05e8854085
Summary: This diff introduces a new Merge operation into rocksdb. The purpose of this review is mostly getting feedback from the team (everyone please) on the design. Please focus on the four files under include/leveldb/, as they spell the client visible interface change. include/leveldb/db.h include/leveldb/merge_operator.h include/leveldb/options.h include/leveldb/write_batch.h Please go over local/my_test.cc carefully, as it is a concerete use case. Please also review the impelmentation files to see if the straw man implementation makes sense. Note that, the diff does pass all make check and truly supports forward iterator over db and a version of Get that's based on iterator. Future work: - Integration with compaction - A raw Get implementation I am working on a wiki that explains the design and implementation choices, but coding comes just naturally and I think it might be a good idea to share the code earlier. The code is heavily commented. Test Plan: run all local tests Reviewers: dhruba, heyongqiang Reviewed By: dhruba CC: leveldb, zshao, sheki, emayanke, MarkCallaghan Differential Revision: https://reviews.facebook.net/D9651
119 lines
3.7 KiB
C++
119 lines
3.7 KiB
C++
// 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.
|
|
|
|
#ifndef STORAGE_LEVELDB_DB_MEMTABLE_H_
|
|
#define STORAGE_LEVELDB_DB_MEMTABLE_H_
|
|
|
|
#include <string>
|
|
#include "leveldb/db.h"
|
|
#include "db/dbformat.h"
|
|
#include "db/skiplist.h"
|
|
#include "db/version_set.h"
|
|
#include "util/arena.h"
|
|
|
|
namespace leveldb {
|
|
|
|
class InternalKeyComparator;
|
|
class Mutex;
|
|
class MemTableIterator;
|
|
|
|
class MemTable {
|
|
public:
|
|
// MemTables are reference counted. The initial reference count
|
|
// is zero and the caller must call Ref() at least once.
|
|
explicit MemTable(const InternalKeyComparator& comparator,
|
|
int numlevel = 7);
|
|
|
|
// Increase reference count.
|
|
void Ref() { ++refs_; }
|
|
|
|
// Drop reference count. Delete if no more references exist.
|
|
void Unref() {
|
|
--refs_;
|
|
assert(refs_ >= 0);
|
|
if (refs_ <= 0) {
|
|
delete this;
|
|
}
|
|
}
|
|
|
|
// Returns an estimate of the number of bytes of data in use by this
|
|
// data structure.
|
|
//
|
|
// REQUIRES: external synchronization to prevent simultaneous
|
|
// operations on the same MemTable.
|
|
size_t ApproximateMemoryUsage();
|
|
|
|
// Return an iterator that yields the contents of the memtable.
|
|
//
|
|
// The caller must ensure that the underlying MemTable remains live
|
|
// while the returned iterator is live. The keys returned by this
|
|
// iterator are internal keys encoded by AppendInternalKey in the
|
|
// db/dbformat.{h,cc} module.
|
|
Iterator* NewIterator();
|
|
|
|
// Add an entry into memtable that maps key to value at the
|
|
// specified sequence number and with the specified type.
|
|
// Typically value will be empty if type==kTypeDeletion.
|
|
void Add(SequenceNumber seq, ValueType type,
|
|
const Slice& key,
|
|
const Slice& value);
|
|
|
|
// If memtable contains a value for key, store it in *value and return true.
|
|
// If memtable contains a deletion for key, store a NotFound() error
|
|
// in *status and return true.
|
|
// If memtable contains Merge operation as the most recent entry for a key,
|
|
// and the merge process does not stop (not reaching a value or delete),
|
|
// store the current merged result in value and MergeInProgress in s.
|
|
// return false
|
|
// Else, return false.
|
|
bool Get(const LookupKey& key, std::string* value, Status* s,
|
|
const Options& options);
|
|
|
|
// Returns the edits area that is needed for flushing the memtable
|
|
VersionEdit* GetEdits() { return &edit_; }
|
|
|
|
// Returns the sequence number of the first element that was inserted
|
|
// into the memtable
|
|
SequenceNumber GetFirstSequenceNumber() { return first_seqno_; }
|
|
|
|
private:
|
|
~MemTable(); // Private since only Unref() should be used to delete it
|
|
|
|
struct KeyComparator {
|
|
const InternalKeyComparator comparator;
|
|
explicit KeyComparator(const InternalKeyComparator& c) : comparator(c) { }
|
|
int operator()(const char* a, const char* b) const;
|
|
};
|
|
friend class MemTableIterator;
|
|
friend class MemTableBackwardIterator;
|
|
friend class MemTableList;
|
|
|
|
typedef SkipList<const char*, KeyComparator> Table;
|
|
|
|
KeyComparator comparator_;
|
|
int refs_;
|
|
Arena arena_;
|
|
Table table_;
|
|
|
|
// These are used to manage memtable flushes to storage
|
|
bool flush_in_progress_; // started the flush
|
|
bool flush_completed_; // finished the flush
|
|
uint64_t file_number_; // filled up after flush is complete
|
|
|
|
// The udpates to be applied to the transaction log when this
|
|
// memtable is flushed to storage.
|
|
VersionEdit edit_;
|
|
|
|
// The sequence number of the kv that was inserted first
|
|
SequenceNumber first_seqno_;
|
|
|
|
// No copying allowed
|
|
MemTable(const MemTable&);
|
|
void operator=(const MemTable&);
|
|
};
|
|
|
|
} // namespace leveldb
|
|
|
|
#endif // STORAGE_LEVELDB_DB_MEMTABLE_H_
|