Summary:
introduce the class WBWIMemTable that implements ReadOnlyMemTable interface with data stored in a WriteBatchWithIndex object.
This PR implements the main read path: Get, MultiGet and Iterator. It only supports Put, Delete and SingleDelete operations for now. All the keys in the WBWIMemTable will be assigned a global sequence number through WBWIMemTable::SetGlobalSequenceNumber().
Planned follow up PRs:
- Create WBWIMemTable with a transaction's WBWI and ingest it into a DB during Transaction::Commit()
- Support for Merge. This will be more complicated since we can have multiple updates with the same user key for Merge.
- Support for other operations like WideColumn and other ReadOnlyMemTable methods.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13123
Test Plan: * A mini-stress test for the read path is added as a new unit test
Reviewed By: jowlyzhang
Differential Revision: D65633419
Pulled By: cbi42
fbshipit-source-id: 0684fe47260b41f51ca39c300eb72ca5bc9c5a3b
Summary:
The bug only happens for transaction db with 2pc. The main change is in `MemTableList::TryInstallMemtableFlushResults`. Before this fix, `memtables_to_flush` may not include all flushed memtables, and it causes the min_log_number for the flush to be incorrect. The code path for calculating min_log_number is `MemTableList::TryInstallMemtableFlushResults() -> GetDBRecoveryEditForObsoletingMemTables() -> PrecomputeMinLogNumberToKeep2PC() -> FindMinPrepLogReferencedByMemTable()`. Inside `FindMinPrepLogReferencedByMemTable()`, we need to exclude all memtables being flushed.
The PR also includes some documentation changes.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13127
Test Plan: added a new unit that fails before this change.
Reviewed By: ltamasi
Differential Revision: D65679270
Pulled By: cbi42
fbshipit-source-id: 611f34bd6ef4cba51f8b54cb1be416887b5a9c5e
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
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
Summary:
This PR adds some missing pieces in order to handle UDT setting toggles while replay WALs for WriteCommitted transactions DB. Specifically, all the transaction markers for no op, prepare, commit, rollback are currently not carried over from the original WriteBatch to the new WriteBatch when there is a timestamp setting difference detected. This PR fills that gap.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13121
Test Plan: Added unit tests
Reviewed By: ltamasi
Differential Revision: D65558801
Pulled By: jowlyzhang
fbshipit-source-id: 8176882637b95f6dc0dad10d7fe21056fa5173d1
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13119
The patch adds a new API `Transaction::GetAttributeGroupIterator` that can be used to create a multi-column-family attribute group iterator over the specified column families, including the data from both the transaction and the underlying database. This API is currently supported for optimistic and write-committed pessimistic transactions.
Reviewed By: jowlyzhang
Differential Revision: D65548324
fbshipit-source-id: 0fb8a22129494770fdba3d6024eef72b3e051136
Summary:
This PR does a few misc things for file ingestion flow:
- Add an invalid argument status return for the combination of `allow_global_seqno = false` and external files' key range overlap in `Prepare` stage.
- Add a MemTables status check for when column family is flushed before `Run`.
- Replace the column family dropped check with an assertion after thread enters the write queue and before it exits the write queue, since dropping column family can only happen in the single threaded write queue too and we already checked once after enter write queue.
- Add an `ExternalSstFileIngestionJob::GetColumnFamilyData` API.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13100
Test Plan: Added unit tests, and stress tested the ingestion path
Reviewed By: hx235
Differential Revision: D65180472
Pulled By: jowlyzhang
fbshipit-source-id: 180145dd248a7507a13a543481b135e5a31ebe2d
Summary:
This assertion could fail if the compaction input files were successfully trivially moved. On re-locking db mutex after successful `LogAndApply`, those files could have been picked up again by some other compactions. And the assertion will fail.
Example failure: P1669529213
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13109
Reviewed By: cbi42
Differential Revision: D65308574
Pulled By: jowlyzhang
fbshipit-source-id: 32413bdc8e28e67a0386c3fe6327bf0b302b9d1d
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
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13113
The patch makes some small improvements related to `allow_unprepared_value` and multi-CF iterators as groundwork for further changes:
1) Similarly to `BaseDeltaIterator`'s base iterator, `MultiCfIteratorImpl` gets passed its child iterators by the client. Even though they are currently guaranteed to have been created using the same read options as each other and the multi-CF iterator, it is safer to not assume this and call `PrepareValue` unconditionally before using any child iterator's `value()` or `columns()`.
