Summary:
Since a RangeDelAggregator is created for each read request, these heap-allocating member variables were consuming significant CPU (~3% total) which slowed down request throughput. The map and pinning manager are only necessary when range deletions exist, so we can defer their initialization until the first range deletion is encountered. Currently lazy initialization is done for reads only since reads pass us a single snapshot, which is easier to store on the stack for later insertion into the map than the vector passed to us by flush or compaction.
Note the Arena member variable is still expensive, I will figure out what to do with it in a subsequent diff. It cannot be lazily initialized because we currently use this arena even to allocate empty iterators, which is necessary even when no range deletions exist.
Closes https://github.com/facebook/rocksdb/pull/1539
Differential Revision: D4203488
Pulled By: ajkr
fbshipit-source-id: 3b36279
Summary:
these functions were too complicated to change with exit points everywhere, so refactored them.
btw, please review urgently, this is a prereq to fix the 5.0 perf regression
Closes https://github.com/facebook/rocksdb/pull/1534
Differential Revision: D4198972
Pulled By: ajkr
fbshipit-source-id: 04ebfb7
Summary:
Remove the ticker count because:
* Having to reset the ticker count in WriteImpl is ineffiecent;
* It doesn't make sense to have it as a ticker count if multiple db
instance share a statistics object.
Closes https://github.com/facebook/rocksdb/pull/1531
Differential Revision: D4194442
Pulled By: yiwu-arbug
fbshipit-source-id: e2110a9
Summary:
pinned_iters_mgr_ pins iterators allocated with arena_, so we should order the
instance variable declarations such that the pinned iterators have their destructors
executed before the arena is destroyed.
Closes https://github.com/facebook/rocksdb/pull/1528
Differential Revision: D4191984
Pulled By: ajkr
fbshipit-source-id: 1386f20
Summary:
It is hard to measure acutal memory usage by std containers. Even
providing a custom allocator will miss count some of the usage. Here we
only do a wild guess on its memory usage.
Closes https://github.com/facebook/rocksdb/pull/1511
Differential Revision: D4179945
Pulled By: yiwu-arbug
fbshipit-source-id: 32ab929
Summary:
Previously we used TableCache::NewIterator() for multiple purposes (data
block iterator and range deletion iterator), and returned non-ok status in
the data block iterator. In one case where the caller only used the range
deletion block iterator (9e7cf3469b/db/version_set.cc (L965-L973)),
we didn't check/free the data block iterator containing non-ok status, which
caused a valgrind error.
So, this diff decouples creation of data block and range deletion block iterators,
and updates the callers accordingly. Both functions can return non-ok status
in an InternalIterator. Since the non-ok status is returned in an iterator that the
callers will definitely use, it should be more usable/less error-prone.
Closes https://github.com/facebook/rocksdb/pull/1513
Differential Revision: D4181423
Pulled By: ajkr
fbshipit-source-id: 835b8f5
Summary:
Return an error from DeleteRange() (or Write() if the user is using the
low-level WriteBatch API) if an unsupported table type is configured.
Closes https://github.com/facebook/rocksdb/pull/1519
Differential Revision: D4185933
Pulled By: ajkr
fbshipit-source-id: abcdf84
Summary:
It's possible that we set min_write_buffer_number_to_merge to 0.
This should never happen
Closes https://github.com/facebook/rocksdb/pull/1515
Differential Revision: D4183356
Pulled By: yiwu-arbug
fbshipit-source-id: c9d39d7
Summary:
Adjusted AddToBuilder() to take lower_bound and upper_bound, which serve two purposes: (1) only range deletions overlapping with the interval [lower_bound, upper_bound) will be added to the output file, and (2) the output file's boundaries will not be extended before lower_bound or after upper_bound. Our computation of lower_bound/upper_bound consider both subcompaction boundaries and previous/next files within the subcompaction.
Test cases are here (level subcompactions: https://gist.github.com/ajkr/63c7eae3e9667c5ebdc0a7efb74ac332, and universal subcompactions: https://gist.github.com/ajkr/5a62af77c4ebe4052a1955c496d51fdb) but can't be included in this diff as they depend on committing the API first. They fail before this change and pass after.
Closes https://github.com/facebook/rocksdb/pull/1501
Reviewed By: yhchiang
Differential Revision: D4171685
Pulled By: ajkr
fbshipit-source-id: ee99db8
Summary:
This conditional should only open a new file that's dedicated to range deletions when it's the sole output of the subcompaction. Previously, we created such a file whenever the table builder was nullptr, which would've also been the case whenever the CompactionIterator's final key coincided with the final output table becoming full.
