mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-29 18:33:58 +00:00
522de4f59e
Summary: When a block based table file is opened, if prefetch_index_and_filter is true, it will prefetch the index and filter blocks, putting them into the block cache. What this feature adds: when a L0 block based table file is opened, if pin_l0_filter_and_index_blocks_in_cache is true in the options (and prefetch_index_and_filter is true), then the filter and index blocks aren't released back to the block cache at the end of BlockBasedTableReader::Open(). Instead the table reader takes ownership of them, hence pinning them, ie. the LRU cache will never push them out. Meanwhile in the table reader, further accesses will not hit the block cache, thus avoiding lock contention. When the table reader is destroyed, it releases the pinned blocks (if there were any). This has to happen before the cache is destroyed, so I had to introduce a TableReader::Close(), to guarantee the order of destruction. Test Plan: Added two unit tests for this. Existing unit tests run fine (default is pin_l0_filter_and_index_blocks_in_cache=false). DISABLE_JEMALLOC=1 OPT=-g make all valgrind_check -j32 Mac: OK. Linux: with D55287 patched in it's OK. Reviewers: sdong Reviewed By: sdong Subscribers: andrewkr, leveldb, dhruba Differential Revision: https://reviews.facebook.net/D54801
121 lines
5 KiB
C++
121 lines
5 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.
|
|
//
|
|
// Thread-safe (provides internal synchronization)
|
|
|
|
#pragma once
|
|
#include <string>
|
|
#include <vector>
|
|
#include <stdint.h>
|
|
|
|
#include "db/dbformat.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/cache.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/table.h"
|
|
#include "rocksdb/options.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 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, 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 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);
|
|
|
|
// 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);
|
|
|
|
// 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);
|
|
|
|
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,
|
|
unique_ptr<TableReader>* table_reader,
|
|
bool skip_filters = false, int level = -1);
|
|
|
|
const ImmutableCFOptions& ioptions_;
|
|
const EnvOptions& env_options_;
|
|
Cache* const cache_;
|
|
std::string row_cache_id_;
|
|
};
|
|
|
|
} // namespace rocksdb
|