2) Again similarly to `BaseDeltaIterator`, it makes sense to pass the entire `ReadOptions` structure to `MultiCfIteratorImpl` in case it turns out to require other read options in the future.
3) The constructors of the various multi-CF iterator classes now take an rvalue reference to a vector of column family handle + `unique_ptr` to child iterator pairs and use move semantics to take ownership of this vector (instead of taking two separate vectors of column family handles and raw iterator pointers).
4) Constructor arguments and the members of `MultiCfIteratorImpl` are reordered for consistency.
Reviewed By: jowlyzhang
Differential Revision: D65407521
fbshipit-source-id: 66c2c689ec8b036740bd98641b7b5c0ff7e777f2
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
Summary:
This PR sets up follow-up changes for large transaction support. It introduces an interface that allows custom implementations of immutable memtables. Since transactions use a WriteBatchWithIndex to index their operations, I plan to add a ReadOnlyMemTable implementation backed by WriteBatchWithIndex. This will enable direct ingestion of WriteBatchWithIndex into the DB as an immutable memtable, bypassing memtable writes for transactions.
The changes mostly involve moving required methods for immutable memtables into the ReadOnlyMemTable class.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13107
Test Plan:
* Existing unit test and stress test.
* Performance: I do not expect this change to cause noticeable performance regressions with LTO and devirtualization. The memtable-only readrandom benchmark shows no consistent performance difference:
```
USE_LTO=1 OPTIMIZE_LEVEL="-O3" DEBUG_LEVEL=0 make -j160 db_bench
(for I in $(seq 1 50);do ./db_bench --benchmarks=fillseq,readrandom --write_buffer_size=268435456 --writes=250000 --num=250000 --reads=500000 --seed=1723056275 2>&1 | grep "readrandom"; done;) | awk '{ t += $5; c++; print } END { print 1.0 * t / c }';
3 runs:
main: 760728, 752727, 739600
PR: 763036, 750696, 739022
```
Reviewed By: jowlyzhang
Differential Revision: D65365062
Pulled By: cbi42
fbshipit-source-id: 40c673ab856b91c65001ef6d6ac04b65286f2882
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
Summary:
An earlier change (b34cef57b7) removed apparently unused functionality where an obsolete blob file number is passed for removal from TableCache, which manages SST files. This was actually relying on broken/fragile abstractions wherein TableCache and BlobFileCache share the same Cache and using the TableCache interface to manipulate blob file caching. No unit test was actually checking for removal of obsolete blob files from the cache (which is somewhat tricky to check and a second order correctness requirement).
Here we fix the leak and add a DEBUG+ASAN-only check in DB::Close() that no obsolete files are lingering in the table/blob file cache.
Fixes https://github.com/facebook/rocksdb/issues/13066
Important follow-up (FIXME): The added check discovered some apparent cases of leaked (into table_cache) SST file readers that would stick around until DB::Close(). Need to enable that check, diagnose, and fix.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13106
Test Plan:
added a check that is called during DB::Close in ASAN builds (to minimize paying the cost in all unit tests). Without the fix, the check failed in at least these tests:
```
db_blob_basic_test DBBlobBasicTest.DynamicallyWarmCacheDuringFlush
db_blob_compaction_test DBBlobCompactionTest.CompactionReadaheadMerge
db_blob_compaction_test DBBlobCompactionTest.MergeBlobWithBase
db_blob_compaction_test DBBlobCompactionTest.CompactionDoNotFillCache
db_blob_compaction_test DBBlobCompactionTest.SkipUntilFilter
db_blob_compaction_test DBBlobCompactionTest.CompactionFilter
db_blob_compaction_test DBBlobCompactionTest.CompactionReadaheadFilter
db_blob_compaction_test DBBlobCompactionTest.CompactionReadaheadGarbageCollection
```
Reviewed By: ltamasi
Differential Revision: D65296123
Pulled By: pdillinger
fbshipit-source-id: 2276d76482beb2c75c9010bc1bec070bb23a24c0
Summary:
Follow ups from https://github.com/facebook/rocksdb/issues/13089
- Take `TableProperties` as `const &` instead of `std::shared_ptr<const TableProperties>`
- Move TableProperties OptionsTypeMap definition to another place for other use outside of Remote Compaction
- Add a test verify that the set of field serializations of TableProperties is complete
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13095
Test Plan:
```
./options_settable_test --gtest_filter="*TablePropertiesAllFieldsSettable*"
```
I also intentionally tried adding a new field to `TableProperties`. If it's missed in the OptionsType map, the test detects the missing bytes set and successfully fails.
