mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 22:41:48 +00:00
931 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
anand76
|
ee258619be |
Fix missing cases of corruption retries (#13122)
Summary: This PR fixes a few cases where RocksDB was not retrying checksum failure/corruption of file reads with the `verify_and_reconstruct_read` IO option. After fixing these cases, we can almost always successfully open the DB and execute reads even if we see transient corruptions, provided the `FileSystem` supports the `verify_and_reconstruct_read` option. The specific cases fixed in this PR are - 1. CURRENT file 2. IDENTITY file 3. OPTIONS file 4. SST footer Pull Request resolved: https://github.com/facebook/rocksdb/pull/13122 Test Plan: Unit test in `db_io_failure_test.cc` that injects corruption at various stages of DB open and reads Reviewed By: jaykorean Differential Revision: D65617982 Pulled By: anand1976 fbshipit-source-id: 4324b88cc7eee5501ab5df20ef7a95bb12ed3ea7 |
||
|
Peter Dillinger
|
485ee4f45c |
Fix and test for leaks of open SST files (#13117)
Summary: Follow-up to https://github.com/facebook/rocksdb/issues/13106 which revealed that some SST file readers (in addition to blob files) were being essentially leaked in TableCache (until DB::Close() time). Patched sources of leaks: * Flush that is not committed (builder.cc) * Various obsolete SST files picked up by directory scan but not caught by SubcompactionState::Cleanup() cleaning up from some failed compactions. Dozens of unit tests fail without the "backstop" TableCache::Evict() call in PurgeObsoleteFiles(). We also needed to adjust the check for leaks as follows: * Ok if DB::Open never finished (see comment) * Ok if deletions are disabled (see comment) * Allow "quarantined" files to be in table_cache because (presumably) they might become live again. * Get live files from all live Versions. Suggested follow-up: * Potentially delete more obsolete files sooner with a FIXME in db_impl_files.cc. This could potentially be high value because it seems to gate deletion of any/all newer obsolete files on all older compactions finishing. * Try to catch obsolete files in more places using the VersionSet::obsolete_files_ pipeline rather than relying on them being picked up with directory scan, or deleting them outside of normal mechanisms. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13117 Test Plan: updated check used in most all unit tests in ASAN build Reviewed By: hx235 Differential Revision: D65502988 Pulled By: pdillinger fbshipit-source-id: aa0795a8a09d9ec578d25183fe43e2a35849209c |
||
|
Andrew Chang
|
a7ecbfd590 |
Remove early return when scanning files for temperature change compaction (#13112)
Summary: This is a small follow-up to https://github.com/facebook/rocksdb/pull/13083. When we check the `newest_key_time` of files for temperature change compaction, we currently return early if we ever find a file with an unknown `est_newest_key_time`. However, it is possible for a younger file to have a populated value for `newest_key_time`, since this is a new table property. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13112 Test Plan: The existing unit tests are sufficient. Reviewed By: cbi42 Differential Revision: D65451797 Pulled By: archang19 fbshipit-source-id: 28e67c2d35a6315f912471f2848de87dd7088d99 |
||
|
Peter Dillinger
|
e7ffca9493 |
Refactoring toward making preserve/preclude options mutable (#13114)
Summary: Move them to MutableCFOptions and perform appropriate refactorings to make that work. I didn't want to mix up refactoring with interesting functional changes. Potentially non-trivial bits here: * During DB Open or RegisterRecordSeqnoTimeWorker we use `GetLatestMutableCFOptions()` because either (a) there might not be a current version, or (b) we are in the process of applying the desired next options. * Upgrade some test infrastructure to allow some options in MutableCFOptions to be mutable (should be a temporary state) * Fix a warning that showed up about uninitialized `paranoid_memory_checks` Pull Request resolved: https://github.com/facebook/rocksdb/pull/13114 Test Plan: existing tests, manually check options are still not settable with SetOptions Reviewed By: jowlyzhang Differential Revision: D65429031 Pulled By: pdillinger fbshipit-source-id: 6e0906d08dd8ddf62731cefffe9b8d94149942b9 |
||
|
Andrew Ryan Chang
|
af2a36d2c7 |
Record newest_key_time as a table property (#13083)
Summary: This PR does two things: 1. Adds a new table property `newest_key_time` 2. Uses this property to improve TTL and temperature change compaction. ### Context The current `creation_time` table property should really be named `oldest_ancestor_time`. For flush output files, this is the oldest key time in the file. For compaction output files, this is the minimum among all oldest key times in the input files. The problem with using the oldest ancestor time for TTL compaction is that we may end up dropping files earlier than we should. What we really want is the newest (i.e. "youngest") key time. Right now we take a roundabout way to estimate this value -- we take the value of the _oldest_ key time for the _next_ (newer) SST file. This is also why the current code has checks for `index >= 1`. Our new property `newest_key_time` is set to the file creation time during flushes, and the max over all input files for compactions. There were some additional smaller changes that I had to make for testing purposes: - Refactoring the mock table reader to support specifying my own table properties - Refactoring out a test utility method `GetLevelFileMetadatas` that would otherwise be copy/pasted in 3 places Credit to cbi42 for the problem explanation and proposed solution ### Testing - Added a dedicated unit test to my `newest_key_time` logic in isolation (i.e. are we populating the property on flush and compaction) - Updated the existing unit tests (for TTL/temperate change compaction), which were comprehensive enough to break when I first made my code changes. I removed the test setup code which set the file metadata `oldest_ancestor_time`, so we know we are actually only using the new table property instead. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13083 Reviewed By: cbi42 Differential Revision: D65298604 Pulled By: archang19 fbshipit-source-id: 898ef91b692ab33f5129a2a16b64ecadd4c32432 |
||
|
Yu Zhang
|
9c94559de7 |
Optimize compaction for standalone range deletion files (#13078)
Summary: This PR adds some optimization for compacting standalone range deletion files. A standalone range deletion file is one with just a single range deletion. Currently, such a file is used in bulk loading to achieve something like atomically delete old version of all data with one big range deletion and adding new version of data. These are the changes included in the PR: 1) When a standalone range deletion file is ingested via bulk loading, it's marked for compaction. 2) When picking input files during compaction picking, we attempt to only pick a standalone range deletion file when oldest snapshot is at or above the file's seqno. To do this, `PickCompaction` API is updated to take existing snapshots as an input. This is only done for the universal compaction + UDT disabled combination, we save querying for existing snapshots and not pass it for all other cases. 3) At `Compaction` construction time, the input files will be filtered to examine if any of them can be skipped for compaction iterator. For example, if all the data of the file is deleted by a standalone range tombstone, and the oldest snapshot is at or above such range tombstone, this file will be filtered out. 4) Every time a snapshot is released, we examine if any column family has standalone range deletion files that becomes eligible to be scheduled for compaction. And schedule one for it. Potential future improvements: - Add some dedicated statistics for the filtered files. - Extend this input filtering to L0 files' compactions cases when a newer L0 file could shadow an older L0 file Pull Request resolved: https://github.com/facebook/rocksdb/pull/13078 Test Plan: Added unit tests and stress tested a few rounds Reviewed By: cbi42 Differential Revision: D64879415 Pulled By: jowlyzhang fbshipit-source-id: 02b8683fddbe11f093bcaa0a38406deb39f44d9e |
||
|
Peter Dillinger
|
ac24f152a1 |
Refactor table_factory into MutableCFOptions (#13077)
Summary: This is setting up for a fix to a data race in SetOptions on BlockBasedTableOptions (BBTO), https://github.com/facebook/rocksdb/issues/10079 The race will be fixed by replacing `table_factory` with a modified copy whenever we want to modify a BBTO field. An argument could be made that this change creates more entaglement between features (e.g. BlobSource <-> MutableCFOptions), rather than (conceptually) minimizing the dependencies of each feature, but * Most of these things already depended on ImmutableOptions * Historically there has been a lot of plumbing (and possible small CPU overhead) involved in adding features that need to reach a lot of places, like `block_protection_bytes_per_key`. Keeping those wrapped up in options simplifies that. * SuperVersion management generally takes care of lifetime management of MutableCFOptions, so is not that difficult. (Crash test agrees so far.) There are some FIXME places where it is known to be unsafe to replace `block_cache` unless/until we handle shared_ptr tracking properly. HOWEVER, replacing `block_cache` is generally dubious, at least while existing users of the old block cache (e.g. table readers) can continue indefinitely. The change to cf_options.cc is essentially just moving code (not changing). I'm not concerned about the performance of copying another shared_ptr with MutableCFOptions, but I left a note about considering an improvement if more shared_ptr are added to it. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13077 Test Plan: existing tests, crash test. Unit test DBOptionsTest.GetLatestCFOptions updated with some temporary logic. MemoryTest required some refactoring (simplification) for the change. Reviewed By: cbi42 Differential Revision: D64546903 Pulled By: pdillinger fbshipit-source-id: 69ae97ce5cf4c01b58edc4c5d4687eb1e5bf5855 |
