mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 11:43:49 +00:00
151242ce46
Summary:
**Context:**
The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them.
**Summary**
- Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros`
- Fixed the default histogram in `RandomAccessFileReader`
- New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader`
- Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288
Test Plan:
- **Stress test**
- **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.** (without blob)
- May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads.
```
./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10)
```
```
// BlockBasedTable
rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805
rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116
rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689
// PlainTable
Does not apply
```
- **Db bench 2: performance**
**Read**
SETUP: db with 900 files
```
./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none
```run till convergence
```
./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3
```
Pre-change
`readrandom [AVG 60 runs] : 21568 (± 248) ops/sec`
Post-change (no regression, -0.3%)
`readrandom [AVG 60 runs] : 21486 (± 236) ops/sec`
**Compaction/Flush**run till convergence
```
./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none
rocksdb.sst.read.micros COUNT : 33820
rocksdb.sst.read.flush.micros COUNT : 1800
rocksdb.sst.read.compaction.micros COUNT : 32020
```
Pre-change
`fillseq [AVG 46 runs] : 1391 (± 214) ops/sec; 0.7 (± 0.1) MB/sec`
Post-change (no regression, ~-0.4%)
`fillseq [AVG 46 runs] : 1385 (± 216) ops/sec; 0.7 (± 0.1) MB/sec`
Reviewed By: ajkr
Differential Revision: D44007011
Pulled By: hx235
fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
73 lines
2.9 KiB
C++
73 lines
2.9 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 "db/version_set.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
// Instead of opening a `DB` to perform certain manifest updates, this
|
|
// uses the underlying `VersionSet` API to read and modify the MANIFEST. This
|
|
// allows us to use the user's real options, while not having to worry about
|
|
// the DB persisting new SST files via flush/compaction or attempting to read/
|
|
// compact files which may fail, particularly for the file we intend to remove
|
|
// (the user may want to remove an already deleted file from MANIFEST).
|
|
class OfflineManifestWriter {
|
|
public:
|
|
OfflineManifestWriter(const DBOptions& options, const std::string& db_path)
|
|
: wc_(options.delayed_write_rate),
|
|
wb_(options.db_write_buffer_size),
|
|
immutable_db_options_(WithDbPath(options, db_path)),
|
|
tc_(NewLRUCache(1 << 20 /* capacity */,
|
|
options.table_cache_numshardbits)),
|
|
versions_(db_path, &immutable_db_options_, sopt_, tc_.get(), &wb_, &wc_,
|
|
/*block_cache_tracer=*/nullptr, /*io_tracer=*/nullptr,
|
|
/*db_id*/ "", /*db_session_id*/ "") {}
|
|
|
|
Status Recover(const std::vector<ColumnFamilyDescriptor>& column_families) {
|
|
return versions_.Recover(column_families, /*read_only*/ false,
|
|
/*db_id*/ nullptr,
|
|
/*no_error_if_files_missing*/ true);
|
|
}
|
|
|
|
Status LogAndApply(const ReadOptions& read_options, ColumnFamilyData* cfd,
|
|
VersionEdit* edit,
|
|
FSDirectory* dir_contains_current_file) {
|
|
// Use `mutex` to imitate a locked DB mutex when calling `LogAndApply()`.
|
|
InstrumentedMutex mutex;
|
|
mutex.Lock();
|
|
Status s = versions_.LogAndApply(
|
|
cfd, *cfd->GetLatestMutableCFOptions(), read_options, edit, &mutex,
|
|
dir_contains_current_file, false /* new_descriptor_log */);
|
|
mutex.Unlock();
|
|
return s;
|
|
}
|
|
|
|
VersionSet& Versions() { return versions_; }
|
|
const ImmutableDBOptions& IOptions() { return immutable_db_options_; }
|
|
|
|
private:
|
|
WriteController wc_;
|
|
WriteBufferManager wb_;
|
|
ImmutableDBOptions immutable_db_options_;
|
|
std::shared_ptr<Cache> tc_;
|
|
EnvOptions sopt_;
|
|
VersionSet versions_;
|
|
|
|
static ImmutableDBOptions WithDbPath(const DBOptions& options,
|
|
const std::string& db_path) {
|
|
ImmutableDBOptions rv(options);
|
|
if (rv.db_paths.empty()) {
|
|
// `VersionSet` expects options that have been through
|
|
// `SanitizeOptions()`, which would sanitize an empty `db_paths`.
|
|
rv.db_paths.emplace_back(db_path, 0 /* target_size */);
|
|
}
|
|
return rv;
|
|
}
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|