Summary:
before file ingestion (in preparation phase), verify the checksums of
the blocks of the external SST file, including properties block with global
seqno.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4916
Differential Revision: D13863501
Pulled By: riversand963
fbshipit-source-id: dc54697f970e3807832e2460f7228fcc7efe81ee
Summary:
While stepping through the code I noticed that there is a redundant call to TableFileName.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4925
Differential Revision: D13845749
Pulled By: sagar0
fbshipit-source-id: 31db45716b4d720e0e0350dd457b49d6f1848e7d
Summary:
Store_index_in_file is a less useful feature. To simplify the code to maintain, we are dropping the feature.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4914
Differential Revision: D13791883
Pulled By: siying
fbshipit-source-id: d187c5d662584866103e4b77d09dfb925509ae2e
Summary:
https://github.com/facebook/rocksdb/pull/4053 avoids memcopy for Get() results if files are immortable
(read-only DB, max_open_files=-1) and the file is ammaped. The same optimization is being applied to PlainTable
here.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4924
Differential Revision: D13827749
Pulled By: siying
fbshipit-source-id: 1f2cbfc530b40ce08ccd53f95f6e78de4d1c2f96
Summary:
I didn't find where customized hash function is used in DynamicBloom. This can only reduce performance. Remove it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4915
Differential Revision: D13794452
Pulled By: siying
fbshipit-source-id: e38669b11e01444d2d782da11c7decabbd851819
Summary:
Previously compaction was not collapsing operands for a first
key on a layer, even in cases when it was its root of history. Some
tests (CompactionJobTest.NonAssocMerge) was actually accounting
for that bug,
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4909
Differential Revision: D13781169
Pulled By: finik
fbshipit-source-id: d2de353ecf05bec39b942cd8d5b97a8dc445f336
Summary:
- If block cache disabled or not used for meta-blocks, `BlockBasedTableReader::Rep::uncompression_dict` owns the `UncompressionDict`. It is preloaded during `PrefetchIndexAndFilterBlocks`.
- If block cache is enabled and used for meta-blocks, block cache owns the `UncompressionDict`, which holds dictionary and digested dictionary when needed. It is never prefetched though there is a TODO for this in the code. The cache key is simply the compression dictionary block handle.
- New stats for compression dictionary accesses in block cache: "BLOCK_CACHE_COMPRESSION_DICT_*" and "compression_dict_block_read_count"
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4881
Differential Revision: D13663801
Pulled By: ajkr
fbshipit-source-id: bdcc54044e180855cdcc57639b493b0e016c9a3f
Summary:
Even one key falls in a file's range, we can not infer it definitely exists in this file.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4902
Differential Revision: D13795018
Pulled By: siying
fbshipit-source-id: 590956f727e9440fcdee55ad9541ace934c64914
Summary:
compaction_pri = kMinOverlappingRatio usually provides much better write amplification than the default.
https://github.com/facebook/rocksdb/pull/4907 fixes one shortcome of this option. Make it default.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4911
Differential Revision: D13789262
Pulled By: siying
fbshipit-source-id: d90acf8c4dede44f00d183ca4c7a210259378269
Summary:
Right now, CompactionPri = kMinOverlappingRatio provides best write amplification, but it doesn't
prioritize files with more tombstones. We combine the two good features: make kMinOverlappingRatio
to boost files with lots of tombstones too.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4907
Differential Revision: D13788774
Pulled By: siying
fbshipit-source-id: 1991cbb495fb76c8b529de69896e38d81ed9d9b3
Summary:
This is essentially a re-submission of #4251 with a few improvements:
- Split `CompressionDict` into two separate classes: `CompressionDict` and `UncompressionDict`
- Eliminated `Init` functions. Instead do all initialization work in constructors.
- Added test case for parallel DB open, which is the scenario where #4251 failed under TSAN.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4849
Differential Revision: D13606039
Pulled By: ajkr
fbshipit-source-id: 08c236059798c710db9cbf545fce0f371232d447
Summary:
Fix how CompactionIterator::findEarliestVisibleSnapshots handles released snapshot. It fixing the two scenarios:
Scenario 1:
key1 has two values v1 and v2. There're two snapshots s1 and s2 taken after v1 and v2 are committed. Right after compaction output v2, s1 is released. Now findEarliestVisibleSnapshot may see s1 being released, and return the next snapshot, which is s2. That's larger than v2's earliest visible snapshot, which was s1.