||
|
Yu Zhang
|
8181dfb1c4 |
Fix a bug for surfacing write unix time (#13057)
Summary: The write unix time from non L0 files are not surfaced properly because the level's wrapper iterator doesn't have a `write_unix_time` implementation that delegates to the corresponding file. The unit test didn't catch this because it incorrectly destroy the old db and reopen to check write time, instead of just reopen and check. This fix also include a change to support ldb's scan command to get write time for easier debugging. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13057 Test Plan: Updated unit tests Reviewed By: pdillinger Differential Revision: D64015107 Pulled By: jowlyzhang fbshipit-source-id: 244474f78a034f80c9235eea2aa8a0f4e54dff59 |
||
|
Yu Zhang
|
263fa15b44 |
Handle a possible overflow (#13046)
Summary: Stress test detects this variable could potentially overflow, so added some runtime handling to avoid it. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13046 Test Plan: Existing tests Reviewed By: hx235 Differential Revision: D63911396 Pulled By: jowlyzhang fbshipit-source-id: 7c9abcd74ac9937b211c0ea4bb683677390837c5 |
||
|
Levi Tamasi
|
54ace7f340 |
Change the semantics of blob_garbage_collection_force_threshold to provide better control over space amp (#13022)
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/13022 Currently, `blob_garbage_collection_force_threshold` applies to the oldest batch of blob files, which is typically only a small subset of the blob files currently eligible for garbage collection. This can result in a form of head-of-line blocking: no GC-triggered compactions will be scheduled if the oldest batch does not currently exceed the threshold, even if a lot of higher-numbered blob files do. This can in turn lead to high space amplification that exceeds the soft bound implicit in the force threshold (e.g. 50% would suggest a space amp of <2 and 75% would imply a space amp of <4). The patch changes the semantics of this configuration threshold to apply to the entire set of blob files that are eligible for garbage collection based on `blob_garbage_collection_age_cutoff`. This provides more intuitive semantics for the option and can provide a better write amp/space amp trade-off. (Note that GC-triggered compactions still pick the same SST files as before, so triggered GC still targets the oldest the blob files.) Reviewed By: jowlyzhang Differential Revision: D62977860 fbshipit-source-id: a999f31fe9cdda313de513f0e7a6fc707424d4a3 |
||
|
Peter Dillinger
|
98c33cb8e3 |
Steps toward making IDENTITY file obsolete (#13019)
Summary: * Set write_dbid_to_manifest=true by default * Add new option write_identity_file (default true) that allows us to opt-in to future behavior without identity file * Refactor related DB open code to minimize code duplication _Recommend hiding whitespace changes for review_ Intended follow-up: add support to ldb for reading and even replacing the DB identity in the manifest. Could be a variant of `update_manifest` command or based on it. Pull Request resolved: https://github.com/facebook/rocksdb/pull/13019 Test Plan: unit tests and stress test updated for new functionality Reviewed By: anand1976 Differential Revision: D62898229 Pulled By: pdillinger fbshipit-source-id: c08b25cf790610b034e51a9de0dc78b921abbcf0 |
||
|
Nicholas Ormrod
|
0e04ef1a96 |
Deshim coro in fbcode/internal_repo_rocksdb
Summary: The following rules were deshimmed: ``` //folly/experimental/coro:accumulate -> //folly/coro:accumulate //folly/experimental/coro:async_generator -> //folly/coro:async_generator //folly/experimental/coro:async_pipe -> //folly/coro:async_pipe //folly/experimental/coro:async_scope -> //folly/coro:async_scope //folly/experimental/coro:async_stack -> //folly/coro:async_stack //folly/experimental/coro:baton -> //folly/coro:baton //folly/experimental/coro:blocking_wait -> //folly/coro:blocking_wait //folly/experimental/coro:collect -> //folly/coro:collect //folly/experimental/coro:concat -> //folly/coro:concat //folly/experimental/coro:coroutine -> //folly/coro:coroutine //folly/experimental/coro:current_executor -> //folly/coro:current_executor //folly/experimental/coro:detach_on_cancel -> //folly/coro:detach_on_cancel //folly/experimental/coro:detail_barrier -> //folly/coro:detail_barrier //folly/experimental/coro:detail_barrier_task -> //folly/coro:detail_barrier_task //folly/experimental/coro:detail_current_async_frame -> //folly/coro:detail_current_async_frame //folly/experimental/coro:detail_helpers -> //folly/coro:detail_helpers //folly/experimental/coro:detail_malloc -> //folly/coro:detail_malloc //folly/experimental/coro:detail_manual_lifetime -> //folly/coro:detail_manual_lifetime //folly/experimental/coro:detail_traits -> //folly/coro:detail_traits //folly/experimental/coro:filter -> //folly/coro:filter //folly/experimental/coro:future_util -> //folly/coro:future_util //folly/experimental/coro:generator -> //folly/coro:generator //folly/experimental/coro:gmock_helpers -> //folly/coro:gmock_helpers //folly/experimental/coro:gtest_helpers -> //folly/coro:gtest_helpers //folly/experimental/coro:inline_task -> //folly/coro:inline_task //folly/experimental/coro:invoke -> //folly/coro:invoke //folly/experimental/coro:merge -> //folly/coro:merge //folly/experimental/coro:mutex -> //folly/coro:mutex //folly/experimental/coro:promise -> //folly/coro:promise //folly/experimental/coro:result -> //folly/coro:result //folly/experimental/coro:retry -> //folly/coro:retry //folly/experimental/coro:rust_adaptors -> //folly/coro:rust_adaptors //folly/experimental/coro:scope_exit -> //folly/coro:scope_exit //folly/experimental/coro:shared_lock -> //folly/coro:shared_lock //folly/experimental/coro:shared_mutex -> //folly/coro:shared_mutex //folly/experimental/coro:sleep -> //folly/coro:sleep //folly/experimental/coro:small_unbounded_queue -> //folly/coro:small_unbounded_queue //folly/experimental/coro:task -> //folly/coro:task //folly/experimental/coro:timed_wait -> //folly/coro:timed_wait //folly/experimental/coro:timeout -> //folly/coro:timeout //folly/experimental/coro:traits -> //folly/coro:traits //folly/experimental/coro:transform -> //folly/coro:transform //folly/experimental/coro:unbounded_queue -> //folly/coro:unbounded_queue //folly/experimental/coro:via_if_async -> //folly/coro:via_if_async //folly/experimental/coro:with_async_stack -> //folly/coro:with_async_stack //folly/experimental/coro:with_cancellation -> //folly/coro:with_cancellation //folly/experimental/coro:bounded_queue -> //folly/coro:bounded_queue //folly/experimental/coro:shared_promise -> //folly/coro:shared_promise //folly/experimental/coro:cleanup -> //folly/coro:cleanup //folly/experimental/coro:auto_cleanup_fwd -> //folly/coro:auto_cleanup_fwd //folly/experimental/coro:auto_cleanup -> //folly/coro:auto_cleanup ``` The following headers were deshimmed: ``` folly/experimental/coro/Accumulate.h -> folly/coro/Accumulate.h folly/experimental/coro/Accumulate-inl.h -> folly/coro/Accumulate-inl.h folly/experimental/coro/AsyncGenerator.h -> folly/coro/AsyncGenerator.h folly/experimental/coro/AsyncPipe.h -> folly/coro/AsyncPipe.h folly/experimental/coro/AsyncScope.h -> folly/coro/AsyncScope.h folly/experimental/coro/AsyncStack.h -> folly/coro/AsyncStack.h folly/experimental/coro/Baton.h -> folly/coro/Baton.h folly/experimental/coro/BlockingWait.h -> folly/coro/BlockingWait.h folly/experimental/coro/Collect.h -> folly/coro/Collect.h folly/experimental/coro/Collect-inl.h -> folly/coro/Collect-inl.h folly/experimental/coro/Concat.h -> folly/coro/Concat.h folly/experimental/coro/Concat-inl.h -> folly/coro/Concat-inl.h folly/experimental/coro/Coroutine.h -> folly/coro/Coroutine.h folly/experimental/coro/CurrentExecutor.h -> folly/coro/CurrentExecutor.h folly/experimental/coro/DetachOnCancel.h -> folly/coro/DetachOnCancel.h folly/experimental/coro/detail/Barrier.h -> folly/coro/detail/Barrier.h folly/experimental/coro/detail/BarrierTask.h -> folly/coro/detail/BarrierTask.h folly/experimental/coro/detail/CurrentAsyncFrame.h -> folly/coro/detail/CurrentAsyncFrame.h folly/experimental/coro/detail/Helpers.h -> folly/coro/detail/Helpers.h folly/experimental/coro/detail/Malloc.h -> folly/coro/detail/Malloc.h folly/experimental/coro/detail/ManualLifetime.h -> folly/coro/detail/ManualLifetime.h folly/experimental/coro/detail/Traits.h -> folly/coro/detail/Traits.h folly/experimental/coro/Filter.h -> folly/coro/Filter.h folly/experimental/coro/Filter-inl.h -> folly/coro/Filter-inl.h folly/experimental/coro/FutureUtil.h -> folly/coro/FutureUtil.h folly/experimental/coro/Generator.h -> folly/coro/Generator.h folly/experimental/coro/GmockHelpers.h -> folly/coro/GmockHelpers.h folly/experimental/coro/GtestHelpers.h -> folly/coro/GtestHelpers.h folly/experimental/coro/detail/InlineTask.h -> folly/coro/detail/InlineTask.h folly/experimental/coro/Invoke.h -> folly/coro/Invoke.h folly/experimental/coro/Merge.h -> folly/coro/Merge.h folly/experimental/coro/Merge-inl.h -> folly/coro/Merge-inl.h folly/experimental/coro/Mutex.h -> folly/coro/Mutex.h folly/experimental/coro/Promise.h -> folly/coro/Promise.h folly/experimental/coro/Result.h -> folly/coro/Result.h folly/experimental/coro/Retry.h -> folly/coro/Retry.h folly/experimental/coro/RustAdaptors.h -> folly/coro/RustAdaptors.h folly/experimental/coro/ScopeExit.h -> folly/coro/ScopeExit.h folly/experimental/coro/SharedLock.h -> folly/coro/SharedLock.h folly/experimental/coro/SharedMutex.h -> folly/coro/SharedMutex.h folly/experimental/coro/Sleep.h -> folly/coro/Sleep.h folly/experimental/coro/Sleep-inl.h -> folly/coro/Sleep-inl.h folly/experimental/coro/SmallUnboundedQueue.h -> folly/coro/SmallUnboundedQueue.h folly/experimental/coro/Task.h -> folly/coro/Task.h folly/experimental/coro/TimedWait.h -> folly/coro/TimedWait.h folly/experimental/coro/Timeout.h -> folly/coro/Timeout.h folly/experimental/coro/Timeout-inl.h -> folly/coro/Timeout-inl.h folly/experimental/coro/Traits.h -> folly/coro/Traits.h folly/experimental/coro/Transform.h -> folly/coro/Transform.h folly/experimental/coro/Transform-inl.h -> folly/coro/Transform-inl.h folly/experimental/coro/UnboundedQueue.h -> folly/coro/UnboundedQueue.h folly/experimental/coro/ViaIfAsync.h -> folly/coro/ViaIfAsync.h folly/experimental/coro/WithAsyncStack.h -> folly/coro/WithAsyncStack.h folly/experimental/coro/WithCancellation.h -> folly/coro/WithCancellation.h folly/experimental/coro/BoundedQueue.h -> folly/coro/BoundedQueue.h folly/experimental/coro/SharedPromise.h -> folly/coro/SharedPromise.h folly/experimental/coro/Cleanup.h -> folly/coro/Cleanup.h folly/experimental/coro/AutoCleanup-fwd.h -> folly/coro/AutoCleanup-fwd.h folly/experimental/coro/AutoCleanup.h -> folly/coro/AutoCleanup.h ``` This is a codemod. It was automatically generated and will be landed once it is approved and tests are passing in sandcastle. You have been added as a reviewer by Sentinel or Butterfly. Autodiff project: dcoro Autodiff partition: fbcode.internal_repo_rocksdb Autodiff bookmark: ad.dcoro.fbcode.internal_repo_rocksdb Reviewed By: dtolnay Differential Revision: D62684411 fbshipit-source-id: 8dbd31ab64fcdd99435d322035b9668e3200e0a3 |
