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
100 lines
3.5 KiB
C++
100 lines
3.5 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_INCLUDE_TABLE_H_
|
|
#define STORAGE_LEVELDB_INCLUDE_TABLE_H_
|
|
|
|
#include <memory>
|
|
#include <stdint.h>
|
|
#include "leveldb/iterator.h"
|
|
#include "leveldb/env.h"
|
|
|
|
namespace leveldb {
|
|
|
|
class Block;
|
|
class BlockHandle;
|
|
class Footer;
|
|
struct Options;
|
|
class RandomAccessFile;
|
|
struct ReadOptions;
|
|
class TableCache;
|
|
|
|
using std::unique_ptr;
|
|
|
|
// A Table is a sorted map from strings to strings. Tables are
|
|
// immutable and persistent. A Table may be safely accessed from
|
|
// multiple threads without external synchronization.
|
|
class Table {
|
|
public:
|
|
// Attempt to open the table that is stored in bytes [0..file_size)
|
|
// of "file", and read the metadata entries necessary to allow
|
|
// retrieving data from the table.
|
|
//
|
|
// If successful, returns ok and sets "*table" to the newly opened
|
|
// table. The client should delete "*table" when no longer needed.
|
|
// If there was an error while initializing the table, sets "*table"
|
|
// to nullptr and returns a non-ok status. Does not take ownership of
|
|
// "*source", but the client must ensure that "source" remains live
|
|
// for the duration of the returned table's lifetime.
|
|
//
|
|
// *file must remain live while this Table is in use.
|
|
static Status Open(const Options& options,
|
|
const EnvOptions& soptions,
|
|
unique_ptr<RandomAccessFile>&& file,
|
|
uint64_t file_size,
|
|
unique_ptr<Table>* table);
|
|
|
|
~Table();
|
|
|
|
// Returns a new iterator over the table contents.
|
|
// The result of NewIterator() is initially invalid (caller must
|
|
// call one of the Seek methods on the iterator before using it).
|
|
Iterator* NewIterator(const ReadOptions&) const;
|
|
|
|
// Given a key, return an approximate byte offset in the file where
|
|
// the data for that key begins (or would begin if the key were
|
|
// present in the file). The returned value is in terms of file
|
|
// bytes, and so includes effects like compression of the underlying data.
|
|
// E.g., the approximate offset of the last key in the table will
|
|
// be close to the file length.
|
|
uint64_t ApproximateOffsetOf(const Slice& key) const;
|
|
|
|
// Returns true if the block for the specified key is in cache.
|
|
// REQUIRES: key is in this table.
|
|
bool TEST_KeyInCache(const ReadOptions& options, const Slice& key);
|
|
|
|
private:
|
|
struct Rep;
|
|
Rep* rep_;
|
|
|
|
explicit Table(Rep* rep) { rep_ = rep; }
|
|
static Iterator* BlockReader(void*, const ReadOptions&,
|
|
const EnvOptions& soptions, const Slice&);
|
|
static Iterator* BlockReader(void*, const ReadOptions&, const Slice&,
|
|
bool* didIO);
|
|
|
|
// Calls (*handle_result)(arg, ...) repeatedly, starting with the entry found
|
|
// after a call to Seek(key), until handle_result returns false.
|
|
// May not make such a call if filter policy says that key is not present.
|
|
friend class TableCache;
|
|
Status InternalGet(
|
|
const ReadOptions&, const Slice& key,
|
|
void* arg,
|
|
bool (*handle_result)(void* arg, const Slice& k, const Slice& v, bool));
|
|
|
|
|
|
void ReadMeta(const Footer& footer);
|
|
void ReadFilter(const Slice& filter_handle_value);
|
|
|
|
static void SetupCacheKeyPrefix(Rep* rep);
|
|
|
|
// No copying allowed
|
|
Table(const Table&);
|
|
void operator=(const Table&);
|
|
};
|
|
|
|
} // namespace leveldb
|
|
|
|
#endif // STORAGE_LEVELDB_INCLUDE_TABLE_H_
|