The fix: the only place we check against last snapshot and current key snapshot is when we decide whether to compact out a value if it is hidden by a later value. In the check if we see current snapshot is even larger than last snapshot, we know last snapshot is released, and we are safe to compact out current key.
Scenario 2:
key1 has two values v1 and v2. there are two snapshots s1 and s2 taken after v1 and v2 are committed. During compaction before we process the key, s1 is released. When compaction process v2, snapshot checker may return kSnapshotReleased, and the earliest visible snapshot for v2 become s2. When compaction process v1, snapshot checker may return kIsInSnapshot (for WritePrepared transaction, it could be because v1 is still in commit cache). The result will become inconsistent here.
The fix: remember the set of released snapshots ever reported by snapshot checker, and ignore them when finding result for findEarliestVisibleSnapshot.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4890
Differential Revision: D13705538
Pulled By: maysamyabandeh
fbshipit-source-id: e577f0d9ee1ff5a6035f26859e56902ecc85a5a4
Summary:
Compaction iterator keep a copy of list of live snapshots at the beginning of compaction, and then query snapshot checker to verify if values of a sequence number is visible to these snapshots. However when the snapshot is released in the middle of compaction, the snapshot checker implementation (i.e. WritePreparedSnapshotChecker) may remove info with the snapshot and may report incorrect result, which lead to values being compacted out when it shouldn't. This patch conservatively keep the values if snapshot checker determines that the snapshots is released.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4858
Differential Revision: D13617146
Pulled By: maysamyabandeh
fbshipit-source-id: cf18a94f6f61a94bcff73c280f117b224af5fbc3
Summary:
By convention, time_t almost always stores the integral number of seconds since
00:00 hours, Jan 1, 1970 UTC, according to http://www.cplusplus.com/reference/ctime/time_t/.
We surely want more precision than seconds.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4868
Differential Revision: D13633046
Pulled By: riversand963
fbshipit-source-id: 4e01e23a22e8838023c51a91247a286dbf3a5396
Summary:
With WritePrepared transaction, flush/compaction can contain uncommitted keys, and those keys can get committed during compaction. If a snapshot is taken before the key is committed, it should not see the key. On the other hand, compaction grab the list of snapshots at its beginning, and only consider those snapshots to dedup keys. Consider the case:
```
seq = 1: put "foo" = "bar"
seq = 2: transaction T: delete "foo", prepare
seq = 3: compaction start
seq = 4: take snapshot S
seq = 5: transaction T: commit.
...
seq = N: compaction iterator reached key "foo".
```
When compaction start, the list of snapshot is empty. Compaction doesn't take snapshot S into account. When it reached "foo", transaction T is committed. Compaction may think the value "foo=bar" is not visible by any snapshot (which is wrong), and compact the value out.
The fix is to explicitly take a snapshot before compaction grabbing the list of snapshots. Compaction will then has to keep keys visible to this snapshot.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4883
Differential Revision: D13668775
Pulled By: maysamyabandeh
fbshipit-source-id: 1cab9615f94b7d3e8522cc3d44c3a14c7d4720e4
Summary:
The AdvanceMaxEvictedSeq algorithm assumes that new snapshots always have sequence number larger than the last max_evicted_seq_. To enforce this assumption we make two changes:
i) max is not advanced beyond the last published seq, with the exception that the evicted commit entry itself is not published yet, which is quite rare.
ii) When obtaining the snapshot if the max_evicted_seq_ is not published yet, commit a dummy entry so that it waits for it to be published and also increased the latest published seq by one above the max.
To test these non-realistic corner cases we create a commit cache with size 1 so that every single commit results into eviction.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4886
Differential Revision: D13685270
Pulled By: maysamyabandeh
fbshipit-source-id: 5461bc09c2a9b75798bfcb9853a256c81cdac0b0
Summary:
Right now the error mesage when options.wal_dir doesn't exist is not helpful to users. Be more specific
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4874
Differential Revision: D13642425
Pulled By: siying
fbshipit-source-id: 9a3172ed0f799af233b0f3b2e5e35bc7ce04c7b5
Summary:
If we do not do this, then reading MutableCFOptions may have a race condition
with SetOptions which modifies MutableCFOptions.
Also reserve space in advance for vectors to avoid reallocation changing the
address of its elements.
