mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-02 10:15:54 +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
133 lines
4 KiB
C++
133 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).
|
|
|
|
#include "utilities/trace/file_trace_reader_writer.h"
|
|
|
|
#include "env/composite_env_wrapper.h"
|
|
#include "file/random_access_file_reader.h"
|
|
#include "file/writable_file_writer.h"
|
|
#include "trace_replay/trace_replay.h"
|
|
#include "util/coding.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
const unsigned int FileTraceReader::kBufferSize = 1024; // 1KB
|
|
|
|
FileTraceReader::FileTraceReader(
|
|
std::unique_ptr<RandomAccessFileReader>&& reader)
|
|
: file_reader_(std::move(reader)),
|
|
offset_(0),
|
|
buffer_(new char[kBufferSize]) {}
|
|
|
|
FileTraceReader::~FileTraceReader() {
|
|
Close().PermitUncheckedError();
|
|
delete[] buffer_;
|
|
}
|
|
|
|
Status FileTraceReader::Close() {
|
|
file_reader_.reset();
|
|
return Status::OK();
|
|
}
|
|
|
|
Status FileTraceReader::Reset() {
|
|
if (file_reader_ == nullptr) {
|
|
return Status::IOError("TraceReader is closed.");
|
|
}
|
|
offset_ = 0;
|
|
return Status::OK();
|
|
}
|
|
|
|
Status FileTraceReader::Read(std::string* data) {
|
|
assert(file_reader_ != nullptr);
|
|
Status s = file_reader_->Read(IOOptions(), offset_, kTraceMetadataSize,
|
|
&result_, buffer_, nullptr);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
if (result_.size() == 0) {
|
|
// No more data to read
|
|
// Todo: Come up with a better way to indicate end of data. May be this
|
|
// could be avoided once footer is introduced.
|
|
return Status::Incomplete();
|
|
}
|
|
if (result_.size() < kTraceMetadataSize) {
|
|
return Status::Corruption("Corrupted trace file.");
|
|
}
|
|
*data = result_.ToString();
|
|
offset_ += kTraceMetadataSize;
|
|
|
|
uint32_t payload_len =
|
|
DecodeFixed32(&buffer_[kTraceTimestampSize + kTraceTypeSize]);
|
|
|
|
// Read Payload
|
|
unsigned int bytes_to_read = payload_len;
|
|
unsigned int to_read =
|
|
bytes_to_read > kBufferSize ? kBufferSize : bytes_to_read;
|
|
while (to_read > 0) {
|
|
s = file_reader_->Read(IOOptions(), offset_, to_read, &result_, buffer_,
|
|
nullptr);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
if (result_.size() < to_read) {
|
|
return Status::Corruption("Corrupted trace file.");
|
|
}
|
|
data->append(result_.data(), result_.size());
|
|
|
|
offset_ += to_read;
|
|
bytes_to_read -= to_read;
|
|
to_read = bytes_to_read > kBufferSize ? kBufferSize : bytes_to_read;
|
|
}
|
|
|
|
return s;
|
|
}
|
|
|
|
FileTraceWriter::FileTraceWriter(
|
|
std::unique_ptr<WritableFileWriter>&& file_writer)
|
|
: file_writer_(std::move(file_writer)) {}
|
|
|
|
FileTraceWriter::~FileTraceWriter() { Close().PermitUncheckedError(); }
|
|
|
|
Status FileTraceWriter::Close() {
|
|
file_writer_.reset();
|
|
return Status::OK();
|
|
}
|
|
|
|
Status FileTraceWriter::Write(const Slice& data) {
|
|
return file_writer_->Append(data);
|
|
}
|
|
|
|
uint64_t FileTraceWriter::GetFileSize() { return file_writer_->GetFileSize(); }
|
|
|
|
Status NewFileTraceReader(Env* env, const EnvOptions& env_options,
|
|
const std::string& trace_filename,
|
|
std::unique_ptr<TraceReader>* trace_reader) {
|
|
std::unique_ptr<RandomAccessFileReader> file_reader;
|
|
Status s = RandomAccessFileReader::Create(
|
|
env->GetFileSystem(), trace_filename, FileOptions(env_options),
|
|
&file_reader, nullptr);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
trace_reader->reset(new FileTraceReader(std::move(file_reader)));
|
|
return s;
|
|
}
|
|
|
|
Status NewFileTraceWriter(Env* env, const EnvOptions& env_options,
|
|
const std::string& trace_filename,
|
|
std::unique_ptr<TraceWriter>* trace_writer) {
|
|
std::unique_ptr<WritableFileWriter> file_writer;
|
|
Status s = WritableFileWriter::Create(env->GetFileSystem(), trace_filename,
|
|
FileOptions(env_options), &file_writer,
|
|
nullptr);
|
|
if (!s.ok()) {
|
|
return s;
|
|
}
|
|
trace_writer->reset(new FileTraceWriter(std::move(file_writer)));
|
|
return s;
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|