mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
4da34b97ee
Summary: ### Context: Background compactions and flush generate large reads and writes, and can be long running, especially for universal compaction. In some cases, this can impact foreground reads and writes by users. ### Solution User, Flush, and Compaction reads share some code path. For this task, we update the rate_limiter_priority in ReadOptions for code paths (e.g. FindTable (mainly in BlockBasedTable::Open()) and various iterators), and eventually update the rate_limiter_priority in IOOptions for FSRandomAccessFile. **This PR is for the Read path.** The **Read:** dynamic priority for different state are listed as follows: | State | Normal | Delayed | Stalled | | ----- | ------ | ------- | ------- | | Flush (verification read in BuildTable()) | IO_USER | IO_USER | IO_USER | | Compaction | IO_LOW | IO_USER | IO_USER | | User | User provided | User provided | User provided | We will respect the read_options that the user provided and will not set it. The only sst read for Flush is the verification read in BuildTable(). It claims to be "regard as user read". **Details** 1. Set read_options.rate_limiter_priority dynamically: - User: Do not update the read_options. Use the read_options that the user provided. - Compaction: Update read_options in CompactionJob::ProcessKeyValueCompaction(). - Flush: Update read_options in BuildTable(). 2. Pass the rate limiter priority to FSRandomAccessFile functions: - After calling the FindTable(), read_options is passed through GetTableReader(table_cache.cc), BlockBasedTableFactory::NewTableReader(block_based_table_factory.cc), and BlockBasedTable::Open(). The Open() needs some updates for the ReadOptions variable and the updates are also needed for the called functions, including PrefetchTail(), PrepareIOOptions(), ReadFooterFromFile(), ReadMetaIndexblock(), ReadPropertiesBlock(), PrefetchIndexAndFilterBlocks(), and ReadRangeDelBlock(). - In RandomAccessFileReader, the functions to be updated include Read(), MultiRead(), ReadAsync(), and Prefetch(). - Update the downstream functions of NewIndexIterator(), NewDataBlockIterator(), and BlockBasedTableIterator(). ### Test Plans Add unit tests. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9996 Reviewed By: anand1976 Differential Revision: D36452483 Pulled By: gitbw95 fbshipit-source-id: 60978204a4f849bb9261cb78d9bc1cb56d6008cf
72 lines
2.9 KiB
C++
72 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, bool async_io,
|
|
Env::IOPriority rate_limiter_priority);
|
|
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 if underlying FS supports prefetching.
|
|
size_t readahead_size_;
|
|
size_t readahead_limit_ = 0;
|
|
// initial_auto_readahead_size_ is used if RocksDB uses internal prefetch
|
|
// buffer.
|
|
uint64_t initial_auto_readahead_size_;
|
|
int64_t num_file_reads_ = 0;
|
|
uint64_t prev_offset_ = 0;
|
|
size_t prev_len_ = 0;
|
|
std::unique_ptr<FilePrefetchBuffer> prefetch_buffer_;
|
|
};
|
|
} // namespace ROCKSDB_NAMESPACE
|