Summary:
Production:
* Fixes GarbageCollect (and auto-GC triggered by PurgeOldBackups, DeleteBackup, or CreateNewBackup) to clean up backup directory independent of current settings (except max_valid_backups_to_open; see issue https://github.com/facebook/rocksdb/issues/4997) and prior settings used with same backup directory.
* Fixes GarbageCollect (and auto-GC) not to attempt to remove "." and ".." entries from directories.
* Clarifies contract with users in modifying BackupEngine operations. In short, leftovers from any incomplete operation are cleaned up by any subsequent call to that same kind of operation (PurgeOldBackups and DeleteBackup considered the same kind of operation). GarbageCollect is available to clean up after all kinds. (NB: right now PurgeOldBackups and DeleteBackup will clean up after incomplete CreateNewBackup, but we aren't promising to continue that behavior.)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6023
Test Plan:
* Refactors open parameters to use an option enum, for readability, etc. (Also fixes an unused parameter bug in the redundant OpenDBAndBackupEngineShareWithChecksum.)
* Fixes an apparent bug in ShareTableFilesWithChecksumsTransition in which old backup data was destroyed in the transition to be tested. That test is now augmented to ensure GarbageCollect (or auto-GC) does not remove shared files when BackupEngine is opened with share_table_files=false.
* Augments DeleteTmpFiles test to ensure that CreateNewBackup does auto-GC when an incompletely created backup is detected.
Differential Revision: D18453559
Pulled By: pdillinger
fbshipit-source-id: 5e54e7b08d711b161bc9c656181012b69a8feac4
Summary:
Only if there is a crash, power failure, or I/O error in
DeleteBackup, shared or private files from the backup might be left
behind that are not cleaned up by PurgeOldBackups or DeleteBackup-- only
by GarbageCollect. This makes the BackupEngine API "leaky by default."
Even if it means a modest performance hit, I think we should make
Delete and Purge do as they say, with ongoing best effort: i.e. future
calls will attempt to finish any incomplete work from earlier calls.
This change does that by having DeleteBackup and PurgeOldBackups do a
GarbageCollect, unless (to minimize performance hit) this BackupEngine
has already done a GarbageCollect and there have been no
deletion-related I/O errors in that GarbageCollect or since then.
Rejected alternative 1: remove meta file last instead of first. This would in theory turn partially deleted backups into corrupted backups, but code changes would be needed to allow the missing files and consider it acceptably corrupt, rather than failing to open the BackupEngine. This might be a reasonable choice, but I mostly rejected it because it doesn't solve the legacy problem of cleaning up existing lingering files.
Rejected alternative 2: use a deletion marker file. If deletion started with creating a file that marks a backup as flagged for deletion, then we could reliably detect partially deleted backups and efficiently finish removing them. In addition to not solving the legacy problem, this could be precarious if there's a disk full situation, and we try to create a new file in order to delete some files. Ugh.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6015
Test Plan: Updated unit tests
Differential Revision: D18401333
Pulled By: pdillinger
fbshipit-source-id: 12944e372ce6809f3f5a4c416c3b321a8927d925
Summary:
The calculation in BlockBasedTable::MultiGet for the required buffer length for reading in compressed blocks is incorrect. It needs to take the 5-byte block trailer into account.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6014
Test Plan: Add a unit test DBBasicTest.MultiGetBufferOverrun that fails in asan_check before the fix, and passes after.
Differential Revision: D18412753
Pulled By: anand1976
fbshipit-source-id: 754dfb66be1d5f161a7efdf87be872198c7e3b72
Summary:
This PR fixes https://github.com/facebook/rocksdb/issues/5975. In ```BlockBasedTable::RetrieveMultipleBlocks()```, we were calling ```MaybeReadBlocksAndLoadToCache()```, which is a no-op if neither uncompressed nor compressed block cache are configured.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5991
Test Plan:
1. Add unit tests that fail with the old code and pass with the new
2. make check and asan_check
Cc spetrunia
Differential Revision: D18272744
Pulled By: anand1976
fbshipit-source-id: e62fa6090d1a6adf84fcd51dfd6859b03c6aebfe
Summary:
A recent change introduced readahead inside VerifyChecksum(). However it is not compatible with mmap mode and generated wrong checksum verification failure. Fix it by not enabling readahead in mmap
mode.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5945
Test Plan: Add a unit test that used to fail.
