` is called on an object, and resource closure/recovery of underlying native/C++ objects and/or non-memory resource cannot be adequately controlled through GC finalization. The RocksDB Java/JNI interface provides and encourages the use of AutoCloseable objects with close() methods, allowing predictable disposal of resources at exit from try-with-resource blocks. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9523 Reviewed By: mrambacher Differential Revision: D34079843 Pulled By: jay-zhuang fbshipit-source-id: d1f0463a89a548b5d57bfaa50154379e722d189a | 09 February 2022, 19:32:53 UTC |
685044d | Yanqin Jin | 09 February 2022, 17:49:35 UTC | Remove timestamp from key in expected state (#9525) Summary: The keys as part of write batch read from trace file can contain trailing timestamps. This PR removes them before calling `ExpectedState`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9525 Test Plan: make check make crash_test_with_ts Reviewed By: ajkr Differential Revision: D34082358 Pulled By: riversand963 fbshipit-source-id: 78c925659e2a19e4a8278fb4a8ddf5070e265c04 | 09 February 2022, 17:50:54 UTC |
9745c68 | Akanksha Mahajan | 09 February 2022, 03:27:46 UTC | Remove deprecated option new_table_reader_for_compaction_inputs (#9443) Summary: In RocksDB option new_table_reader_for_compaction_inputs has not effect on Compaction or on the behavior of RocksDB library. Therefore, we are removing it in the upcoming 7.0 release. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9443 Test Plan: CircleCI Reviewed By: ajkr Differential Revision: D33788508 Pulled By: akankshamahajan15 fbshipit-source-id: 324ca6f12bfd019e9bd5e1b0cdac39be5c3cec7d | 09 February 2022, 03:31:28 UTC |
2ee25e8 | Levi Tamasi | 09 February 2022, 01:50:44 UTC | Remove cat_ignore_eagain (#9531) Summary: ... since it was only necessary to work around a bug on certain Ubuntu 16.04 images (and we now use 20.04 across the board). Pull Request resolved: https://github.com/facebook/rocksdb/pull/9531 Test Plan: Watch CI. Reviewed By: ajkr Differential Revision: D34089424 Pulled By: ltamasi fbshipit-source-id: f15f86332c119099f61b9bdc74604657fc5d964e | 09 February 2022, 01:51:59 UTC |
68a9c18 | Peter Dillinger | 08 February 2022, 21:54:29 UTC | FilterPolicy API changes for 7.0 (#9501) Summary: * Inefficient block-based filter is no longer customizable in the public API, though (for now) can still be enabled. * Removed deprecated FilterPolicy::CreateFilter() and FilterPolicy::KeyMayMatch() * Removed `rocksdb_filterpolicy_create()` from C API * Change meaning of nullptr return from GetBuilderWithContext() from "use block-based filter" to "generate no filter in this case." This is a cleaner solution to the proposal in https://github.com/facebook/rocksdb/issues/8250. * Also, when user specifies bits_per_key < 0.5, we now round this down to "no filter" because we expect a filter with >= 80% FP rate is unlikely to be worth the CPU cost of accessing it (esp with cache_index_and_filter_blocks=1 or partition_filters=1). * bits_per_key >= 0.5 and < 1.0 is still rounded up to 1.0 (for 62% FP rate) * This also gives us some support for configuring filters from OPTIONS file as currently saved: `filter_policy=rocksdb.BuiltinBloomFilter`. Opening from such an options file will enable reading filters (an improvement) but not writing new ones. (See Customizable follow-up below.) * Also removed deprecated functions * FilterBitsBuilder::CalculateNumEntry() * FilterPolicy::GetFilterBitsBuilder() * NewExperimentalRibbonFilterPolicy() * Remove default implementations of * FilterBitsBuilder::EstimateEntriesAdded() * FilterBitsBuilder::ApproximateNumEntries() * FilterPolicy::GetBuilderWithContext() * Remove support for "filter_policy=experimental_ribbon" configuration string. * Allow "filter_policy=bloomfilter:n" without bool to discourage use of block-based filter. Some pieces for https://github.com/facebook/rocksdb/issues/9389 Likely