rocksdb/db/table_cache.h
Maysam Yabandeh caf0f53a74 Index value delta encoding (#3983)
Summary:
Given that index value is a BlockHandle, which is basically an <offset, size> pair we can apply delta encoding on the values. The first value at each index restart interval encoded the full BlockHandle but the rest encode only the size. Refer to IndexBlockIter::DecodeCurrentValue for the detail of the encoding. This reduces the index size which helps using the  block cache more efficiently. The feature is enabled with using format_version 4.

The feature comes with a bit of cpu overhead which should be paid back by the higher cache hits due to smaller index block size.
Results with sysbench read-only using 4k blocks and using 16 index restart interval:
Format 2:
19585   rocksdb read-only range=100
Format 3:
19569   rocksdb read-only range=100
Format 4:
19352   rocksdb read-only range=100
Pull Request resolved: https://github.com/facebook/rocksdb/pull/3983

Differential Revision: D8361343

Pulled By: maysamyabandeh

fbshipit-source-id: f882ee082322acac32b0072e2bdbb0b5f854e651
2018-08-09 16:58:40 -07:00

156 lines
6.7 KiB
C++

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root 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.
//
// Thread-safe (provides internal synchronization)
#pragma once
#include <string>
#include <vector>
#include <stdint.h>
#include "db/dbformat.h"
#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 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 FileMetaData& file_meta, RangeDelAggregator* range_del_agg,
const SliceTransform* prefix_extractor = nullptr,
TableReader** table_reader_ptr = nullptr,
HistogramImpl* file_read_hist = nullptr, bool for_compaction = false,
Arena* arena = nullptr, bool skip_filters = false, int level = -1);
// 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 FileMetaData& file_meta, const Slice& k,
GetContext* get_context,
const SliceTransform* prefix_extractor = nullptr,
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 SliceTransform* prefix_extractor = nullptr,
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,
const SliceTransform* prefix_extractor = nullptr,
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,
const SliceTransform* prefix_extractor = nullptr);
// 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;
// The tables opened with this TableCache will be immortal, i.e., their
// lifetime is as long as that of the DB.
void SetTablesAreImmortal() {
if (cache_->GetCapacity() >= kInfiniteCapacity) {
immortal_tables_ = true;
}
}
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,
const SliceTransform* prefix_extractor = nullptr,
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_;
bool immortal_tables_;
};
} // namespace rocksdb