||
|
Yu Zhang
|
0c6e9c036a |
Make compaction always use the input version with extra ref protection (#12992)
Summary: `Compaction` is already creating its own ref for the input Version: |
||
|
Peter Dillinger
|
96340dbce2 |
Options for file temperature for more files (#12957)
Summary: We have a request to use the cold tier as primary source of truth for the DB, and to best support such use cases and to complement the existing options controlling SST file temperatures, we add two new DB options: * `metadata_write_temperature` for DB "small" files that don't contain much user data * `wal_write_temperature` for WALs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12957 Test Plan: Unit test included, though it's hard to be sure we've covered all the places Reviewed By: jowlyzhang Differential Revision: D61664815 Pulled By: pdillinger fbshipit-source-id: 8e19c9dd8fd2db059bb15f74938d6bc12002e82b |
||
|
Yu Zhang
|
295326b6ee |
Best efforts recovery recover seqno prefix (#12938)
Summary: This PR make best efforts recovery more permissive by allowing it to recover incomplete Version that presents a valid point in time view from the user's perspective. Currently, a Version is only valid and saved if all files consisting that Version can be found. With this change, if only a suffix of L0 files (and their associated blob files) are missing, a valid Version is also available to be saved and recover to. Note that we don't do this if the column family was atomically flushed. Because atomic flush also need a consistent view across the column families, we cannot guarantee that if we are recovering to incomplete version. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12938 Test Plan: Existing tests and added unit tests. Reviewed By: anand1976 Differential Revision: D61414381 Pulled By: jowlyzhang fbshipit-source-id: f9b73deb34d35ad696ab42315928b656d586262a |
||
|
Yu Zhang
|
d458331ee9 |
Move file tracking in VersionEditHandlerPointInTime to VersionBuilder (#12928)
Summary: `VersionEditHandlerPointInTime` is tracking found files, missing files, intermediate files in order to decide to build a `Version` on negative edge trigger (transition from valid to invalid) without applying the current `VersionEdit`. However, applying `VersionEdit` and check completeness of a `Version` are specialization of `VersionBuilder`. More importantly, when we augment best efforts recovery to recover not just complete point in time Version but also a prefix of seqno for a point in time Version, such checks need to be duplicated in `VersionEditHandlerPointInTime` and `VersionBuilder`. To avoid this, this refactor move all the file tracking functionality in `VersionEditHandlerPointInTime` into `VersionBuilder`. To continue to let `VersionEditHandlerPIT` do the edge trigger check and build a `Version` before applying the current `VersionEdit`, a suite of APIs to supporting creating a save point and its associated functions are added in `VersionBuilder` to achieve this. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12928 Test Plan: Existing tests Reviewed By: anand1976 Differential Revision: D61171320 Pulled By: jowlyzhang fbshipit-source-id: 604f66f8b1e3a3e13da59d8ba357c74e8a366dbc |
||
|
Yu Zhang
|
9883b5f497 |
Fix manifest_number_ point to invalid file (#12882)
Summary: This PR fix `VersionSet`'s `manifest_number_` could be pointing to an invalid number intermediately. This happens when a new manifest roll is attempted but fast failed after loading table handlers and before the new manifest file creation/writing is actually attempted. In theory, a later manifest roll effort will overthrow this intermediate invalid in memory state. There is on harm when the DB crashes in this invalid state either. But efforts that takes a file snapshot of the DB like backup will incorrectly try to copy a non existing manifest file. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12882 Reviewed By: cbi42 Differential Revision: D60204956 Pulled By: jowlyzhang fbshipit-source-id: effbdb124b582f879d114988af06ac63867fc549 |
||
|
anand76
|
0fca5e31b4 |
Fix race between manifest error recovery and file ingestion (#12871)
Summary: This PR fixes an assertion failure in `DBImpl::ResumeImpl` - `assert(!versions_->descriptor_log_)`. In `VersionSet`, `descriptor_log_` has a pointer to the current MANIFEST writer. When there's an error updating the manifest, `descriptor_log_` is reset, and the error recovery thread checks `io_status()` in `VersionSet` and attempts to write a new MANIFEST. If another DB manipulation happens at the same time (like external file ingestion, column family manipulation etc), it calls `LogAndApply`, which also attempts to write a new MANIFEST. The assertion in `ResumeImpl` might fail in this case since the other MANIFEST writer may have updated `descriptor_log_`. To prevent the assertion, this fix updates both `io_status_` and `descriptor_log_` while holding the DB mutex. The other option would have been to simply remove the assert. But I think its important to have it to ensure the invariant that `io_status_` is cleared if the MANIFEST is written successfully, and this fix makes things easier to reason about. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12871 Test Plan: Existing tests and crash test Reviewed By: hx235 Differential Revision: D59926947 Pulled By: anand1976 fbshipit-source-id: af9ad18da3e29fc62c7ec2e30e0738aa33d4e5f1 |
||
|
anand76
|
5aa675457e |
Fix unhandled MANIFEST write errors (#12865)
Summary: The failure of `WriteCurrentStateToManifest()` in `VersionSet::ProcessManifestWrites()` was not handled properly. If it failed, `manifest_io_status` was not updated, leading to `manifest_file_number_` being updated to the newly created manifest even though its bad. This would lead to the bad manifest immediately getting deleted, and also the good manifest (referenced by `CURRENT`) getting deleted by obsolete file deletion because of `manifest_file_number_` not referencing its number. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12865 Reviewed By: hx235 Differential Revision: D59782940 Pulled By: anand1976 fbshipit-source-id: f752fb9a1c23fd3d734616e273613cbac204301b |
||
|
WangQian
|
755010f8d3 |
Fix the bug with using the user comparator to compare prefix. (#12862)
Summary: Fixes https://github.com/facebook/rocksdb/issues/12855 Pull Request resolved: https://github.com/facebook/rocksdb/pull/12862 Reviewed By: cbi42 Differential Revision: D59771651 Pulled By: jowlyzhang fbshipit-source-id: ffe0025143f51f9ce1b46900c3fef6a20eb34f4a |
||
|
Peter Dillinger
|
39455974cb |
Fix possible double-free on TruncatedRangeDelIterator (#12805)
Summary: Not sure where or how it happens, but using a recent CircleCI failure I got a reliable db_stress reproducer. Using std::unique_ptr appropriately for managing them has apparently (and unsurprisingly) fixed the problem without needing to know exactly where the problem was. Suggested follow-up: * Three or even four levels of pointers is very confusing to work with. Surely this part can be cleaned up to be simpler. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12805 Test Plan: Reproducer passes, plus ASAN test and crash test runs. I don't think it's worth the extra work to track down the details and create a careful unit test. ``` ./db_stress --WAL_size_limit_MB=1 --WAL_ttl_seconds=60 --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --adm_policy=2 --advise_random_on_open=1 --allow_data_in_errors=True --allow_fallocate=1 --async_io=0 --auto_readahead_size=1 --avoid_flush_during_recovery=0 --avoid_flush_during_shutdown=1 --avoid_unnecessary_blocking_io=1 --backup_max_size=104857600 --backup_one_in=100000 --batch_protection_bytes_per_key=0 --bgerror_resume_retry_interval=1000000 --block_align=1 --block_protection_bytes_per_key=4 --block_size=16384 --bloom_before_level=2147483646 --bloom_bits=15 --bottommost_compression_type=none --bottommost_file_compaction_delay=3600 --bytes_per_sync=262144 --cache_index_and_filter_blocks=0 --cache_index_and_filter_blocks_with_high_priority=0 --cache_size=33554432 --cache_type=tiered_lru_cache --charge_compression_dictionary_building_buffer=0 --charge_file_metadata=1 --charge_filter_construction=0 --charge_table_reader=0 --check_multiget_consistency=1 --check_multiget_entity_consistency=1 --checkpoint_one_in=10000 --checksum_type=kxxHash --clear_column_family_one_in=0 --compact_files_one_in=1000000 --compact_range_one_in=1000 --compaction_pri=0 --compaction_readahead_size=0 --compaction_ttl=0 --compress_format_version=2 --compressed_secondary_cache_ratio=0.2 --compressed_secondary_cache_size=0 --compression_checksum=0 --compression_max_dict_buffer_bytes=0 --compression_max_dict_bytes=0 --compression_parallel_threads=1 --compression_type=none --compression_use_zstd_dict_trainer=0 --compression_zstd_max_train_bytes=0 --continuous_verification_interval=0 --daily_offpeak_time_utc= --data_block_index_type=0 --db=/dev/shm/rocksdb.gpxs/rocksdb_crashtest_blackbox --db_write_buffer_size=0 --default_temperature=kWarm --default_write_temperature=kCold --delete_obsolete_files_period_micros=21600000000 --delpercent=4 --delrangepercent=1 --destroy_db_initially=0 --detect_filter_construct_corruption=0 --disable_file_deletions_one_in=10000 --disable_manual_compaction_one_in=1000000 --disable_wal=0 --dump_malloc_stats=1 --enable_checksum_handoff=1 --enable_compaction_filter=0 --enable_custom_split_merge=0 --enable_do_not_compress_roles=0 --enable_index_compression=0 --enable_memtable_insert_with_hint_prefix_extractor=0 --enable_pipelined_write=1 --enable_sst_partitioner_factory=0 --enable_thread_tracking=1 --enable_write_thread_adaptive_yield=0 --error_recovery_with_no_fault_injection=0 --expected_values_dir=/dev/shm/rocksdb.gpxs/rocksdb_crashtest_expected --fail_if_options_file_error=0 --fifo_allow_compaction=0 --file_checksum_impl=none --fill_cache=1 --flush_one_in=1000000 --format_version=3 --get_all_column_family_metadata_one_in=1000000 --get_current_wal_file_one_in=0 --get_live_files_apis_one_in=10000 --get_properties_of_all_tables_one_in=100000 --get_property_one_in=100000 --get_sorted_wal_files_one_in=0 --hard_pending_compaction_bytes_limit=274877906944 --high_pri_pool_ratio=0 --index_block_restart_interval=4 --index_shortening=0 --index_type=0 --ingest_external_file_one_in=0 --initial_auto_readahead_size=16384 --inplace_update_support=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --key_may_exist_one_in=100 --last_level_temperature=kHot --level_compaction_dynamic_level_bytes=0 --lock_wal_one_in=1000000 --log_file_time_to_roll=0 --log_readahead_size=0 --long_running_snapshots=1 --low_pri_pool_ratio=0 --lowest_used_cache_tier=2 --manifest_preallocation_size=5120 --manual_wal_flush_one_in=1000 --mark_for_compaction_one_file_in=10 --max_auto_readahead_size=16384 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=2500000 --max_key_len=3 --max_log_file_size=0 --max_manifest_file_size=1073741824 --max_sequential_skip_in_iterations=1 --max_total_wal_size=0 --max_write_batch_group_size_bytes=16 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_insert_hint_per_batch=1 --memtable_max_range_deletions=100 --memtable_prefix_bloom_size_ratio=0 --memtable_protection_bytes_per_key=4 --memtable_whole_key_filtering=0 --memtablerep=skip_list --metadata_charge_policy=0 --metadata_read_fault_one_in=32 --metadata_write_fault_one_in=0 --min_write_buffer_number_to_merge=2 --mmap_read=1 --mock_direct_io=False --nooverwritepercent=1 --num_file_reads_for_auto_readahead=0 --open_files=100 --open_metadata_read_fault_one_in=0 --open_metadata_write_fault_one_in=8 --open_read_fault_one_in=0 --open_write_fault_one_in=16 --ops_per_thread=100000000 --optimize_filters_for_hits=1 --optimize_filters_for_memory=0 --optimize_multiget_for_io=1 --paranoid_file_checks=1 --partition_filters=0 --partition_pinning=1 --pause_background_one_in=1000000 --periodic_compaction_seconds=0 --prefix_size=-1 --prefixpercent=0 --prepopulate_block_cache=1 --preserve_internal_time_seconds=60 --progress_reports=0 --promote_l0_one_in=0 --read_amp_bytes_per_bit=0 --read_fault_one_in=32 --readahead_size=524288 --readpercent=50 --recycle_log_file_num=1 --reopen=0 --report_bg_io_stats=1 --reset_stats_one_in=10000 --sample_for_compression=5 --secondary_cache_fault_one_in=32 --secondary_cache_uri= --set_options_one_in=10000 --skip_stats_update_on_db_open=0 --snapshot_hold_ops=100000 --soft_pending_compaction_bytes_limit=68719476736 --sqfc_name=bar --sqfc_version=1 --sst_file_manager_bytes_per_sec=104857600 --sst_file_manager_bytes_per_truncate=0 --stats_dump_period_sec=0 --stats_history_buffer_size=1048576 --strict_bytes_per_sync=1 --subcompactions=3 --sync=0 --sync_fault_injection=1 --table_cache_numshardbits=0 --target_file_size_base=524288 --target_file_size_multiplier=2 --test_batches_snapshots=0 --test_cf_consistency=1 --top_level_index_pinning=1 --uncache_aggressiveness=5 --universal_max_read_amp=-1 --unpartitioned_pinning=2 --use_adaptive_mutex=0 --use_adaptive_mutex_lru=0 --use_attribute_group=1 --use_delta_encoding=1 --use_direct_io_for_flush_and_compaction=0 --use_direct_reads=0 --use_full_merge_v1=0 --use_get_entity=0 --use_merge=0 --use_multi_cf_iterator=0 --use_multi_get_entity=0 --use_multiget=1 --use_put_entity_one_in=1 --use_sqfc_for_range_queries=1 --use_timed_put_one_in=0 --use_write_buffer_manager=0 --user_timestamp_size=0 --value_size_mult=32 --verification_only=0 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_compression=1 --verify_db_one_in=100000 --verify_file_checksums_one_in=0 --verify_iterator_with_expected_state_one_in=0 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=0 --wal_compression=none --write_buffer_size=1048576 --write_dbid_to_manifest=1 --write_fault_one_in=0 --writepercent=35 ``` Reviewed By: cbi42 Differential Revision: D58958390 Pulled By: pdillinger fbshipit-source-id: 1271cfdcc3c574f78cd59f3c68148f7ed4a19c47 |
||
|
Peter Dillinger
|
21eb82ebec |
Disable "uncache" behavior in DB shutdown (#12751)
Summary: Crash test showed a potential use-after-free where a file marked as obsolete and eligible for uncache on destruction is destroyed in the VersionSet destructor, which only happens as part of DB shutdown. At that point, the in-memory column families have already been destroyed, so attempting to uncache could use-after-free on stuff like getting the `user_comparator()` from the `internal_comparator()`. I attempted to make it smarter, but wasn't able to untangle the destruction dependencies in a way that was safe, understandable, and maintainable. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12751 Test Plan: Reproduced by adding uncache_aggressiveness to an existing (but otherwise unrelated) test. This makes it a fair regression test. Also added testing to ensure that trivial moves and DB close & reopen are well behaved with uncache_aggressiveness. Specifically, this issue doesn't seem to be because things are uncached inappropriately in those cases. Reviewed By: ltamasi Differential Revision: D58390058 Pulled By: pdillinger fbshipit-source-id: 66ac9cb13bf02638fa80ee5b7218153d8bc7cfd3 |
||
|
Peter Dillinger
|
b34cef57b7 |
Support pro-actively erasing obsolete block cache entries (#12694)
Summary: Currently, when files become obsolete, the block cache entries associated with them just age out naturally. With pure LRU, this is not too bad, as once you "use" enough cache entries to (re-)fill the cache, you are guranteed to have purged the obsolete entries. However, HyperClockCache is a counting clock cache with a somewhat longer memory, so could be more negatively impacted by previously-hot cache entries becoming obsolete, and taking longer to age out than newer single-hit entries. Part of the reason we still have this natural aging-out is that there's almost no connection between block cache entries and the file they are associated with. Everything is hashed into the same pool(s) of entries with nothing like a secondary index based on file. Keeping track of such an index could be expensive. This change adds a new, mutable CF option `uncache_aggressiveness` for erasing obsolete block cache entries. The process can be speculative, lossy, or unproductive because not all potential block cache entries associated with files will be resident in memory, and attempting to remove them all could be wasted CPU time. Rather than a simple on/off switch, `uncache_aggressiveness` basically tells RocksDB how much CPU you're willing to burn trying to purge obsolete block cache entries. When such efforts are not sufficiently productive for a file, we stop and move on. The option is in ColumnFamilyOptions so that it is dynamically changeable for already-open files, and customizeable by CF. Note that this block cache removal happens as part of the process of purging obsolete files, which is often in a background thread (depending on `background_purge_on_iterator_cleanup` and `avoid_unnecessary_blocking_io` options) rather than along CPU critical paths. Notable auxiliary code details: * Possibly fixing some issues with trivial moves with `only_delete_metadata`: unnecessary TableCache::Evict in that case and missing from the ObsoleteFileInfo move operator. (Not able to reproduce an current failure.) * Remove suspicious TableCache::Erase() from VersionSet::AddObsoleteBlobFile() (TODO follow-up item) Marked EXPERIMENTAL until more thorough validation is complete. Direct stats of this functionality are omitted because they could be misleading. Block cache hit rate is a better indicator of benefit, and CPU profiling a better indicator of cost. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12694 Test Plan: * Unit tests added, including refactoring an existing test to make better use of parameterized tests. * Added to crash test. * Performance, sample command: ``` for I in `seq 1 10`; do for UA in 300; do for CT in lru_cache fixed_hyper_clock_cache auto_hyper_clock_cache; do rm -rf /dev/shm/test3; TEST_TMPDIR=/dev/shm/test3 /usr/bin/time ./db_bench -benchmarks=readwhilewriting -num=13000000 -read_random_exp_range=6 -write_buffer_size=10000000 -bloom_bits=10 -cache_type=$CT -cache_size=390000000 -cache_index_and_filter_blocks=1 -disable_wal=1 -duration=60 -statistics -uncache_aggressiveness=$UA 2>&1 | grep -E 'micros/op|rocksdb.block.cache.data.(hit|miss)|rocksdb.number.keys.(read|written)|maxresident' | awk '/rocksdb.block.cache.data.miss/ { miss = $4 } /rocksdb.block.cache.data.hit/ { hit = $4 } { print } END { print "hit rate = " ((hit * 1.0) / (miss + hit)) }' | tee -a results-$CT-$UA; done; done; done ``` Averaging 10 runs each case, block cache data block hit rates ``` lru_cache UA=0 -> hit rate = 0.327, ops/s = 87668, user CPU sec = 139.0 UA=300 -> hit rate = 0.336, ops/s = 87960, user CPU sec = 139.0 fixed_hyper_clock_cache UA=0 -> hit rate = 0.336, ops/s = 100069, user CPU sec = 139.9 UA=300 -> hit rate = 0.343, ops/s = 100104, user CPU sec = 140.2 auto_hyper_clock_cache UA=0 -> hit rate = 0.336, ops/s = 97580, user CPU sec = 140.5 UA=300 -> hit rate = 0.345, ops/s = 97972, user CPU sec = 139.8 ``` Conclusion: up to roughly 1 percentage point of improved block cache hit rate, likely leading to overall improved efficiency (because the foreground CPU cost of cache misses likely outweighs the background CPU cost of erasure, let alone I/O savings). Reviewed By: ajkr Differential Revision: D57932442 Pulled By: pdillinger fbshipit-source-id: 84a243ca5f965f731f346a4853009780a904af6c |