Closes https://github.com/facebook/rocksdb/pull/1507
Differential Revision: D4174613
Pulled By: ajkr
fbshipit-source-id: 9ffacea
Summary:
This makes it easier to implement future optimizations like range collapsing.
Closes https://github.com/facebook/rocksdb/pull/1504
Differential Revision: D4172214
Pulled By: ajkr
fbshipit-source-id: ac4942f
Summary:
Currently our skip-list have an optimization to speedup sequential
inserts from a single stream, by remembering the last insert position.
We extend the idea to support sequential inserts from multiple streams,
and even tolerate small reordering wihtin each stream.
This PR is the interface part adding the following:
- Add `memtable_insert_prefix_extractor` to allow specifying prefix for each key.
- Add `InsertWithHint()` interface to memtable, to allow underlying
implementation to return a hint of insert position, which can be later
pass back to optimize inserts.
- Memtable will maintain a map from prefix to hints and pass the hint
via `InsertWithHint()` if `memtable_insert_prefix_extractor` is non-null.
Closes https://github.com/facebook/rocksdb/pull/1419
Differential Revision: D4079367
Pulled By: yiwu-arbug
fbshipit-source-id: 3555326
Summary:
Implement a insert hint into skip-list to hint insert position. This is
to optimize for the write workload where there are multiple stream of
sequential writes. For example, there is a stream of keys of a1, a2,
a3... but also b1, b2, b2... Each stream are not neccessary strictly
sequential, but can get reorder a little bit. User can specify a prefix
extractor and the `SkipListRep` can thus maintan a hint for each of the
stream for fast insert into memtable.
This is the internal implementation part. See #1419 for the interface part.
See inline comments for details.
Closes https://github.com/facebook/rocksdb/pull/1449
Differential Revision: D4106781
Pulled By: yiwu-arbug
fbshipit-source-id: f4d48c4
Summary:
If user did not call SstFileWriter::Finish() or called Finish() but it failed.
We need to abandon the builder, to avoid destructing it while it's open
Closes https://github.com/facebook/rocksdb/pull/1502
Differential Revision: D4171660
Pulled By: IslamAbdelRahman
fbshipit-source-id: ab6f434
Summary:
Currently the compaction stats are printed to stdout. We want to export the compaction stats in a map format so that the upper layer apps (e.g., MySQL) could present
the stats in any format required by the them.
Closes https://github.com/facebook/rocksdb/pull/1477
Differential Revision: D4149836
Pulled By: maysamyabandeh
fbshipit-source-id: b3df19f
Summary:
This is a previous fix that has a typo
Closes https://github.com/facebook/rocksdb/pull/1487
Differential Revision: D4157381
Pulled By: lightmark
fbshipit-source-id: f079be8
Summary:
Originally sequence ids were calculated, in recovery, based off of the first seqid found if the first log recovered. The working seqid was then incremented from that value based on every insertion that took place. This was faulty because of the potential for missing log files or inserts that skipped the WAL. The current recovery scheme grabs sequence from current recovering batch and increments using memtableinserter to track how many actual inserts take place. This works for 2PC batches as well scenarios where some logs are missing or inserts that skip the WAL.
Closes https://github.com/facebook/rocksdb/pull/1486
Differential Revision: D4156064
Pulled By: reidHoruff
fbshipit-source-id: a6da8d9
Summary:
This fixes a correctness issue where ranges with same begin key would overwrite each other.
This diff uses InternalKey as TombstoneMap's key such that all tombstones have unique keys even when their start keys overlap. We also update TombstoneMap to use an internal key comparator.
End-to-end tests pass and are here (https://gist.github.com/ajkr/851ffe4c1b8a15a68d33025be190a7d9) but cannot be included yet since the DeleteRange() API is yet to be checked in. Note both tests failed before this fix.
Closes https://github.com/facebook/rocksdb/pull/1484
Differential Revision: D4155248
Pulled By: ajkr
fbshipit-source-id: 304b4b9
Summary:
Fix the following RocksDB Lite build failure in c_test.cc
db/c_test.c:1051:3: error: implicit declaration of function 'fprintf' is invalid in C99 [-Werror,-Wimplicit-function-declaration]
fprintf(stderr, "SKIPPED\n");
^
db/c_test.c:1051:3: error: declaration of built-in function 'fprintf' requires inclusion of the header <stdio.h> [-Werror,-Wbuiltin-requires-header]
db/c_test.c:1051:11: error: use of undeclared identifier 'stderr'
fprintf(stderr, "SKIPPED\n");
^
3 errors generated.
