rocksdb/db/table_cache.h

214 lines
9.9 KiB
C
Raw Normal View History

// 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"
#include "trace_replay/block_cache_tracer.h"
namespace rocksdb {
class Env;
class Arena;
struct FileDescriptor;
class GetContext;
class HistogramImpl;
// Manages caching for TableReader objects for a column family. The actual
// cache is allocated separately and passed to the constructor. TableCache
// wraps around the underlying SST file readers by providing Get(),
// MultiGet() and NewIterator() methods that hide the instantiation,
// caching and access to the TableReader. The main purpose of this is
// performance - by caching the TableReader, it avoids unnecessary file opens
// and object allocation and instantiation. One exception is compaction, where
// a new TableReader may be instantiated - see NewIterator() comments
//
// Another service provided by TableCache is managing the row cache - if the
// DB is configured with a row cache, and the lookup key is present in the row
// cache, lookup is very fast. The row cache is obtained from
// ioptions.row_cache
class TableCache {
public:
TableCache(const ImmutableCFOptions& ioptions,
const EnvOptions& storage_options, Cache* cache,
BlockCacheTracer* const block_cache_tracer);
~TableCache();
// Return an iterator for the specified file number (the corresponding
// file length must be exactly "file_size" bytes). If "table_reader_ptr"
// is non-nullptr, also sets "*table_reader_ptr" to point to the Table object
// underlying the returned iterator, or nullptr if no Table object underlies
// the returned iterator. The returned "*table_reader_ptr" 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 for_compaction If true, a new TableReader may be allocated (but
// not cached), depending on the CF options
// @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, TableReader** table_reader_ptr,
HistogramImpl* file_read_hist, TableReaderCaller caller, Arena* arena,
bool skip_filters, int level, const InternalKey* smallest_compaction_key,
const InternalKey* largest_compaction_key);
// If a seek to internal key "k" in specified file finds an entry,
// call get_context->SaveValue() repeatedly until
// it returns false. As a side effect, it will insert the TableReader
// into the cache and potentially evict another entry
// @param get_context Context for get operation. The result of the lookup
// can be retrieved by calling get_context->State()
// @param file_read_hist If non-nullptr, the file reader statistics are
// recorded
// @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);
// Return the range delete tombstone iterator of the file specified by
// `file_meta`.
Status GetRangeTombstoneIterator(
const ReadOptions& options,
const InternalKeyComparator& internal_comparator,
const FileMetaData& file_meta,
std::unique_ptr<FragmentedRangeTombstoneIterator>* out_iter);
// If a seek to internal key "k" in specified file finds an entry,
// call get_context->SaveValue() repeatedly until
// it returns false. As a side effect, it will insert the TableReader
// into the cache and potentially evict another entry
// @param mget_range Pointer to the structure describing a batch of keys to
// be looked up in this table file. The result is stored
// in the embedded GetContext
// @param skip_filters Disables loading/accessing the filter block
// @param level The level this table is at, -1 for "not set / don't know"
