Summary:
Throughput: 46k tps in our sysbench settings (filling the details later)
The idea is to have the simplest change that gives us a reasonable boost
in 2PC throughput.
Major design changes:
1. The WAL file internal buffer is not flushed after each write. Instead
it is flushed before critical operations (WAL copy via fs) or when
FlushWAL is called by MySQL. Flushing the WAL buffer is also protected
via mutex_.
2. Use two sequence numbers: last seq, and last seq for write. Last seq
is the last visible sequence number for reads. Last seq for write is the
next sequence number that should be used to write to WAL/memtable. This
allows to have a memtable write be in parallel to WAL writes.
3. BatchGroup is not used for writes. This means that we can have
parallel writers which changes a major assumption in the code base. To
accommodate for that i) allow only 1 WriteImpl that intends to write to
memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes
come via group commit phase which is serial anyway, ii) make all the
parts in the code base that assumed to be the only writer (via
EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are
protected via a stat_mutex_.
Note: the first commit has the approach figured out but is not clean.
Submitting the PR anyway to get the early feedback on the approach. If
we are ok with the approach I will go ahead with this updates:
0) Rebase with Yi's pipelining changes
1) Currently batching is disabled by default to make sure that it will be
consistent with all unit tests. Will make this optional via a config.
2) A couple of unit tests are disabled. They need to be updated with the
serial commit of 2PC taken into account.
3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires
releasing mutex_ beforehand (the same way EnterUnbatched does). This
needs to be cleaned up.
Closes https://github.com/facebook/rocksdb/pull/2345
Differential Revision: D5210732
Pulled By: maysamyabandeh
fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
Summary:
Improve write buffer manager in several ways:
1. Size is tracked when arena block is allocated, rather than every allocation, so that it can better track actual memory usage and the tracking overhead is slightly lower.
2. We start to trigger memtable flush when 7/8 of the memory cap hits, instead of 100%, and make 100% much harder to hit.
3. Allow a cache object to be passed into buffer manager and the size allocated by memtable can be costed there. This can help users have one single memory cap across block cache and memtable.
Closes https://github.com/facebook/rocksdb/pull/2350
Differential Revision: D5110648
Pulled By: siying
fbshipit-source-id: b4238113094bf22574001e446b5d88523ba00017
Summary:
Some users want to monitor column family activity in their custom memtable implementations. Previously there was no way to figure out with which column family a memtable is associated. This diff:
- adds an overload to MemTableRepFactory::CreateMemTableRep() that provides the CF ID. For compatibility, its default implementation calls the old overload.
- updates MemTable to create MemTableRep's using the new overload.
Closes https://github.com/facebook/rocksdb/pull/2346
Differential Revision: D5108061
Pulled By: ajkr
fbshipit-source-id: 3a1921214a348dd8ea0f54e1cab3b71c3d46d616
Summary:
Blob db rely on base db returning sequence number through write batch after DB::Write(). However after recent changes to the write path, DB::Writ()e no longer return sequence number in some cases. Fixing it by have WriteBatchInternal::InsertInto() always encode sequence number into write batch.
Stacking on #2375.
Closes https://github.com/facebook/rocksdb/pull/2385
Differential Revision: D5148358
Pulled By: yiwu-arbug
fbshipit-source-id: 8bda0aa07b9334ed03ed381548b39d167dc20c33
Summary:
Previously sst_file_writer only supports kTypeValue, we need kTypeMerge and kTypeDeletion also as user requested.
Closes https://github.com/facebook/rocksdb/pull/2361
Differential Revision: D5139402
Pulled By: lightmark
fbshipit-source-id: 092a60756d01692539d817a3765ebfd58a8d7f88
Summary:
Disable direct reads for log and manifest. Direct reads should not affect sequential_file
Also add kDirectIO for option_config_ in db_test_util
Closes https://github.com/facebook/rocksdb/pull/2337
Differential Revision: D5100261
Pulled By: lightmark
fbshipit-source-id: 0ebfd13b93fa1b8f9acae514ac44f8125a05868b
Summary:
When user doesn't set a limit on compaction output file size, let's use the sum of the input files' sizes. This will avoid passing UINT64_MAX as fallocate()'s length. Reported in #2249.
