Igor Canadi
11 years ago
commit
ac92420fc5
@ -0,0 +1,39 @@ |
|||||||
|
# Rocksdb Change Log |
||||||
|
|
||||||
|
## 2.7.0 (01/28/2014) |
||||||
|
|
||||||
|
### Public API changes |
||||||
|
|
||||||
|
* Renamed `StackableDB::GetRawDB()` to `StackableDB::GetBaseDB()`. |
||||||
|
* Renamed `WriteBatch::Data()` `const std::string& Data() const`. |
||||||
|
* Renamed class `TableStats` to `TableProperties`. |
||||||
|
* Deleted class `PrefixHashRepFactory`. Please use `NewHashSkipListRepFactory()` instead. |
||||||
|
* Supported multi-threaded `EnableFileDeletions()` and `DisableFileDeletions()`. |
||||||
|
* Added `DB::GetOptions()`. |
||||||
|
* Added `DB::GetDbIdentity()`. |
||||||
|
|
||||||
|
### New Features |
||||||
|
|
||||||
|
* Added [BackupableDB](https://github.com/facebook/rocksdb/wiki/How-to-backup-RocksDB%3F) |
||||||
|
* Implemented [TailingIterator](https://github.com/facebook/rocksdb/wiki/Tailing-Iterator), a special type of iterator that |
||||||
|
doesn't create a snapshot (can be used to read newly inserted data) |
||||||
|
and is optimized for doing sequential reads. |
||||||
|
* Added property block for table, which allows (1) a table to store |
||||||
|
its metadata and (2) end user to collect and store properties they |
||||||
|
are interested in. |
||||||
|
* Enabled caching index and filter block in block cache (turned off by default). |
||||||
|
* Supported error report when doing manual compaction. |
||||||
|
* Supported additional Linux platform flavors and Mac OS. |
||||||
|
* Put with `SliceParts` - Variant of `Put()` that gathers output like `writev(2)` |
||||||
|
* Bug fixes and code refactor for compatibility with upcoming Column |
||||||
|
Family feature. |
||||||
|
|
||||||
|
### Performance Improvements |
||||||
|
|
||||||
|
* Huge benchmark performance improvements by multiple efforts. For example, increase in readonly QPS from about 530k in 2.6 release to 1.1 million in 2.7 [1] |
||||||
|
* Speeding up a way RocksDB deleted obsolete files - no longer listing the whole directory under a lock -- decrease in p99 |
||||||
|
* Use raw pointer instead of shared pointer for statistics: [5b825d](https://github.com/facebook/rocksdb/commit/5b825d6964e26ec3b4bb6faa708ebb1787f1d7bd) -- huge increase in performance -- shared pointers are slow |
||||||
|
* Optimized locking for `Get()` -- [1fdb3f](https://github.com/facebook/rocksdb/commit/1fdb3f7dc60e96394e3e5b69a46ede5d67fb976c) -- 1.5x QPS increase for some workloads |
||||||
|
* Cache speedup - [e8d40c3](https://github.com/facebook/rocksdb/commit/e8d40c31b3cca0c3e1ae9abe9b9003b1288026a9) |
||||||
|
* Implemented autovector, which allocates first N elements on stack. Most of vectors in RocksDB are small. Also, we never want to allocate heap objects while holding a mutex. -- [c01676e4](https://github.com/facebook/rocksdb/commit/c01676e46d3be08c3c140361ef1f5884f47d3b3c) |
||||||
|
* Lots of efforts to move malloc, memcpy and IO outside of locks |
||||||
@ -0,0 +1,298 @@ |
|||||||
|
|
||||||
|
// 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.
