rocksdb/table/block_based/block_prefetcher.cc
Akanksha Mahajan 0c7f455f85 Make initial auto readahead_size configurable (#9836)
Summary:
Make initial auto readahead_size configurable

Pull Request resolved: https://github.com/facebook/rocksdb/pull/9836

Test Plan:
Added new unit test
Ran regression:
Without change:

```
./db_bench -use_existing_db=true -db=/tmp/prefix_scan_prefetch_main -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1
Initializing RocksDB Options from the specified file
Initializing RocksDB Options from command-line flags
RocksDB:    version 7.0
Date:       Thu Mar 17 13:11:34 2022
CPU:        24 * Intel Core Processor (Broadwell)
CPUCache:   16384 KB
Keys:       32 bytes each (+ 0 bytes user-defined timestamp)
Values:     512 bytes each (256 bytes after compression)
Entries:    5000000
Prefix:    0 bytes
Keys per prefix:    0
RawSize:    2594.0 MB (estimated)
FileSize:   1373.3 MB (estimated)
Write rate: 0 bytes/second
Read rate: 0 ops/second
Compression: Snappy
Compression sampling rate: 0
Memtablerep: SkipListFactory
Perf Level: 1
------------------------------------------------
DB path: [/tmp/prefix_scan_prefetch_main]
seekrandom   :  483618.390 micros/op 2 ops/sec;  338.9 MB/s (249 of 249 found)
```

With this change:
```
 ./db_bench -use_existing_db=true -db=/tmp/prefix_scan_prefetch_main -benchmarks="seekrandom" -key_size=32 -value_size=512 -num=5000000 -use_direct_reads=true -seek_nexts=327680 -duration=120 -ops_between_duration_checks=1
Set seed to 1649895440554504 because --seed was 0
Initializing RocksDB Options from the specified file
Initializing RocksDB Options from command-line flags
RocksDB:    version 7.2
Date:       Wed Apr 13 17:17:20 2022
CPU:        24 * Intel Core Processor (Broadwell)
CPUCache:   16384 KB
Keys:       32 bytes each (+ 0 bytes user-defined timestamp)
Values:     512 bytes each (256 bytes after compression)
Entries:    5000000
Prefix:    0 bytes
Keys per prefix:    0
RawSize:    2594.0 MB (estimated)
FileSize:   1373.3 MB (estimated)
Write rate: 0 bytes/second
Read rate: 0 ops/second
Compression: Snappy
Compression sampling rate: 0
Memtablerep: SkipListFactory
Perf Level: 1
------------------------------------------------
DB path: [/tmp/prefix_scan_prefetch_main]
... finished 100 ops
seekrandom   :  476892.488 micros/op 2 ops/sec;  344.6 MB/s (252 of 252 found)
```

Reviewed By: anand1976

Differential Revision: D35632815

Pulled By: akankshamahajan15

fbshipit-source-id: c8057a88f9294c9d03b1d434b03affe02f74d796
2022-04-15 17:28:09 -07:00

101 lines
3.7 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.
#include "table/block_based/block_prefetcher.h"
#include "table/block_based/block_based_table_reader.h"
namespace ROCKSDB_NAMESPACE {
void BlockPrefetcher::PrefetchIfNeeded(const BlockBasedTable::Rep* rep,
const BlockHandle& handle,
size_t readahead_size,
bool is_for_compaction, bool async_io) {
if (is_for_compaction) {
rep->CreateFilePrefetchBufferIfNotExists(
compaction_readahead_size_, compaction_readahead_size_,
&prefetch_buffer_, false, async_io);
return;
}
// Explicit user requested readahead.
if (readahead_size > 0) {
rep->CreateFilePrefetchBufferIfNotExists(
readahead_size, readahead_size, &prefetch_buffer_, false, async_io);
return;
}
// Implicit readahead.
// If max_auto_readahead_size is set to be 0 by user, no data will be
// prefetched.
size_t max_auto_readahead_size = rep->table_options.max_auto_readahead_size;
if (max_auto_readahead_size == 0 || initial_auto_readahead_size_ == 0) {
return;
}
size_t len = BlockBasedTable::BlockSizeWithTrailer(handle);
size_t offset = handle.offset();
// If FS supports prefetching (readahead_limit_ will be non zero in that case)
// and current block exists in prefetch buffer then return.
if (offset + len <= readahead_limit_) {
UpdateReadPattern(offset, len);
return;
}
if (!IsBlockSequential(offset)) {
UpdateReadPattern(offset, len);
ResetValues(rep->table_options.initial_auto_readahead_size);
return;
}
UpdateReadPattern(offset, len);
// Implicit auto readahead, which will be enabled if the number of reads
// reached `kMinNumFileReadsToStartAutoReadahead` (default: 2) and scans are
// sequential.
num_file_reads_++;
if (num_file_reads_ <=
BlockBasedTable::kMinNumFileReadsToStartAutoReadahead) {
return;
}
if (initial_auto_readahead_size_ > max_auto_readahead_size) {
initial_auto_readahead_size_ = max_auto_readahead_size;
}
if (rep->file->use_direct_io()) {
rep->CreateFilePrefetchBufferIfNotExists(initial_auto_readahead_size_,
max_auto_readahead_size,
&prefetch_buffer_, true, async_io);
return;
}
if (readahead_size_ > max_auto_readahead_size) {
readahead_size_ = max_auto_readahead_size;
}
// If prefetch is not supported, fall back to use internal prefetch buffer.
// Discarding other return status of Prefetch calls intentionally, as
// we can fallback to reading from disk if Prefetch fails.
Status s = rep->file->Prefetch(
handle.offset(),
BlockBasedTable::BlockSizeWithTrailer(handle) + readahead_size_);
if (s.IsNotSupported()) {
rep->CreateFilePrefetchBufferIfNotExists(initial_auto_readahead_size_,
max_auto_readahead_size,
&prefetch_buffer_, true, async_io);
return;
}
readahead_limit_ = offset + len + readahead_size_;
// Keep exponentially increasing readahead size until
// max_auto_readahead_size.
readahead_size_ = std::min(max_auto_readahead_size, readahead_size_ * 2);
}
} // namespace ROCKSDB_NAMESPACE