Test setup:
- command: `TEST_TMPDIR=/data/rocksdb-test/ strace -e fallocate ./db_compaction_test --gtest_filter=DBCompactionTest.ManualCompactionUnknownOutputSize`
- filesystem: xfs
before this diff:
`fallocate(10, 01, 0, 1844674407370955160) = -1 ENOSPC (No space left on device)`
after this diff:
`fallocate(10, 01, 0, 1977) = 0`
Closes https://github.com/facebook/rocksdb/pull/2252
Differential Revision: D5007275
Pulled By: ajkr
fbshipit-source-id: 4491404a6ae8a41328aede2e2d6f4d9ac3e38880
Summary:
Move some files under util/ to new directories env/, monitoring/ options/ and cache/
Closes https://github.com/facebook/rocksdb/pull/2090
Differential Revision: D4833681
Pulled By: siying
fbshipit-source-id: 2fd8bef
Summary:
It is confusing to have auto_roll_logger to stay under db/, which has nothing to do with database. Move filename together as it is a dependency.
Closes https://github.com/facebook/rocksdb/pull/2080
Differential Revision: D4821141
Pulled By: siying
fbshipit-source-id: ca7d768
Summary:
Allow the users to specify the target index partition size.
With this patch an index partition is cut before its estimated in-memory size goes above the configured value for metadata_block_size. The filter partitions are still cut right after an index partition is cut.
Closes https://github.com/facebook/rocksdb/pull/2041
Differential Revision: D4780216
Pulled By: maysamyabandeh
fbshipit-source-id: 95a0831
Summary:
Fixing some bugs in MockEnv so it be actually used.
Closes https://github.com/facebook/rocksdb/pull/1914
Differential Revision: D4609923
Pulled By: maysamyabandeh
fbshipit-source-id: ca25735
Summary:
Avoid to run db_wal_test in all the DB test options, and some small changes.
Closes https://github.com/facebook/rocksdb/pull/1921
Differential Revision: D4622054
Pulled By: siying
fbshipit-source-id: 890fd64
Summary:
we occasionally missing this call so the file size will be wrong
Closes https://github.com/facebook/rocksdb/pull/1894
Differential Revision: D4598446
Pulled By: lightmark
fbshipit-source-id: 42b6ef5
Summary:
Partition Index blocks and use a Partition-index as a 2nd level index.
The two-level index can be used by setting
BlockBasedTableOptions::kTwoLevelIndexSearch as the index type and
configuring BlockBasedTableOptions::index_per_partition
t15539501
Closes https://github.com/facebook/rocksdb/pull/1814
Differential Revision: D4473535
Pulled By: maysamyabandeh
fbshipit-source-id: bffb87e
Summary:
This fix the issue with tests failing under GCC 481, I am not sure what is the exact reason
Closes https://github.com/facebook/rocksdb/pull/1735
Differential Revision: D4374094
Pulled By: IslamAbdelRahman
fbshipit-source-id: b3625bc
Summary:
Iterator should be in corrupted status if merge operator return false.
Also add test to make sure if max_successive_merges is hit during write,
data will not be lost.
Closes https://github.com/facebook/rocksdb/pull/1665
Differential Revision: D4322695
Pulled By: yiwu-arbug
fbshipit-source-id: b327b05
Summary:
If the WriteOptions.no_slowdown flag is set AND we need to wait or sleep for
the write request, then fail immediately with Status::Incomplete().
