mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-26 16:30:56 +00:00
6fbe96baf8
Summary: This diff introduces RangeDelAggregator, which takes ownership of iterators provided to it via AddTombstones(). The tombstones are organized in a two-level map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data copy by holding Slices returned by the iterator, which remain valid thanks to pinning. For compaction, we create a hierarchical range tombstone iterator with structure matching the iterator over compaction input data. An aggregator based on that iterator is used by CompactionIterator to determine which keys are covered by range tombstones. In case of merge operand, the same aggregator is used by MergeHelper. Upon finishing each file in the compaction, relevant range tombstones are added to the output file's range tombstone metablock and file boundaries are updated accordingly. To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete() considers tombstones in the key's snapshot stripe. When this function is used outside of compaction, it also checks newer stripes, which can contain covering tombstones. Currently the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges within a stripe such that binary search can be used. RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range to a new table's range tombstone meta-block. Since range tombstones may fall in the gap between files, we may need to extend some files' key-ranges. The strategy is (1) first file extends as far left as possible and other files do not extend left, (2) all files extend right until either the start of the next file or the end of the last range tombstone in the gap, whichever comes first. One other notable change is adding release/move semantics to ScopedArenaIterator such that it can be used to transfer ownership of an arena-allocated iterator, similar to how unique_ptr is used for malloc'd data. Depends on D61473 Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927 Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark Reviewed By: lightmark Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D62205
128 lines
4.9 KiB
C++
128 lines
4.9 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 compressed block contents to file.
|
|
void WriteBlock(BlockBuilder* block, BlockHandle* handle, bool is_data_block);
|
|
|
|
// Compress and write block content to the file.
|
|
void WriteBlock(const Slice& block_contents, BlockHandle* handle,
|
|
bool is_data_block);
|
|
// Directly write data to the file.
|
|
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;
|
|
};
|
|
|
|
Slice CompressBlock(const Slice& raw,
|
|
const CompressionOptions& compression_options,
|
|
CompressionType* type, uint32_t format_version,
|
|
const Slice& compression_dict,
|
|
std::string* compressed_output);
|
|
|
|
} // namespace rocksdb
|