Reviewed By: pdillinger
Differential Revision: D65077398
Pulled By: jaykorean
fbshipit-source-id: cf10560eb4a467ca523b11fd64945dbc86ac378f
Summary:
In Remote Compactions, the primary host receives the serialized compaction result from the remote worker and deserializes it to build the output. Unlike Local Compactions, where table properties are built by TableBuilder, in Remote Compactions, these properties were not included in the serialized compaction result. This was likely done intentionally since the table properties are already available in the SST files.
Because TableProperties are not populated as part of CompactionOutputs for remote compactions, we were unable to log the table properties in OnCompactionComplete and use them for verification. We are adding the TableProperties as part of the CompactionServiceOutputFile in this PR. By including the TableProperties in the serialized compaction result, the primary host will be able to access them and verify that they match the values read from the actual SST files.
We are also adding the populating `format_version` in table_properties of in TableBuilder. This has not been a big issue because the `format_version` is written to the SST files directly from `TableOptions.format_version`. When loaded from the SST files, it's populated directly by reading from the MetaBlock. This info has only been missing in the TableBuilder's Rep.props.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13089
Test Plan:
```
./compaction_job_test
```
```
./compaction_service_test
```
Reviewed By: pdillinger
Differential Revision: D64878740
Pulled By: jaykorean
fbshipit-source-id: b6f2fdce851e6477ecb4dd5a87cdc62e176b746b
Summary:
Fix a longstanding race condition in SetOptions for `block_based_table_factory` options. The fix is mostly described in new, unified `TableFactoryParseFn()` in `cf_options.cc`. Also in this PR:
* Adds a virtual `Clone()` function to TableFactory
* To avoid behavioral hiccups with `SetOptions`, make the "hidden state" of `BlockBasedTableFactory` shared between an original and a clone. For example, `TailPrefetchStats`
* `Configurable` was allowed to be copied but was not safe to do so, because the copy would have and use pointers into object it was copied from (!!!). This has been fixed using relative instead of absolute pointers, though it's still technically relying on undefined behavior (consistent object layout for non-standard-layout types).
For future follow-up:
* Deny SetOptions on block cache options (dubious and not yet made safe with proper shared_ptr handling)
Fixes https://github.com/facebook/rocksdb/issues/10079
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13082
Test Plan:
added to unit tests and crash test
Ran TSAN blackbox crashtest for hours with options to amplify potential race (see https://github.com/facebook/rocksdb/issues/10079)
Reviewed By: cbi42
Differential Revision: D64947243
Pulled By: pdillinger
fbshipit-source-id: 8390299149f50e2a2b39a5247680f2637edb23c8
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
Summary:
we currently record write operations to tracer before checking callback in PipelinedWriteImpl and WriteImplWALOnly. For optimistic transaction DB, this means that an operation can be recorded to tracer even when it's not written to DB or WAL. I suspect this is the reason some of our optimistic txn crash test is failing. The evidence is that the trace contains some duplicated entry and has more entries compared to the corresponding entry in WAL. This PR moves the tracer logic to be after checking callback status.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13088
Test Plan: monitor crash test.
Reviewed By: hx235
Differential Revision: D64711753
Pulled By: cbi42
fbshipit-source-id: 55fd1223538ec6294ce84a957c306d3d9d91df5f
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13079
The patch adds support for the new read option `allow_unprepared_value` to the multi-column-family iterators `CoalescingIterator` and `AttributeGroupIterator`. When this option is set, these iterators populate their value (`value()` + `columns()` or `attribute_groups()`) in an on-demand fashion when `PrepareValue()` is called. Calling `PrepareValue()` on the child iterators is similarly deferred until `PrepareValue()` is called on the main iterator.