|
||||||
|
//
|
||||||
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
||||||
|
// Use of this source code is governed by a BSD-style license that can be
|
||||||
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
||||||
|
|
||||||
|
#include "db/internal_stats.h" |
||||||
|
|
||||||
|
#include <vector> |
||||||
|
|
||||||
|
namespace rocksdb { |
||||||
|
|
||||||
|
bool InternalStats::GetProperty(const Slice& property, std::string* value, |
||||||
|
VersionSet* version_set, int immsize) { |
||||||
|
Version* current = version_set->current(); |
||||||
|
Slice in = property; |
||||||
|
Slice prefix("rocksdb."); |
||||||
|
if (!in.starts_with(prefix)) return false; |
||||||
|
in.remove_prefix(prefix.size()); |
||||||
|
|
||||||
|
if (in.starts_with("num-files-at-level")) { |
||||||
|
in.remove_prefix(strlen("num-files-at-level")); |
||||||
|
uint64_t level; |
||||||
|
bool ok = ConsumeDecimalNumber(&in, &level) && in.empty(); |
||||||
|
if (!ok || (int)level >= number_levels_) { |
||||||
|
return false; |
||||||
|
} else { |
||||||
|
char buf[100]; |
||||||
|
snprintf(buf, sizeof(buf), "%d", |
||||||
|
current->NumLevelFiles(static_cast<int>(level))); |
||||||
|
*value = buf; |
||||||
|
return true; |
||||||
|
} |
||||||
|
} else if (in == "levelstats") { |
||||||
|
char buf[1000]; |
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Level Files Size(MB)\n" |
||||||
|
"--------------------\n"); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
for (int level = 0; level < number_levels_; level++) { |
||||||
|
snprintf(buf, sizeof(buf), "%3d %8d %8.0f\n", level, |
||||||
|
current->NumLevelFiles(level), |
||||||
|
current->NumLevelBytes(level) / 1048576.0); |
||||||
|
value->append(buf); |
||||||
|
} |
||||||
|
return true; |
||||||
|
|
||||||
|
} else if (in == "stats") { |
||||||
|
char buf[1000]; |
||||||
|
|
||||||
|
uint64_t wal_bytes = 0; |
||||||
|
uint64_t wal_synced = 0; |
||||||
|
uint64_t user_bytes_written = 0; |
||||||
|
uint64_t write_other = 0; |
||||||
|
uint64_t write_self = 0; |
||||||
|
uint64_t write_with_wal = 0; |
||||||
|
uint64_t total_bytes_written = 0; |
||||||
|
uint64_t total_bytes_read = 0; |
||||||
|
uint64_t micros_up = env_->NowMicros() - started_at_; |
||||||
|
// Add "+1" to make sure seconds_up is > 0 and avoid NaN later
|
||||||
|
double seconds_up = (micros_up + 1) / 1000000.0; |
||||||
|
uint64_t total_slowdown = 0; |
||||||
|
uint64_t total_slowdown_count = 0; |
||||||
|
uint64_t interval_bytes_written = 0; |
||||||
|
uint64_t interval_bytes_read = 0; |
||||||
|
uint64_t interval_bytes_new = 0; |
||||||
|
double interval_seconds_up = 0; |
||||||
|
|
||||||
|
if (statistics_) { |
||||||
|
wal_bytes = statistics_->getTickerCount(WAL_FILE_BYTES); |
||||||
|
wal_synced = statistics_->getTickerCount(WAL_FILE_SYNCED); |
||||||
|
user_bytes_written = statistics_->getTickerCount(BYTES_WRITTEN); |
||||||
|
write_other = statistics_->getTickerCount(WRITE_DONE_BY_OTHER); |
||||||
|
write_self = statistics_->getTickerCount(WRITE_DONE_BY_SELF); |
||||||
|
write_with_wal = statistics_->getTickerCount(WRITE_WITH_WAL); |
||||||
|
} |
||||||
|
|
||||||
|
// Pardon the long line but I think it is easier to read this way.
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
" Compactions\n" |
||||||
|
"Level Files Size(MB) Score Time(sec) Read(MB) Write(MB) Rn(MB) Rnp1(MB) Wnew(MB) RW-Amplify Read(MB/s) Write(MB/s) Rn Rnp1 Wnp1 NewW Count msComp msStall Ln-stall Stall-cnt\n" |
||||||
|
"------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\n" |
||||||
|
); |
||||||
|
value->append(buf); |
||||||
|
for (int level = 0; level < number_levels_; level++) { |
||||||
|
int files = current->NumLevelFiles(level); |