Introduce a new MultiGet batching implementation (#5011) Summary: This PR introduces a new MultiGet() API, with the underlying implementation grouping keys based on SST file and batching lookups in a file. The reason for the new API is twofold - the definition allows callers to allocate storage for status and values on stack instead of std::vector, as well as return values as PinnableSlices in order to avoid copying, and it keeps the original MultiGet() implementation intact while we experiment with batching. Batching is useful when there is some spatial locality to the keys being queries, as well as larger batch sizes. The main benefits are due to - 1. Fewer function calls, especially to BlockBasedTableReader::MultiGet() and FullFilterBlockReader::KeysMayMatch() 2. Bloom filter cachelines can be prefetched, hiding the cache miss latency The next step is to optimize the binary searches in the level_storage_info, index blocks and data blocks, since we could reduce the number of key comparisons if the keys are relatively close to each other. The batching optimizations also need to be extended to other formats, such as PlainTable and filter formats. This also needs to be added to db_stress. Benchmark results from db_bench for various batch size/locality of reference combinations are given below. Locality was simulated by offsetting the keys in a batch by a stride length. Each SST file is about 8.6MB uncompressed and key/value size is 16/100 uncompressed. To focus on the cpu benefit of batching, the runs were single threaded and bound to the same cpu to eliminate interference from other system events. The results show a 10-25% improvement in micros/op from smaller to larger batch sizes (4 - 32). Batch Sizes 1 | 2 | 4 | 8 | 16 | 32 Random pattern (Stride length 0) 4.158 | 4.109 | 4.026 | 4.05 | 4.1 | 4.074 - Get 4.438 | 4.302 | 4.165 | 4.122 | 4.096 | 4.075 - MultiGet (no batching) 4.461 | 4.256 | 4.277 | 4.11 | 4.182 | 4.14 - MultiGet (w/ batching) Good locality (Stride length 16) 4.048 | 3.659 | 3.248 | 2.99 | 2.84 | 2.753 4.429 | 3.728 | 3.406 | 3.053 | 2.911 | 2.781 4.452 | 3.45 | 2.833 | 2.451 | 2.233 | 2.135 Good locality (Stride length 256) 4.066 | 3.786 | 3.581 | 3.447 | 3.415 | 3.232 4.406 | 4.005 | 3.644 | 3.49 | 3.381 | 3.268 4.393 | 3.649 | 3.186 | 2.882 | 2.676 | 2.62 Medium locality (Stride length 4096) 4.012 | 3.922 | 3.768 | 3.61 | 3.582 | 3.555 4.364 | 4.057 | 3.791 | 3.65 | 3.57 | 3.465 4.479 | 3.758 | 3.316 | 3.077 | 2.959 | 2.891 dbbench command used (on a DB with 4 levels, 12 million keys)- TEST_TMPDIR=/dev/shm numactl -C 10 ./db_bench.tmp -use_existing_db=true -benchmarks="readseq,multireadrandom" -write_buffer_size=4194304 -target_file_size_base=4194304 -max_bytes_for_level_base=16777216 -num=12000000 -reads=12000000 -duration=90 -threads=1 -compression_type=none -cache_size=4194304000 -batch_size=32 -disable_auto_compactions=true -bloom_bits=10 -cache_index_and_filter_blocks=true -pin_l0_filter_and_index_blocks_in_cache=true -multiread_batched=true -multiread_stride=4 Pull Request resolved: https://github.com/facebook/rocksdb/pull/5011 Differential Revision: D14348703 Pulled By: anand1976 fbshipit-source-id: 774406dab3776d979c809522a67bedac6c17f84b
2019-04-11 21:24:09 +00:00
Status MultiGet(const ReadOptions& options,
const InternalKeyComparator& internal_comparator,
const FileMetaData& file_meta,
const MultiGetContext::Range* mget_range,
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);
// Returns approximated offset of a key in a file represented by fd.
uint64_t ApproximateOffsetOf(
const Slice& key, const FileDescriptor& fd, TableReaderCaller caller,
const InternalKeyComparator& internal_comparator,
const SliceTransform* prefix_extractor = nullptr);
// Returns approximated data size between start and end keys in a file
// represented by fd (the start key must not be greater than the end key).
uint64_t ApproximateSize(const Slice& start, const Slice& end,
const FileDescriptor& fd, TableReaderCaller caller,
const InternalKeyComparator& internal_comparator,
const SliceTransform* prefix_extractor = nullptr);
// Release the handle from a cache
void ReleaseHandle(Cache::Handle* handle);
Cache* get_cache() const { return cache_; }
// 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,
bool record_read_stats, HistogramImpl* file_read_hist,
std::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);
const ImmutableCFOptions& ioptions_;
const EnvOptions& env_options_;
Cache* const cache_;
std::string row_cache_id_;
bool immortal_tables_;
BlockCacheTracer* const block_cache_tracer_;
};
} // namespace rocksdb