Test plan
```
$make clean && make -j32 all check
$make clean && COMPILE_WITH_TSAN=1 make -j32 all check
$make clean && COMPILE_WITH_ASAN=1 make -j32 all check
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4876
Differential Revision: D13644500
Pulled By: riversand963
fbshipit-source-id: 4b8112c5c819d5a2922bb61ad1521b3d2fb2fd47
Summary:
The vector returned by SnapshotList::GetAll could have duplicate entries if two separate snapshots have the same sequence number. However, when this vector is used in compaction the duplicate entires are of no use and could be safely ignored. Moreover not having duplicate entires simplifies reasoning in the compaction_iterator.cc code. For example when searching for the previous_snap we currently use the snapshot before the current one but the way the code uses that it expects it to be also less than the current snapshot, which would be simpler to read if there is no duplicate entry in the snapshot list.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4860
Differential Revision: D13615502
Pulled By: maysamyabandeh
fbshipit-source-id: d45bf01213ead5f39db811f951802da6fcc3332b
Summary:
https://github.com/facebook/rocksdb/pull/3340 introduces preloading when max_open_files != -1.
It doesn't preload index and filter in non-initial file loading case. This is a little bit too
complicated to understand. We observed in one MyRocks use case where the filter is expected to be
preloaded but is not. To simplify the use case, we simply always prefetch the index and filter.
They anyway is expected to be loaded in the file verification phase anyway.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4852
Differential Revision: D13595402
Pulled By: siying
fbshipit-source-id: d4d8624eb3e849e20aeb990df2100502d85aff31
Summary:
In compaction iterator, if the next value of single delete is a blob value, it should not treated as mismatch. This is only a minor fix and doesn't affect correctness.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4848
Differential Revision: D13585812
Pulled By: yiwu-arbug
fbshipit-source-id: 0ff6223fa03a644ac9fd8a2d77f9d6711d0a62b0
Summary:
Previously for point lookup we decided which file to look into based on user key overlap only. We also did not truncate range tombstones in the point lookup code path. These two ideas did not interact well in cases like this:
- L1 has range tombstone [a, c)#1 and point key b#2. The data is split between file1 with range [a#1,1, b#72057594037927935,15], and file2 with range [b#2, c#1].
- L1's file2 gets compacted to L2.
- User issues `Get()` for b#3.
- L1's file1 is opened and the range tombstone [a, c)#1 is found for b, while no point-key for b is found in L1.
- `Get()` assumes that the range tombstone must cover all data in that range in lower levels, so short circuits and returns `NotFound`.
The solution to this problem is to not look into files that only overlap with the point lookup at a range tombstone sentinel endpoint. In the above example, this would mean not opening L1's file1 or its tombstones during the `Get()`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4829
Differential Revision: D13561355
Pulled By: ajkr
fbshipit-source-id: a13c21c816870a2f5d32a48af6dbd719a7d9d19f
Summary:
as titled.
Since different bg flush threads can flush different sets of column families
(due to column family creation and drop), we decide not to let one thread
perform atomic flush result installation for other threads. Bg flush threads
will install their atomic flush results sequentially to MANIFEST, using
a conditional variable, i.e. atomic_flush_install_cv_ to coordinate.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4791
Differential Revision: D13498930
Pulled By: riversand963
fbshipit-source-id: dd7482fc41f4bd22dad1e1ef7d4764ef424688d7
Summary:
Declare Jemalloc non-standard APIs as weak symbols, so that if Jemalloc is linked with the binary, these symbols will be replaced by Jemalloc's, otherwise they will be nullptr. This is similar to how folly detect jemalloc, but we assume the main program use jemalloc as long as jemalloc is linked: https://github.com/facebook/folly/blob/master/folly/memory/Malloc.h#L147
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4844
Differential Revision: D13574934
Pulled By: yiwu-arbug
fbshipit-source-id: 7ea871beb1be7d5a1259cc38f9b78078793db2db
Summary:
The original implementation has two problems:
1. f0dda35d7d/db/db_impl_write.cc (L478)f0dda35d7d/db/write_thread.h (L231)
If the callback status of leader of the write_group fails, then the whole write_group will not write to WAL, this may cause data loss.
2. f0dda35d7d/db/write_thread.h (L130)
The annotation says that Writer.status is the status of memtable inserter, but the original implementation use it for another case which is not consistent with the original design. Looks like we can still reuse Writer.status, but we should modify the annotation, so Writer.status is not only the status of memtable inserter.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4838
Differential Revision: D13574070
Pulled By: yiwu-arbug
fbshipit-source-id: a2a2aefcfd329c4c6a91652bf090aaf1ce119c4b
Summary:
DBSSTTest.RateLimitedDelete is flakey. The root cause is not completely identified, but
the compaction waiting in the test doesn't strictly wait for compaction cleaning to finish, which
may cause test flakiness. Fix it first and see whether the failures still happen.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4840
Differential Revision: D13567273
Pulled By: siying
fbshipit-source-id: 6fce38b912aff92a925231e7aa9bb0fef892761a
Summary:
- To be consistent with the accounting of other optypes in `TableProperties`, we should count range tombstones in `TableProperties::num_entries` and `TableProperties::num_deletions`.