||||||
|
if (compaction_stats_[level].micros > 0 || files > 0) { |
||||||
|
int64_t bytes_read = compaction_stats_[level].bytes_readn + |
||||||
|
compaction_stats_[level].bytes_readnp1; |
||||||
|
int64_t bytes_new = compaction_stats_[level].bytes_written - |
||||||
|
compaction_stats_[level].bytes_readnp1; |
||||||
|
double amplify = (compaction_stats_[level].bytes_readn == 0) |
||||||
|
? 0.0 |
||||||
|
: (compaction_stats_[level].bytes_written + |
||||||
|
compaction_stats_[level].bytes_readnp1 + |
||||||
|
compaction_stats_[level].bytes_readn) / |
||||||
|
(double)compaction_stats_[level].bytes_readn; |
||||||
|
|
||||||
|
total_bytes_read += bytes_read; |
||||||
|
total_bytes_written += compaction_stats_[level].bytes_written; |
||||||
|
|
||||||
|
uint64_t stalls = level == 0 ? (stall_counts_[LEVEL0_SLOWDOWN] + |
||||||
|
stall_counts_[LEVEL0_NUM_FILES] + |
||||||
|
stall_counts_[MEMTABLE_COMPACTION]) |
||||||
|
: stall_leveln_slowdown_count_[level]; |
||||||
|
|
||||||
|
double stall_us = level == 0 ? (stall_micros_[LEVEL0_SLOWDOWN] + |
||||||
|
stall_micros_[LEVEL0_NUM_FILES] + |
||||||
|
stall_micros_[MEMTABLE_COMPACTION]) |
||||||
|
: stall_leveln_slowdown_[level]; |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"%3d %8d %8.0f %5.1f %9.0f %9.0f %9.0f %9.0f %9.0f %9.0f " |
||||||
|
"%10.1f %9.1f %11.1f %8d %8d %8d %8d %8d %8d %9.1f %9.1f " |
||||||
|
"%9lu\n", |
||||||
|
level, files, current->NumLevelBytes(level) / 1048576.0, |
||||||
|
current->NumLevelBytes(level) / |
||||||
|
version_set->MaxBytesForLevel(level), |
||||||
|
compaction_stats_[level].micros / 1e6, bytes_read / 1048576.0, |
||||||
|
compaction_stats_[level].bytes_written / 1048576.0, |
||||||
|
compaction_stats_[level].bytes_readn / 1048576.0, |
||||||
|
compaction_stats_[level].bytes_readnp1 / 1048576.0, |
||||||
|
bytes_new / 1048576.0, amplify, |
||||||
|
// +1 to avoid division by 0
|
||||||
|
(bytes_read / 1048576.0) / |
||||||
|
((compaction_stats_[level].micros + 1) / 1000000.0), |
||||||
|
(compaction_stats_[level].bytes_written / 1048576.0) / |
||||||
|
((compaction_stats_[level].micros + 1) / 1000000.0), |
||||||
|
compaction_stats_[level].files_in_leveln, |
||||||
|
compaction_stats_[level].files_in_levelnp1, |
||||||
|
compaction_stats_[level].files_out_levelnp1, |
||||||
|
compaction_stats_[level].files_out_levelnp1 - |
||||||
|
compaction_stats_[level].files_in_levelnp1, |
||||||
|
compaction_stats_[level].count, |
||||||
|
(int)((double)compaction_stats_[level].micros / 1000.0 / |
||||||
|
(compaction_stats_[level].count + 1)), |
||||||
|
(double)stall_us / 1000.0 / (stalls + 1), stall_us / 1000000.0, |
||||||
|
(unsigned long)stalls); |
||||||
|
total_slowdown += stall_leveln_slowdown_[level]; |
||||||
|
total_slowdown_count += stall_leveln_slowdown_count_[level]; |
||||||
|
value->append(buf); |
||||||
|
} |
||||||
|
} |
||||||
|
|
||||||
|
interval_bytes_new = user_bytes_written - last_stats_.ingest_bytes_; |
||||||
|
interval_bytes_read = total_bytes_read - last_stats_.compaction_bytes_read_; |
||||||
|
interval_bytes_written = |
||||||
|
total_bytes_written - last_stats_.compaction_bytes_written_; |
||||||
|
interval_seconds_up = seconds_up - last_stats_.seconds_up_; |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), "Uptime(secs): %.1f total, %.1f interval\n", |
||||||
|
seconds_up, interval_seconds_up); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Writes cumulative: %llu total, %llu batches, " |
||||||
|
"%.1f per batch, %.2f ingest GB\n", |
||||||
|
(unsigned long long)(write_other + write_self), |
||||||
|
(unsigned long long)write_self, |
||||||
|
(write_other + write_self) / (double)(write_self + 1), |
