Revision aed7abbcca7574ed438c3b22e27db9bf249e8de3 authored by Xin Tong on 18 May 2018, 00:49:06 UTC, committed by Facebook Github Bot on 18 May 2018, 00:57:48 UTC
Summary: Running. TEST_TMPDIR=/dev/shm ./buck-out/gen/rocks/tools/rocks_db_bench --benchmarks=readwhilewriting --num=5000000 -benchmark_write_rate_limit=2000000 --threads=32 Collected esan data and reorder field. Accesses to 4th and 6th fields take majority of the access. Group them. Overall, this struct takes 10%+ of the total accesses in the program. (637773011/6107964986) ==2433831== class rocksdb::InlineSkipList ==2433831== size = 48, count = 637773011, ratio = 112412, array access = 0 ==2433831== # 0: offset = 0, size = 2, count = 455137, type = i16 ==2433831== # 1: offset = 2, size = 2, count = 6, type = i16 ==2433831== # 2: offset = 4, size = 4, count = 182303, type = i32 ==2433831== # 3: offset = 8, size = 8, count = 263953900, type = %"class.rocksdb::MemTableRep::KeyComparator"* ==2433831== # 4: offset = 16, size = 8, count = 136409, type = %"class.rocksdb::Allocator"* ==2433831== # 5: offset = 24, size = 8, count = 366628820, type = %"struct.rocksdb::InlineSkipList<const rocksdb::MemTableRep::KeyComparator &>::Node"* ==2433831== # 6: offset = 32, size = 4, count = 6280031, type = %"struct.std::atomic" = type { %"struct.std::__atomic_base" } ==2433831== # 7: offset = 40, size = 8, count = 136405, type = %"struct.rocksdb::InlineSkipList<const rocksdb::MemTableRep::KeyComparator &>::Splice"* ==2433831==EfficiencySanitizer: total struct field access count = 6107964986 Before re-ordering [trentxintong@devbig460.frc2 ~/fbsource/fbcode]$ fgrep readwhilewriting without-ro.log readwhilewriting : 0.036 micros/op 27545605 ops/sec; 26.8 MB/s (45954 of 5000000 found) readwhilewriting : 0.036 micros/op 28024240 ops/sec; 27.2 MB/s (43158 of 5000000 found) readwhilewriting : 0.037 micros/op 27345145 ops/sec; 27.1 MB/s (46725 of 5000000 found) readwhilewriting : 0.037 micros/op 27072588 ops/sec; 27.3 MB/s (42605 of 5000000 found) readwhilewriting : 0.034 micros/op 29578781 ops/sec; 28.3 MB/s (44294 of 5000000 found) readwhilewriting : 0.035 micros/op 28528304 ops/sec; 27.7 MB/s (44176 of 5000000 found) readwhilewriting : 0.037 micros/op 27075497 ops/sec; 26.5 MB/s (43763 of 5000000 found) readwhilewriting : 0.036 micros/op 28024117 ops/sec; 27.1 MB/s (40622 of 5000000 found) readwhilewriting : 0.037 micros/op 27078709 ops/sec; 27.6 MB/s (47774 of 5000000 found) readwhilewriting : 0.034 micros/op 29020689 ops/sec; 28.1 MB/s (45066 of 5000000 found) AVERAGE()=27.37 MB/s After re-ordering [trentxintong@devbig460.frc2 ~/fbsource/fbcode]$ fgrep readwhilewriting ro.log readwhilewriting : 0.036 micros/op 27542409 ops/sec; 27.7 MB/s (46163 of 5000000 found) readwhilewriting : 0.036 micros/op 28021148 ops/sec; 28.2 MB/s (46155 of 5000000 found) readwhilewriting : 0.036 micros/op 28021035 ops/sec; 27.3 MB/s (44039 of 5000000 found) readwhilewriting : 0.036 micros/op 27538659 ops/sec; 27.5 MB/s (46781 of 5000000 found) readwhilewriting : 0.036 micros/op 28028604 ops/sec; 27.6 MB/s (44689 of 5000000 found) readwhilewriting : 0.036 micros/op 27541452 ops/sec; 27.3 MB/s (43156 of 5000000 found) readwhilewriting : 0.034 micros/op 29041338 ops/sec; 28.8 MB/s (44895 of 5000000 found) readwhilewriting : 0.036 micros/op 27784974 ops/sec; 26.3 MB/s (39963 of 5000000 found) readwhilewriting : 0.036 micros/op 27538892 ops/sec; 28.1 MB/s (46570 of 5000000 found) readwhilewriting : 0.038 micros/op 26622473 ops/sec; 27.0 MB/s (43236 of 5000000 found) AVERAGE()=27.58 MB/s Closes https://github.com/facebook/rocksdb/pull/3855 Reviewed By: siying Differential Revision: D8048781 Pulled By: trentxintong fbshipit-source-id: bc9807a9845e2a92cb171ce1ecb5a2c8a51f1481