Reviewed By: jowlyzhang
Differential Revision: D64570587
fbshipit-source-id: 783c8d408ad10074417dabca7b82c5e1fe5cab36
Summary:
# Summary
There was a [test failure](https://github.com/facebook/rocksdb/actions/runs/11381731053/job/31663774089?fbclid=IwZXh0bgNhZW0CMTEAAR0YJVdnkKUhN15RJQrLsvicxqzReS6y4A14VFQbWu-81XJsSsyNepXAr2c_aem_JyQqNdtpeKFSA6CjlD-pDg) from uninit value in the CompactionServiceInput
```
[ RUN ] CompactionJobTest.InputSerialization
==79945== Use of uninitialised value of size 8
==79945== at 0x58EA69B: _itoa_word (_itoa.c:179)
==79945== by 0x5906574: __vfprintf_internal (vfprintf-internal.c:1687)
==79945== by 0x591AF99: __vsnprintf_internal (vsnprintf.c:114)
==79945== by 0x1654AE: std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > __gnu_cxx::__to_xstring<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, char>(int (*)(char*, unsigned long, char const*, __va_list_tag*), unsigned long, char const*, ...) (string_conversions.h:111)
==79945== by 0x5126C65: to_string (basic_string.h:6568)
==79945== by 0x5126C65: rocksdb::SerializeSingleOptionHelper(void const*, rocksdb::OptionType, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >*) (options_helper.cc:541)
==79945== by 0x512718B: rocksdb::OptionTypeInfo::Serialize(rocksdb::ConfigOptions const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, void const*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >*) const (options_helper.cc:1084)
```
This was due to `options_file_number` value not set in the unit test. However, this value is guaranteed to be set in the normal path. It was just missing in the test path. Setting the 0 as the default value for uninitialized fields in the `CompactionServiceInput` and `CompactionServiceResult` for now.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13080
Test Plan: Existing tests should be sufficient
Reviewed By: cbi42
Differential Revision: D64573567
Pulled By: jaykorean
fbshipit-source-id: 7843a951770c74445620623d069a52ba93ad94d5
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
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13076
The patch makes it possible to construct an `IteratorAttributeGroup` using an `AttributeGroup` instance, and implements `operator==` / `operator!=` for these two classes consistently. It also makes some minor improvements in the related test suites `CoalescingIteratorTest` and `AttributeGroupIteratorTest`.
Reviewed By: jaykorean
Differential Revision: D64510653
fbshipit-source-id: 95d3340168fa3b34e7ef534587b19131f0a27fb7
Summary:
Compaction stats code is not so straightforward to understand. Here's a bit of context for this PR and why this change was made.
- **CompactionStats (compaction_stats_.stats):** Internal stats about the compaction used for logging and public metrics.
- **CompactionJobStats (compaction_job_stats_)**: The public stats at job level. It's part of Compaction event listener and included in the CompactionResult.
- **CompactionOutputsStats**: output stats only. resides in CompactionOutputs. It gets aggregated toward the CompactionStats (internal stats).
The internal stats, `compaction_stats_.stats`, has the output information recorded from the compaction iterator, but it does not have any input information (input records, input output files) until `UpdateCompactionStats()` gets called. We cannot simply call `UpdateCompactionStats()` to fill in the input information in the remote compaction (which is a subcompaction of the primary host's compaction) because the `compaction->inputs()` have the full list of input files and `UpdateCompactionStats()` takes the entire list of records in all files. `num_input_records` gets double-counted if multiple sub-compactions are submitted to the remote worker.
The job level stats (in the case of remote compaction, it's subcompaction level stat), `compaction_job_stats_`, has the correct input records, but has no output information. We can use `UpdateCompactionJobStats(compaction_stats_.stats)` to set the output information (num_output_records, num_output_files, etc.) from the `compaction_stats_.stats`, but it also sets all other fields including the input information which sets all back to 0.