Differential Revision: D18021443
fbshipit-source-id: 6f2eb600f81b26edb02222563a4006869d576bff
Summary:
Partition Filters make use of a top-level index to find the partition that might have the bloom hash of the key. The index is with internal key format (before format version 3). Each partition contains the i) blooms of the keys in that range ii) bloom of prefixes of keys in that range, iii) the bloom of the prefix of the last key in the previous partition.
When ::SeekForPrev(key), we first perform a prefix bloom test on the SST file. The partition however is identified using the full internal key, rather than the prefix key. The reason is to be compatible with the internal key format of the top-level index. This creates a corner case. Example:
- SST k, Partition N: P1K1, P1K2
- SST k, top-level index: P1K2
- SST k+1, Partition 1: P2K1, P3K1
- SST k+1 top-level index: P3K1
When SeekForPrev(P1K3), it should point us to P1K2. However SST k top-level index would reject P1K3 since it is out of range.
One possible fix would be to search with the prefix P1 (instead of full internal key P1K3) however the details of properly comparing prefix with full internal key might get complicated. The fix we apply in this PR is to look into the last partition anyway even if the key is out of range.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5907
Differential Revision: D17889918
Pulled By: maysamyabandeh
fbshipit-source-id: 169fd7b3c71dbc08808eae5a8340611ebe5bdc1e
Summary:
When an iterator reseek happens with the user specifying a new iterate_upper_bound in ReadOptions, and the new seek position is at the end of the same data block, the Seek() ends up using a stale value of data_block_within_upper_bound_ and may return incorrect results.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5883
Test Plan: Added a new test case DBIteratorTest.IterReseekNewUpperBound. Verified that it failed due to the assertion failure without the fix, and passes with the fix.
Differential Revision: D17752740
Pulled By: anand1976
fbshipit-source-id: f9b635ff5d6aeb0e1bef102cf8b2f900efd378e3
Summary:
This reverts commit 9fad3e21eb.
Iterator verification in stress tests sometimes fail for assertion
table/block_based/block_based_table_reader.cc:2973: void rocksdb::BlockBasedTableIterator<TBlockIter, TValue>::FindBlockForward() [with TBlockIter = rocksdb::DataBlockIter; TValue = rocksdb::Slice]: Assertion `!next_block_is_out_of_bound || user_comparator_.Compare(*read_options_.iterate_upper_bound, index_iter_->user_key()) <= 0' failed.
It is likely to be linked to https://github.com/facebook/rocksdb/pull/5286 together with https://github.com/facebook/rocksdb/pull/5468 as the former PR makes some child iterator's seek being avoided, so that upper bound condition fails to be updated there. Strictly speaking, the former PR was merged before the latter one, but the latter one feels a more important improvement so I choose to revert the former one for now.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5871
Differential Revision: D17689196
fbshipit-source-id: 4ded5be68f67bee2782d31a29cb72ea68f59dd8c
Summary:
In preparing to utilize a new Intel instruction extension, I
noticed problems with the existing build script in regard to the
existing utilized extensions, either with USE_SSE or PORTABLE flags.
* PORTABLE=0 was interpreted the same as PORTABLE=1. Now empty and 0
mean the same. (I guess you were not supposed to set PORTABLE= if you
wanted non-portable--except that...)
* The Facebook build script extensions would set PORTABLE=1 even if
it's already set in a make var or environment. Now it does not override
a non-empty setting, so use PORTABLE=0 for fully optimized build,
overriding Facebook environment default.