follow-up (later PRs): * Refactoring toward FilterPolicy Customizable, so that we can generate filters with same configuration as before when configuring from options file. * Remove support for user enabling block-based filter (ignore `bool use_block_based_builder`) * Some months after this change, we could even remove read support for block-based filter, because it is not critical to DB data preservation. * Make FilterBitsBuilder::FinishV2 to avoid `using FilterBitsBuilder::Finish` mess and add support for specifying a MemoryAllocator (for cache warming) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9501 Test Plan: A number of obsolete tests deleted and new tests or test cases added or updated. Reviewed By: hx235 Differential Revision: D34008011 Pulled By: pdillinger fbshipit-source-id: a39a720457c354e00d5b59166b686f7f59e392aa | 08 February 2022, 21:56:46 UTC |
ddce0c3 | Akanksha Mahajan | 08 February 2022, 21:48:55 UTC | Add releases till 6.29.fb to compatibility check (#9529) Summary: Add releases till 6.29.fb to compatibility check for forward and backward compatibility Pull Request resolved: https://github.com/facebook/rocksdb/pull/9529 Test Plan: run locally Reviewed By: hx235 Differential Revision: D34086063 Pulled By: akankshamahajan15 fbshipit-source-id: 4ccff513c99cf2d0e41da0b76ab27ffcfdffe7df | 08 February 2022, 21:50:18 UTC |
036bbab | satyajanga | 08 February 2022, 20:14:25 UTC | Use the comparator from the sst file table properties in sst_dump_tool (#9491) Summary: We introduced a new Comparator for timestamp in user keys. In the sst_dump_tool by default we use BytewiseComparator to read sst files. This change allows us to read comparator_name from table properties in meta data block and use it to read. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9491 Test Plan: added unittests for new functionality. make check ![image](https://user-images.githubusercontent.com/4923556/152915444-28b88a1f-7b4e-47d0-815f-7011552bd9a2.png) ![image](https://user-images.githubusercontent.com/4923556/152916196-bea3d2a1-a3d5-4362-b911-036131b83e8d.png) Reviewed By: riversand963 Differential Revision: D33993614 Pulled By: satyajanga fbshipit-source-id: 4b5cf938e6d2cb3931d763bef5baccc900b8c536 | 08 February 2022, 20:15:35 UTC |
d7c868b | Peter Dillinger | 08 February 2022, 03:34:39 UTC | Work around snappy linker issue with newer compilers (#9517) Summary: After https://github.com/facebook/rocksdb/issues/9481, we are using newer default compiler for build-format-compatible CircleCI nightly job, which fails on building 2.2.fb.branch branch because it tries to use a pre-compiled libsnappy.a that is checked into the repo (!). This works around that by setting SNAPPY_LDFLAGS=-lsnappy, which is only understood by such old versions. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9517 Test Plan: Run check_format_compatible.sh on Ubuntu 20 AWS machine, watch nightly run Reviewed By: hx235 Differential Revision: D34055561 Pulled By: pdillinger fbshipit-source-id: 45f9d428dd082f026773bfa8d9dd4dad66fc9378 | 08 February 2022, 03:36:01 UTC |
5cb137a | Peter Dillinger | 08 February 2022, 02:20:51 UTC | Work around some new clang-analyze failures (#9515) Summary: ... seen only in internal clang-analyze runs after https://github.com/facebook/rocksdb/issues/9481 * Mostly, this works around falsely reported leaks by using std::unique_ptr in some places where clang-analyze was getting confused. (I didn't see any changes in C++17 that could make our Status implementation leak memory.) * Also fixed SetBGError returning address of a stack variable. * Also fixed another false null deref report by adding an assert. Also, use SKIP_LINK=1 to speed up `make analyze` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9515 Test Plan: Was able to reproduce the reported errors locally and verify they're fixed (except SetBGError). Otherwise, existing tests Reviewed By: hx235 Differential Revision: D34054630 Pulled By: pdillinger fbshipit-source-id: 38600ef3da75ddca307dff96b7a1a523c2885c2e | 08 February 2022, 02:24:36 UTC |
