rocksdb/table/data_block_footer.cc
Fenggang Wu 19ec44fd39 Improve point-lookup performance using a data block hash index (#4174)
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
2018-08-15 14:30:03 -07:00

61 lines
1.8 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 "data_block_footer.h"
#include "rocksdb/table.h"
namespace rocksdb {
const int kDataBlockIndexTypeBitShift = 31;
// 0x7FFFFFFF
const uint32_t kMaxNumRestarts = (1u << kDataBlockIndexTypeBitShift) - 1u;
// 0x7FFFFFFF
const uint32_t kNumRestartsMask = (1u << kDataBlockIndexTypeBitShift) - 1u;
uint32_t PackIndexTypeAndNumRestarts(
BlockBasedTableOptions::DataBlockIndexType index_type,
uint32_t num_restarts) {
if (num_restarts > kMaxNumRestarts) {
assert(0); // mute travis "unused" warning
}
uint32_t block_footer = num_restarts;
if (index_type == BlockBasedTableOptions::kDataBlockBinaryAndHash) {
block_footer |= 1u << kDataBlockIndexTypeBitShift;
} else if (index_type != BlockBasedTableOptions::kDataBlockBinarySearch) {
assert(0);
}
return block_footer;
}
void UnPackIndexTypeAndNumRestarts(
uint32_t block_footer,
BlockBasedTableOptions::DataBlockIndexType* index_type,
uint32_t* num_restarts) {
if (index_type) {
if (block_footer & 1u << kDataBlockIndexTypeBitShift) {
*index_type = BlockBasedTableOptions::kDataBlockBinaryAndHash;
} else {
*index_type = BlockBasedTableOptions::kDataBlockBinarySearch;
}
}
if (num_restarts) {
*num_restarts = block_footer & kNumRestartsMask;
assert(*num_restarts <= kMaxNumRestarts);
}
}
} // namespace rocksdb