* Put in an explanation of the USE_SSE flag where it's used by
build_detect_platform, and cleaned up some confusing/redundant
associated logic.
* If USE_SSE was set and expected intrinsics were not available,
build_detect_platform would exit early but build would proceed with
broken, incomplete configuration. Now warning is gracefully recovered.
* If USE_SSE was set and expected intrinsics were not available,
build would still try to use flags like -msse4.2 etc. which could lead
to unexpected compilation failure or binary incompatibility. Now those
flags are not used if the warning is issued.
This should not break or change existing, valid build scripts.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5800
Test Plan: manual case testing
Differential Revision: D17369543
Pulled By: pdillinger
fbshipit-source-id: 4ee244911680ae71144d272c40aceea548e3ce88
Summary:
prefetch data for following block，avoid cache miss when doing crc caculate
I do performance test at kunpeng-920 server(arm-v8, 64core@2.6GHz)
./db_bench --benchmarks=crc32c --block_size=500000000
before optimise : 587313.500 micros/op 1 ops/sec; 811.9 MB/s (500000000 per op)
after optimise : 289248.500 micros/op 3 ops/sec; 1648.5 MB/s (500000000 per op)
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5773
Differential Revision: D17347339
fbshipit-source-id: bfcd74f0f0eb4b322b959be68019ddcaae1e3341
Summary:
PR https://github.com/facebook/rocksdb/issues/4020 implicitly enabled the hash index as well in stress/crash
tests, resulting in assertion failures in Block. This patch disables
the hash index until we can pinpoint the root cause of these issues.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5792
Test Plan:
Ran tools/db_crashtest.py and made sure it only uses index types 0 and 2
(binary search and partitioned index).
Differential Revision: D17346777
Pulled By: ltamasi
fbshipit-source-id: b4318f37f1fda3ee1bbff4ef2c2f556ca9e6b551
Summary:
This is required to compile on Windows with Visual Studio 2015.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5786
Differential Revision: D17335994
fbshipit-source-id: 8f9568310bc6f697e312b5e24ad465e9084f0011
Summary:
The max batch size that we can write to the WAL is controlled by a static manner. So if the leader write is less than 128 KB we will have the batch size as leader write size + 128 KB else the limit will be 1 MB. Both of them are statically defined.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5759
Differential Revision: D17329298
fbshipit-source-id: a3d910629d8d8ca84ea39ad89c2b2d284571ded5
Summary:
Use delete to disable automatic generated methods instead of private, and put the constructor together for more clear.This modification cause the unused field warning, so add unused attribute to disable this warning.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5009
Differential Revision: D17288733
fbshipit-source-id: 8a767ce096f185f1db01bd28fc88fef1cdd921f3
Summary:
cmake doesn't re-generate the timestamp on subsequent builds causing rebuilds of the lib
This improves compile time turn-arounds if you have rocksdb as a compileable library include, since with the state its now it will re-generate the time stamp .cc file each time you build, and thus re-compile + re-link the rocksdb library though anything in the source actually changed.
The original timestamp is recorded into `CMakeCache.txt` and will remain there until you flush this cache.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4799
Differential Revision: D17290040
fbshipit-source-id: 28357fef3422693c9c19e88fa2873c8db0f662ed
Summary:
- In `db_stress`, support choosing index type and whether to enable filter partitioning, and randomly set those options in crash test
- When partitioned filter is enabled by crash test, force partitioned index to also be enabled since it's a prerequisite
Pull Request resolved: https://github.com/facebook/rocksdb/pull/4020
Test Plan:
currently this is blocked on fixing the bug that crash test caught:
```
$ TEST_TMPDIR=/data/compaction_bench python ./tools/db_crashtest.py blackbox --simple --interval=10 --max_key=10000000
...
