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
118 lines
4.3 KiB
C++
118 lines
4.3 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 <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include "db/table_properties_collector.h"
|
|
#include "rocksdb/options.h"
|
|
#include "rocksdb/table_properties.h"
|
|
#include "util/file_reader_writer.h"
|
|
#include "util/mutable_cf_options.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class Slice;
|
|
class Status;
|
|
|
|
struct TableReaderOptions {
|
|
// @param skip_filters Disables loading/accessing the filter block
|
|
TableReaderOptions(const ImmutableCFOptions& _ioptions,
|
|
const EnvOptions& _env_options,
|
|
const InternalKeyComparator& _internal_comparator,
|
|
bool _skip_filters = false, int _level = -1)
|
|
: ioptions(_ioptions),
|
|
env_options(_env_options),
|
|
internal_comparator(_internal_comparator),
|
|
skip_filters(_skip_filters),
|
|
level(_level) {}
|
|
|
|
const ImmutableCFOptions& ioptions;
|
|
const EnvOptions& env_options;
|
|
const InternalKeyComparator& internal_comparator;
|
|
// This is only used for BlockBasedTable (reader)
|
|
bool skip_filters;
|
|
// what level this table/file is on, -1 for "not set, don't know"
|
|
int level;
|
|
};
|
|
|
|
struct TableBuilderOptions {
|
|
TableBuilderOptions(
|
|
const ImmutableCFOptions& _ioptions,
|
|
const InternalKeyComparator& _internal_comparator,
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
_int_tbl_prop_collector_factories,
|
|
CompressionType _compression_type,
|
|
const CompressionOptions& _compression_opts, bool _skip_filters)
|
|
: ioptions(_ioptions),
|
|
internal_comparator(_internal_comparator),
|
|
int_tbl_prop_collector_factories(_int_tbl_prop_collector_factories),
|
|
compression_type(_compression_type),
|
|
compression_opts(_compression_opts),
|
|
skip_filters(_skip_filters) {}
|
|
const ImmutableCFOptions& ioptions;
|
|
const InternalKeyComparator& internal_comparator;
|
|
const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
|
|
int_tbl_prop_collector_factories;
|
|
CompressionType compression_type;
|
|
const CompressionOptions& compression_opts;
|
|
// This is only used for BlockBasedTableBuilder
|
|
bool skip_filters = false;
|
|
};
|
|
|
|
// TableBuilder provides the interface used to build a Table
|
|
// (an immutable and sorted map from keys to values).
|
|
//
|
|
// Multiple threads can invoke const methods on a TableBuilder without
|
|
// external synchronization, but if any of the threads may call a
|
|
// non-const method, all threads accessing the same TableBuilder must use
|
|
// external synchronization.
|
|
class TableBuilder {
|
|
public:
|
|
// REQUIRES: Either Finish() or Abandon() has been called.
|
|
virtual ~TableBuilder() {}
|
|
|
|
// 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
|
|
virtual void Add(const Slice& key, const Slice& value) = 0;
|
|
|
|
// Return non-ok iff some error has been detected.
|
|
virtual Status status() const = 0;
|
|
|
|
// Finish building the table.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
virtual Status Finish() = 0;
|
|
|
|
// Indicate that the contents of this builder should be abandoned.
|
|
// If the caller is not going to call Finish(), it must call Abandon()
|
|
// before destroying this builder.
|
|
// REQUIRES: Finish(), Abandon() have not been called
|
|
virtual void Abandon() = 0;
|
|
|
|
// Number of calls to Add() so far.
|
|
virtual uint64_t NumEntries() const = 0;
|
|
|
|
// Size of the file generated so far. If invoked after a successful
|
|
// Finish() call, returns the size of the final generated file.
|
|
virtual uint64_t FileSize() const = 0;
|
|
|
|
// If the user defined table properties collector suggest the file to
|
|
// be further compacted.
|
|
virtual bool NeedCompact() const { return false; }
|
|
|
|
// Returns table properties
|
|
virtual TableProperties GetTableProperties() const = 0;
|
|
};
|
|
|
|
} // namespace rocksdb
|