Therefore, we are overriding `UpdateCompactionJobStats()` in remote worker only to update job level stats, `compaction_job_stats_`, with output information of the internal stats.
Baiscally, we are merging the aggregated output info from the internal stats and aggregated input info from the compaction job stats.
In this PR we are also fixing how we are setting `is_remote_compaction` in CompactionJobStats.
- OnCompactionBegin event, if options.compaction_service is set, `is_remote_compaction=true` for all compactions except for trivial moves
- OnCompactionCompleted event, if any of the sub_compactions were done remotely, compaction level stats's `is_remote_compaction` will be true
Other minor changes
- num_output_records is already available in CompactionJobStats. No need to store separately in CompactionResult.
- total_bytes is not needed.
- Renamed `SubcompactionState::AggregateCompactionStats()` to `SubcompactionState::AggregateCompactionOutputStats()` to make it clear that it's only aggregating output stats.
- Renamed `SetTotalBytes()` to `AddBytesWritten()` to make it more clear that it's adding total written bytes from the compaction output.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13071
Test Plan:
Unit Tests added and updated
```
./compaction_service_test
```
Reviewed By: anand1976
Differential Revision: D64479657
Pulled By: jaykorean
fbshipit-source-id: a7a776a00dc718abae95d856b661bcbafd3b0ed5
Summary:
Some users want to check if a file in their DB was created by SstFileWriter and ingested into hte DB. Files created by SstFileWriter records additional table properties cbebbad7d9/table/sst_file_writer_collectors.h (L17-L21). These are not exposed so I'm adding an API to SstFileWriter to check for them.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13072
Test Plan: added some assertions.
Reviewed By: jowlyzhang
Differential Revision: D64411518
Pulled By: cbi42
fbshipit-source-id: 279bfef48615aa6f78287b643d8445a1471e7f07
Summary:
add `IngestExternalFileOptions::fill_cache` to allow users to ingest files without loading index/filter/data and other blocks into block cache during file ingestion. This can be useful when users are ingesting files into a CF that is not available to readers yet.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13067
Test Plan:
* unit test: `ExternalSSTFileTest.NoBlockCache`
* ran one round of crash test with fill_cache disabled: `python3 ./tools/db_crashtest.py --simple blackbox --ops_per_thread=1000000 --interval=30 --ingest_external_file_one_in=200 --level0_stop_writes_trigger=200 --level0_slowdown_writes_trigger=100 --sync_fault_injection=0 --disable_wal=0 --manual_wal_flush_one_in=0`
Reviewed By: jowlyzhang
Differential Revision: D64356424
Pulled By: cbi42
fbshipit-source-id: b380c26f5987238e1ed7d42ceef0390cfaa0b8e2
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13069
Currently, when using range scans with BlobDB, the iterator logic eagerly loads values from blob files when landing on a new entry. This can be wasteful in use cases where the values associated with some keys in the range are not used by the application. The patch introduces a new read option `allow_unprepared_value`; when specified, this option results in the above eager loading getting bypassed. Values needed by the application can be then loaded on an on-demand basis by calling the new iterator API `PrepareValue`. Note that currently, only regular single-CF iterators are supported; multi-CF iterators and transactions will be extended in later PRs.
Reviewed By: jowlyzhang
Differential Revision: D64360723
fbshipit-source-id: ee55502fa15dcb307a984922b9afc9d9da15d6e1
Summary:
In https://github.com/facebook/rocksdb/issues/13025 , we made a change to load the latest options file in the remote worker instead of serializing the entire set of options.
That was done under assumption that OPTIONS file do not get purged often. While testing, we learned that this happens more often than we want it to be, so we want to prevent the OPTIONS file from getting purged anytime between when the remote compaction is scheduled and the option is loaded in the remote worker.