Verification failed for column family 0 key 937501: Value not found: NotFound:
Crash-recovery verification failed :(
```
Differential Revision: D8508683
Pulled By: maysamyabandeh
fbshipit-source-id: 0337e5d0558bcef26b1f3699f47265a2c1e99629
Summary:
On older macOS like 10.10 we saw the following compiler error:
```
/go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb/env/env_posix.cc:845:19:
error: use of undeclared identifier 'CLOCK_THREAD_CPUTIME_ID'
clock_gettime(CLOCK_THREAD_CPUTIME_ID, &ts);
^
```
According to mac's `man clock_gettime`: "These functions first appeared in Mac
OSX 10.12". So we should not try to compile it on earlier versions.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5570
Test Plan:
verified it compiles now on 10.10. Also did some investigation to
ensure it does not cause regression on macOS 10.12+, although I do not
have access to such an environment to really test.
Differential Revision: D17322629
Pulled By: riversand963
fbshipit-source-id: e0a412223854f826b4d83e6d15c3739ff4620d7d
Summary:
for fillbatch benchmar, the numEntries should be [num_] but not [num_ / 1000] because numEntries is just the total entries we want to test
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5198
Differential Revision: D17274664
Pulled By: anand1976
fbshipit-source-id: f96e952babdbac63fb99d14e1254d478a10437be
Summary:
i.e. if alive logfile is not being moved to archive while we are in GetSortedWalsOfType()
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5695
Differential Revision: D17279489
Pulled By: vjnadimpalli
fbshipit-source-id: 02bcf920a75b812edba8b87c6079b4e6fd5e683c
Summary:
Bug found by valgrind. New DynamicBloom wasn't allocating in
block sizes. New assertion added that probes starting in final word
would be in bounds.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5783
Test Plan: ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 valgrind --leak-check=full ./dynamic_bloom_test
Differential Revision: D17270623
Pulled By: pdillinger
fbshipit-source-id: 1e0407504b875133a771383cd488c70f91be2b87
Summary:
Check that we don't accidentally change the on-disk format of
existing Bloom filter implementations, including for various
CACHE_LINE_SIZE (by changing temporarily).
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5778
Test Plan: thisisthetest
Differential Revision: D17269630
Pulled By: pdillinger
fbshipit-source-id: c77017662f010a77603b7d475892b1f0d5563d8b
Summary:
When building with clang 9, warning is reported for InternalDBStatsType type names shadowed the one for statistics. Rename them.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5779
Test Plan: Build with clang 9 and see it passes.
Differential Revision: D17239378
fbshipit-source-id: af28fb42066c738cd1b841f9fe21ab4671dafd18
Summary:
cmake list add +crypto flag when use armv8 cpu
the function crc32c_arm64 use HAVE_ARM64_CRYPTO to check if can enable arm-neon instructions :
#ifdef HAVE_ARM64_CRYPTO
/* Crc32c Parallel computation
* Algorithm comes from Intel whitepaper:
* crc-iscsi-polynomial-crc32-instruction-paper
*
* Input data is divided into three equal-sized blocks
* Three parallel blocks (crc0, crc1, crc2) for 1024 Bytes
* One Block: 42(BLK_LENGTH) * 8(step length: crc32c_u64) bytes
*/
but the cmakelist not check and pass crypto flag now
I check the default Makefile has it:
ifeq (,$(shell $(CXX) -fsyntax-only -march=armv8-a+crc -xc /dev/null 2>&1))
CXXFLAGS += -march=armv8-a+crc+crypto
CFLAGS += -march=armv8-a+crc+crypto
ARMCRC_SOURCE=1
endif
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5750
Differential Revision: D17242027
fbshipit-source-id: 443c9b89755b4bc34e265205ab922db1b2e14bde
Summary:
ReadYourOwnWriteStress occasionally times out on some platforms. The patch splits it to three.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5776
Differential Revision: D17231743
Pulled By: maysamyabandeh
fbshipit-source-id: d42eeaf22f61a48d50f9c404d98b1081ae8dac94
Summary:
