rocksdb/table/cuckoo_table_reader.h
Maysam Yabandeh caf0f53a74 Index value delta encoding (#3983)
Summary:
Given that index value is a BlockHandle, which is basically an <offset, size> pair we can apply delta encoding on the values. The first value at each index restart interval encoded the full BlockHandle but the rest encode only the size. Refer to IndexBlockIter::DecodeCurrentValue for the detail of the encoding. This reduces the index size which helps using the  block cache more efficiently. The feature is enabled with using format_version 4.

The feature comes with a bit of cpu overhead which should be paid back by the higher cache hits due to smaller index block size.
Results with sysbench read-only using 4k blocks and using 16 index restart interval:
Format 2:
19585   rocksdb read-only range=100
Format 3:
19569   rocksdb read-only range=100
Format 4:
19352   rocksdb read-only range=100
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3983

Differential Revision: D8361343

Pulled By: maysamyabandeh

fbshipit-source-id: f882ee082322acac32b0072e2bdbb0b5f854e651
2018-08-09 16:58:40 -07:00

89 lines
3.0 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
#ifndef ROCKSDB_LITE
#include <string>
#include <memory>
#include <utility>
#include <vector>
#include "db/dbformat.h"
#include "options/cf_options.h"
#include "rocksdb/env.h"
#include "rocksdb/options.h"
#include "table/table_reader.h"
#include "util/file_reader_writer.h"
namespace rocksdb {
class Arena;
class TableReader;
class CuckooTableReader: public TableReader {
public:
CuckooTableReader(const ImmutableCFOptions& ioptions,
std::unique_ptr<RandomAccessFileReader>&& file,
uint64_t file_size, const Comparator* user_comparator,
uint64_t (*get_slice_hash)(const Slice&, uint32_t,
uint64_t));
~CuckooTableReader() {}
std::shared_ptr<const TableProperties> GetTableProperties() const override {
return table_props_;
}
Status status() const { return status_; }
Status Get(const ReadOptions& readOptions, const Slice& key,
GetContext* get_context, const SliceTransform* prefix_extractor,
bool skip_filters = false) override;
InternalIterator* NewIterator(const ReadOptions&,
const SliceTransform* prefix_extractor,
Arena* arena = nullptr,
bool skip_filters = false,
bool for_compaction = false) override;
void Prepare(const Slice& target) override;
// Report an approximation of how much memory has been used.
size_t ApproximateMemoryUsage() const override;
// Following methods are not implemented for Cuckoo Table Reader
uint64_t ApproximateOffsetOf(const Slice& /*key*/) override { return 0; }
void SetupForCompaction() override {}
// End of methods not implemented.
private:
friend class CuckooTableIterator;
void LoadAllKeys(std::vector<std::pair<Slice, uint32_t>>* key_to_bucket_id);
std::unique_ptr<RandomAccessFileReader> file_;
Slice file_data_;
bool is_last_level_;
bool identity_as_first_hash_;
bool use_module_hash_;
std::shared_ptr<const TableProperties> table_props_;
Status status_;
uint32_t num_hash_func_;
std::string unused_key_;
uint32_t key_length_;
uint32_t user_key_length_;
uint32_t value_length_;
uint32_t bucket_length_;
uint32_t cuckoo_block_size_;
uint32_t cuckoo_block_bytes_minus_one_;
uint64_t table_size_;
const Comparator* ucomp_;
uint64_t (*get_slice_hash_)(const Slice& s, uint32_t index,
uint64_t max_num_buckets);
};
} // namespace rocksdb
#endif // ROCKSDB_LITE