rocksdb/table/block_based/block_prefetcher.h
akankshamahajan 5cb2d09d47 Refactor FilePrefetchBuffer code (#12097)
Summary:
Summary - Refactor FilePrefetchBuffer code
- Implementation:
FilePrefetchBuffer maintains a deque of free buffers (free_bufs_) of size num_buffers_ and buffers (bufs_) which contains the prefetched data. Whenever a buffer is consumed or is outdated (w.r.t. to requested offset), that buffer is cleared and returned to free_bufs_.

 If a buffer is available in free_bufs_, it's moved to bufs_ and is sent for prefetching. num_buffers_ defines how many buffers are maintained that contains prefetched data.
If num_buffers_ == 1, it's a sequential read flow. Read API will be called on that one buffer whenever the data is requested and is not in the buffer.
If num_buffers_ > 1, then the data is prefetched asynchronosuly in the buffers whenever the data is consumed from the buffers and that buffer is freed.
If num_buffers > 1, then requested data can be overlapping between 2 buffers. To return the continuous buffer overlap_bufs_ is used. The requested data is copied from 2 buffers to the overlap_bufs_ and overlap_bufs_ is returned to
the caller.

- Merged Sync and Async code flow into one in FilePrefetchBuffer.

Test Plan -
- Crash test passed
- Unit tests
- Pending - Benchmarks

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12097

Reviewed By: ajkr

Differential Revision: D51759552

Pulled By: akankshamahajan15

fbshipit-source-id: 69a352945affac2ed22be96048d55863e0168ad5
2024-01-05 09:29:01 -08:00

75 lines
3 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,
const std::function<void(bool, uint64_t&, uint64_t&)>& readaheadsize_cb,
bool is_async_io_prefetch);
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