- Updated assertions in stress test's `OnTableFileCreated` handler to accept files with range tombstones only.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4841
Differential Revision: D13568424
Pulled By: ajkr
fbshipit-source-id: 0139d7806494eda20ece67ec460d2458dbbf6026
Summary:
Avoid locking the DB mutex in order to reference SuperVersions. Instead, we get the thread local cached SuperVersion for each column family in the list. It depends on finding a sequence number that overlaps with all the open memtables. We start with the latest published sequence number, and if any of the memtables is sealed before we can get all the SuperVersions, the process is repeated. After a few times, give up and lock the DB mutex.
Tests:
1. Unit tests
2. make check
3. db_bench -
TEST_TMPDIR=/dev/shm ./db_bench -use_existing_db=true -benchmarks=readrandom -write_buffer_size=4194304 -target_file_size_base=4194304 -max_bytes_for_level_base=16777216 -num=5000000 -reads=1000000 -threads=32 -compression_type=none -cache_size=1048576000 -batch_size=1 -bloom_bits=1
readrandom : 0.167 micros/op 5983920 ops/sec; 426.2 MB/s (1000000 of 1000000 found)
Multireadrandom with batch size 1:
multireadrandom : 0.176 micros/op 5684033 ops/sec; (1000000 of 1000000 found)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4754
Differential Revision: D13363550
Pulled By: anand1976
fbshipit-source-id: 6243e8de7dbd9c8bb490a8eca385da0c855b1dd4
Summary:
The `flush_reason` parameter in `DBImpl::InstallSuperVersionAndScheduleWork` is
not used. Remove it.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4816
Differential Revision: D13543218
Pulled By: riversand963
fbshipit-source-id: 8fc75d49462ce092e85aef0fe0c50936140db153
Summary:
Choose to preload some files if options.max_open_files != -1. This can slightly narrow the gap of performance between options.max_open_files is -1 and a large number. To avoid a significant regression to DB reopen speed if options.max_open_files != -1. Limit the files to preload in DB open time to 16.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3340
Differential Revision: D6686945
Pulled By: siying
fbshipit-source-id: 8ec11bbdb46e3d0cdee7b6ad5897a09c5a07869f
Summary:
1. Remove unused API SubtractCompactionTask().
2. Assert outstanding tasks drop to zero in ConcurrentTaskLimiterImpl destructor.
3. Remove GetOutstandingTask() check from manual compaction test, as TEST_WaitForCompact() doesn't synced with 'delete prepicked_compaction' in DBImpl::BGWorkCompaction(), which may make the test flaky.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4795
Differential Revision: D13542183
Pulled By: siying
fbshipit-source-id: 5eb2a47e62efe4126937149aa0df6e243ebefc33
Summary:
Add a new per level counter for block cache hits, increase it by one on every successful attempt to get an entry from cache.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4796
Differential Revision: D13513688
Pulled By: zinoale
fbshipit-source-id: 104df038f1232e3356e162eb2d8ca138e34a8281
Summary:
Previously we were cleaning up range tombstone meta-block by calling `ReleaseCachedEntry`, which wouldn't work if `value != nullptr && cache_handle == nullptr`. This happened at least in the case with mmap reads and block cache both enabled. I noticed `NewDataBlockIterator` intends to handle all these cases, so migrated to that instead of `NewUnfragmentedRangeTombstoneIterator`.
Also changed the table-opening logic to fail on `ReadRangeDelBlock` failure, since that can cause data corruption. Added a test case to verify this behavior. Note the test case does not fail on `TryReopen` because failure to preload table handlers is not considered critical. However, it does fail on any read involving that file since it cannot return correct data.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4810
Differential Revision: D13534296
Pulled By: ajkr
fbshipit-source-id: 55dde1111717cea6ec4bf38418daab81ccef3599
Summary:
Introduce the first CPU timing counter, perf_context.get_cpu_nanos. This opens a door to more CPU counters in the future.
Only Posix Env has it implemented using clock_gettime() with CLOCK_THREAD_CPUTIME_ID. How accurate the counter is depends on the platform.