1 parent fa43948
statistics.h
// Copyright (c) 2011-present, Facebook, Inc. 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 "rocksdb/statistics.h"
#include <vector>
#include <atomic>
#include <string>
#include "monitoring/histogram.h"
#include "port/likely.h"
#include "port/port.h"
#include "util/core_local.h"
#include "util/mutexlock.h"
#ifdef __clang__
#define ROCKSDB_FIELD_UNUSED __attribute__((__unused__))
#else
#define ROCKSDB_FIELD_UNUSED
#endif // __clang__
namespace rocksdb {
enum TickersInternal : uint32_t {
INTERNAL_TICKER_ENUM_START = TICKER_ENUM_MAX,
INTERNAL_TICKER_ENUM_MAX
};
enum HistogramsInternal : uint32_t {
INTERNAL_HISTOGRAM_START = HISTOGRAM_ENUM_MAX,
INTERNAL_HISTOGRAM_ENUM_MAX
};
class StatisticsImpl : public Statistics {
public:
StatisticsImpl(std::shared_ptr<Statistics> stats,
bool enable_internal_stats);
virtual ~StatisticsImpl();
virtual uint64_t getTickerCount(uint32_t ticker_type) const override;
virtual void histogramData(uint32_t histogram_type,
HistogramData* const data) const override;
std::string getHistogramString(uint32_t histogram_type) const override;
virtual void setTickerCount(uint32_t ticker_type, uint64_t count) override;
virtual uint64_t getAndResetTickerCount(uint32_t ticker_type) override;
virtual void recordTick(uint32_t ticker_type, uint64_t count) override;
virtual void measureTime(uint32_t histogram_type, uint64_t value) override;
virtual Status Reset() override;
virtual std::string ToString() const override;
virtual bool HistEnabledForType(uint32_t type) const override;
private:
// If non-nullptr, forwards updates to the object pointed to by `stats_`.
std::shared_ptr<Statistics> stats_;
// TODO(ajkr): clean this up since there are no internal stats anymore
bool enable_internal_stats_;
// Synchronizes anything that operates across other cores' local data,
// such that operations like Reset() can be performed atomically.
mutable port::Mutex aggregate_lock_;
// The ticker/histogram data are stored in this structure, which we will store
// per-core. It is cache-aligned, so tickers/histograms belonging to different
// cores can never share the same cache line.
//
// Alignment attributes expand to nothing depending on the platform
struct StatisticsData {
std::atomic_uint_fast64_t tickers_[INTERNAL_TICKER_ENUM_MAX] = {{0}};
HistogramImpl histograms_[INTERNAL_HISTOGRAM_ENUM_MAX];
char
padding[(CACHE_LINE_SIZE -
(INTERNAL_TICKER_ENUM_MAX * sizeof(std::atomic_uint_fast64_t) +
INTERNAL_HISTOGRAM_ENUM_MAX * sizeof(HistogramImpl)) %
CACHE_LINE_SIZE)] ROCKSDB_FIELD_UNUSED;
};
static_assert(sizeof(StatisticsData) % 64 == 0, "Expected 64-byte aligned");
CoreLocalArray<StatisticsData> per_core_stats_;
uint64_t getTickerCountLocked(uint32_t ticker_type) const;
std::unique_ptr<HistogramImpl> getHistogramImplLocked(
uint32_t histogram_type) const;
void setTickerCountLocked(uint32_t ticker_type, uint64_t count);
};
// Utility functions
inline void MeasureTime(Statistics* statistics, uint32_t histogram_type,
uint64_t value) {
if (statistics) {
statistics->measureTime(histogram_type, value);
}
}
inline void RecordTick(Statistics* statistics, uint32_t ticker_type,
uint64_t count = 1) {
if (statistics) {
statistics->recordTick(ticker_type, count);
}
}
inline void SetTickerCount(Statistics* statistics, uint32_t ticker_type,
uint64_t count) {
if (statistics) {
statistics->setTickerCount(ticker_type, count);
}
}
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...