b234a3f569
Summary: ... by bypassing tracking of last_key in BlockBuilder when last_key is already known (for BlockBasedTableBuilder::data_block). I tried extracting a base class of BlockBuilder without the last_key tracking at all, but that became complicated by NewFlushBlockPolicy() in the public API referencing BlockBuilder, which would need to be the base class, and I don't want to replace nearly all the internal references to BlockBuilder. Possible follow-up: * Investigate / consider using AddWithLastKey in more places This improvement should stack with https://github.com/facebook/rocksdb/issues/9039 Pull Request resolved: https://github.com/facebook/rocksdb/pull/9040 Test Plan: TEST_TMPDIR=/dev/shm/rocksdb1 ./db_bench -benchmarks=fillseq -memtablerep=vector -allow_concurrent_memtable_write=false -num=50000000 Compiled with DEBUG_LEVEL=0 Test vs. control runs simulaneous for better accuracy, units = ops/sec Run 1: 278929 vs. 267799 (+4.2%) Run 2: 281836 vs. 267432 (+5.4%) Run 3: 278279 vs. 270454 (+2.9%) (This benchmark is chosen to have detectable signal-to-noise, not to represent expected improvement percent on real workloads.) Reviewed By: mrambacher Differential Revision: D31706033 Pulled By: pdillinger fbshipit-source-id: 8a50fe6fefdd67b6d7665ffa687bbdcf5ad0d5ec
102 lines
4.1 KiB
C++
102 lines
4.1 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/block_based/data_block_hash_index.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
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();
|
|
|
|
// Swap the contents in BlockBuilder with buffer, then reset the BlockBuilder.
|
|
void SwapAndReset(std::string& buffer);
|
|
|
|
// REQUIRES: Finish() has not been called since the last call to Reset().
|
|
// REQUIRES: key is larger than any previously added key
|
|
// DO NOT mix with AddWithLastKey() between Resets. For efficiency, use
|
|
// AddWithLastKey() in contexts where previous added key is already known
|
|
// and delta encoding might be used.
|
|
void Add(const Slice& key, const Slice& value,
|
|
const Slice* const delta_value = nullptr);
|
|
|
|
// A faster version of Add() if the previous key is already known for all
|
|
// Add()s.
|
|
// REQUIRES: Finish() has not been called since the last call to Reset().
|
|
// REQUIRES: key is larger than any previously added key
|
|
// REQUIRES: if AddWithLastKey has been called since last Reset(), last_key
|
|
// is the key from most recent AddWithLastKey. (For convenience, last_key
|
|
// is ignored on first call after creation or Reset().)
|
|
// DO NOT mix with Add() between Resets.
|
|
void AddWithLastKey(const Slice& key, const Slice& value,
|
|
const Slice& last_key,
|
|
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:
|
|
inline void AddWithLastKeyImpl(const Slice& key, const Slice& value,
|
|
const Slice& last_key,
|
|
const Slice* const delta_value,
|
|
size_t buffer_size);
|
|
|
|
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_;
|
|
#ifndef NDEBUG
|
|
bool add_with_last_key_called_ = false;
|
|
#endif
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|