You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/include/rocksdb/iterator.h

128 lines
4.7 KiB

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same 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.
//
// An iterator yields a sequence of key/value pairs from a source.
// The following class defines the interface. Multiple implementations
// are provided by this library. In particular, iterators are provided
// to access the contents of a Table or a DB.
//
// Multiple threads can invoke const methods on an Iterator without
// external synchronization, but if any of the threads may call a
// non-const method, all threads accessing the same Iterator must use
// external synchronization.
#ifndef STORAGE_ROCKSDB_INCLUDE_ITERATOR_H_
#define STORAGE_ROCKSDB_INCLUDE_ITERATOR_H_
#include <string>
#include "rocksdb/slice.h"
#include "rocksdb/status.h"
namespace rocksdb {
class Cleanable {
public:
Cleanable();
~Cleanable();
// Clients are allowed to register function/arg1/arg2 triples that
// will be invoked when this iterator is destroyed.
//
// Note that unlike all of the preceding methods, this method is
// not abstract and therefore clients should not override it.
typedef void (*CleanupFunction)(void* arg1, void* arg2);
void RegisterCleanup(CleanupFunction function, void* arg1, void* arg2);
protected:
struct Cleanup {
CleanupFunction function;
void* arg1;
void* arg2;
Cleanup* next;
};
Cleanup cleanup_;
};
class Iterator : public Cleanable {
public:
Iterator() {}
virtual ~Iterator() {}
// An iterator is either positioned at a key/value pair, or
// not valid. This method returns true iff the iterator is valid.
virtual bool Valid() const = 0;
// Position at the first key in the source. The iterator is Valid()
// after this call iff the source is not empty.
virtual void SeekToFirst() = 0;
// Position at the last key in the source. The iterator is
// Valid() after this call iff the source is not empty.
virtual void SeekToLast() = 0;
// Position at the first key in the source that at or past target
// The iterator is Valid() after this call iff the source contains
// an entry that comes at or past target.
virtual void Seek(const Slice& target) = 0;
// Moves to the next entry in the source. After this call, Valid() is
// true iff the iterator was not positioned at the last entry in the source.
// REQUIRES: Valid()
virtual void Next() = 0;
// Moves to the previous entry in the source. After this call, Valid() is
// true iff the iterator was not positioned at the first entry in source.
// REQUIRES: Valid()
virtual void Prev() = 0;
// Return the key for the current entry. The underlying storage for
// the returned slice is valid only until the next modification of
// the iterator.
// REQUIRES: Valid()
virtual Slice key() const = 0;
// Return the value for the current entry. The underlying storage for
// the returned slice is valid only until the next modification of
// the iterator.
// REQUIRES: !AtEnd() && !AtStart()
virtual Slice value() const = 0;
// If an error has occurred, return it. Else return an ok status.
// If non-blocking IO is requested and this operation cannot be
// satisfied without doing some IO, then this returns Status::Incomplete().
virtual Status status() const = 0;
// Property "rocksdb.iterator.is-key-pinned":
// If returning "1", this means that the Slice returned by key() is valid
// as long as the iterator is not deleted and ReleasePinnedData() is not
// called.
// It is guaranteed to always return "1" if
// - Iterator created with ReadOptions::pin_data = true
// - DB tables were created with
// BlockBasedTableOptions::use_delta_encoding
// set to false.
// Property "rocksdb.iterator.super-version-number":
// LSM version used by the iterator. The same format as DB Property
// kCurrentSuperVersionNumber. See its comment for more information.
virtual Status GetProperty(std::string prop_name, std::string* prop);
Introduce ReadOptions::pin_data (support zero copy for keys) Summary: This patch update the Iterator API to introduce new functions that allow users to keep the Slices returned by key() valid as long as the Iterator is not deleted ReadOptions::pin_data : If true keep loaded blocks in memory as long as the iterator is not deleted Iterator::IsKeyPinned() : If true, this mean that the Slice returned by key() is valid as long as the iterator is not deleted Also add a new option BlockBasedTableOptions::use_delta_encoding to allow users to disable delta_encoding if needed. Benchmark results (using https://phabricator.fb.com/P20083553) ``` // $ du -h /home/tec/local/normal.4K.Snappy/db10077 // 6.1G /home/tec/local/normal.4K.Snappy/db10077 // $ du -h /home/tec/local/zero.8K.LZ4/db10077 // 6.4G /home/tec/local/zero.8K.LZ4/db10077 // Benchmarks for shard db10077 // _build/opt/rocks/benchmark/rocks_copy_benchmark \ // --normal_db_path="/home/tec/local/normal.4K.Snappy/db10077" \ // --zero_db_path="/home/tec/local/zero.8K.LZ4/db10077" // First run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 1.73s 576.97m // BM_StringPiece 103.74% 1.67s 598.55m // ============================================================================ // Match rate : 1000000 / 1000000 // Second run // ============================================================================ // rocks/benchmark/RocksCopyBenchmark.cpp relative time/iter iters/s // ============================================================================ // BM_StringCopy 611.99ms 1.63 // BM_StringPiece 203.76% 300.35ms 3.33 // ============================================================================ // Match rate : 1000000 / 1000000 ``` Test Plan: Unit tests Reviewers: sdong, igor, anthony, yhchiang, rven Reviewed By: rven Subscribers: dhruba, lovro, adsharma Differential Revision: https://reviews.facebook.net/D48999
9 years ago
private:
// No copying allowed
Iterator(const Iterator&);
void operator=(const Iterator&);
};
// Return an empty iterator (yields nothing).
extern Iterator* NewEmptyIterator();
// Return an empty iterator with the specified status.
extern Iterator* NewErrorIterator(const Status& status);
} // namespace rocksdb
#endif // STORAGE_ROCKSDB_INCLUDE_ITERATOR_H_