49623f9c8e
Summary: **Context:** Through heap profiling, we discovered that `BlockBasedTableReader` objects can accumulate and lead to high memory usage (e.g, `max_open_file = -1`). These memories are currently not saved, not tracked, not constrained and not cache evict-able. As a first step to improve this, similar to https://github.com/facebook/rocksdb/pull/8428, this PR is to track an estimate of `BlockBasedTableReader` object's memory in block cache and fail future creation if the memory usage exceeds the available space of cache at the time of creation. **Summary:** - Approximate big memory users (`BlockBasedTable::Rep` and `TableProperties` )' memory usage in addition to the existing estimated ones (filter block/index block/un-compression dictionary) - Charge all of these memory usages to block cache on `BlockBasedTable::Open()` and release them on `~BlockBasedTable()` as there is no memory usage fluctuation of concern in between - Refactor on CacheReservationManager (and its call-sites) to add concurrent support for BlockBasedTable used in this PR. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9748 Test Plan: - New unit tests - db bench: `OpenDb` : **-0.52% in ms** - Setup `./db_bench -benchmarks=fillseq -db=/dev/shm/testdb -disable_auto_compactions=1 -write_buffer_size=1048576` - Repeated run with pre-change w/o feature and post-change with feature, benchmark `OpenDb`: `./db_bench -benchmarks=readrandom -use_existing_db=1 -db=/dev/shm/testdb -reserve_table_reader_memory=true (remove this when running w/o feature) -file_opening_threads=3 -open_files=-1 -report_open_timing=true| egrep 'OpenDb:'` #-run | (feature-off) avg milliseconds | std milliseconds | (feature-on) avg milliseconds | std milliseconds | change (%) -- | -- | -- | -- | -- | -- 10 | 11.4018 | 5.95173 | 9.47788 | 1.57538 | -16.87382694 20 | 9.23746 | 0.841053 | 9.32377 | 1.14074 | 0.9343477536 40 | 9.0876 | 0.671129 | 9.35053 | 1.11713 | 2.893283155 80 | 9.72514 | 2.28459 | 9.52013 | 1.0894 | -2.108041632 160 | 9.74677 | 0.991234 | 9.84743 | 1.73396 | 1.032752389 320 | 10.7297 | 5.11555 | 10.547 | 1.97692 | **-1.70275031** 640 | 11.7092 | 2.36565 | 11.7869 | 2.69377 | **0.6635807741** - db bench on write with cost to cache in WriteBufferManager (just in case this PR's CRM refactoring accidentally slows down anything in WBM) : `fillseq` : **+0.54% in micros/op** `./db_bench -benchmarks=fillseq -db=/dev/shm/testdb -disable_auto_compactions=1 -cost_write_buffer_to_cache=true -write_buffer_size=10000000000 | egrep 'fillseq'` #-run | (pre-PR) avg micros/op | std micros/op | (post-PR) avg micros/op | std micros/op | change (%) -- | -- | -- | -- | -- | -- 10 | 6.15 | 0.260187 | 6.289 | 0.371192 | 2.260162602 20 | 7.28025 | 0.465402 | 7.37255 | 0.451256 | 1.267813605 40 | 7.06312 | 0.490654 | 7.13803 | 0.478676 | **1.060579461** 80 | 7.14035 | 0.972831 | 7.14196 | 0.92971 | **0.02254791432** - filter bench: `bloom filter`: **-0.78% in ms/key** - ` ./filter_bench -impl=2 -quick -reserve_table_builder_memory=true | grep 'Build avg'` #-run | (pre-PR) avg ns/key | std ns/key | (post-PR) ns/key | std ns/key | change (%) -- | -- | -- | -- | -- | -- 10 | 26.4369 | 0.442182 | 26.3273 | 0.422919 | **-0.4145720565** 20 | 26.4451 | 0.592787 | 26.1419 | 0.62451 | **-1.1465262** - Crash test `python3 tools/db_crashtest.py blackbox --reserve_table_reader_memory=1 --cache_size=1` killed as normal Reviewed By: ajkr Differential Revision: D35136549 Pulled By: hx235 fbshipit-source-id: 146978858d0f900f43f4eb09bfd3e83195e3be28
102 lines
3.3 KiB
C++
102 lines
3.3 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.