These uninitialized member variables can cause a key to not be pinned when it should be, causing erroneous behavior. For example ingesting a file with range deletion tombstones will yield an "external file have corrupted keys" on a Mac.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5720
Differential Revision: D17217673
fbshipit-source-id: cd7df7ce3ad9cf69c841c4d3dc6fd144eff9e212
Summary:
Fixes https://github.com/facebook/rocksdb/issues/5734. By reading the code the assert don't quite make sense to me, since `dataSize` and `fileOffset` has no correlation. But my knowledge about `EncryptedEnv` is very limited.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5735
Test Plan:
run `ENCRYPTED_ENV=1 ./db_encryption_test`
Signed-off-by: Yi Wu <yiwu@pingcap.com>
Differential Revision: D17133849
fbshipit-source-id: bb7262d308e5b2503c400b180edc252668df0ef0
Summary:
The `#include "core_local.h"` was pulling in libgcc's `posix_memalign()`
declaration. That declaration specifies `throw()` whereas musl libc's
declaration does not. This was leading to the following compiler error
when using musl libc:
```
In file included from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb/port/jemalloc_helper.h:26:0,
from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb/util/jemalloc_nodump_allocator.h:11,
from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb/util/jemalloc_nodump_allocator.cc:6:
/go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:63:29: error: declaration of 'int posix_memalign(void**, size_t, size_t) throw ()' has a different exception specifier
# define je_posix_memalign posix_memalign
^
/go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:63:29: note: from previous declaration 'int posix_memalign(void**, size_t, size_t)'
# define je_posix_memalign posix_memalign
^
/go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:202:38: note: in expansion of macro 'je_posix_memalign'
JEMALLOC_EXPORT int JEMALLOC_NOTHROW je_posix_memalign(void **memptr,
^~~~~~~~~~~~~~~~~
make[4]: *** [CMakeFiles/rocksdb.dir/util/jemalloc_nodump_allocator.cc.o] Error 1
```
Since `#include "core_local.h"` is not actually used, we can just remove
it. I verified that fixes the build.
There was a related PR here (https://github.com/facebook/rocksdb/issues/2188), although the problem description is
slightly different.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5583
Differential Revision: D16343227
fbshipit-source-id: 0386bc2b5fd55b2c3b5fba19382014efa52e44f8
Summary:
FullFilterBitsBuilder::CalculateSpace use CACHE_LINE_SIZE which is 64@X86 but 128@ARM64
when it run bloom_test.FullVaryingLengths it failed on ARM64 server,
the assert can be fixed by change 128->CACHE_LINE_SIZE*2 as merged
ASSERT_LE(FilterSize(), (size_t)((length * 10 / 8) + CACHE_LINE_SIZE * 2 + 5)) << length;
run bloom_test
before fix:
/root/rocksdb-master/util/bloom_test.cc:281: Failure
Expected: (FilterSize()) <= ((size_t)((length * 10 / 8) + 128 + 5)), actual: 389 vs 383
200
[ FAILED ] FullBloomTest.FullVaryingLengths (32 ms)
[----------] 4 tests from FullBloomTest (32 ms total)
[----------] Global test environment tear-down
[==========] 7 tests from 2 test cases ran. (116 ms total)
[ PASSED ] 6 tests.
[ FAILED ] 1 test, listed below:
[ FAILED ] FullBloomTest.FullVaryingLengths
after fix:
Filters: 37 good, 0 mediocre
[ OK ] FullBloomTest.FullVaryingLengths (90 ms)
[----------] 4 tests from FullBloomTest (90 ms total)
[----------] Global test environment tear-down
[==========] 7 tests from 2 test cases ran. (174 ms total)
[ PASSED ] 7 tests.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5745
Differential Revision: D17076047
fbshipit-source-id: e7beb5d55d4855fceb2b84bc8119a6b0759de635
Summary:
Since DynamicBloom is now only used in-memory, we're free to
change it without schema compatibility issues. The new implementation
is drawn from (with manifest permission)
303542a767/bloom_simulation_tests/foo.cc (L613)
This has several speed advantages over the prior implementation:
* Uses fastrange instead of %
* Minimum logic to determine first (and all) probed memory addresses
* (Major) Two probes per 64-bit memory fetch/write.