||||||
|
user_bytes_written / (1048576.0 * 1024)); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"WAL cumulative: %llu WAL writes, %llu WAL syncs, " |
||||||
|
"%.2f writes per sync, %.2f GB written\n", |
||||||
|
(unsigned long long)write_with_wal, (unsigned long long)wal_synced, |
||||||
|
write_with_wal / (double)(wal_synced + 1), |
||||||
|
wal_bytes / (1048576.0 * 1024)); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Compaction IO cumulative (GB): " |
||||||
|
"%.2f new, %.2f read, %.2f write, %.2f read+write\n", |
||||||
|
user_bytes_written / (1048576.0 * 1024), |
||||||
|
total_bytes_read / (1048576.0 * 1024), |
||||||
|
total_bytes_written / (1048576.0 * 1024), |
||||||
|
(total_bytes_read + total_bytes_written) / (1048576.0 * 1024)); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Compaction IO cumulative (MB/sec): " |
||||||
|
"%.1f new, %.1f read, %.1f write, %.1f read+write\n", |
||||||
|
user_bytes_written / 1048576.0 / seconds_up, |
||||||
|
total_bytes_read / 1048576.0 / seconds_up, |
||||||
|
total_bytes_written / 1048576.0 / seconds_up, |
||||||
|
(total_bytes_read + total_bytes_written) / 1048576.0 / seconds_up); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
// +1 to avoid divide by 0 and NaN
|
||||||
|
snprintf( |
||||||
|
buf, sizeof(buf), |
||||||
|
"Amplification cumulative: %.1f write, %.1f compaction\n", |
||||||
|
(double)(total_bytes_written + wal_bytes) / (user_bytes_written + 1), |
||||||
|
(double)(total_bytes_written + total_bytes_read + wal_bytes) / |
||||||
|
(user_bytes_written + 1)); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
uint64_t interval_write_other = write_other - last_stats_.write_other_; |
||||||
|
uint64_t interval_write_self = write_self - last_stats_.write_self_; |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Writes interval: %llu total, %llu batches, " |
||||||
|
"%.1f per batch, %.1f ingest MB\n", |
||||||
|
(unsigned long long)(interval_write_other + interval_write_self), |
||||||
|
(unsigned long long)interval_write_self, |
||||||
|
(double)(interval_write_other + interval_write_self) / |
||||||
|
(interval_write_self + 1), |
||||||
|
(user_bytes_written - last_stats_.ingest_bytes_) / 1048576.0); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
uint64_t interval_write_with_wal = |
||||||
|
write_with_wal - last_stats_.write_with_wal_; |
||||||
|
|
||||||
|
uint64_t interval_wal_synced = wal_synced - last_stats_.wal_synced_; |
||||||
|
uint64_t interval_wal_bytes = wal_bytes - last_stats_.wal_bytes_; |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"WAL interval: %llu WAL writes, %llu WAL syncs, " |
||||||
|
"%.2f writes per sync, %.2f MB written\n", |
||||||
|
(unsigned long long)interval_write_with_wal, |
||||||
|
(unsigned long long)interval_wal_synced, |
||||||
|
interval_write_with_wal / (double)(interval_wal_synced + 1), |
||||||
|
interval_wal_bytes / (1048576.0 * 1024)); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Compaction IO interval (MB): " |
||||||
|
"%.2f new, %.2f read, %.2f write, %.2f read+write\n", |
||||||
|
interval_bytes_new / 1048576.0, interval_bytes_read / 1048576.0, |
||||||
|
interval_bytes_written / 1048576.0, |
||||||
|
(interval_bytes_read + interval_bytes_written) / 1048576.0); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Compaction IO interval (MB/sec): " |
||||||
|
"%.1f new, %.1f read, %.1f write, %.1f read+write\n", |
||||||
|
interval_bytes_new / 1048576.0 / interval_seconds_up, |
||||||
|
interval_bytes_read / 1048576.0 / interval_seconds_up, |
||||||
|
interval_bytes_written / 1048576.0 / interval_seconds_up, |
||||||
|
(interval_bytes_read + interval_bytes_written) / 1048576.0 / |