bbe4763 | Akanksha Mahajan | 07 February 2022, 20:00:54 UTC | Remove Deprecated overloads of DB::GetApproximateSizes (#9458) Summary: In RocksDB few overloads of DB::GetApproximateSizes are marked as DEPRECATED_FUNC, and we are removing it in the upcoming 7.0 release. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9458 Test Plan: CircleCI Reviewed By: riversand963 Differential Revision: D34043791 Pulled By: akankshamahajan15 fbshipit-source-id: 815c0ad283a6627c4b241479c7d40ce03a758493 | 07 February 2022, 20:02:57 UTC |
bd08374 | Peter Dillinger | 07 February 2022, 18:38:50 UTC | Add GetTemperature on existing files (#9498) Summary: For tiered storage Pull Request resolved: https://github.com/facebook/rocksdb/pull/9498 Test Plan: Just API placeholders for now Reviewed By: jay-zhuang Differential Revision: D33993094 Pulled By: pdillinger fbshipit-source-id: 3cf19a450c7232e05306e94018559b26e9fd35db | 07 February 2022, 18:40:31 UTC |
98942a2 | Levi Tamasi | 07 February 2022, 18:24:25 UTC | Update HISTORY for PR 9504 (#9513) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9513 Reviewed By: riversand963 Differential Revision: D34046181 Pulled By: ltamasi fbshipit-source-id: a5d8d3bf84e5c13bdc6cbd5ba1b4216bad9adfc5 | 07 February 2022, 18:29:59 UTC |
c234ac9 | Hui Xiao | 07 February 2022, 17:56:30 UTC | Clarify Google benchmark < 1.6.0 in INSTALL.md (#9505) Summary: **Context:** Google benchmark [v1.6.0](https://github.com/google/benchmark/releases/tag/v1.6.0) introduced a breaking change "`introduce accessorrs for public data members (https://github.com/google/benchmark/pull/1208)`" that will fail RocksDB build of microbench developed based on previous code. For example, https://github.com/facebook/rocksdb/issues/9489. **Summary:** Clarify the maximum version of Google benchmark needed. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9505 Test Plan: CI Reviewed By: ajkr Differential Revision: D34023447 Pulled By: hx235 fbshipit-source-id: 0128ffc31485f2d752ab2116771f6ae53231fcd7 | 07 February 2022, 18:00:46 UTC |
c0d2d26 | Peter Dillinger | 07 February 2022, 17:38:27 UTC | Temporary disable Travis s390x Makefile build (#9512) Summary: Due to some unexplained errors with gcc-7 ``` Assembler messages: Error: invalid switch -march=z14 Error: unrecognized option -march=z14 ``` Relevant to https://github.com/facebook/rocksdb/issues/9388 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9512 Test Plan: CI Reviewed By: hx235 Differential Revision: D34044989 Pulled By: pdillinger fbshipit-source-id: a5406e8f30b2b187949f75c8cee4e2a0eb976670 | 07 February 2022, 17:47:00 UTC |
0cc0543 | Levi Tamasi | 07 February 2022, 17:14:40 UTC | Mitigate the overhead of building the hash of file locations (#9504) Summary: The patch builds on the refactoring done in https://github.com/facebook/rocksdb/issues/9494 and improves the performance of building the hash of file locations in `VersionStorageInfo` in two ways. First, the hash building is moved from `AddFile` (which is called under the DB mutex) to a separate post-processing step done as part of `PrepareForVersionAppend` (during which the mutex is *not* held). Second, the space necessary for the hash is preallocated to prevent costly reallocation/rehashing operations. These changes mitigate the overhead of the file location hash, which can be significant with certain workloads where the baseline CPU usage is low (see https://github.com/facebook/rocksdb/issues/9351, which is a workload where keys are sorted, WAL is turned off, the vector memtable implementation is used, and there are lots of small SST files). Fixes https://github.com/facebook/rocksdb/issues/9351 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9504 Test Plan: `make check` ``` numactl --interleave=all ./db_bench --benchmarks=fillseq --allow_concurrent_memtable_write=false --level0_file_num_compaction_trigger=4 --level0_slowdown_writes_trigger=20 --level0_stop_writes_trigger=30 --max_background_jobs=8 --max_write_buffer_number=8 --db=/data/ltamasi-dbbench --wal_dir=/data/ltamasi-dbbench --num=800000000 --num_levels=8 --key_size=20 --value_size=400 --block_size=8192 --cache_size=51539607552 --cache_numshardbits=6 --compression_max_dict_bytes=0 --compression_ratio=0.5 --compression_type=lz4 --bytes_per_sync=8388608 --cache_index_and_filter_blocks=1 --cache_high_pri_pool_ratio=0.5 --benchmark_write_rate_limit=0 --write_buffer_size=16777216 --target_file_size_base=16777216 --max_bytes_for_level_base=67108864 --verify_checksum=1 --delete_obsolete_files_period_micros=62914560 --max_bytes_for_level_multiplier=8 --statistics=0 --stats_per_interval=1 --stats_interval_seconds=20 --histogram=1 --bloom_bits=10 --open_files=-1 --subcompactions=1 --compaction_style=0 --level_compaction_dynamic_level_bytes=true --pin_l0_filter_and_index_blocks_in_cache=1 --soft_pending_compaction_bytes_limit=167503724544 --hard_pending_compaction_bytes_limit=335007449088 --min_level_to_compress=0 --use_existing_db=0 --sync=0 --threads=1 --memtablerep=vector --disable_wal=1 --seed=<some_seed> ``` Final statistics before this patch: ``` Cumulative writes: 0 writes, 697M keys, 0 commit groups, 0.0 writes per commit group, ingest: 283.25 GB, 241.08 MB/s Interval writes: 0 writes, 1264K keys, 0 commit groups, 0.0 writes per commit group, ingest: 525.69 MB, 176.67 MB/s ``` With the patch: ``` Cumulative writes: 0 writes, 759M keys, 0 commit groups, 0.0 writes per commit group, ingest: 308.57 GB, 262.63 MB/s Interval writes: 0 writes, 1555K keys, 0 commit groups, 0.0 writes per commit group, ingest: 646.61 MB, 215.11 MB/s ``` Reviewed By: riversand963 Differential Revision: D34014734 Pulled By: ltamasi fbshipit-source-id: acb2703677451d5ccaa7e9d950844b33d240695b | 07 February 2022, 17:17:14 UTC |
b69f436 | Jay Zhuang | 07 February 2022, 16:31:27 UTC | Fix flaky test EnvPosixTestWithParam.RunMany (#9502) Summary: Thread-pool pops a thread function and then run the function, which may cause thread-pool is empty but the last function is still running. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9502 Test Plan: `gtest-parallel ./env_test --gtest_filter=DefaultEnvWithoutDirectIO/EnvPosixTestWithParam.RunMany/0 -r 10000 -w 1000` Reviewed By: ajkr Differential Revision: D34011184 Pulled By: jay-zhuang fbshipit-source-id: 8c38bef155205bef96fd1c988dcc643a6b2ac270 | 07 February 2022, 17:07:59 UTC |
1f96bc6 | Levi Tamasi | 07 February 2022, 01:35:50 UTC | Upgrade to Ubuntu 20.04 in our CircleCI config (#9486) Summary: Ubuntu 16.04 has reached EOL. The patch upgrades the image for all of our CircleCI jobs to the latest, namely `ubuntu-2004:202111-02`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9486 Test Plan: Watch the CI build results. Reviewed By: ajkr Differential Revision: D34029339 Pulled By: ltamasi fbshipit-source-id: a266b631c04d227fe29b8156be61229605eb9dd7 | 07 February 2022, 01:37:12 UTC |
fd3e0f4 | Peter Dillinger | 05 February 2022, 01:12:03 UTC | Require C++17 (#9481) Summary: Drop support for some old compilers by requiring C++17 standard (or higher). See https://github.com/facebook/rocksdb/issues/9388 First modification based on this is to remove some conditional compilation in slice.h (also better for ODR) Also in this PR: * Fix some Makefile formatting that seems to affect ASSERT_STATUS_CHECKED config in some cases * Add c_test to NON_PARALLEL_TEST in Makefile * Fix a clang-analyze reported "potential leak" in lru_cache_test * Better "compatibility" definition of DEFINE_uint32 for old versions of gflags * Fix a linking problem with shared libraries in Makefile (`./random_test: error while loading shared libraries: librocksdb.so.6.29: cannot open shared object file: No such file or directory`) * Always set ROCKSDB_SUPPORT_THREAD_LOCAL and use