Closes https://github.com/facebook/rocksdb/pull/1479
Differential Revision: D4151160
Pulled By: yhchiang
fbshipit-source-id: a471a30
Summary:
copied from: 5ebfd2623a
Opening existing RocksDB attempts recovery from log files, which uses
wrong sequence number to create the memtable. This is a regression
introduced in change a400336.
This change includes a test demonstrating the problem, without the fix
the test fails with "Operation failed. Try again.: Transaction could not
check for conflicts for operation at SequenceNumber 1 as the MemTable
only contains changes newer than SequenceNumber 2. Increasing the value
of the max_write_buffer_number_to_maintain option could reduce the
frequency of this error"
This change is a joint effort by Peter 'Stig' Edwards thatsafunnyname
and me.
Closes https://github.com/facebook/rocksdb/pull/1458
Differential Revision: D4143791
Pulled By: reidHoruff
fbshipit-source-id: 5a25033
Summary:
A deadlock is possible if this happen
(1) Writer thread is stopped because it's waiting for compaction to finish
(2) Compaction is waiting for current IngestExternalFile() calls to finish
(3) IngestExternalFile() is waiting to be able to acquire the writer thread
(4) WriterThread is held by stopped writes that are waiting for compactions to finish
This patch fix the issue by not incrementing num_running_ingest_file_ except when we acquire the writer thread.
This patch include a unittest to reproduce the described scenario
Closes https://github.com/facebook/rocksdb/pull/1480
Differential Revision: D4151646
Pulled By: IslamAbdelRahman
fbshipit-source-id: 09b39db
Summary:
In ForwardIterator::SeekInternal(), we may end up passing empty Slice representing an internal key to InternalKeyComparator::Compare.
and when we try to extract the user key from this empty Slice, we will create a slice with size = 0 - 8 ( which will overflow and cause us to read invalid memory as well )
Scenarios to reproduce these issues are in the unit tests
Closes https://github.com/facebook/rocksdb/pull/1467
Differential Revision: D4136660
Pulled By: lightmark
fbshipit-source-id: 151e128
Summary:
Note: reviewed in https://reviews.facebook.net/D65115
- DBIter maintains a range tombstone accumulator. We don't cleanup obsolete tombstones yet, so if the user seeks back and forth, the same tombstones would be added to the accumulator multiple times.
- DBImpl::NewInternalIterator() (used to make DBIter's underlying iterator) adds memtable/L0 range tombstones, L1+ range tombstones are added on-demand during NewSecondaryIterator() (see D62205)
- DBIter uses ShouldDelete() when advancing to check whether keys are covered by range tombstones
Closes https://github.com/facebook/rocksdb/pull/1464
Differential Revision: D4131753
Pulled By: ajkr
fbshipit-source-id: be86559
Summary:
During Get()/MultiGet(), build up a RangeDelAggregator with range
tombstones as we search through live memtable, immutable memtables, and
SST files. This aggregator is then used by memtable.cc's SaveValue() and
GetContext::SaveValue() to check whether keys are covered.
added tests for Get on memtables/files; end-to-end tests mainly in https://reviews.facebook.net/D64761
Closes https://github.com/facebook/rocksdb/pull/1456
Differential Revision: D4111271
Pulled By: ajkr
fbshipit-source-id: 6e388d4
Summary:
IngestExternalFile is very useful when doing bulk load. This pr expose this API to c so many bindings can benefit from it too.
Closes https://github.com/facebook/rocksdb/pull/1454
Differential Revision: D4113420
Pulled By: yiwu-arbug
fbshipit-source-id: 307c6ae
Summary:
Changed BuildTable() (used for flush) to (1) add range
tombstones to the aggregator, which is used by CompactionIterator to
determine which keys can be removed; and (2) add aggregator's range
tombstones to the table that is output for the flush.
Closes https://github.com/facebook/rocksdb/pull/1438
Differential Revision: D4100025
Pulled By: ajkr
fbshipit-source-id: cb01a70
Summary:
Passing std::atomic<uint64_t> variables to ASSERT_EQ()
results in compile error
C2718 'const T1': actual parameter with requested alignment of 8 won't be aligned.