Closes https://github.com/facebook/rocksdb/pull/1527
Differential Revision: D4191405
Pulled By: maysamyabandeh
fbshipit-source-id: 7f3ce3f
Summary:
Changes in the diff
API changes:
- Introduce IngestExternalFile to replace AddFile (I think this make the API more clear)
- Introduce IngestExternalFileOptions (This struct will encapsulate the options for ingesting the external file)
- Deprecate AddFile() API
Logic changes:
- If our file overlap with the memtable we will flush the memtable
- We will find the first level in the LSM tree that our file key range overlap with the keys in it
- We will find the lowest level in the LSM tree above the the level we found in step 2 that our file can fit in and ingest our file in it
- We will assign a global sequence number to our new file
- Remove AddFile restrictions by using global sequence numbers
Other changes:
- Refactor all AddFile logic to be encapsulated in ExternalSstFileIngestionJob
Test Plan:
unit tests (still need to add more)
addfile_stress (https://reviews.facebook.net/D65037)
Reviewers: yiwu, andrewkr, lightmark, yhchiang, sdong
Reviewed By: sdong
Subscribers: jkedgar, hcz, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D65061
Summary:
reland https://reviews.facebook.net/D62523
- Update SstFileWriter to include a property for a global sequence number in the SST file `rocksdb.external_sst_file.global_seqno`
- Update TableProperties to be aware of the offset of each property in the file
- Update BlockBasedTableReader and Block to be able to honor the sequence number in `rocksdb.external_sst_file.global_seqno` property and use it to overwrite all sequence number in the file
Something worth mentioning is that we don't update the seqno in the index block since and when doing a binary search, the reason for that is that it's guaranteed that SST files with global seqno will have only one user_key and each key will have seqno=0 encoded in it, This mean that this key is greater than any other key with seqno> 0. That mean that we can actually keep the current logic for these blocks
Test Plan: unit tests
Reviewers: sdong, yhchiang
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D65211
Summary: Currently the WAL file preallocation size is 1.1 * write_buffer_size. This, however, will be over-estimated if options.db_write_buffer_size or options.max_total_wal_size is set and is much smaller.
Test Plan: Add a unit test.
Reviewers: andrewkr, yiwu
Reviewed By: yiwu
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D63957
Summary:
This diff update ForwardIterator to support pinning keys and values, which will allow DBIter to take advantage of that and eliminate memcpy when executing merge operators
This diff is stacked on D61305
Test Plan:
existing tests (updated them to test tailing iterator)
new test
Reviewers: andrewkr, yhchiang, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D60009
Summary: With read_options.background_purge_on_iterator_cleanup=true, File deletion and closing can still happen in forward iterator, or WAL file closing. Cover those cases too.
Test Plan: I am adding unit tests.
Reviewers: andrewkr, IslamAbdelRahman, yiwu
Reviewed By: yiwu
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D61503
Summary:
DB::AddFile() right now always add the ingested file to L0
update the logic to add the file to the lowest possible level
Test Plan: unit tests
Reviewers: jkedgar, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba, yoshinorim
Differential Revision: https://reviews.facebook.net/D59637
Summary: filter_deltes is not a frequently used feature. Remove it.
Test Plan: Run all test suites.
Reviewers: igor, yhchiang, IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D59427
Summary: Fixing error with win build where we compare int64_t with size_t.
Test Plan: make check
Reviewers: andrewkr
Reviewed By: andrewkr
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D57885
Summary:
Add an option `iterator_readahead_size` to `ReadOptions` to enable
configurable readahead for iterators similar to the corresponding
option for compaction.
Test Plan:
```
make commit_prereq
```
Reviewers: kumar.rangarajan, ott, igor, sdong
Reviewed By: sdong
Subscribers: yiwu, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D55419
Summary:
This is needed so we can measure compression ratio improvements
achieved by D52287.
The property compares raw data size against the total file size for a given
level. If the level is empty it should return 0.0.
Test Plan: new unit test
Reviewers: IslamAbdelRahman, yhchiang, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D56967
Summary:
Introude SstFileManager::SetMaxAllowedSpaceUsage() that can be used to limit the maximum space usage allowed for RocksDB.