||
|
Changyu Bi
|
fecb10c2fa |
Improve universal compaction sorted-run trigger (#12477)
Summary: Universal compaction currently uses `level0_file_num_compaction_trigger` for two purposes: 1. the trigger for checking if there is any compaction to do, and 2. the limit on the number of sorted runs. RocksDB will do compaction to keep the number of sorted runs no more than the value of this option. This can make the option inflexible. A value that is too small causes higher write amp: more compactions to reduce the number of sorted runs. A value that is too big delays potential compaction work and causes worse read performance. This PR introduce an option `CompactionOptionsUniversal::max_read_amp` for only the second purpose: to specify the hard limit on the number of sorted runs. For backward compatibility, `max_read_amp = -1` by default, which means to fallback to the current behavior. When `max_read_amp > 0`,`level0_file_num_compaction_trigger` will only serve as a trigger to find potential compaction. When `max_read_amp = 0`, RocksDB will auto-tune the limit on the number of sorted runs. The estimation is based on DB size, write_buffer_size and size_ratio, so it is adaptive to the size change of the DB. See more in `UniversalCompactionBuilder::PickCompaction()`. Alternatively, users now can configure `max_read_amp` to a very big value and keep `level0_file_num_compaction_trigger` small. This will allow `size_ratio` and `max_size_amplification_percent` to control the number of sorted runs. This essentially disables compactions with reason kUniversalSortedRunNum. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12477 Test Plan: * new unit test * existing unit test for default behavior * updated crash test with the new option * benchmark: * Create a DB that is roughly 24GB in the last level. When `max_read_amp = 0`, we estimate that the DB needs 9 levels to avoid excessive compactions to reduce the number of sorted runs. * We then run fillrandom to ingest another 24GB data to compare write amp. * case 1: small level0 trigger: `level0_file_num_compaction_trigger=5, max_read_amp=-1` * write-amp: 4.8 * case 2: auto-tune: `level0_file_num_compaction_trigger=5, max_read_amp=0` * write-amp: 3.6 * case 3: auto-tune with minimal trigger: `level0_file_num_compaction_trigger=1, max_read_amp=0` * write-amp: 3.8 * case 4: hard-code a good value for trigger: `level0_file_num_compaction_trigger=9` * write-amp: 2.8 ``` Case 1: ** Compaction Stats [default] ** Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB) ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ L0 0/0 0.00 KB 1.0 0.0 0.0 0.0 22.6 22.6 0.0 1.0 0.0 163.2 141.94 111.10 108 1.314 0 0 0.0 0.0 L45 8/0 1.81 GB 0.0 39.6 11.1 28.5 39.3 10.8 0.0 3.5 209.0 207.3 194.25 191.29 43 4.517 348M 2498K 0.0 0.0 L46 13/0 3.12 GB 0.0 15.3 9.5 5.8 15.0 9.3 0.0 1.6 203.1 199.3 77.13 75.88 16 4.821 134M 2362K 0.0 0.0 L47 19/0 4.68 GB 0.0 15.4 10.5 4.9 14.7 9.8 0.0 1.4 204.0 194.9 77.38 76.15 8 9.673 135M 5920K 0.0 0.0 L48 38/0 9.42 GB 0.0 19.6 11.7 7.9 17.3 9.4 0.0 1.5 206.5 182.3 97.15 95.02 4 24.287 172M 20M 0.0 0.0 L49 91/0 22.70 GB 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.00 0.00 0 0.000 0 0 0.0 0.0 Sum 169/0 41.74 GB 0.0 89.9 42.9 47.0 109.0 61.9 0.0 4.8 156.7 189.8 587.85 549.45 179 3.284 791M 31M 0.0 0.0 Case 2: ** Compaction Stats [default] ** Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB) ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ L0 1/0 214.47 MB 1.2 0.0 0.0 0.0 22.6 22.6 0.0 1.0 0.0 164.5 140.81 109.98 108 1.304 0 0 0.0 0.0 L44 0/0 0.00 KB 0.0 1.3 1.3 0.0 1.2 1.2 0.0 1.0 206.1 204.9 6.24 5.98 3 2.081 11M 51K 0.0 0.0 L45 4/0 844.36 MB 0.0 7.1 5.4 1.7 7.0 5.4 0.0 1.3 194.6 192.9 37.41 36.00 13 2.878 62M 489K 0.0 0.0 L46 11/0 2.57 GB 0.0 14.6 9.8 4.8 14.3 9.5 0.0 1.5 193.7 189.8 77.09 73.54 17 4.535 128M 2411K 0.0 0.0 L47 24/0 5.81 GB 0.0 19.8 12.0 7.8 18.8 11.0 0.0 1.6 191.4 181.1 106.19 101.21 9 11.799 174M 9166K 0.0 0.0 L48 38/0 9.42 GB 0.0 19.6 11.8 7.9 17.3 9.4 0.0 1.5 197.3 173.6 101.97 97.23 4 25.491 172M 20M 0.0 0.0 L49 91/0 22.70 GB 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.00 0.00 0 0.000 0 0 0.0 0.0 Sum 169/0 41.54 GB 0.0 62.4 40.3 22.1 81.3 59.2 0.0 3.6 136.1 177.2 469.71 423.94 154 3.050 549M 32M 0.0 0.0 Case 3: ** Compaction Stats [default] ** Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB) ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ L0 0/0 0.00 KB 5.0 0.0 0.0 0.0 22.6 22.6 0.0 1.0 0.0 163.8 141.43 111.13 108 1.310 0 0 0.0 0.0 L44 0/0 0.00 KB 0.0 0.8 0.8 0.0 0.8 0.8 0.0 1.0 201.4 200.2 4.26 4.19 2 2.130 7360K 33K 0.0 0.0 L45 4/0 844.38 MB 0.0 6.3 5.0 1.2 6.2 5.0 0.0 1.2 202.0 200.3 31.81 31.50 12 2.651 55M 403K 0.0 0.0 L46 7/0 1.62 GB 0.0 13.3 8.8 4.6 13.1 8.6 0.0 1.5 198.9 195.7 68.72 67.89 17 4.042 117M 1696K 0.0 0.0 L47 24/0 5.81 GB 0.0 21.7 12.9 8.8 20.6 11.8 0.0 1.6 198.5 188.6 112.04 109.97 12 9.336 191M 9352K 0.0 0.0 L48 41/0 10.14 GB 0.0 24.8 13.0 11.8 21.9 10.1 0.0 1.7 198.6 175.6 127.88 125.36 6 21.313 218M 25M 0.0 0.0 L49 91/0 22.70 GB 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.00 0.00 0 0.000 0 0 0.0 0.0 Sum 167/0 41.10 GB 0.0 67.0 40.5 26.4 85.4 58.9 0.0 3.8 141.1 179.8 486.13 450.04 157 3.096 589M 36M 0.0 0.0 Case 4: ** Compaction Stats [default] ** Level Files Size Score Read(GB) Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop Rblob(GB) Wblob(GB) ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ L0 0/0 0.00 KB 0.7 0.0 0.0 0.0 22.6 22.6 0.0 1.0 0.0 158.6 146.02 114.68 108 1.352 0 0 0.0 0.0 L42 0/0 0.00 KB 0.0 1.7 1.7 0.0 1.7 1.7 0.0 1.0 185.4 184.3 9.25 8.96 4 2.314 14M 67K 0.0 0.0 L43 0/0 0.00 KB 0.0 2.5 2.5 0.0 2.5 2.5 0.0 1.0 197.8 195.6 13.01 12.65 4 3.253 22M 202K 0.0 0.0 L44 4/0 844.40 MB 0.0 4.2 4.2 0.0 4.1 4.1 0.0 1.0 188.1 185.1 22.81 21.89 5 4.562 36M 503K 0.0 0.0 L45 13/0 3.12 GB 0.0 7.5 6.5 1.0 7.2 6.2 0.0 1.1 188.7 181.8 40.69 39.32 5 8.138 65M 2282K 0.0 0.0 L46 17/0 4.18 GB 0.0 8.3 7.1 1.2 7.9 6.6 0.0 1.1 192.2 181.8 44.23 43.06 4 11.058 73M 3846K 0.0 0.0 L47 22/0 5.34 GB 0.0 8.9 7.5 1.4 8.2 6.8 0.0 1.1 189.1 174.1 48.12 45.37 3 16.041 78M 6098K 0.0 0.0 L48 27/0 6.58 GB 0.0 9.2 7.6 1.6 8.2 6.6 0.0 1.1 195.2 172.9 48.52 47.11 2 24.262 81M 9217K 0.0 0.0 L49 91/0 22.70 GB 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.00 0.00 0 0.000 0 0 0.0 0.0 Sum 174/0 42.74 GB 0.0 42.3 37.0 5.3 62.4 57.1 0.0 2.8 116.3 171.3 372.66 333.04 135 2.760 372M 22M 0.0 0.0 setup: ./db_bench --benchmarks=fillseq,compactall,waitforcompaction --num=200000000 --compression_type=none --disable_wal=1 --compaction_style=1 --num_levels=50 --target_file_size_base=268435456 --max_compaction_bytes=6710886400 --level0_file_num_compaction_trigger=10 --write_buffer_size=268435456 --seed 1708494134896523 benchmark: ./db_bench --benchmarks=overwrite,waitforcompaction,stats --num=200000000 --compression_type=none --disable_wal=1 --compaction_style=1 --write_buffer_size=268435456 --level0_file_num_compaction_trigger=5 --target_file_size_base=268435456 --use_existing_db=1 --num_levels=50 --writes=200000000 --universal_max_read_amp=-1 --seed=1716488324800233 ``` Reviewed By: ajkr Differential Revision: D55370922 Pulled By: cbi42 fbshipit-source-id: 9be69979126b840d08e93e7059260e76a878bb2a |
||
|
anand76
|
0ed93552f4 |
Implement obsolete file deletion (GC) in follower (#12657)
Summary: This PR implements deletion of obsolete files in a follower RocksDB instance. The follower tails the leader's MANIFEST and creates links to newly added SST files. These links need to be deleted once those files become obsolete in order to reclaim space. There are three cases to be considered - 1. New files added and links created, but the Version could not be installed due to some missing files. Those links need to be preserved so a subsequent catch up attempt can succeed. We insert the next file number in the `VersionSet` to `pending_outputs_` to prevent their deletion. 2. Files deleted from the previous successfully installed `Version`. These are deleted as usual in `PurgeObsoleteFiles`. 3. New files added by a `VersionEdit` and deleted by a subsequent `VersionEdit`, both processed in the same catchup attempt. Links will be created for the new files when verifying a candidate `Version`. Those need to be deleted explicitly as they're never added to `VersionStorageInfo`, and thus not deleted by `PurgeObsoleteFiles`. Test plan - New unit tests in `db_follower_test`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12657 Reviewed By: jowlyzhang Differential Revision: D57462697 Pulled By: anand1976 fbshipit-source-id: 898f15570638dd4930f839ffd31c560f9cb73916 |
||
|
Changyu Bi
|
6fdc4c5282 |
Fix a corruption bug in CreateColumnFamilyWithImport() (#12602)
Summary: when importing files from multiple CFs into a new CF, we were reusing the epoch numbers assigned by the original CFs. This means L0 files in the new CF can have the same epoch number (assigned originally by different CFs). While CreateColumnFamilyWithImport() requires each original CF to have disjoint key range, after an intra-l0 compaction, we still can end up with L0 files with the same epoch number but overlapping key range. This PR attempt to fix this by reassigning epoch numbers when importing multiple CFs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12602 Test Plan: a new repro unit test. Before this PR, it fails with ``` [ RUN ] ImportColumnFamilyTest.AssignEpochNumberToMultipleCF db/import_column_family_test.cc:1048: Failure db_->WaitForCompact(o) Corruption: force_consistency_checks(DEBUG): VersionBuilder: L0 files of same epoch number but overlapping range https://github.com/facebook/rocksdb/issues/44 , smallest key: '6B6579303030303030' seq:511, type:1 , largest key: '6B6579303031303239' seq:510, type:1 , epoch number: 3 vs. file https://github.com/facebook/rocksdb/issues/36 , smallest key: '6B6579303030313030' seq:401, type:1 , largest key: '6B6579303030313939' seq:500, type:1 , epoch number: 3 ``` Reviewed By: hx235 Differential Revision: D56851808 Pulled By: cbi42 fbshipit-source-id: 01b8c790c9f1f2a168047ead670e73633f705b84 |
||
