caf0f53a74
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
65 lines
2.1 KiB
C++
65 lines
2.1 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 "db/dbformat.h"
|
|
#include "rocksdb/types.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class Comparator;
|
|
class Env;
|
|
class Arena;
|
|
template <class TValue>
|
|
class InternalIteratorBase;
|
|
using InternalIterator = InternalIteratorBase<Slice>;
|
|
|
|
// Return an iterator that provided the union of the data in
|
|
// children[0,n-1]. Takes ownership of the child iterators and
|
|
// will delete them when the result iterator is deleted.
|
|
//
|
|
// The result does no duplicate suppression. I.e., if a particular
|
|
// key is present in K child iterators, it will be yielded K times.
|
|
//
|
|
// REQUIRES: n >= 0
|
|
extern InternalIterator* NewMergingIterator(
|
|
const InternalKeyComparator* comparator, InternalIterator** children, int n,
|
|
Arena* arena = nullptr, bool prefix_seek_mode = false);
|
|
|
|
class MergingIterator;
|
|
|
|
// A builder class to build a merging iterator by adding iterators one by one.
|
|
class MergeIteratorBuilder {
|
|
public:
|
|
// comparator: the comparator used in merging comparator
|
|
// arena: where the merging iterator needs to be allocated from.
|
|
explicit MergeIteratorBuilder(const InternalKeyComparator* comparator,
|
|
Arena* arena, bool prefix_seek_mode = false);
|
|
~MergeIteratorBuilder();
|
|
|
|
// Add iter to the merging iterator.
|
|
void AddIterator(InternalIterator* iter);
|
|
|
|
// Get arena used to build the merging iterator. It is called one a child
|
|
// iterator needs to be allocated.
|
|
Arena* GetArena() { return arena; }
|
|
|
|
// Return the result merging iterator.
|
|
InternalIterator* Finish();
|
|
|
|
private:
|
|
MergingIterator* merge_iter;
|
|
InternalIterator* first_iter;
|
|
bool use_merging_iter;
|
|
Arena* arena;
|
|
};
|
|
|
|
} // namespace rocksdb
|