mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 07:30:54 +00:00
19ec44fd39
Summary: Add hash index support to data blocks, which helps to reduce the CPU utilization of point-lookup operations. This feature is backward compatible with the data block created without the hash index. It is disabled by default unless `BlockBasedTableOptions::data_block_index_type` is set to `data_block_index_type = kDataBlockBinaryAndHash.` The DB size would be bigger with the hash index option as a hash table is added at the end of each data block. If the hash utilization ratio is 1:1, the space overhead is one byte per key. The hash table utilization ratio is adjustable using `BlockBasedTableOptions::data_block_hash_table_util_ratio`. A lower utilization ratio will improve more on the point-lookup efficiency, but take more space too. Pull Request resolved: https://github.com/facebook/rocksdb/pull/4174 Differential Revision: D8965914 Pulled By: fgwu fbshipit-source-id: 1c6bae5d1fc39c80282d8890a72e9e67bc247198
78 lines
2.9 KiB
C++
78 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 <vector>
|
|
|
|
#include <stdint.h>
|
|
#include "rocksdb/slice.h"
|
|
#include "rocksdb/table.h"
|
|
#include "table/data_block_hash_index.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class BlockBuilder {
|
|
public:
|
|
BlockBuilder(const BlockBuilder&) = delete;
|
|
void operator=(const BlockBuilder&) = delete;
|
|
|
|
explicit BlockBuilder(int block_restart_interval,
|
|
bool use_delta_encoding = true,
|
|
bool use_value_delta_encoding = false,
|
|
BlockBasedTableOptions::DataBlockIndexType index_type =
|
|
BlockBasedTableOptions::kDataBlockBinarySearch,
|
|
double data_block_hash_table_util_ratio = 0.75);
|
|
|
|
// Reset the contents as if the BlockBuilder was just constructed.
|
|
void Reset();
|
|
|
|
// REQUIRES: Finish() has not been called since the last call to Reset().
|
|
// REQUIRES: key is larger than any previously added key
|
|
void Add(const Slice& key, const Slice& value,
|
|
const Slice* const delta_value = nullptr);
|
|
|
|
// Finish building the block and return a slice that refers to the
|
|
// block contents. The returned slice will remain valid for the
|
|
// lifetime of this builder or until Reset() is called.
|
|
Slice Finish();
|
|
|
|
// Returns an estimate of the current (uncompressed) size of the block
|
|
// we are building.
|
|
inline size_t CurrentSizeEstimate() const {
|
|
return estimate_ + (data_block_hash_index_builder_.Valid()
|
|
? data_block_hash_index_builder_.EstimateSize()
|
|
: 0);
|
|
}
|
|
|
|
// Returns an estimated block size after appending key and value.
|
|
size_t EstimateSizeAfterKV(const Slice& key, const Slice& value) const;
|
|
|
|
// Return true iff no entries have been added since the last Reset()
|
|
bool empty() const {
|
|
return buffer_.empty();
|
|
}
|
|
|
|
private:
|
|
const int block_restart_interval_;
|
|
//TODO(myabandeh): put it into a separate IndexBlockBuilder
|
|
const bool use_delta_encoding_;
|
|
// Refer to BlockIter::DecodeCurrentValue for format of delta encoded values
|
|
const bool use_value_delta_encoding_;
|
|
|
|
std::string buffer_; // Destination buffer
|
|
std::vector<uint32_t> restarts_; // Restart points
|
|
size_t estimate_;
|
|
int counter_; // Number of entries emitted since restart
|
|
bool finished_; // Has Finish() been called?
|
|
std::string last_key_;
|
|
DataBlockHashIndexBuilder data_block_hash_index_builder_;
|
|
};
|
|
|
|
} // namespace rocksdb
|