mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +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
121 lines
4.6 KiB
C++
121 lines
4.6 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 <stdint.h>
|
|
#include <limits>
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
|
|
#include "rocksdb/flush_block_policy.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/status.h"
|
|
#include "table/table_builder.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class BlockBuilder;
|
|
class BlockHandle;
|
|
class WritableFile;
|
|
struct BlockBasedTableOptions;
|
|
|
|
extern const uint64_t kBlockBasedTableMagicNumber;
|
|
extern const uint64_t kLegacyBlockBasedTableMagicNumber;
|
|
|
|
class BlockBasedTableBuilder : public TableBuilder {
|
|
public:
|
|
// Create a builder that will store the contents of the table it is
|
|
// building in *file. Does not close the file. It is up to the
|
|
// caller to close the file after calling Finish().
|
|
// @param compression_dict Data for presetting the compression library's
|
|
// dictionary, or nullptr.
|
|
BlockBasedTableBuilder(
|
|
const ImmutableCFOptions& ioptions,
|
|
const BlockBasedTableOptions& table_options,
|
|
const InternalKeyComparator& internal_comparator,
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
int_tbl_prop_collector_factories,
|
|
uint32_t column_family_id, WritableFileWriter* file,
|
|
const CompressionType compression_type,
|
|
const CompressionOptions& compression_opts,
|
|
const std::string* compression_dict, const bool skip_filters,
|
|
const std::string& column_family_name);
|
|
|
|
// REQUIRES: Either Finish() or Abandon() has been called.
|
|
~BlockBasedTableBuilder();
|
|
|
|
// Add key,value to the table being constructed.
|
|
// REQUIRES: key is after any previously added key according to comparator.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
void Add(const Slice& key, const Slice& value) override;
|
|
|
|
// Return non-ok iff some error has been detected.
|
|
Status status() const override;
|
|
|
|
// Finish building the table. Stops using the file passed to the
|
|
// constructor after this function returns.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
Status Finish() override;
|
|
|
|
// Indicate that the contents of this builder should be abandoned. Stops
|
|
// using the file passed to the constructor after this function returns.
|
|
// If the caller is not going to call Finish(), it must call Abandon()
|
|
// before destroying this builder.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
void Abandon() override;
|
|
|
|
// Number of calls to Add() so far.
|
|
uint64_t NumEntries() const override;
|
|
|
|
// Size of the file generated so far. If invoked after a successful
|
|
// Finish() call, returns the size of the final generated file.
|
|
uint64_t FileSize() const override;
|
|
|
|
bool NeedCompact() const override;
|
|
|
|
// Get table properties
|
|
TableProperties GetTableProperties() const override;
|
|
|
|
private:
|
|
bool ok() const { return status().ok(); }
|
|
|
|
// Call block's Finish() method and then write the finalize block contents to
|
|
// file.
|
|
void WriteBlock(BlockBuilder* block, BlockHandle* handle, bool is_data_block);
|
|
|
|
// Directly write block content to the file.
|
|
void WriteBlock(const Slice& block_contents, BlockHandle* handle,
|
|
bool is_data_block);
|
|
void WriteRawBlock(const Slice& data, CompressionType, BlockHandle* handle);
|
|
Status InsertBlockInCache(const Slice& block_contents,
|
|
const CompressionType type,
|
|
const BlockHandle* handle);
|
|
struct Rep;
|
|
class BlockBasedTablePropertiesCollectorFactory;
|
|
class BlockBasedTablePropertiesCollector;
|
|
Rep* rep_;
|
|
|
|
// Advanced operation: flush any buffered key/value pairs to file.
|
|
// Can be used to ensure that two adjacent entries never live in
|
|
// the same data block. Most clients should not need to use this method.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
void Flush();
|
|
|
|
// Some compression libraries fail when the raw size is bigger than int. If
|
|
// uncompressed size is bigger than kCompressionSizeLimit, don't compress it
|
|
const uint64_t kCompressionSizeLimit = std::numeric_limits<int>::max();
|
|
|
|
// No copying allowed
|
|
BlockBasedTableBuilder(const BlockBasedTableBuilder&) = delete;
|
|
void operator=(const BlockBasedTableBuilder&) = delete;
|
|
};
|
|
|
|
} // namespace rocksdb
|