||||||
|
interval_seconds_up); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
// +1 to avoid divide by 0 and NaN
|
||||||
|
snprintf( |
||||||
|
buf, sizeof(buf), |
||||||
|
"Amplification interval: %.1f write, %.1f compaction\n", |
||||||
|
(double)(interval_bytes_written + wal_bytes) / (interval_bytes_new + 1), |
||||||
|
(double)(interval_bytes_written + interval_bytes_read + wal_bytes) / |
||||||
|
(interval_bytes_new + 1)); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Stalls(secs): %.3f level0_slowdown, %.3f level0_numfiles, " |
||||||
|
"%.3f memtable_compaction, %.3f leveln_slowdown\n", |
||||||
|
stall_micros_[LEVEL0_SLOWDOWN] / 1000000.0, |
||||||
|
stall_micros_[LEVEL0_NUM_FILES] / 1000000.0, |
||||||
|
stall_micros_[MEMTABLE_COMPACTION] / 1000000.0, |
||||||
|
total_slowdown / 1000000.0); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
snprintf(buf, sizeof(buf), |
||||||
|
"Stalls(count): %lu level0_slowdown, %lu level0_numfiles, " |
||||||
|
"%lu memtable_compaction, %lu leveln_slowdown\n", |
||||||
|
(unsigned long)stall_counts_[LEVEL0_SLOWDOWN], |
||||||
|
(unsigned long)stall_counts_[LEVEL0_NUM_FILES], |
||||||
|
(unsigned long)stall_counts_[MEMTABLE_COMPACTION], |
||||||
|
(unsigned long)total_slowdown_count); |
||||||
|
value->append(buf); |
||||||
|
|
||||||
|
last_stats_.compaction_bytes_read_ = total_bytes_read; |
||||||
|
last_stats_.compaction_bytes_written_ = total_bytes_written; |
||||||
|
last_stats_.ingest_bytes_ = user_bytes_written; |
||||||
|
last_stats_.seconds_up_ = seconds_up; |
||||||
|
last_stats_.wal_bytes_ = wal_bytes; |
||||||
|
last_stats_.wal_synced_ = wal_synced; |
||||||
|
last_stats_.write_with_wal_ = write_with_wal; |
||||||
|
last_stats_.write_other_ = write_other; |
||||||
|
last_stats_.write_self_ = write_self; |
||||||
|
|
||||||
|
return true; |
||||||
|
} else if (in == "sstables") { |
||||||
|
*value = current->DebugString(); |
||||||
|
return true; |
||||||
|
} else if (in == "num-immutable-mem-table") { |
||||||
|
*value = std::to_string(immsize); |
||||||
|
return true; |
||||||
|
} |
||||||
|
|
||||||
|
return false; |
||||||
|
} |
||||||
|
|
||||||
|
} // namespace rocksdb
|
||||||
@ -0,0 +1,149 @@ |
|||||||
|
// Copyright (c) 2013, 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.
|
||||||
|
//
|
||||||
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
||||||
|
// Use of this source code is governed by a BSD-style license that can be
|
||||||
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
||||||
|
//
|
||||||
|
|
||||||
|
#pragma once |
||||||
|
#include "rocksdb/statistics.h" |
||||||
|
#include "util/statistics.h" |
||||||
|
#include "db/version_set.h" |
||||||
|
|
||||||
|
#include <vector> |
||||||
|
#include <string> |
||||||
|
|
||||||
|
namespace rocksdb { |
||||||
|
class InternalStats { |
||||||
|
public: |
||||||
|
enum WriteStallType { |
||||||
|
LEVEL0_SLOWDOWN, |
||||||
|
MEMTABLE_COMPACTION, |
||||||
|
LEVEL0_NUM_FILES, |
||||||
|
WRITE_STALLS_ENUM_MAX, |
||||||
|
}; |
||||||
|
|
||||||
|
InternalStats(int num_levels, Env* env, Statistics* statistics) |
||||||
|
: compaction_stats_(num_levels), |
||||||
|
stall_micros_(WRITE_STALLS_ENUM_MAX, 0), |
||||||
|
stall_counts_(WRITE_STALLS_ENUM_MAX, 0), |
||||||
|
stall_leveln_slowdown_(num_levels, 0), |
||||||
|
stall_leveln_slowdown_count_(num_levels, 0), |
||||||
|
number_levels_(num_levels), |
||||||
|
statistics_(statistics), |
||||||
|
env_(env), |
||||||
|
started_at_(env->NowMicros()) {} |
||||||
|
|
||||||
|
// Per level compaction stats. compaction_stats_[level] stores the stats for
|
||||||
|
// compactions that produced data for the specified "level".