Like how we are protecting new SST files from getting purged using `min_pending_output`, we are doing the same by keeping track of `min_options_file_number`. Any OPTIONS file with number greater than `min_options_file_number` will be protected from getting purged. Just like `min_pending_output`, `min_options_file_number` gets bumped when the compaction is done. This is only applicable when `options.compaction_service` is set.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13074
Test Plan:
```
./compaction_service_test --gtest_filter="*PreservedOptionsLocalCompaction*"
./compaction_service_test --gtest_filter="*PreservedOptionsRemoteCompaction*"
```
Reviewed By: anand1976
Differential Revision: D64433795
Pulled By: jaykorean
fbshipit-source-id: 0d902773f0909d9481dec40abf0b4c54ce5e86b2
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13075
The patch simplifies the iteration logic in `MultiCFIteratorImpl::{Advance,Populate}Iterator` a bit and adds some assertions to uniformly enforce the invariant that any iterators currently on the heap should be valid and have an OK status.
Reviewed By: jaykorean
Differential Revision: D64429566
fbshipit-source-id: 36bc22465285b670f859692a048e10f21df7da7a
Summary:
This PR assigns levels to files in separate batches if they overlap. This approach can potentially assign external files to lower levels.
In the prepare stage, if the input files' key range overlaps themselves, we divide them up in the user specified order into multiple batches. Where the files in the same batch do not overlap with each other, but key range could overlap between batches. If the input files' key range don't overlap, they always just make one default batch.
During the level assignment stage, we assign levels to files one batch after another. It's guaranteed that files within one batch are not overlapping, we assign level to each file one after another. If the previous batch's uppermost level is specified, all files in this batch will be assigned to levels that are higher than that level. The uppermost level used by this batch of files is also tracked, so that it can be used by the next batch.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13064
Test Plan:
Updated test and added new test
Manually stress tested
Reviewed By: cbi42
Differential Revision: D64428373
Pulled By: jowlyzhang
fbshipit-source-id: 5aeff125c14094c87cc50088505010dfd2da3d6e
Summary:
- When `FileChecksumGenFactory` is set, include the `file_checksum` and `file_checksum_func_name` in the output file metadata
- ~~In Remote Compaction, try opening the output files in the temporary directory to do a quick sanity check before returning the result with status.~~
- After offline discussion, we decided to rely on Primary's existing Compaction flow to sanity check the output files. If the output file is corrupted, we will still be able to catch it and not installing it even after renaming them to cf_paths. The corrupted file in the cf_path won't be added to the MANIFEST and will be purged as part of the next `PurgeObsoleteFiles()` call.
- Unit Test has been added to validate above.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13060
Test Plan:
Unit test added
```
./compaction_service_test --gtest_filter="*CorruptedOutput*"
./compaction_service_test --gtest_filter="*TruncatedOutput*"
./compaction_service_test --gtest_filter="*CustomFileChecksum*"
./compaction_job_test --gtest_filter="*ResultSerialization*"
```
Reviewed By: cbi42
Differential Revision: D64189645
Pulled By: jaykorean
fbshipit-source-id: 6cf28720169c960c80df257806bfee3c0d177159
Summary:
In theory, there should be no danger in mutability, as table
builders and readers work from copies of BlockBasedTableOptions.
However, there is currently an unresolved read-write race that
affecting SetOptions on BBTO fields. This should be generally
acceptable for non-pointer options of 64 bits or less, but a fix
is needed to make it mutability general here. See
https://github.com/facebook/rocksdb/issues/10079
This change systematically sets all of those "simple" options (and future
such options) as mutable. (Resurrecting this PR perhaps preferable to
proposed https://github.com/facebook/rocksdb/issues/13063)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10021
Test Plan: Some unit test updates. XXX comment added to stress test code
Reviewed By: cbi42
Differential Revision: D64360967
Pulled By: pdillinger
fbshipit-source-id: ff220fa778331852fe331b42b76ac4adfcd2d760
Summary:
When user-defined timestamps are not persisted, currently we replace the actual timestamp with min timestamp after an entry is output from compaction iterator. Compaction iterator won't be able to help with removing stale entries this way. This PR adds a wrapper iterator `TimestampStrippingIterator` for `MemTableIterator` that does the min timestamp replacement at the memtable iteration step. It is used by flush and can help remove stale entries from landing in L0 files.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13035
Test Plan: Added unit test
Reviewed By: pdillinger, cbi42
Differential Revision: D63423682
Pulled By: jowlyzhang
fbshipit-source-id: 087dcc9cee97b9ea51b8d2b88dc91c2984d54e55
Summary:
When the input files are not overlapping, a.k.a `files_overlap_=false`, it's best to assign them to non L0 levels so that they are not one sorted run each. This can be done regardless of compaction style being leveled or universal without any side effects.
