mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-02 10:15:54 +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
92 lines
3.8 KiB
C++
92 lines
3.8 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 <string>
|
|
|
|
#include "file/filename.h"
|
|
#include "options/db_options.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/file_system.h"
|
|
#include "rocksdb/sst_file_writer.h"
|
|
#include "rocksdb/status.h"
|
|
#include "rocksdb/system_clock.h"
|
|
#include "rocksdb/types.h"
|
|
#include "trace_replay/io_tracer.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
// use_fsync maps to options.use_fsync, which determines the way that
|
|
// the file is synced after copying.
|
|
extern IOStatus CopyFile(FileSystem* fs, const std::string& source,
|
|
std::unique_ptr<WritableFileWriter>& dest_writer,
|
|
uint64_t size, bool use_fsync,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const Temperature temperature);
|
|
extern IOStatus CopyFile(FileSystem* fs, const std::string& source,
|
|
const std::string& destination, uint64_t size,
|
|
bool use_fsync,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const Temperature temperature);
|
|
inline IOStatus CopyFile(const std::shared_ptr<FileSystem>& fs,
|
|
const std::string& source,
|
|
const std::string& destination, uint64_t size,
|
|
bool use_fsync,
|
|
const std::shared_ptr<IOTracer>& io_tracer,
|
|
const Temperature temperature) {
|
|
return CopyFile(fs.get(), source, destination, size, use_fsync, io_tracer,
|
|
temperature);
|
|
}
|
|
extern IOStatus CreateFile(FileSystem* fs, const std::string& destination,
|
|
const std::string& contents, bool use_fsync);
|
|
|
|
inline IOStatus CreateFile(const std::shared_ptr<FileSystem>& fs,
|
|
const std::string& destination,
|
|
const std::string& contents, bool use_fsync) {
|
|
return CreateFile(fs.get(), destination, contents, use_fsync);
|
|
}
|
|
|
|
extern Status DeleteDBFile(const ImmutableDBOptions* db_options,
|
|
const std::string& fname,
|
|
const std::string& path_to_sync, const bool force_bg,
|
|
const bool force_fg);
|
|
|
|
extern IOStatus GenerateOneFileChecksum(
|
|
FileSystem* fs, const std::string& file_path,
|
|
FileChecksumGenFactory* checksum_factory,
|
|
const std::string& requested_checksum_func_name, std::string* file_checksum,
|
|
std::string* file_checksum_func_name,
|
|
size_t verify_checksums_readahead_size, bool allow_mmap_reads,
|
|
std::shared_ptr<IOTracer>& io_tracer, RateLimiter* rate_limiter,
|
|
Env::IOPriority rate_limiter_priority);
|
|
|
|
inline IOStatus PrepareIOFromReadOptions(const ReadOptions& ro,
|
|
SystemClock* clock, IOOptions& opts) {
|
|
if (ro.deadline.count()) {
|
|
std::chrono::microseconds now =
|
|
std::chrono::microseconds(clock->NowMicros());
|
|
// Ensure there is atleast 1us available. We don't want to pass a value of
|
|
// 0 as that means no timeout
|
|
if (now >= ro.deadline) {
|
|
return IOStatus::TimedOut("Deadline exceeded");
|
|
}
|
|
opts.timeout = ro.deadline - now;
|
|
}
|
|
|
|
if (ro.io_timeout.count() &&
|
|
(!opts.timeout.count() || ro.io_timeout < opts.timeout)) {
|
|
opts.timeout = ro.io_timeout;
|
|
}
|
|
|
|
opts.rate_limiter_priority = ro.rate_limiter_priority;
|
|
opts.io_activity = ro.io_activity;
|
|
|
|
return IOStatus::OK();
|
|
}
|
|
|
|
// Test method to delete the input directory and all of its contents.
|
|
// This method is destructive and is meant for use only in tests!!!
|
|
Status DestroyDir(Env* env, const std::string& dir);
|
|
} // namespace ROCKSDB_NAMESPACE
|