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
74 lines
2.9 KiB
C++
74 lines
2.9 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).
|
|
//
|
|
// 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 "table/block_based/block_based_table_reader.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
class BlockPrefetcher {
|
|
public:
|
|
explicit BlockPrefetcher(size_t compaction_readahead_size,
|
|
size_t initial_auto_readahead_size)
|
|
: compaction_readahead_size_(compaction_readahead_size),
|
|
readahead_size_(initial_auto_readahead_size),
|
|
initial_auto_readahead_size_(initial_auto_readahead_size) {}
|
|
|
|
void PrefetchIfNeeded(const BlockBasedTable::Rep* rep,
|
|
const BlockHandle& handle, size_t readahead_size,
|
|
bool is_for_compaction,
|
|
const bool no_sequential_checking,
|
|
const ReadOptions& read_options);
|
|
FilePrefetchBuffer* prefetch_buffer() { return prefetch_buffer_.get(); }
|
|
|
|
void UpdateReadPattern(const uint64_t& offset, const size_t& len) {
|
|
prev_offset_ = offset;
|
|
prev_len_ = len;
|
|
}
|
|
|
|
bool IsBlockSequential(const uint64_t& offset) {
|
|
return (prev_len_ == 0 || (prev_offset_ + prev_len_ == offset));
|
|
}
|
|
|
|
void ResetValues(size_t initial_auto_readahead_size) {
|
|
num_file_reads_ = 1;
|
|
// Since initial_auto_readahead_size_ can be different from
|
|
// the value passed to BlockBasedTableOptions.initial_auto_readahead_size in
|
|
// case of adaptive_readahead, so fallback the readahead_size_ to that value
|
|
// in case of reset.
|
|
initial_auto_readahead_size_ = initial_auto_readahead_size;
|
|
readahead_size_ = initial_auto_readahead_size_;
|
|
readahead_limit_ = 0;
|
|
return;
|
|
}
|
|
|
|
void SetReadaheadState(ReadaheadFileInfo::ReadaheadInfo* readahead_info) {
|
|
num_file_reads_ = readahead_info->num_file_reads;
|
|
initial_auto_readahead_size_ = readahead_info->readahead_size;
|
|
TEST_SYNC_POINT_CALLBACK("BlockPrefetcher::SetReadaheadState",
|
|
&initial_auto_readahead_size_);
|
|
}
|
|
|
|
private:
|
|
// Readahead size used in compaction, its value is used only if
|
|
// lookup_context_.caller = kCompaction.
|
|
size_t compaction_readahead_size_;
|
|
|
|
// readahead_size_ is used in non-compaction read if underlying FS supports
|
|
// prefetching.
|
|
size_t readahead_size_;
|
|
size_t readahead_limit_ = 0;
|
|
// initial_auto_readahead_size_ is used in non-compaction read if RocksDB uses
|
|
// internal prefetch buffer.
|
|
uint64_t initial_auto_readahead_size_;
|
|
uint64_t num_file_reads_ = 0;
|
|
uint64_t prev_offset_ = 0;
|
|
size_t prev_len_ = 0;
|
|
std::unique_ptr<FilePrefetchBuffer> prefetch_buffer_;
|
|
};
|
|
} // namespace ROCKSDB_NAMESPACE
|