|
||||||
|
struct CompactionStats { |
||||||
|
uint64_t micros; |
||||||
|
|
||||||
|
// Bytes read from level N during compaction between levels N and N+1
|
||||||
|
int64_t bytes_readn; |
||||||
|
|
||||||
|
// Bytes read from level N+1 during compaction between levels N and N+1
|
||||||
|
int64_t bytes_readnp1; |
||||||
|
|
||||||
|
// Total bytes written during compaction between levels N and N+1
|
||||||
|
int64_t bytes_written; |
||||||
|
|
||||||
|
// Files read from level N during compaction between levels N and N+1
|
||||||
|
int files_in_leveln; |
||||||
|
|
||||||
|
// Files read from level N+1 during compaction between levels N and N+1
|
||||||
|
int files_in_levelnp1; |
||||||
|
|
||||||
|
// Files written during compaction between levels N and N+1
|
||||||
|
int files_out_levelnp1; |
||||||
|
|
||||||
|
// Number of compactions done
|
||||||
|
int count; |
||||||
|
|
||||||
|
CompactionStats() |
||||||
|
: micros(0), |
||||||
|
bytes_readn(0), |
||||||
|
bytes_readnp1(0), |
||||||
|
bytes_written(0), |
||||||
|
files_in_leveln(0), |
||||||
|
files_in_levelnp1(0), |
||||||
|
files_out_levelnp1(0), |
||||||
|
count(0) {} |
||||||
|
|
||||||
|
void Add(const CompactionStats& c) { |
||||||
|
this->micros += c.micros; |
||||||
|
this->bytes_readn += c.bytes_readn; |
||||||
|
this->bytes_readnp1 += c.bytes_readnp1; |
||||||
|
this->bytes_written += c.bytes_written; |
||||||
|
this->files_in_leveln += c.files_in_leveln; |
||||||
|
this->files_in_levelnp1 += c.files_in_levelnp1; |
||||||
|
this->files_out_levelnp1 += c.files_out_levelnp1; |
||||||
|
this->count += 1; |
||||||
|
} |
||||||
|
}; |
||||||
|
|
||||||
|
void AddCompactionStats(int level, const CompactionStats& stats) { |
||||||
|
compaction_stats_[level].Add(stats); |
||||||
|
} |
||||||
|
|
||||||
|
void RecordWriteStall(WriteStallType write_stall_type, uint64_t micros) { |
||||||
|
stall_micros_[write_stall_type] += micros; |
||||||
|
stall_counts_[write_stall_type]++; |
||||||
|
} |
||||||
|
|
||||||
|
void RecordLevelNSlowdown(int level, uint64_t micros) { |
||||||
|
stall_leveln_slowdown_[level] += micros; |
||||||
|
stall_leveln_slowdown_count_[level] += micros; |
||||||
|
} |
||||||
|
|
||||||
|
bool GetProperty(const Slice& property, std::string* value, |
||||||
|
VersionSet* version_set, int immsize); |
||||||
|
|
||||||
|
private: |
||||||
|
std::vector<CompactionStats> compaction_stats_; |
||||||
|
|
||||||
|
// Used to compute per-interval statistics
|
||||||
|
struct StatsSnapshot { |
||||||
|
uint64_t compaction_bytes_read_; // Bytes read by compaction
|
||||||
|
uint64_t compaction_bytes_written_; // Bytes written by compaction
|
||||||
|
uint64_t ingest_bytes_; // Bytes written by user
|
||||||
|
uint64_t wal_bytes_; // Bytes written to WAL
|
||||||
|
uint64_t wal_synced_; // Number of times WAL is synced
|
||||||
|
uint64_t write_with_wal_; // Number of writes that request WAL
|
||||||
|
// These count the number of writes processed by the calling thread or
|
||||||
|
// another thread.
|
||||||
|
uint64_t write_other_; |
||||||
|
uint64_t write_self_; |
||||||
|
double seconds_up_; |
||||||
|
|
||||||
|
StatsSnapshot() |
||||||
|
: compaction_bytes_read_(0), |
||||||
|
compaction_bytes_written_(0), |
||||||
|
ingest_bytes_(0), |
||||||
|
wal_bytes_(0), |
||||||
|
wal_synced_(0), |
||||||
|
write_with_wal_(0), |
||||||
|
write_other_(0), |
||||||
|
write_self_(0), |
||||||
|
seconds_up_(0) {} |
||||||
|
}; |
||||||
|
|
||||||
|
// Counters from the previous time per-interval stats were computed
|
||||||
|
StatsSnapshot last_stats_; |
||||||
|
|
||||||
|
// These count the number of microseconds for which MakeRoomForWrite stalls.
|
||||||
|
std::vector<uint64_t> stall_micros_; |
||||||
|
std::vector<uint64_t> stall_counts_; |
||||||
|
std::vector<uint64_t> stall_leveln_slowdown_; |
||||||
|
std::vector<uint64_t> stall_leveln_slowdown_count_; |
||||||
|
|
||||||
|
int number_levels_; |
||||||
|
Statistics* statistics_; |
||||||
|
Env* env_; |
||||||
|
uint64_t started_at_; |
||||||
|
}; |
||||||
|
|
||||||
|
} // namespace rocksdb
|
||||||
Loading…
Reference in new issue