thread_local (from C++11) * TODO in later PR: clean up that obsolete flag * Fix a cosmetic typo in c.h (https://github.com/facebook/rocksdb/issues/9488) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9481 Test Plan: CircleCI config substantially updated. * Upgrade to latest Ubuntu images for each release * Generally prefer Ubuntu 20, but keep a couple Ubuntu 16 builds with oldest supported compilers, to ensure compatibility * Remove .circleci/cat_ignore_eagain except for Ubuntu 16 builds, because this is to work around a kernel bug that should not affect anything but Ubuntu 16. * Remove designated gcc-9 build, because the default linux build now uses GCC 9 from Ubuntu 20. * Add some `apt-key add` to fix some apt "couldn't be verified" errors * Generally drop SKIP_LINK=1; work-around no longer needed * Generally `add-apt-repository` before `apt-get update` as manual testing indicated the reverse might not work. Travis: * Use gcc-7 by default (remove specific gcc-7 and gcc-4.8 builds) * TODO in later PR: fix s390x "Assembler messages: Error: invalid switch -march=z14" failure AppVeyor: * Completely dropped because we are dropping VS2015 support and CircleCI covers VS >= 2017 Also local testing with old gflags (out of necessity when using ROCKSDB_NO_FBCODE=1). Reviewed By: mrambacher Differential Revision: D33946377 Pulled By: pdillinger fbshipit-source-id: ae077c823905b45370a26c0103ada119459da6c1 | 05 February 2022, 01:13:10 UTC |
42c8afd | Radek Hubner | 05 February 2022, 00:00:51 UTC | WriteOptions - add missing java API. (#9295) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9295 Reviewed By: riversand963 Differential Revision: D33672440 Pulled By: ajkr fbshipit-source-id: 85f73a9297888b00255b636e7826b37186aba45c | 05 February 2022, 00:08:06 UTC |
2c3a780 | Si Ke | 05 February 2022, 00:00:39 UTC | Fixed all RocksJava test failures in Centos and Alpine (#9395) Summary: Fixed all RocksJava test failures in Centos and Alpine 32 bit and 64 bit OSes Pull Request resolved: https://github.com/facebook/rocksdb/pull/9395 Reviewed By: mrambacher Differential Revision: D33771987 Pulled By: ajkr fbshipit-source-id: fed91033b8df08f191ad65e1fb745a9264bbfa70 | 05 February 2022, 00:03:56 UTC |
83ff350 | Jermy Li | 05 February 2022, 00:00:19 UTC | jni: expose memtable_whole_key_filtering option (#9394) Summary: refer to: https://github.com/facebook/rocksdb/wiki/Prefix-Seek#configure-prefix-bloom-filter Pull Request resolved: https://github.com/facebook/rocksdb/pull/9394 Reviewed By: mrambacher Differential Revision: D33671533 Pulled By: ajkr fbshipit-source-id: d90db1712efdd5dd65020329867381d6b3cf2626 | 05 February 2022, 00:01:16 UTC |
afc280f | Peter Dillinger | 04 February 2022, 22:15:06 UTC | Enhance new cache key testing & comments (#9329) Summary: Follow-up to https://github.com/facebook/rocksdb/issues/9126 Added new unit tests to validate some of the claims of guaranteed uniqueness within certain large bounds. Also cleaned up the cache_bench -stress-cache-key tool with better comments and description. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9329 Test Plan: no changes to production code Reviewed By: mrambacher Differential Revision: D33269328 Pulled By: pdillinger fbshipit-source-id: 3a2b684a6b2b15f79dc872e563e3d16563be26de | 04 February 2022, 22:15:58 UTC |
42e0751 | Levi Tamasi | 04 February 2022, 16:18:18 UTC | Clean up VersionStorageInfo a bit (#9494) Summary: The patch does some cleanup in and around `VersionStorageInfo`: * Renames the method `PrepareApply` to `PrepareAppend` in `Version` to make it clear that it is to be called before appending the `Version` to `VersionSet` (via `AppendVersion`), not before applying any `VersionEdit`s. * Introduces a helper method `VersionStorageInfo::PrepareForVersionAppend` (called by `Version::PrepareAppend`) that encapsulates the population of the various derived data structures in `VersionStorageInfo`, and turns the methods