rocksdb/db/table_cache.h

149 lines
6.4 KiB
C
Raw Normal View History

// 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.
// This source code is also licensed under the GPLv2 license found in the
// COPYING file in the root directory of this source tree.
//
// 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.
//
// Thread-safe (provides internal synchronization)
#pragma once
#include <string>
#include <vector>
#include <stdint.h>
#include "db/dbformat.h"
Compaction Support for Range Deletion 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
2016-10-18 21:04:56 +02:00
#include "db/range_del_aggregator.h"
#include "options/cf_options.h"
#include "port/port.h"
#include "rocksdb/cache.h"
#include "rocksdb/env.h"
#include "rocksdb/options.h"
#include "rocksdb/table.h"
#include "table/table_reader.h"
namespace rocksdb {
class Env;
class Arena;
struct FileDescriptor;
class GetContext;
class HistogramImpl;
class InternalIterator;
class TableCache {
public:
TableCache(const ImmutableCFOptions& ioptions,
const EnvOptions& storage_options, Cache* cache);
~TableCache();
// Return an iterator for the specified file number (the corresponding
// file length must be exactly "file_size" bytes). If "tableptr" is
// non-nullptr, also sets "*tableptr" to point to the Table object
// underlying the returned iterator, or nullptr if no Table object underlies
// the returned iterator. The returned "*tableptr" object is owned by
// the cache and should not be deleted, and is valid for as long as the
// returned iterator is live.
// @param range_del_agg If non-nullptr, adds range deletions to the
// aggregator. If an error occurs, returns it in a NewErrorInternalIterator
// @param skip_filters Disables loading/accessing the filter block
// @param level The level this table is at, -1 for "not set / don't know"
InternalIterator* NewIterator(
const ReadOptions& options, const EnvOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_fd, RangeDelAggregator* range_del_agg,
TableReader** table_reader_ptr = nullptr,
HistogramImpl* file_read_hist = nullptr, bool for_compaction = false,
Arena* arena = nullptr, bool skip_filters = false, int level = -1);
InternalIterator* NewRangeTombstoneIterator(
const ReadOptions& options, const EnvOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_fd, HistogramImpl* file_read_hist,
bool skip_filters, int level);
// If a seek to internal key "k" in specified file finds an entry,
// call (*handle_result)(arg, found_key, found_value) repeatedly until
// it returns false.
// @param get_context State for get operation. If its range_del_agg() returns
// non-nullptr, adds range deletions to the aggregator. If an error occurs,
// returns non-ok status.
// @param skip_filters Disables loading/accessing the filter block
// @param level The level this table is at, -1 for "not set / don't know"
Status Get(const ReadOptions& options,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_fd, const Slice& k,
GetContext* get_context, HistogramImpl* file_read_hist = nullptr,
bool skip_filters = false, int level = -1);
// Evict any entry for the specified file number
static void Evict(Cache* cache, uint64_t file_number);
// Clean table handle and erase it from the table cache
// Used in DB close, or the file is not live anymore.
void EraseHandle(const FileDescriptor& fd, Cache::Handle* handle);
// Find table reader
// @param skip_filters Disables loading/accessing the filter block
// @param level == -1 means not specified
Status FindTable(const EnvOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_fd, Cache::Handle**,
const bool no_io = false, bool record_read_stats = true,
HistogramImpl* file_read_hist = nullptr,
bool skip_filters = false, int level = -1,
bool prefetch_index_and_filter_in_cache = true);
// Get TableReader from a cache handle.
TableReader* GetTableReaderFromHandle(Cache::Handle* handle);
// Get the table properties of a given table.
// @no_io: indicates if we should load table to the cache if it is not present
// in table cache yet.
// @returns: `properties` will be reset on success. Please note that we will
// return Status::Incomplete() if table is not present in cache and
// we set `no_io` to be true.
Status GetTableProperties(const EnvOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& file_meta,
std::shared_ptr<const TableProperties>* properties,
bool no_io = false);
// Return total memory usage of the table reader of the file.
// 0 if table reader of the file is not loaded.
size_t GetMemoryUsageByTableReader(
const EnvOptions& toptions,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& fd);
// Release the handle from a cache
void ReleaseHandle(Cache::Handle* handle);
// Capacity of the backing Cache that indicates inifinite TableCache capacity.
// For example when max_open_files is -1 we set the backing Cache to this.
static const int kInfiniteCapacity = 0x400000;
private:
// Build a table reader
Status GetTableReader(const EnvOptions& env_options,
const InternalKeyComparator& internal_comparator,
const FileDescriptor& fd, bool sequential_mode,
size_t readahead, bool record_read_stats,
HistogramImpl* file_read_hist,
unique_ptr<TableReader>* table_reader,
bool skip_filters = false, int level = -1,
bool prefetch_index_and_filter_in_cache = true,
bool for_compaction = false);
const ImmutableCFOptions& ioptions_;
const EnvOptions& env_options_;
Cache* const cache_;
std::string row_cache_id_;
};
} // namespace rocksdb