|
Peter Dillinger
|
a178d15baf |
More checks around num_entries vs. num_deletions (#12600)
Summary: We've seen an internal crash test+sanitizer failure seemingly caused by underflow on `current_num_non_deletions_` which would happen if num_entries < num_deletions. (T186407810) This change adds an additional check (fail earlier?) and coerces read table properties to satisfy the invariant that is supposed to be provided by https://github.com/facebook/rocksdb/pull/4841 but could be violated by older files, due to https://github.com/facebook/rocksdb/pull/4016. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12600 Test Plan: existing tests Reviewed By: ajkr Differential Revision: D56796191 Pulled By: pdillinger fbshipit-source-id: 6d22cc40eb74974c42b311293ee2775c6af95afc |
||
|
Andrew Kryczka
|
b2931a5c53 |
Fixed MultiGet() error handling to not skip blob dereference (#12597)
Summary: See comment at top of the test case and release note. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12597 Reviewed By: jaykorean Differential Revision: D56718786 Pulled By: ajkr fbshipit-source-id: 8dce185bb0d24a358372fc2b553d181793fc335f |
||
|
anand76
|
97991960e9 |
Retry DB::Open upon a corruption detected while reading the MANIFEST (#12518)
Summary: This PR is a counterpart of https://github.com/facebook/rocksdb/issues/12427 . On file systems that support storage level data checksum and reconstruction, retry opening the DB if a corruption is detected when reading the MANIFEST. This could be done in `log::Reader`, but its a little complicated since the sequential file would have to be reopened in order to re-read the same data, and we may miss some subtle corruptions that don't result in checksum mismatch. The approach chosen here instead is to make the decision to retry in `DBImpl::Recover`, based on either an explicit corruption in the MANIFEST file, or missing SST files due to bad data in the MANIFEST. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12518 Reviewed By: ajkr Differential Revision: D55932155 Pulled By: anand1976 fbshipit-source-id: 51755a29b3eb14b9d8e98534adb2e7d54b12ced9 |
||
|
Jay Huh
|
02ea0d6367 |
Reserve vector in advance to avoid resizing in GetLiveFilesMetaData (#12554)
Summary: As title Pull Request resolved: https://github.com/facebook/rocksdb/pull/12554 Test Plan: Existing CI Reviewed By: ajkr Differential Revision: D56252201 Pulled By: jaykorean fbshipit-source-id: 06211555a54ce5e6bf656b81109022494e6787ea |
||
|
Peter Dillinger
|
b515a5db3f |
Replace ScopedArenaIterator with ScopedArenaPtr<InternalIterator> (#12470)
Summary: ScopedArenaIterator is not an iterator. It is a pointer wrapper. And we don't need a custom implemented pointer wrapper when std::unique_ptr can be instantiated with what we want. So this adds ScopedArenaPtr<T> to replace those uses. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12470 Test Plan: CI (including ASAN/UBSAN) Reviewed By: jowlyzhang Differential Revision: D55254362 Pulled By: pdillinger fbshipit-source-id: cc96a0b9840df99aa807f417725e120802c0ae18 |
||
|
Peter Dillinger
|
54cb9c77d9 |
Prefer static_cast in place of most reinterpret_cast (#12308)
Summary: The following are risks associated with pointer-to-pointer reinterpret_cast: * Can produce the "wrong result" (crash or memory corruption). IIRC, in theory this can happen for any up-cast or down-cast for a non-standard-layout type, though in practice would only happen for multiple inheritance cases (where the base class pointer might be "inside" the derived object). We don't use multiple inheritance a lot, but we do. * Can mask useful compiler errors upon code change, including converting between unrelated pointer types that you are expecting to be related, and converting between pointer and scalar types unintentionally. I can only think of some obscure cases where static_cast could be troublesome when it compiles as a replacement: * Going through `void*` could plausibly cause unnecessary or broken pointer arithmetic. Suppose we have `struct Derived: public Base1, public Base2`. If we have `Derived*` -> `void*` -> `Base2*` -> `Derived*` through reinterpret casts, this could plausibly work (though technical UB) assuming the `Base2*` is not dereferenced. Changing to static cast could introduce breaking pointer arithmetic. * Unnecessary (but safe) pointer arithmetic could arise in a case like `Derived*` -> `Base2*` -> `Derived*` where before the Base2 pointer might not have been dereferenced. This could potentially affect performance. With some light scripting, I tried replacing pointer-to-pointer reinterpret_casts with static_cast and kept the cases that still compile. Most occurrences of reinterpret_cast have successfully been changed (except for java/ and third-party/). 294 changed, 257 remain. A couple of related interventions included here: * Previously Cache::Handle was not actually derived from in the implementations and just used as a `void*` stand-in with reinterpret_cast. Now there is a relationship to allow static_cast. In theory, this could introduce pointer arithmetic (as described above) but is unlikely without multiple inheritance AND non-empty Cache::Handle. * Remove some unnecessary casts to void* as this is allowed to be implicit (for better or worse). Most of the remaining reinterpret_casts are for converting to/from raw bytes of objects. We could consider better idioms for these patterns in follow-up work. I wish there were a way to implement a template variant of static_cast that would only compile if no pointer arithmetic is generated, but best I can tell, this is not possible. AFAIK the best you could do is a dynamic check that the void* conversion after the static cast is unchanged. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12308 Test Plan: existing tests, CI Reviewed By: ltamasi Differential Revision: D53204947 Pulled By: pdillinger fbshipit-source-id: 9de23e618263b0d5b9820f4e15966876888a16e2 |
||
|
Yu Zhang
|
e3e8fbb497 |
Add a separate range classes for internal usage (#12071)
Summary: Introduce some different range classes `UserKeyRange` and `UserKeyRangePtr` to be used by internal implementation. The `Range` class is used in both public APIs like `DB::GetApproximateSizes`, `DB::GetApproximateMemTableStats`, `DB::GetPropertiesOfTablesInRange` etc and internal implementations like `ColumnFamilyData::RangesOverlapWithMemtables`, `VersionSet::GetPropertiesOfTablesInRange`. These APIs have different expectations of what keys this range class contain. Public API users are supposed to populate the range with the user keys without timestamp, in the same way that point lookup and range scan APIs' key input only expect the user key without timestamp. The internal APIs implementation expect a user key whose format is compatible with the user comparator, a.k.a a user key with the timestamp. This PR contains: 1) introducing counterpart range class `UserKeyRange` `UserKeyRangePtr` for internal implementation while leave the existing `Range` and `RangePtr` class only for public APIs. Internal implementations are updated to use this new class instead. 2) add user-defined timestamp support for `DB::GetPropertiesOfTablesInRange` API and `DeleteFilesInRanges` API. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12071 Test Plan: existing tests Added test for `DB::GetPropertiesOfTablesInRange` and `DeleteFilesInRanges` APIs for when user-defined timestamp is enabled. The change in external_file_ingestion_job doesn't have a user-defined timestamp enabled test case coverage, will add one in a follow up PR that adds file ingestion support for UDT. Reviewed By: ltamasi Differential Revision: D53292608 Pulled By: jowlyzhang fbshipit-source-id: 9a9279e23c640a6d8f8232636501a95aef7638b8 |
||
|
anand76
|
95b41eec6d |
Fix potential incorrect result for duplicate key in MultiGet (#12295)
Summary: The RocksDB correctness testing has recently discovered a possible, but very unlikely, correctness issue with MultiGet. The issue happens when all of the below conditions are met - 1. Duplicate keys in a MultiGet batch 2. Key matches the last key in a non-zero, non-bottommost level file 3. Final value is not in the file (merge operand, not snapshot visible etc) 4. Multiple entries exist for the key in the file spanning more than 1 data block. This can happen due to snapshots, which would force multiple versions of the key in the file, and they may spill over to another data block 5. Lookup attempt in the SST for the first of the duplicates fails with IO error on a data block (NOT the first data block, but the second or subsequent uncached block), but no errors for the other duplicates 6. Value or merge operand for the key is present in the very next level The problem is, in FilePickerMultiGet, when looking up keys in a level we use FileIndexer and the overlapping file in the current level to determine the search bounds for that key in the file list in the next level. If the next level is empty, the search bounds are reset and we do a full binary search in the next non-empty level's LevelFilesBrief. However, under the conditions https://github.com/facebook/rocksdb/issues/1 and https://github.com/facebook/rocksdb/issues/2 listed above, only the first of the duplicates has its next-level search bounds updated, and the remaining duplicates are skipped. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12295 Test Plan: Add unit tests that fail an assertion or return wrong result without the fix Reviewed By: hx235 Differential Revision: D53187634 Pulled By: anand1976 fbshipit-source-id: a5eadf4fede9bbdec784cd993b15e3341436d1ea |
||
|
Andrew Kryczka
|
7fe93162c5 |
Log pending compaction bytes in a couple places (#12267)
Summary: This PR adds estimated pending compaction bytes in two places: - The "Level summary", which is printed to the info LOG after every flush or compaction - The "rocksdb.cfstats" property, which is printed to the info LOG periodically according to `stats_dump_period_sec` Pull Request resolved: https://github.com/facebook/rocksdb/pull/12267 Test Plan: Ran `./db_bench -benchmarks=filluniquerandom -stats_dump_period_sec=1 -statistics=true -write_buffer_size=524288` and looked at the LOG. ``` ** Compaction Stats [default] ** ... Estimated pending compaction bytes: 12117691 ... 2024/01/22-13:15:12.283563 1572872 (Original Log Time 2024/01/22-13:15:12.283540) [/db_impl/db_impl_compaction_flush.cc:371] [default] Level summary: files[10 1 0 0 0 0 0] max score 0.50, estimated pending compaction bytes 12359137 ``` Reviewed By: cbi42 Differential Revision: D52973337 Pulled By: ajkr fbshipit-source-id: c4e546bd9bdac387eebeeba303d04125212037b8 |
