mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 07:30:54 +00:00
843d2e3137
Summary: This adds a new metablock containing a shared dictionary that is used to compress all data blocks in the SST file. The size of the shared dictionary is configurable in CompressionOptions and defaults to 0. It's currently only used for zlib/lz4/lz4hc, but the block will be stored in the SST regardless of the compression type if the user chooses a nonzero dictionary size. During compaction, computes the dictionary by randomly sampling the first output file in each subcompaction. It pre-computes the intervals to sample by assuming the output file will have the maximum allowable length. In case the file is smaller, some of the pre-computed sampling intervals can be beyond end-of-file, in which case we skip over those samples and the dictionary will be a bit smaller. After the dictionary is generated using the first file in a subcompaction, it is loaded into the compression library before writing each block in each subsequent file of that subcompaction. On the read path, gets the dictionary from the metablock, if it exists. Then, loads that dictionary into the compression library before reading each block. Test Plan: new unit test Reviewers: yhchiang, IslamAbdelRahman, cyan, sdong Reviewed By: sdong Subscribers: andrewkr, yoshinorim, kradhakrishnan, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D52287
77 lines
3.1 KiB
C++
77 lines
3.1 KiB
C++
// 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.
|
|
#pragma once
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include "db/table_properties_collector.h"
|
|
#include "rocksdb/comparator.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/status.h"
|
|
#include "rocksdb/types.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/immutable_options.h"
|
|
#include "rocksdb/table_properties.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
struct Options;
|
|
struct FileMetaData;
|
|
|
|
class Env;
|
|
struct EnvOptions;
|
|
class Iterator;
|
|
class TableCache;
|
|
class VersionEdit;
|
|
class TableBuilder;
|
|
class WritableFileWriter;
|
|
class InternalStats;
|
|
class InternalIterator;
|
|
|
|
// @param column_family_name Name of the column family that is also identified
|
|
// by column_family_id, or empty string if unknown. It must outlive the
|
|
// TableBuilder returned by this function.
|
|
// @param compression_dict Data for presetting the compression library's
|
|
// dictionary, or nullptr.
|
|
TableBuilder* NewTableBuilder(
|
|
const ImmutableCFOptions& options,
|
|
const InternalKeyComparator& internal_comparator,
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
int_tbl_prop_collector_factories,
|
|
uint32_t column_family_id, const std::string& column_family_name,
|
|
WritableFileWriter* file, const CompressionType compression_type,
|
|
const CompressionOptions& compression_opts,
|
|
const std::string* compression_dict = nullptr,
|
|
const bool skip_filters = false);
|
|
|
|
// Build a Table file from the contents of *iter. The generated file
|
|
// will be named according to number specified in meta. On success, the rest of
|
|
// *meta will be filled with metadata about the generated table.
|
|
// If no data is present in *iter, meta->file_size will be set to
|
|
// zero, and no Table file will be produced.
|
|
//
|
|
// @param column_family_name Name of the column family that is also identified
|
|
// by column_family_id, or empty string if unknown.
|
|
extern Status BuildTable(
|
|
const std::string& dbname, Env* env, const ImmutableCFOptions& options,
|
|
const EnvOptions& env_options, TableCache* table_cache,
|
|
InternalIterator* iter, FileMetaData* meta,
|
|
const InternalKeyComparator& internal_comparator,
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
int_tbl_prop_collector_factories,
|
|
uint32_t column_family_id, const std::string& column_family_name,
|
|
std::vector<SequenceNumber> snapshots,
|
|
SequenceNumber earliest_write_conflict_snapshot,
|
|
const CompressionType compression,
|
|
const CompressionOptions& compression_opts, bool paranoid_file_checks,
|
|
InternalStats* internal_stats,
|
|
const Env::IOPriority io_priority = Env::IO_HIGH,
|
|
TableProperties* table_properties = nullptr, int level = -1);
|
|
|
|
} // namespace rocksdb
|