Make PerfStepTimer to take an Env as an argument, and sometimes pass it in. The direct reason is to make the unit tests to use SpecialEnv where we can ingest logic there. But in long term, this is a good change.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4741
Differential Revision: D13287798
Pulled By: siying
fbshipit-source-id: 090361049d9d5095d1d1a369fe1338d2e2e1c73f
Summary:
To avoid a race on the flag, make it an atomic_bool. This
doesn't seem to significantly affect benchmarks.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4801
Differential Revision: D13523845
Pulled By: abhimadan
fbshipit-source-id: 3bc29f53c50a4e06cd9f8c6232a4bb221868e055
Summary:
This TODO was already addressed, but I forgot to remove it
before landing the PR it came from.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4800
Differential Revision: D13522284
Pulled By: abhimadan
fbshipit-source-id: 7766bc4f5b54e47d355cf26137ef5e86c604472a
Summary:
This PR contains the following fixes:
1. Fixing Makefile to support non-default locations of developer tools
2. Fixing compile error using a patch from https://github.com/facebook/rocksdb/pull/4007
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4687
Differential Revision: D13287263
Pulled By: riversand963
fbshipit-source-id: 4525eb42ba7b6f82af5f9bfb8e52fa4024e27ccc
Summary:
1) `transaction_base.h` overrides from `transaction.h` with a `const boolean do_validate`.
The non-const base declaration, which I cannot see the need for, causes a compilation error on Microsoft Windows.
2) Implicit cast from `double` to `uint64_t` causes a compilation error on Microsoft Windows.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4798
Differential Revision: D13519734
Pulled By: sagar0
fbshipit-source-id: 6e8cb80e9a589b1122e1500c21b8e3a3a472b459
Summary:
in certain cases, we do not perform memtable switching if the active
memtable of the column family is empty. Two exceptions:
1. In manual flush, if cached_recoverable_state_empty_ is false, then we need
to switch memtable due to requirement of transaction.
2. In switch WAL, we need to switch memtable anyway because we have to seal the
memtable if the WAL on which it depends will be closed.
This change can potentially delay the occurence of write stalls because number
of memtables increase more slowly.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4792
Differential Revision: D13499501
Pulled By: riversand963
fbshipit-source-id: 91c9b17ae753578578039f3851667d93610005e1
Summary:
Now that v2 is fully functional, the v1 aggregator is removed.
The v2 aggregator has been renamed.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4778
Differential Revision: D13495930
Pulled By: abhimadan
fbshipit-source-id: 9d69500a60a283e79b6c4fa938fc68a8aa4d40d6
Summary:
RangeDelAggregatorV2 now supports ShouldDelete calls on
snapshot stripes and creation of range tombstone compaction iterators.
RangeDelAggregator is no longer used on any non-test code path, and will
be removed in a future commit.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4758
Differential Revision: D13439254
Pulled By: abhimadan
fbshipit-source-id: fe105bcf8e3d4a2df37a622d5510843cd71b0401
Summary:
The test fails sporadically expecting the DB to be empty after DeleteFilesInRange(..., nullptr, nullptr) call which is not. Debugging shows cases where the files are skipped since they are being compacted. The patch fixes the test by waiting for the last CompactRange to finish before calling DeleteFilesInRange.
Verified by
```
~/gtest-parallel/gtest-parallel ./db_compaction_test --gtest_filter=DBCompactionTest.DeleteFileRange --repeat=10000
```
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4784
Differential Revision: D13469402
Pulled By: maysamyabandeh
fbshipit-source-id: 3d8f44abe205b82c69f01e7edf27e1f8098248e1
Summary:
options_file_number_ must be written under db::mutex_ sine its read is protected by mutex_ in ::GetLiveFiles(). However currently it is written in ::RenameTempFileToOptionsFile() which according to its contract must be called without holding db::mutex_. The patch fixes the race condition by also acquitting the mutex_ before writing options_file_number_. Also it does that only if the rename of option file is successful.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4780
Differential Revision: D13461411
Pulled By: maysamyabandeh
fbshipit-source-id: 2d5bae96a1f3e969ef2505b737cf2d7ae749787b
Summary:
If one column family is dropped, we should simply skip it and continue to flush
other active ones.
Currently we use Status::ShutdownInProgress to notify caller of column families
being dropped. In the future, we should consider using a different Status code.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4708
Differential Revision: D13378954
Pulled By: riversand963
fbshipit-source-id: 42f248cdf2d32d4c0f677cd39012694b8f1328ca
Yanqin Jin