Just my guessing, this special handling may be there because universal compaction used to have an invariant that sequence number on higher levels should not be smaller than sequence number in lower levels. File ingestion used to try to keep up to that promise by doing "sequence number stealing" from the to be assigned level. However, that invariant is no longer true after deletion triggered compaction is added for universal compaction, and we also removed the sequence stealing logic from file ingestion.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13059
Test Plan: Updated existing tests
Reviewed By: cbi42
Differential Revision: D64220100
Pulled By: jowlyzhang
fbshipit-source-id: 70a83afba7f4c52d502c393844e6b3273d5cf628
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13061
As groundwork for further changes, the patch refactors the BlobDB-related parts of `DBIter` by 1) introducing a new internal helper class `DBIter::BlobReader` that encapsulates all members needed to retrieve a blob value (namely, `Version` and the `ReadOptions` fields) and 2) factoring out and cleaning up some duplicate logic related to resolving blob references in the non-Merge (see `SetValueAndColumnsFromBlob`) and Merge (see `MergeWithBlobBaseValue`) cases.
Reviewed By: jowlyzhang
Differential Revision: D64078099
fbshipit-source-id: 22d5bd93e6e5be5cc9ecf6c4ee6954f2eb016aff
Summary:
**Context/Summary:**
A part of this test is to verify compression conditionally happens depending on the shape of the LSM when `options.level_compaction_dynamic_level_bytes = true;`. It uses the total file size to determine whether compression has happened or not. This involves some hard-coded math hard to understand. This PR replaces those with statistics that directly shows whether compression has happened or not.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13044
Test Plan: Existing test
Reviewed By: jaykorean
Differential Revision: D63666361
Pulled By: hx235
fbshipit-source-id: 8c9b1bea9b06ff1e3ed95c576aec6705159af137
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
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
Summary:
a small CF can trigger parallel compaction that applies to the entire DB. This is because the bottommost file size of a small CF can be too small compared to l0 files when a l0->lbase compaction happens. We prevent this by requiring some minimum on the compaction debt.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13054
Test Plan: updated unit test.
Reviewed By: hx235
Differential Revision: D63861042
Pulled By: cbi42
fbshipit-source-id: 43bbf327988ef0ef912cd2fc700e3d096a8d2c18
Summary:
This PR added some optimizations for the per key handling for SST file for the user-defined timestamps in Memtable only feature. CPU profiling shows this part is a big culprit for regression. This optimization saves some string construction/destruction/appending/copying. vector operations like reserve/emplace_back.
When iterating keys in a block, we need to copy some shared bytes from previous key, put it together with the non shared bytes and find a right location to pad the min timestamp. Previously, we create a tmp local string buffer to first construct the key from its pieces, and then copying this local string's content into `IterKey`'s buffer. To avoid having this local string and to avoid this extra copy. Instead of piecing together the key in a local string first, we just track all the pieces that make this key in a reused Slice array. And then copy the pieces in order into `IterKey`'s buffer. Since the previous key should be kept intact while we are copying some shared bytes from it, we added a secondary buffer in `IterKey` and alternate between primary buffer and secondary buffer.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13031
Test Plan: Existing tests.
Reviewed By: ltamasi
Differential Revision: D63416531
Pulled By: jowlyzhang
fbshipit-source-id: 9819b0e02301a2dbc90621b2fe4f651bc912113c
Summary:
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13052
Currently, `MultiCfIteratorImpl` uses `std::function`s for `reset_func_` and `populate_func_`, which uses type erasure and has a performance overhead. The patch turns `MultiCfIteratorImpl` into a template that takes the two function object types as template parameters, and changes `AttributeGroupIteratorImpl` and `CoalescingIterator` so they pass in function objects of named types (as opposed to lambdas).
Reviewed By: jaykorean
Differential Revision: D63802598
fbshipit-source-id: e202f6d80c9054335e5b2571051a67a9e012c2d0
Summary:
This PR makes file ingestion job's flush wait a bit further until the SuperVersion is also updated. This is necessary since follow up operations will use the current SuperVersion to do range overlapping check and level assignment.
