mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-29 00:34:03 +00:00
9a034801ce
Summary:
**Context/Summary:**
- Similar to https://github.com/facebook/rocksdb/pull/11288 but for user read such as `Get(), MultiGet(), DBIterator::XXX(), Verify(File)Checksum()`.
- For this, I refactored some user-facing `MultiGet` calls in `TransactionBase` and various types of `DB` so that it does not call a user-facing `Get()` but `GetImpl()` for passing the `ReadOptions::io_activity` check (see PR conversation)
- New user read stats breakdown are guarded by `kExceptDetailedTimers` since measurement shows they have 4-5% regression to the upstream/main.
- Misc
- More refactoring: with https://github.com/facebook/rocksdb/pull/11288, we complete passing `ReadOptions/IOOptions` to FS level. So we can now replace the previously [added](https://github.com/facebook/rocksdb/pull/9424) `rate_limiter_priority` parameter in `RandomAccessFileReader`'s `Read/MultiRead/Prefetch()` with `IOOptions::rate_limiter_priority`
- Also, `ReadAsync()` call time is measured in `SST_READ_MICRO` now
Pull Request resolved: https://github.com/facebook/rocksdb/pull/11444
Test Plan:
- CI fake db crash/stress test
- Microbenchmarking
**Build** `make clean && ROCKSDB_NO_FBCODE=1 DEBUG_LEVEL=0 make -jN db_basic_bench`
- google benchmark version: 604f6fd3f4
- db_basic_bench_base: upstream
- db_basic_bench_pr: db_basic_bench_base + this PR
- asyncread_db_basic_bench_base: upstream + [db basic bench patch for IteratorNext](https://github.com/facebook/rocksdb/compare/main...hx235:rocksdb:micro_bench_async_read)
- asyncread_db_basic_bench_pr: asyncread_db_basic_bench_base + this PR
**Test**
Get
```
TEST_TMPDIR=/dev/shm ./db_basic_bench_{null_stat|base|pr} --benchmark_filter=DBGet/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/negative_query:0/enable_filter:0/mmap:1/threads:1 --benchmark_repetitions=1000
```
Result
```
Coming soon
```
AsyncRead
```
TEST_TMPDIR=/dev/shm ./asyncread_db_basic_bench_{base|pr} --benchmark_filter=IteratorNext/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1/async_io:1/include_detailed_timers:0 --benchmark_repetitions=1000 > syncread_db_basic_bench_{base|pr}.out
```
Result
```
Base:
1956,1956,1968,1977,1979,1986,1988,1988,1988,1990,1991,1991,1993,1993,1993,1993,1994,1996,1997,1997,1997,1998,1999,2001,2001,2002,2004,2007,2007,2008,
PR (2.3% regression, due to measuring `SST_READ_MICRO` that wasn't measured before):
1993,2014,2016,2022,2024,2027,2027,2028,2028,2030,2031,2031,2032,2032,2038,2039,2042,2044,2044,2047,2047,2047,2048,2049,2050,2052,2052,2052,2053,2053,
```
Reviewed By: ajkr
Differential Revision: D45918925
Pulled By: hx235
fbshipit-source-id: 58a54560d9ebeb3a59b6d807639692614dad058a
102 lines
4 KiB
C++
102 lines
4 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,
|
|
const ReadOptions& read_options);
|
|
|
|
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);
|
|
|
|
inline bool CheckFSFeatureSupport(FileSystem* fs, FSSupportedOps feat) {
|
|
int64_t supported_ops = 0;
|
|
fs->SupportedOps(supported_ops);
|
|
if (supported_ops & (1ULL << feat)) {
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|