* Very fast and effective (murmur-like) hash expansion/re-mixing. (At
least on recent CPUs, integer multiplication is very cheap.)
While a Bloom filter with 512-bit cache locality has about a 1.15x FP
rate penalty (e.g. 0.84% to 0.97%), further restricting to two probes
per 64 bits incurs an additional 1.12x FP rate penalty (e.g. 0.97% to
1.09%). Nevertheless, the unit tests show no "mediocre" FP rate samples,
unlike the old implementation with more erratic FP rates.
Especially for the memtable, we expect speed to outweigh somewhat higher
FP rates. For example, a negative table query would have to be 1000x
slower than a BF query to justify doubling BF query time to shave 10% off
FP rate (working assumption around 1% FP rate). While that seems likely
for SSTs, my data suggests a speed factor of roughly 50x for the memtable
(vs. BF; ~1.5% lower write throughput when enabling memtable Bloom
filter, after this change). Thus, it's probably not worth even 5% more
time in the Bloom filter to shave off 1/10th of the Bloom FP rate, or 0.1%
in absolute terms, and it's probably at least 20% slower to recoup that
much FP rate from this new implementation. Because of this, we do not see
a need for a 'locality' option that affects the MemTable Bloom filter
and have decoupled the MemTable Bloom filter from Options::bloom_locality.
Note that just 3% more memory to the Bloom filter (10.3 bits per key vs.
just 10) is able to make up for the ~12% FP rate drop in the new
implementation:
[] # Nearly "ideal" FP-wise but reasonably fast cache-local implementation
[~/wormhashing/bloom_simulation_tests] ./foo_gcc_IMPL_CACHE_WORM64_FROM32_any.out 10000000 6 10 $RANDOM 100000000
./foo_gcc_IMPL_CACHE_WORM64_FROM32_any.out time: 3.29372 sampled_fp_rate: 0.00985956 ...
[] # Close match to this new implementation
[~/wormhashing/bloom_simulation_tests] ./foo_gcc_IMPL_CACHE_MUL64_BLOCK_FROM32_any.out 10000000 6 10.3 $RANDOM 100000000
./foo_gcc_IMPL_CACHE_MUL64_BLOCK_FROM32_any.out time: 2.10072 sampled_fp_rate: 0.00985655 ...
[] # Old locality=1 implementation
[~/wormhashing/bloom_simulation_tests] ./foo_gcc_IMPL_CACHE_ROCKSDB_DYNAMIC_any.out 10000000 6 10 $RANDOM 100000000
./foo_gcc_IMPL_CACHE_ROCKSDB_DYNAMIC_any.out time: 3.95472 sampled_fp_rate: 0.00988943 ...
Also note the dramatic speed improvement vs. alternatives.
--
Performance unit test: DynamicBloomTest.concurrent_with_perf is updated
to report more precise timing data. (Measure running time of each
thread, not just longest running thread, etc.) Results averaged over
various sizes enabled with --enable_perf and 20 runs each; old dynamic
bloom refers to locality=1, the faster of the old:
old dynamic bloom, avg add latency = 65.6468
new dynamic bloom, avg add latency = 44.3809
old dynamic bloom, avg query latency = 50.6485
new dynamic bloom, avg query latency = 43.2186
old avg parallel add latency = 41.678
new avg parallel add latency = 24.5238
old avg parallel hit latency = 14.6322
new avg parallel hit latency = 12.3939
old avg parallel miss latency = 16.7289
new avg parallel miss latency = 12.2134
Tested on a dedicated 64-bit production machine at Facebook. Significant
improvement all around.
