bae6f58696
Summary:
In MultiGet, access each applicable filter partition only once
per batch, rather than for each applicable key. Also,
* Fix Bloom stats for MultiGet
* Fix/refactor MultiGetContext::Range::KeysLeft, including
* Add efficient BitsSetToOne implementation
* Assert that MultiGetContext::Range does not go beyond shift range
Performance test: Generate db:
$ ./db_bench --benchmarks=fillrandom --num=15000000 --cache_index_and_filter_blocks -bloom_bits=10 -partition_index_and_filters=true
...
Before (middle performing run of three; note some missing Bloom stats):
$ ./db_bench --use-existing-db --benchmarks=multireadrandom --num=15000000 --cache_index_and_filter_blocks --bloom_bits=10 --threads=16 --cache_size=20000000 -partition_index_and_filters -batch_size=32 -multiread_batched -statistics --duration=20 2>&1 | egrep 'micros/op|block.cache.filter.hit|bloom.filter.(full|use)|number.multiget'
multireadrandom : 26.403 micros/op 597517 ops/sec; (548427 of 671968 found)
rocksdb.block.cache.filter.hit COUNT : 83443275
rocksdb.bloom.filter.useful COUNT : 0
rocksdb.bloom.filter.full.positive COUNT : 0
rocksdb.bloom.filter.full.true.positive COUNT : 7931450
rocksdb.number.multiget.get COUNT : 385984
rocksdb.number.multiget.keys.read COUNT : 12351488
rocksdb.number.multiget.bytes.read COUNT : 793145000
rocksdb.number.multiget.keys.found COUNT : 7931450
After (middle performing run of three):
$ ./db_bench_new --use-existing-db --benchmarks=multireadrandom --num=15000000 --cache_index_and_filter_blocks --bloom_bits=10 --threads=16 --cache_size=20000000 -partition_index_and_filters -batch_size=32 -multiread_batched -statistics --duration=20 2>&1 | egrep 'micros/op|block.cache.filter.hit|bloom.filter.(full|use)|number.multiget'
multireadrandom : 21.024 micros/op 752963 ops/sec; (705188 of 863968 found)
rocksdb.block.cache.filter.hit COUNT : 49856682
rocksdb.bloom.filter.useful COUNT : 45684579
rocksdb.bloom.filter.full.positive COUNT : 10395458
rocksdb.bloom.filter.full.true.positive COUNT : 9908456
rocksdb.number.multiget.get COUNT : 481984
rocksdb.number.multiget.keys.read COUNT : 15423488
rocksdb.number.multiget.bytes.read COUNT : 990845600
rocksdb.number.multiget.keys.found COUNT : 9908456
So that's about 25% higher throughput even for random keys
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6757
Test Plan: unit test included
Reviewed By: anand1976
Differential Revision: D21243256
Pulled By: pdillinger
fbshipit-source-id: 5644a1468d9e8c8575be02f4e04bc5d62dbbb57f
39 lines
1.2 KiB
C++
39 lines
1.2 KiB
C++
// Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
#pragma once
|
|
|
|
#include <assert.h>
|
|
#include <stdint.h>
|
|
#ifdef _MSC_VER
|
|
#include <intrin.h>
|
|
#endif
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
template <typename T>
|
|
inline int BitsSetToOne(T v) {
|
|
static_assert(std::is_integral<T>::value, "non-integral type");
|
|
#ifdef _MSC_VER
|
|
static_assert(sizeof(T) <= sizeof(uint64_t), "type too big");
|
|
if (sizeof(T) > sizeof(uint32_t)) {
|
|
return static_cast<int>(__popcnt64(static_cast<uint64_t>(v)));
|
|
} else {
|
|
return static_cast<int>(__popcnt(static_cast<uint32_t>(v)));
|
|
}
|
|
#else
|
|
static_assert(sizeof(T) <= sizeof(unsigned long long), "type too big");
|
|
if (sizeof(T) > sizeof(unsigned long)) {
|
|
return __builtin_popcountll(static_cast<unsigned long long>(v));
|
|
} else if (sizeof(T) > sizeof(unsigned int)) {
|
|
return __builtin_popcountl(static_cast<unsigned long>(v));
|
|
} else {
|
|
return __builtin_popcount(static_cast<unsigned int>(v));
|
|
}
|
|
#endif
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|