||
|
anand76
|
65e162bf09 |
Add some asserts in FilePickerMultiGet for debugging (#12241)
Summary: Add asserts to help debug a crash test failure. The test fails as wollows - ```rocksdb::FilePickerMultiGet::PrepareNextLevel(): Assertion `fp_ctx.search_right_bound == -1 || fp_ctx.search_right_bound == FileIndexer::kLevelMaxIndex' failed``` Also add a unit test to verify an edge case. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12241 Reviewed By: cbi42 Differential Revision: D52819029 Pulled By: anand1976 fbshipit-source-id: 33316985c8ace1aed9ecc2400da8b777aec488ff |
||
|
Hui Xiao
|
06e593376c |
Group SST write in flush, compaction and db open with new stats (#11910)
Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff |
||
|
anand76
|
a036525809 |
Lightweight verification of MANIFEST file after close on shutdown (#12174)
Summary: Do a size verification on the MANIFEST file during DB shutdown, after closing the file. If the verification fails, write a new MANIFEST file. In the future, we can do a more thorough verification if we want to. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12174 Test Plan: Unit test, and some manual verification Reviewed By: ajkr Differential Revision: D52451184 Pulled By: anand1976 fbshipit-source-id: fc3bc170e22f6c9a9c482ee5ff592abab889df83 |
||
|
Changyu Bi
|
3d81f175b4 |
Prioritize marked file in level compaction (#12187)
Summary: When ranking file by compaction priority in a level, prioritize files marked for compaction over files that are not marked. This only applies to default CompactPri kMinOverlappingRatio for now. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12187 Test Plan: * New unit tests Reviewed By: ajkr Differential Revision: D52437194 Pulled By: cbi42 fbshipit-source-id: 65ea9ce5bb421e598d539a55c8219b70844b82b3 |
||
|
Andrew Kryczka
|
d8e47620d7 |
Speedup based on pending compaction bytes relative to data size (#12130)
Summary: RocksDB self throttles per-DB compaction parallelism until it detects compaction pressure. The pressure detection based on pending compaction bytes was only comparing against the slowdown trigger (`soft_pending_compaction_bytes_limit`). Online services tend to set that extremely high to avoid stalling at all costs. Perhaps they should have set it to zero, but we never documented that zero disables stalling so I have been telling everyone to increase it for years. This PR adds pressure detection based on pending compaction bytes relative to the size of bottommost data. The size of bottommost data should be fairly stable and proportional to the logical data size Pull Request resolved: https://github.com/facebook/rocksdb/pull/12130 Reviewed By: hx235 Differential Revision: D52000746 Pulled By: ajkr fbshipit-source-id: 7e1fd170901a74c2d4a69266285e3edf6e7631c7 |
||
|
Levi Tamasi
|
0ebe1614cb |
Eliminate some code duplication in MergeHelper (#12121)
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/12121 The patch eliminates some code duplication by unifying the two sets of `MergeHelper::TimedFullMerge` overloads using variadic templates. It also brings the order of parameters into sync when it comes to the various `TimedFullMerge*` methods. Reviewed By: jaykorean Differential Revision: D51862483 fbshipit-source-id: e3f832a6ff89ba34591451655cf11025d0a0d018 |
||
|
Yu Zhang
|
ba8fa0f546 |
internal_repo_rocksdb (4372117296613874540) (#12117)
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/12117 Reviewed By: ajkr Differential Revision: D51745846 Pulled By: jowlyzhang fbshipit-source-id: 51c806a484b3b43d174b06d2cfe9499191d09914 |
||
|
Yu Zhang
|
509947ce2c |
Quarantine files in a limbo state after a manifest error (#12030)
Summary: Part of the procedures to handle manifest IO error is to disable file deletion in case some files in limbo state get deleted prematurely. This is not ideal because: 1) not all the VersionEdits whose commit encounter such an error contain updates for files, disabling file deletion sometimes are not necessary. 2) `EnableFileDeletion` has a force mode that could make other threads accidentally disrupt this procedure in recovery. 3) Disabling file deletion as a whole is also not as efficient as more precisely tracking impacted files from being prematurely deleted. This PR replaces this mechanism with tracking such files and quarantine them from being deleted in `ErrorHandler`. These are the types of files being actively tracked in quarantine in this PR: 1) new table files and blob files from a background job 2) old manifest file whose immediately following new manifest file's CURRENT file creation gets into unclear state. Current handling is not sufficient to make sure the old manifest file is kept in case it's needed. Note that WAL logs are not part of the quarantine because `min_log_number_to_keep` is a safe mechanism and it's only updated after successful manifest commits so it can prevent this premature deletion issue from happening. We track these files' file numbers because they share the same file number space. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12030 Test Plan: Modified existing unit tests Reviewed By: ajkr Differential Revision: D51036774 Pulled By: jowlyzhang fbshipit-source-id: 84ef26271fbbc888ef70da5c40fe843bd7038716 |
||
|
Jay Huh
|
2dab137182 |
Mark more files for periodic compaction during offpeak (#12031)
Summary: - The struct previously named `OffpeakTimeInfo` has been renamed to `OffpeakTimeOption` to indicate that it's a user-configurable option. Additionally, a new struct, `OffpeakTimeInfo`, has been introduced, which includes two fields: `is_now_offpeak` and `seconds_till_next_offpeak_start`. This change prevents the need to parse the `daily_offpeak_time_utc` string twice. - It's worth noting that we may consider adding more fields to the `OffpeakTimeInfo` struct, such as `elapsed_seconds` and `total_seconds`, as needed for further optimization. - Within `VersionStorageInfo::ComputeFilesMarkedForPeriodicCompaction()`, we've adjusted the `allowed_time_limit` to include files that are expected to expire by the next offpeak start. - We might explore further optimizations, such as evenly distributing files to mark during offpeak hours, if the initial approach results in marking too many files simultaneously during the first scoring in offpeak hours. The primary objective of this PR is to prevent periodic compactions during non-offpeak hours when offpeak hours are configured. We'll start with this straightforward solution and assess whether it suffices for now. Pull Request resolved: https://github.com/facebook/rocksdb/pull/12031 Test Plan: Unit Tests added - `DBCompactionTest::LevelPeriodicCompactionOffpeak` for Leveled - `DBTestUniversalCompaction2::PeriodicCompaction` for Universal Reviewed By: cbi42 Differential Revision: D50900292 Pulled By: jaykorean fbshipit-source-id: 267e7d3332d45a5d9881796786c8650fa0a3b43d |
||
|
Yu Zhang
|
4b013dcbed |
Remove VersionEdit's friends pattern (#12024)
Summary: Almost each of VersionEdit private member has its own getter and setter. Current code access them with a combination of directly accessing private members and via getter and setters. There is no obvious benefits to have this pattern except potential performance gains. I tried this simple benchmark for removing the friends pattern completely, and there is no obvious regression. So I think it would good to remove VersionEdit's friends completely. ```TEST_TMPDIR=/dev/shm/rocksdb1 ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num_column_families=10 -num=50000000``` With change: fillseq : 2.994 micros/op 333980 ops/sec 149.710 seconds 50000000 operations; 36.9 MB/s fillseq : 3.033 micros/op 329656 ops/sec 151.673 seconds 50000000 operations; 36.5 MB/s fillseq : 2.991 micros/op 334369 ops/sec 149.535 seconds 50000000 operations; 37.0 MB/s Without change: fillseq : 3.015 micros/op 331715 ops/sec 150.732 seconds 50000000 operations; 36.7 MB/s fillseq : 3.044 micros/op 328553 ops/sec 152.182 seconds 50000000 operations; 36.3 MB/s fillseq : 3.091 micros/op 323520 ops/sec 154.550 seconds 50000000 operations; 35.8 MB/s Pull Request resolved: https://github.com/facebook/rocksdb/pull/12024 Reviewed By: pdillinger Differential Revision: D50806066 Pulled By: jowlyzhang fbshipit-source-id: 35d287ce638a38c30f243f85992e615b4c90eb27 |
||
|
Jay Huh
|
e230e4d248 |
Make OffpeakTimeInfo available in VersionSet (#12018)
Summary: As mentioned in https://github.com/facebook/rocksdb/issues/11893, we are going to use the offpeak time information to pre-process TTL-based compactions. To do so, we need to access `daily_offpeak_time_utc` in `VersionStorageInfo::ComputeCompactionScore()` where we pick the files to compact. This PR is to make the offpeak time information available at the time of compaction-scoring. We are not changing any compaction scoring logic just yet. Will follow up in a separate PR. There were two ways to achieve what we want. 1. Make `MutableDBOptions` available in `ColumnFamilyData` and `ComputeCompactionScore()` take `MutableDBOptions` along with `ImmutableOptions` and `MutableCFOptions`. 2. Make `daily_offpeak_time_utc` and `IsNowOffpeak()` available in `VersionStorageInfo`. We chose the latter as it involves smaller changes. This change includes the following - Introduction of `OffpeakTimeInfo` and `IsNowOffpeak()` has been moved from `MutableDBOptions` - `OffpeakTimeInfo` added to `VersionSet` and it can be set during construction and by `ChangeOffpeakTimeInfo()` - During `SetDBOptions()`, if offpeak time info needs to change, it calls `MaybeScheduleFlushOrCompaction()` to re-compute compaction scores and process compactions as needed Pull Request resolved: https://github.com/facebook/rocksdb/pull/12018 Test Plan: - `DBOptionsTest::OffpeakTimes` changed to include checks for `MaybeScheduleFlushOrCompaction()` calls and `VersionSet`'s OffpeakTimeInfo value change during `SetDBOptions()`. - `VersionSetTest::OffpeakTimeInfoTest` added to test `ChangeOffpeakTimeInfo()`. `IsNowOffpeak()` tests moved from `DBOptionsTest::OffpeakTimes` Reviewed By: pdillinger Differential Revision: D50723881 Pulled By: jaykorean fbshipit-source-id: 3cff0291936f3729c0e9c7750834b9378fb435f6 |
