ec7a944360
Summary: We occasionally get write stalls (>1s Write() calls) on HDD under read load. The following timers explain almost all of the stalls: - perf_context.db_mutex_lock_nanos - perf_context.db_condition_wait_nanos - iostats_context.open_time - iostats_context.allocate_time - iostats_context.write_time - iostats_context.range_sync_time - iostats_context.logger_time In my experiments each of these occasionally takes >1s on write path under some workload. There are rare cases when Write() takes long but none of these takes long. Test Plan: Added code to our application to write the listed timings to log for slow writes. They usually add up to almost exactly the time Write() call took. Reviewers: rven, yhchiang, sdong Reviewed By: sdong Subscribers: march, dhruba, tnovak Differential Revision: https://reviews.facebook.net/D39177
53 lines
1.4 KiB
C++
53 lines
1.4 KiB
C++
// Copyright (c) 2014, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under the BSD-style license found in the
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
// of patent rights can be found in the PATENTS file in the same directory.
|
|
|
|
#ifndef INCLUDE_ROCKSDB_IOSTATS_CONTEXT_H_
|
|
#define INCLUDE_ROCKSDB_IOSTATS_CONTEXT_H_
|
|
|
|
#include <stdint.h>
|
|
#include <string>
|
|
|
|
#include "rocksdb/perf_level.h"
|
|
|
|
// A thread local context for gathering io-stats efficiently and transparently.
|
|
// Use SetPerfLevel(PerfLevel::kEnableTime) to enable time stats.
|
|
|
|
namespace rocksdb {
|
|
|
|
struct IOStatsContext {
|
|
// reset all io-stats counter to zero
|
|
void Reset();
|
|
|
|
std::string ToString() const;
|
|
|
|
// the thread pool id
|
|
uint64_t thread_pool_id;
|
|
|
|
// number of bytes that has been written.
|
|
uint64_t bytes_written;
|
|
// number of bytes that has been read.
|
|
uint64_t bytes_read;
|
|
|
|
// time spent in open() and fopen().
|
|
uint64_t open_nanos;
|
|
// time spent in fallocate().
|
|
uint64_t allocate_nanos;
|
|
// time spent in write() and pwrite().
|
|
uint64_t write_nanos;
|
|
// time spent in sync_file_range().
|
|
uint64_t range_sync_nanos;
|
|
|
|
// time spent in Logger::Logv().
|
|
uint64_t logger_nanos;
|
|
};
|
|
|
|
#ifndef IOS_CROSS_COMPILE
|
|
extern __thread IOStatsContext iostats_context;
|
|
#endif // IOS_CROSS_COMPILE
|
|
|
|
} // namespace rocksdb
|
|
|
|
#endif // INCLUDE_ROCKSDB_IOSTATS_CONTEXT_H_
|