computing the derived structures (`UpdateNumNonEmptyLevels`, `CalculateBaseBytes` etc.) into private helpers. * Changes `Version::PrepareAppend` so it only calls `UpdateAccumulatedStats` if the `update_stats` flag is set. (Earlier, this was checked by the callee.) Related to this, it also moves the call to `ComputeCompensatedSizes` to `VersionStorageInfo::PrepareForVersionAppend`. * Updates and cleans up `version_builder_test`, `version_set_test`, and `compaction_picker_test` so `PrepareForVersionAppend` is called anytime a new `VersionStorageInfo` is set up or saved. This cleanup also involves splitting `VersionStorageInfoTest.MaxBytesForLevelDynamic` into multiple smaller test cases. * Fixes up a bunch of comments that were outdated or just plain incorrect. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9494 Test Plan: Ran `make check` and the crash test script for a while. Reviewed By: riversand963 Differential Revision: D33971666 Pulled By: ltamasi fbshipit-source-id: fda52faac7783041126e4f8dec0fe01bdcadf65a | 04 February 2022, 16:19:20 UTC |
bec9ab4 | Baptiste Lemaire | 04 February 2022, 13:31:07 UTC | Remove deprecated option DBOptions::max_mem_compaction_level (#9446) Summary: In RocksDB, this option was already marked as "NOT SUPPORTED" for a long time, and setting this option does not have any effect on the behavior of RocksDB library. Therefore, we are removing it in the preparations of the upcoming 7.0 release. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9446 Reviewed By: ajkr Differential Revision: D33793048 Pulled By: bjlemaire fbshipit-source-id: 73316efdb194e90225005246673dae99e65577ae | 04 February 2022, 13:32:28 UTC |
8b62abc | Yanqin Jin | 04 February 2022, 00:17:30 UTC | Disable backup/restore for ts-stress test (#9497) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9497 Reviewed By: ajkr Differential Revision: D33990256 Pulled By: riversand963 fbshipit-source-id: 268ce16b037e23e42b14fa0fcb45535582e1a0d6 | 04 February 2022, 00:18:34 UTC |
629e3e1 | Yanqin Jin | 03 February 2022, 23:14:17 UTC | Fix spelling in public API (#9490) Summary: I feel it would be nice if we can fix this spelling error. In `SizeApproximationOptions`, the `include_memtabtles` should be `include_memtables`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9490 Test Plan: make check Reviewed By: hx235 Differential Revision: D33949862 Pulled By: riversand963 fbshipit-source-id: b2be67501b65d4aabb6b8df1bf25eb8d54cc1466 | 03 February 2022, 23:15:23 UTC |
aae3093 | mrambacher | 03 February 2022, 23:00:03 UTC | Introduce a CountedFileSystem for counting file operations (#9283) Summary: Added a CountedFileSystem that tracks a number of file operations (opens, closes, deletes, renames, flushes, syncs, fsyncs, reads, writes). This class was based on the ReportFileOpEnv from db_bench. This is a stepping stone PR to be able to change the SpecialEnv into a SpecialFileSystem, where several of the file varieties wish to do operation counting. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9283 Reviewed By: pdillinger Differential Revision: D33062004 Pulled By: mrambacher fbshipit-source-id: d0d297a7fb9c48c06cbf685e5fa755c27193b6f5 | 03 February 2022, 23:01:23 UTC |
5104c10 | Hui Xiao | 03 February 2022, 04:38:41 UTC | Update TARGETS and related scripts Reviewed By: ajkr Differential Revision: D33962843 fbshipit-source-id: 9c4e4c46403e50549d341237bae0f495b26c5613 | 03 February 2022, 04:39:59 UTC |
d9ddb53 | anand76 | 02 February 2022, 21:29:07 UTC | Remove default implementation of Name() from FileSystemWrapper (#9474) Summary: Remove default implementation of Name(), which is an abstract method inherited from Customizable, from FileSystemWrapper. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9474 Reviewed By: pdillinger Differential Revision: D33896455 Pulled By: anand1976 fbshipit-source-id: bc3df3bc0cec580cf63c60a52c344f23ca651102 | 02 February 2022, 21:31:04 UTC |