|
|
|
|
#pragma once
|
|
#include <stdint.h>
|
|
|
|
#include <memory>
|
|
#include <string>
|
|
|
|
#include "cache/cache_reservation_manager.h"
|
|
#include "port/port.h"
|
|
#include "rocksdb/flush_block_policy.h"
|
|
#include "rocksdb/table.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
struct ColumnFamilyOptions;
|
|
struct ConfigOptions;
|
|
struct DBOptions;
|
|
struct EnvOptions;
|
|
|
|
class BlockBasedTableBuilder;
|
|
class RandomAccessFileReader;
|
|
class WritableFileWriter;
|
|
|
|
// A class used to track actual bytes written from the tail in the recent SST
|
|
// file opens, and provide a suggestion for following open.
|
|
class TailPrefetchStats {
|
|
public:
|
|
void RecordEffectiveSize(size_t len);
|
|
// 0 indicates no information to determine.
|
|
size_t GetSuggestedPrefetchSize();
|
|
|
|
private:
|
|
const static size_t kNumTracked = 32;
|
|
size_t records_[kNumTracked];
|
|
port::Mutex mutex_;
|
|
size_t next_ = 0;
|
|
size_t num_records_ = 0;
|
|
};
|
|
|
|
class BlockBasedTableFactory : public TableFactory {
|
|
public:
|
|
explicit BlockBasedTableFactory(
|
|
const BlockBasedTableOptions& table_options = BlockBasedTableOptions());
|
|
|
|
~BlockBasedTableFactory() {}
|
|
|
|
// Method to allow CheckedCast to work for this class
|
|
static const char* kClassName() { return kBlockBasedTableName(); }
|
|
|
|
const char* Name() const override { return kBlockBasedTableName(); }
|
|
|
|
using TableFactory::NewTableReader;
|
|
Status NewTableReader(
|
|
const ReadOptions& ro, const TableReaderOptions& table_reader_options,
|
|
std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
|
|
std::unique_ptr<TableReader>* table_reader,
|
|
bool prefetch_index_and_filter_in_cache = true) const override;
|
|
|
|
TableBuilder* NewTableBuilder(
|
|
const TableBuilderOptions& table_builder_options,
|
|
WritableFileWriter* file) const override;
|
|
|
|
// Valdates the specified DB Options.
|
|
Status ValidateOptions(const DBOptions& db_opts,
|
|
const ColumnFamilyOptions& cf_opts) const override;
|
|
Status PrepareOptions(const ConfigOptions& opts) override;
|
|
|
|
std::string GetPrintableOptions() const override;
|
|
|
|
bool IsDeleteRangeSupported() const override { return true; }
|
|
|
|
TailPrefetchStats* tail_prefetch_stats() { return &tail_prefetch_stats_; }
|
|
|
|
protected:
|
|
const void* GetOptionsPtr(const std::string& name) const override;
|
|
#ifndef ROCKSDB_LITE
|
|
Status ParseOption(const ConfigOptions& config_options,
|
|
const OptionTypeInfo& opt_info,
|
|
const std::string& opt_name, const std::string& opt_value,
|
|
void* opt_ptr) override;
|
|
#endif
|
|
void InitializeOptions();
|
|
|
|
private:
|
|
BlockBasedTableOptions table_options_;
|
|
std::shared_ptr<CacheReservationManager> table_reader_cache_res_mgr_;
|
|
mutable TailPrefetchStats tail_prefetch_stats_;
|
|
};
|
|
|
|
extern const std::string kHashIndexPrefixesBlock;
|
|
extern const std::string kHashIndexPrefixesMetadataBlock;
|
|
extern const std::string kPropTrue;
|
|
extern const std::string kPropFalse;
|
|
} // namespace ROCKSDB_NAMESPACE
|