VS2015 defines std::atomic as specially aligned type ( with 'alignas'),
however the compiler does not like declspec(align)ed function
arguments.
Worked around by casting std::atomic<uint64_t> types to uint64_t
in ASSERT_EQ.
Closes https://github.com/facebook/rocksdb/pull/1450
Differential Revision: D4106788
Pulled By: yiwu-arbug
fbshipit-source-id: 5fb42c3
Summary:
Currently the compression suppport and fast CRC support information is printed as info level. They should be in the same level as options, which is header level.
Also add ZSTD to this printing.
Closes https://github.com/facebook/rocksdb/pull/1448
Differential Revision: D4106608
Pulled By: yiwu-arbug
fbshipit-source-id: cb9a076
Summary:
DB Stats now are truncated if there are too many CFs. Extend the buffer size to allow more to be printed out. Also, separate out malloc to another log line.
Closes https://github.com/facebook/rocksdb/pull/1439
Differential Revision: D4100943
Pulled By: yiwu-arbug
fbshipit-source-id: 79f7218
Summary:
The current 10 millisecond waiting for test results may not be sufficient in some test environments. Increase it to 60 seconds and check the results for every 1 milliseond.
Already reviewed: https://reviews.facebook.net/D65457
Closes https://github.com/facebook/rocksdb/pull/1437
Differential Revision: D4099443
Pulled By: siying
fbshipit-source-id: cf1f205
Summary:
A bug that tailingIterator->Seek(target) skips records.
I think the bug is in the SeekInternal starting at lines 387:
search_left_bound > search_right_bound
There are only 2 cases this can happen:
(1) target key is smaller than left most file
(2) target key is larger than right most file
The comment is wrong, there is another possibility that at the higher level there is a big gap such that the file in the lower level fits completely in the gap and then
indexer->GetNextLevelIndex returns search_left_bound > search_right_bound I think pointing on the files after and before the gap.
details: https://github.com/facebook/rocksdb/issues/1372
fixed this bug with test case added.
Closes https://github.com/facebook/rocksdb/pull/1436
Reviewed By: IslamAbdelRahman
Differential Revision: D4099313
Pulled By: lightmark
fbshipit-source-id: 6a675b3
Summary:
Currently, we don't use options.compression_per_level[0] as the compression style for L0 compression type, unless it is None. This behavior
doesn't look like on purpose. This diff will make sure L0 compress using the style of options.compression_per_level[0].
Reviewed and accepted in: https://reviews.facebook.net/D65607
Closes https://github.com/facebook/rocksdb/pull/1435
Differential Revision: D4099368
Pulled By: siying
fbshipit-source-id: cfbbdcd
Summary: As offline discussion with Siying, revert this since it has bug with seek.
Test Plan: make check -j64
Reviewers: yiwu, andrewkr, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D65559
Summary:
The verification condition of the test DBTest.RepeatedWritesToSameKey doesn't hold anymore after 3ce3bb3da2.
Disable the test for now before we find a way to replace it.
Test Plan: Run the test and make sure it is disabled.
Summary: Siying suggested to keep old code for normal mode prev() for safety
Test Plan: make check -j64
Reviewers: yiwu, andrewkr, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D65439
Summary: Using real clock causes failures of DBSSTTest.RateLimitedDelete in some cases. Turn away from the real time. Use fake time instead.
Test Plan: Run the tests and all existing tests.
Reviewers: yiwu, IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D65145
Summary:
The previous fix of reappearing of a deleted row 0ce258f9b3 missed a corner case, which can be reproduced using test CompactionPickerTest.OverlappingUserKeys7. Consider such an example:
input level file: 1[B E] 2[F H]
output level file: 3[A C] 4[D I] 5[I K]
First file 2 is picked, which overlaps to file 4. 4 expands to 5. Now the all range is [D K] with 2 output level files. When we try to expand that, [D K] overlaps with file 1 and 2 in the input level, and 1 and 2 overlaps with 3 and 4 in the output level. So we end up with picking 3 and 4 in the output level. Without expanding, it also has 2 files, so we determine the output level doesn't change, although they are the different two files.
The fix is to expand the output level files after we picked 3 and 4. In that case, there will be three output level files so we will abort the expanding.
I also added two unit tests related to marked_for_compaction and being_compacted. They have been passing though.
Test Plan: Run the new unit test, as well as all other tests.
Reviewers: andrewkr, IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: yoshinorim, leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D65373
Andrew Kryczka