Despite now using std::atomic<uint64_t>, quick before-and-after test on
a 32-bit machine (Intel Atom N270, released 2008) shows no regression in
performance, in some cases modest improvement.
--
Performance integration test (synthetic): with DEBUG_LEVEL=0, used
TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=fillrandom,readmissing,readrandom,stats --num=2000000
and optionally with -memtable_whole_key_filtering -memtable_bloom_size_ratio=0.01
300 runs each configuration.
Write throughput change by enabling memtable bloom:
Old locality=0: -3.06%
Old locality=1: -2.37%
New: -1.50%
conclusion -> seems to substantially close the gap
Readmissing throughput change by enabling memtable bloom:
Old locality=0: +34.47%
Old locality=1: +34.80%
New: +33.25%
conclusion -> maybe a small new penalty from FP rate
Readrandom throughput change by enabling memtable bloom:
Old locality=0: +31.54%
Old locality=1: +31.13%
New: +30.60%
conclusion -> maybe also from FP rate (after memtable flush)
--
Another conclusion we can draw from this new implementation is that the
existing 32-bit hash function is not inherently crippling the Bloom
filter speed or accuracy, below about 5 million keys. For speed, the
implementation is essentially the same whether starting with 32-bits or
64-bits of hash; it just determines whether the first multiplication
after fastrange is a pseudorandom expansion or needed re-mix. Note that
this multiplication can occur while memory is fetching.
For accuracy, in a standard configuration, you need about 5 million
keys before you have about a 1.1x FP penalty due to using a
32-bit hash vs. 64-bit:
[~/wormhashing/bloom_simulation_tests] ./foo_gcc_IMPL_CACHE_MUL64_BLOCK_FROM32_any.out $((5 * 1000 * 1000 * 10)) 6 10 $RANDOM 100000000
./foo_gcc_IMPL_CACHE_MUL64_BLOCK_FROM32_any.out time: 2.52069 sampled_fp_rate: 0.0118267 ...
[~/wormhashing/bloom_simulation_tests] ./foo_gcc_IMPL_CACHE_MUL64_BLOCK_any.out $((5 * 1000 * 1000 * 10)) 6 10 $RANDOM 100000000
./foo_gcc_IMPL_CACHE_MUL64_BLOCK_any.out time: 2.43871 sampled_fp_rate: 0.0109059
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5762
Differential Revision: D17214194
Pulled By: pdillinger
fbshipit-source-id: ad9da031772e985fd6b62a0e1db8e81892520595
Summary:
This avoids rehashing the key in TrackKey() in case the key is not already
in the map of tracked keys, which will happen at least once per key used in a
transaction.
Additionally fix two typos.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5696
Differential Revision: D17210178
Pulled By: lth
fbshipit-source-id: 7e2c28e9e505c1d1c1535d435250cf2b191a6fdf
Summary:
DynamicBloom was being used both for memory-only and for on-disk filters, as part of the PlainTable format. To set up enhancements to the memtable Bloom filter, this splits the code into two copies and removes unused features from each copy. Adds test PlainTableDBTest.BloomSchema to ensure no accidental change to that format.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5767
Differential Revision: D17206963
Pulled By: pdillinger
fbshipit-source-id: 6cce8d55305ed0df051b4c58bdc98c8ad81d0553
Summary:
Iterators reseek to the target key after iterating over max_sequential_skip_in_iterations invalid values. The logic is susceptible to an infinite loop bug, which has been present with WritePrepared Transactions up until 6.2 release. Although the bug is not present on master, the patch adds a unit test to prevent it from resurfacing again.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5727
Differential Revision: D16952759
Pulled By: maysamyabandeh
fbshipit-source-id: d0d973dddc8dfabd5a794931232aa4c862c74f51