||
|
Peter Dillinger
|
4155087746 |
Use manifest to persist pre-allocated seqnos (#11995)
Summary: ... and other fixes for crash test after https://github.com/facebook/rocksdb/issues/11922. * When pre-allocating sequence numbers for establishing a time history, record that last sequence number in the manifest so that it is (most likely) restored on recovery even if no user writes were made or were recovered (e.g. no WAL). * When pre-allocating sequence numbers for establishing a time history, only do this for actually new DBs. * Remove the feature that ensures non-zero sequence number on creating the first column family with preserve/preclude option after initial DB::Open. Until fixed in a way compatible with the crash test, this creates a gap where some data written with active preserve/preclude option won't have a known associated time. Together, these ensure we don't upset the crash test by manipulating sequence numbers after initial DB creation (esp when re-opening with different options). (The crash test expects that the seqno after re-open corresponds to a known point in time from previous crash test operation, matching an expected DB state.) Follow-up work: * Re-fill the gap to ensure all data written under preserve/preclude settings have a known time estimate. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11995 Test Plan: Added to unit test SeqnoTimeTablePropTest.PrePopulateInDB Verified fixes two crash test scenarios: ## 1st reproducer First apply ``` diff --git a/db_stress_tool/expected_state.cc b/db_stress_tool/expected_state.cc index b483e154c..ef63b8d6c 100644 --- a/db_stress_tool/expected_state.cc +++ b/db_stress_tool/expected_state.cc @@ -333,6 +333,7 @@ Status FileExpectedStateManager::SaveAtAndAfter(DB* db) { s = NewFileTraceWriter(Env::Default(), soptions, trace_file_path, &trace_writer); } + if (getenv("CRASH")) assert(false); if (s.ok()) { TraceOptions trace_opts; trace_opts.filter |= kTraceFilterGet; ``` Then ``` mkdir -p /dev/shm/rocksdb_test/rocksdb_crashtest_expected mkdir -p /dev/shm/rocksdb_test/rocksdb_crashtest_whitebox rm -rf /dev/shm/rocksdb_test/rocksdb_crashtest_*/* CRASH=1 ./db_stress --db=/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox --expected_values_dir=/dev/shm/rocksdb_test/rocksdb_crashtest_expected --destroy_db_initially=1 --manual_wal_flush_one_in=1000000 --clear_column_family_one_in=0 --preserve_internal_time_seconds=36000 ./db_stress --db=/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox --expected_values_dir=/dev/shm/rocksdb_test/rocksdb_crashtest_expected --destroy_db_initially=0 --manual_wal_flush_one_in=1000000 --clear_column_family_one_in=0 --preserve_internal_time_seconds=0 ``` Without the fix you get ``` ... DB path: [/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox] (Re-)verified 34 unique IDs Error restoring historical expected values: Corruption: DB is older than any restorable expected state ``` ## 2nd reproducer First apply ``` diff --git a/db_stress_tool/db_stress_test_base.cc b/db_stress_tool/db_stress_test_base.cc index 62ddead7b..f2654980f 100644 --- a/db_stress_tool/db_stress_test_base.cc +++ b/db_stress_tool/db_stress_test_base.cc @@ -1126,6 +1126,7 @@ void StressTest::OperateDb(ThreadState* thread) { // OPERATION write TestPut(thread, write_opts, read_opts, rand_column_families, rand_keys, value); + if (getenv("CRASH")) assert(false); } else if (prob_op < del_bound) { assert(write_bound <= prob_op); // OPERATION delete ``` Then ``` rm -rf /dev/shm/rocksdb_test/rocksdb_crashtest_*/* CRASH=1 ./db_stress --db=/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox --expected_values_dir=/dev/shm/rocksdb_test/rocksdb_crashtest_expected --destroy_db_initially=1 --manual_wal_flush_one_in=1000000 --clear_column_family_one_in=0 --disable_wal=1 --reopen=0 --preserve_internal_time_seconds=0 ./db_stress --db=/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox --expected_values_dir=/dev/shm/rocksdb_test/rocksdb_crashtest_expected --destroy_db_initially=0 --manual_wal_flush_one_in=1000000 --clear_column_family_one_in=0 --disable_wal=1 --reopen=0 --preserve_internal_time_seconds=3600 ``` Without the fix you get ``` DB path: [/dev/shm/rocksdb_test/rocksdb_crashtest_whitebox] (Re-)verified 34 unique IDs db_stress: db_stress_tool/expected_state.cc:380: virtual rocksdb::{anonymous}::ExpectedStateTraceRecordHandler::~ ExpectedStateTraceRecordHandler(): Assertion `IsDone()' failed. ``` Reviewed By: jowlyzhang Differential Revision: D50533346 Pulled By: pdillinger fbshipit-source-id: 1056be45c5b9e537c8c601b28c4b27431a782477 |
||
|
Changyu Bi
|
648fe25bc0 |
Always clear files marked for compaction in ComputeCompactionScore() (#11946)
Summary: We were seeing the following stress test failures: ```LevelCompactionBuilder::PickFileToCompact(const rocksdb::autovector<std::pair<int, rocksdb::FileMetaData*> >&, bool): Assertion `!level_file.second->being_compacted' failed``` This can happen when we are picking a file to be compacted from some files marked for compaction, but that file is already being_compacted. We prevent this by always calling `ComputeCompactionScore()` after we pick a compaction and mark some files as being_compacted. However, if SetOptions() is called to disable marking certain files to be compacted, say `enable_blob_garbage_collection`, we currently just skip the relevant logic in `ComputeCompactionScore()` without clearing the existing files already marked for compaction. This PR fixes this issue by already clearing these files. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11946 Test Plan: existing tests. Reviewed By: akankshamahajan15 Differential Revision: D50232608 Pulled By: cbi42 fbshipit-source-id: 11e4fb5e9d48b0f946ad33b18f7c005f0161f496 |
||
|
Peter Dillinger
|
1d5bddbc58 |
Bootstrap, pre-populate seqno_to_time_mapping (#11922)
Summary: This change has two primary goals (follow-up to https://github.com/facebook/rocksdb/issues/11917, https://github.com/facebook/rocksdb/issues/11920): * Ensure the DB seqno_to_time_mapping has entries that allow us to put a good time lower bound on any writes that happen after setting up preserve/preclude options (either in a new DB, new CF, SetOptions, etc.) and haven't yet aged out of that time window. This allows us to remove a bunch of work-arounds in tests. * For new DBs using preserve/preclude options, automatically reserve some sequence numbers and pre-map them to cover the time span back to the preserve/preclude cut-off time. In the future, this will allow us to import data from another DB by key, value, and write time by assigning an appropriate seqno in this DB for that write time. Note that the pre-population (historical mappings) does not happen if the original options at DB Open time do not have preserve/preclude, so it is recommended to create initial column families at that time with create_missing_column_families, to take advantage of this (future) feature. (Adding these historical mappings after DB Open would risk non-monotonic seqno_to_time_mapping, which is dubious if not dangerous.) Recommended follow-up: * Solve existing race conditions (not memory safety) where parallel operations like CreateColumnFamily or SetDBOptions could leave the wrong setting in effect. * Make SeqnoToTimeMapping more gracefully handle a possible case in which too many mappings are added for the time range of concern. It seems like there could be cases where data is massively excluded from the cold tier because of entries falling off the front of the mapping list (causing GetProximalSeqnoBeforeTime() to return 0). (More investigation needed.) No release note for the minor bug fix because this is still an experimental feature with limited usage. Pull Request resolved: https://github.com/facebook/rocksdb/pull/11922 Test Plan: tests added / updated Reviewed By: jowlyzhang Differential Revision: D49956563 Pulled By: pdillinger fbshipit-source-id: 92beb918c3a298fae9ca8e509717b1067caa1519 |
||
|
Levi Tamasi
|
f42e70bf56 |
Integrate FullMergeV3 into the query and compaction paths (#11858)
Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/11858 The patch builds on https://github.com/facebook/rocksdb/pull/11807 and integrates the `FullMergeV3` API into the read and compaction code paths by updating and extending the logic in `MergeHelper`. In particular, when it comes to merge inputs, the existing `TimedFullMergeWithEntity` is folded into `TimedFullMerge`, since wide-column base values are now handled the same way as plain base values (or no base values for that matter), e.g. they are passed directly to the `MergeOperator`. On the other hand, there is some new differentiation on the output side. Namely, there are now two sets of `TimedFullMerge` variants: one set for contexts where the complete merge result and its value type are needed (used by iterators and compactions), and another set where the merge result is needed in a form determined by the client (used by the point lookup APIs, where e.g. for `Get` we have to extract the value of the default column of any wide-column results). Implementation-wise, the two sets of overloads use different visitors to process the `std::variant` produced by `FullMergeV3`. This has the benefit of eliminating some repeated code e.g. in the point lookup paths, since `TimedFullMerge` now populates the application's result object (`PinnableSlice`/`string` or `PinnableWideColumns`) directly. Moreover, within each set of variants, there is a separate overload for the no base value/plain base value/wide-column base value cases, which eliminates some repeated branching w/r/t to the type of the base value if any. Reviewed By: jaykorean Differential Revision: D49352562 fbshipit-source-id: c2fb9853dba3fbbc6918665bde4195c4ea150a0c |