When this limit is exceeded WriteImpl() will fail and return Status::Aborted()
Test Plan: unit testing
Reviewers: yhchiang, anthony, andrewkr, sdong
Reviewed By: sdong
Subscribers: dhruba
Differential Revision: https://reviews.facebook.net/D53763
Summary: Add a new option to BlockBasedTableOptions that will allow us to change the restart interval for the index block
Test Plan: unit tests
Reviewers: yhchiang, anthony, andrewkr, sdong
Reviewed By: sdong
Subscribers: march, dhruba
Differential Revision: https://reviews.facebook.net/D53721
Summary:
InlineSkipList::InsertConcurrently should invalidate the
sequential-insertion cache prev_[] for all inserts of multi-level nodes,
not just those that increase the height of the skip list. The invariant
for prev_ is that prev_[i] (i > 0) is supposed to be the predecessor of
prev_[0] at level i. Before this diff InsertConcurrently could violate
this constraint when inserting a multi-level node after prev_[i] but
before prev_[0].
This diff also reenables kConcurrentSkipList as db_test's
MultiThreaded/MultiThreadedDBTest.MultiThreaded/29.
Test Plan:
1. unit tests
2. temporarily hack kConcurrentSkipList timing so that it is fast but has a 1.5% failure rate on my dev box (1ms stagger on thread launch, 1s test duration, failure rate baseline over 1000 runs)
3. observe 1000 passes post-fix
Reviewers: igor, sdong
Reviewed By: sdong
Subscribers: MarkCallaghan, dhruba
Differential Revision: https://reviews.facebook.net/D53751
Summary: Disable test that is intermittently failing
Test Plan: unit tests
Reviewers: igor, andrewkr, sdong
Reviewed By: sdong
Subscribers: dhruba
Differential Revision: https://reviews.facebook.net/D53715
Summary:
Concurrent memtable adds were incorrectly computing
the last sequence number for a write batch group when the
write batches were not solitary. This is the cause of
https://github.com/facebook/mysql-5.6/issues/155
Test Plan:
1. unit tests
2. new unit test
3. parallel db_bench stress tests with batch size of 10 and asserts enabled
Reviewers: igor, sdong
Reviewed By: sdong
Subscribers: IslamAbdelRahman, MarkCallaghan, dhruba
Differential Revision: https://reviews.facebook.net/D53595
Summary:
Add a new class SstFileTracker that will be notified whenever a DB add/delete/move and sst file, it will also replace DeleteScheduler
SstFileTracker can be used later to abort writes when we exceed a specific size
Test Plan: unit tests
Reviewers: rven, anthony, yhchiang, sdong
Reviewed By: sdong
Subscribers: igor, lovro, march, dhruba
Differential Revision: https://reviews.facebook.net/D50469
Summary: Break down DBTest.Randomized to multiple gtest tests based on config type
Test Plan: Run the test and all tests. Make sure configurations are correctly set
Reviewers: yhchiang, IslamAbdelRahman, rven, kradhakrishnan, andrewkr, anthony
Reviewed By: anthony
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D53247
Summary:
Moved all the tests that verify property correctness into a separate
file. The goal is to reduce compile time and complexity of db_test. I didn't
add parallelism for db_properties_test, even though these tests were
parallelized in db_test, since the file is small enough that it won't matter.
Some of these moves may be controversial since it's hard to say whether the
test is "verifying property correctness," or "using properties to verify
rocksdb's correctness." I'm interested in any opinions.
Test Plan: ran db_properties_test, also waiting on "make commit-prereq -j32"
Reviewers: yhchiang, IslamAbdelRahman, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D52995
Summary: Skip list now cannot estimate memory across allocators
consistently and hence triggers flush at different time. This breaks certain
unit tests.
The fix is to adopt key count instead of size for flush.
Test Plan: Ran test on dev box and mac (where it used to fail)
Reviewers: sdong
CC: leveldb@
Task ID: #9273334
Blame Rev:
Summary: DBTest.SuggestCompactRangeTest fails for the case when jemalloc is disabled, including ASAN and valgrind builds. It is caused by the improvement of skip list, which allocates different size of nodes for a new records. Fix it by using a special mem table that triggers a flush by number of entries. In that way the behavior will be consistent for all allocators.
Test Plan: Run the test with both of DISABLE_JEMALLOC=1 and 0
Reviewers: anthony, rven, yhchiang, kradhakrishnan, igor, IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: leveldb, dhruba
Differential Revision: https://reviews.facebook.net/D51423
Siying Dong