3dff28cf9b
Summary: For performance purposes, the lower level routines were changed to use a SystemClock* instead of a std::shared_ptr<SystemClock>. The shared ptr has some performance degradation on certain hardware classes. For most of the system, there is no risk of the pointer being deleted/invalid because the shared_ptr will be stored elsewhere. For example, the ImmutableDBOptions stores the Env which has a std::shared_ptr<SystemClock> in it. The SystemClock* within the ImmutableDBOptions is essentially a "short cut" to gain access to this constant resource. There were a few classes (PeriodicWorkScheduler?) where the "short cut" property did not hold. In those cases, the shared pointer was preserved. Using db_bench readrandom perf_level=3 on my EC2 box, this change performed as well or better than 6.17: 6.17: readrandom : 28.046 micros/op 854902 ops/sec; 61.3 MB/s (355999 of 355999 found) 6.18: readrandom : 32.615 micros/op 735306 ops/sec; 52.7 MB/s (290999 of 290999 found) PR: readrandom : 27.500 micros/op 871909 ops/sec; 62.5 MB/s (367999 of 367999 found) (Note that the times for 6.18 are prior to revert of the SystemClock). Pull Request resolved: https://github.com/facebook/rocksdb/pull/8033 Reviewed By: pdillinger Differential Revision: D27014563 Pulled By: mrambacher fbshipit-source-id: ad0459eba03182e454391b5926bf5cdd45657b67
98 lines
4.1 KiB
C++
98 lines
4.1 KiB
C++
// 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 "monitoring/perf_step_timer.h"
|
|
#include "rocksdb/perf_context.h"
|
|
#include "util/stop_watch.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
#if defined(NPERF_CONTEXT) || !defined(ROCKSDB_SUPPORT_THREAD_LOCAL)
|
|
extern PerfContext perf_context;
|
|
#else
|
|
#if defined(OS_SOLARIS)
|
|
extern __thread PerfContext perf_context_;
|
|
#define perf_context (*get_perf_context())
|
|
#else
|
|
extern thread_local PerfContext perf_context;
|
|
#endif
|
|
#endif
|
|
|
|
#if defined(NPERF_CONTEXT)
|
|
|
|
#define PERF_TIMER_STOP(metric)
|
|
#define PERF_TIMER_START(metric)
|
|
#define PERF_TIMER_GUARD(metric)
|
|
#define PERF_TIMER_GUARD_WITH_CLOCK(metric, clock)
|
|
#define PERF_CPU_TIMER_GUARD(metric, clock)
|
|
#define PERF_CONDITIONAL_TIMER_FOR_MUTEX_GUARD(metric, condition, stats, \
|
|
ticker_type)
|
|
#define PERF_TIMER_MEASURE(metric)
|
|
#define PERF_COUNTER_ADD(metric, value)
|
|
#define PERF_COUNTER_BY_LEVEL_ADD(metric, value, level)
|
|
|
|
#else
|
|
|
|
// Stop the timer and update the metric
|
|
#define PERF_TIMER_STOP(metric) perf_step_timer_##metric.Stop();
|
|
|
|
#define PERF_TIMER_START(metric) perf_step_timer_##metric.Start();
|
|
|
|
// Declare and set start time of the timer
|
|
#define PERF_TIMER_GUARD(metric) \
|
|
PerfStepTimer perf_step_timer_##metric(&(perf_context.metric)); \
|
|
perf_step_timer_##metric.Start();
|
|
|
|
// Declare and set start time of the timer
|
|
#define PERF_TIMER_GUARD_WITH_CLOCK(metric, clock) \
|
|
PerfStepTimer perf_step_timer_##metric(&(perf_context.metric), clock); \
|
|
perf_step_timer_##metric.Start();
|
|
|
|
// Declare and set start time of the timer
|
|
#define PERF_CPU_TIMER_GUARD(metric, clock) \
|
|
PerfStepTimer perf_step_timer_##metric( \
|
|
&(perf_context.metric), clock, true, \
|
|
PerfLevel::kEnableTimeAndCPUTimeExceptForMutex); \
|
|
perf_step_timer_##metric.Start();
|
|
|
|
#define PERF_CONDITIONAL_TIMER_FOR_MUTEX_GUARD(metric, condition, stats, \
|
|
ticker_type) \
|
|
PerfStepTimer perf_step_timer_##metric(&(perf_context.metric), nullptr, \
|
|
false, PerfLevel::kEnableTime, stats, \
|
|
ticker_type); \
|
|
if (condition) { \
|
|
perf_step_timer_##metric.Start(); \
|
|
}
|
|
|
|
// Update metric with time elapsed since last START. start time is reset
|
|
// to current timestamp.
|
|
#define PERF_TIMER_MEASURE(metric) perf_step_timer_##metric.Measure();
|
|
|
|
// Increase metric value
|
|
#define PERF_COUNTER_ADD(metric, value) \
|
|
if (perf_level >= PerfLevel::kEnableCount) { \
|
|
perf_context.metric += value; \
|
|
}
|
|
|
|
// Increase metric value
|
|
#define PERF_COUNTER_BY_LEVEL_ADD(metric, value, level) \
|
|
if (perf_level >= PerfLevel::kEnableCount && \
|
|
perf_context.per_level_perf_context_enabled && \
|
|
perf_context.level_to_perf_context) { \
|
|
if ((*(perf_context.level_to_perf_context)).find(level) != \
|
|
(*(perf_context.level_to_perf_context)).end()) { \
|
|
(*(perf_context.level_to_perf_context))[level].metric += value; \
|
|
} \
|
|
else { \
|
|
PerfContextByLevel empty_context; \
|
|
(*(perf_context.level_to_perf_context))[level] = empty_context; \
|
|
(*(perf_context.level_to_perf_context))[level].metric += value; \
|
|
} \
|
|
} \
|
|
|
|
#endif
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|