In debug mode, file ingestion job's second `NeedsFlush` call could have been invoked when the memtables are flushed but the SuperVersion hasn't been updated yet, triggering the assertion.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13045
Test Plan:
Existing tests
Manually stress tested
Reviewed By: cbi42
Differential Revision: D63671151
Pulled By: jowlyzhang
fbshipit-source-id: 95a169e58a7e59f6dd4125e7296e9060fe4c63a7
Summary:
Add the following to the `CompactionServiceJobInfo`
- compaction_reason
- is_full_compaction
- is_manual_compaction
- bottommost_level
Added `is_remote_compaction` to the `CompactionJobStats` and set initial values to avoid UB for uninitialized values.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13029
Test Plan:
```
./compaction_service_test --gtest_filter="*CompactionInfo*"
```
Reviewed By: anand1976
Differential Revision: D63322878
Pulled By: jaykorean
fbshipit-source-id: f02a66ca45e660b9d354a43837d8ec6beb7621fb
Summary:
With some new use cases onboarding to prefix extractors/seek/filters, one of the risks is existing iterator code, e.g. for maintenance tasks, being unintentionally subject to prefix seek semantics. This is a longstanding known design flaw with prefix seek, and `prefix_same_as_start` and `auto_prefix_mode` were steps in the direction of making that obsolete. However, we can't just immediately set `total_order_seek` to true by default, because that would impact so much code instantly.
Here we add a new DB option, `prefix_seek_opt_in_only` that basically allows users to transition to the future behavior when they are ready. When set to true, all iterators will be treated as if `total_order_seek=true` and then the only ways to get prefix seek semantics are with `prefix_same_as_start` or `auto_prefix_mode`.
Related fixes / changes:
* Make sure that `prefix_same_as_start` and `auto_prefix_mode` are compatible with (or override) `total_order_seek` (depending on your interpretation).
* Fix a bug in which a new iterator after dynamically changing the prefix extractor might mix different prefix semantics between memtable and SSTs. Both should use the latest extractor semantics, which means iterators ignoring memtable prefix filters with an old extractor. And that means passing the latest prefix extractor to new memtable iterators that might use prefix seek. (Without the fix, the test added for this fails in many ways.)
Suggested follow-up:
* Investigate a FIXME where a MergeIteratorBuilder is created in db_impl.cc. No unit test detects a change in value that should impact correctness.
* Make memtable prefix bloom compatible with `auto_prefix_mode`, which might require involving the memtablereps because we don't know at iterator creation time (only seek time) whether an auto_prefix_mode seek will be a prefix seek.
* Add `prefix_same_as_start` testing to db_stress
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13026
Test Plan:
tests updated, added. Add combination of `total_order_seek=true` and `auto_prefix_mode=true` to stress test. Ran `make blackbox_crash_test` for a long while.
Manually ran tests with `prefix_seek_opt_in_only=true` as default, looking for unexpected issues. I inspected most of the results and migrated many tests to be ready for such a change (but not all).
Reviewed By: ltamasi
Differential Revision: D63147378
Pulled By: pdillinger
fbshipit-source-id: 1f4477b730683d43b4be7e933338583702d3c25e
Summary:
We've been serializing and deserializing DBOptions and CFOptions (and other CF into) as part of `CompactionServiceInput`. These are all readily available in the OPTIONS file and the remote worker can read the OPTIONS file to obtain the same information. This helps reducing the size of payload significantly.
In a very rare scenario if the OPTIONS file is purged due to options change by primary host at the same time while the remote host is loading the latest options, it may fail. In this case, we just retry once.
This also solves the problem where we had to open the default CF with the CFOption from another CF if the remote compaction is for a non-default column family. (TODO comment in /db_impl_secondary.cc)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/13025
Test Plan:
Unit Tests
```
./compaction_service_test
```
```
./compaction_job_test
```
Also tested with Meta's internal Offload Infra
Reviewed By: anand1976, cbi42
Differential Revision: D63100109
Pulled By: jaykorean
fbshipit-source-id: b7162695e31e2c5a920daa7f432842163a5b156d
Changyu Bi