rocksdb/table/meta_blocks.h
Hui Xiao 151242ce46 Group rocksdb.sst.read.micros stat by IOActivity flush and compaction (#11288)
Summary:
**Context:**
The existing stat rocksdb.sst.read.micros does not reflect each of compaction and flush cases but aggregate them, which is not so helpful for us to understand IO read behavior of each of them.

**Summary**
- Update `StopWatch` and `RandomAccessFileReader` to record `rocksdb.sst.read.micros` and `rocksdb.file.{flush/compaction}.read.micros`
   - Fixed the default histogram in `RandomAccessFileReader`
- New field `ReadOptions/IOOptions::io_activity`; Pass `ReadOptions` through paths under db open, flush and compaction to where we can prepare `IOOptions` and pass it to `RandomAccessFileReader`
- Use `thread_status_util` for assertion in `DbStressFSWrapper` for continuous testing on we are passing correct `io_activity` under db open, flush and compaction

Pull Request resolved: https://github.com/facebook/rocksdb/pull/11288

Test Plan:
- **Stress test**
- **Db bench 1: rocksdb.sst.read.micros COUNT ≈ sum of rocksdb.file.read.flush.micros's and rocksdb.file.read.compaction.micros's.**  (without blob)
     - May not be exactly the same due to `HistogramStat::Add` only guarantees atomic not accuracy across threads.
```
./db_bench -db=/dev/shm/testdb/ -statistics=true -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655 -target_file_size_base=655 -disable_auto_compactions=false -compression_type=none -bloom_bits=3 (-use_plain_table=1 -prefix_size=10)
```
```
// BlockBasedTable
rocksdb.sst.read.micros P50 : 2.009374 P95 : 4.968548 P99 : 8.110362 P100 : 43.000000 COUNT : 40456 SUM : 114805
rocksdb.file.read.flush.micros P50 : 1.871841 P95 : 3.872407 P99 : 5.540541 P100 : 43.000000 COUNT : 2250 SUM : 6116
rocksdb.file.read.compaction.micros P50 : 2.023109 P95 : 5.029149 P99 : 8.196910 P100 : 26.000000 COUNT : 38206 SUM : 108689

// PlainTable
Does not apply
```
- **Db bench 2: performance**

**Read**

SETUP: db with 900 files
```
./db_bench -db=/dev/shm/testdb/ -benchmarks="fillseq" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655  -disable_auto_compactions=true -target_file_size_base=655 -compression_type=none
```run till convergence
```
./db_bench -seed=1678564177044286 -use_existing_db=true -db=/dev/shm/testdb -benchmarks=readrandom[-X60] -statistics=true -num=1000000 -disable_auto_compactions=true -compression_type=none -bloom_bits=3
```
Pre-change
`readrandom [AVG 60 runs] : 21568 (± 248) ops/sec`
Post-change (no regression, -0.3%)
`readrandom [AVG 60 runs] : 21486 (± 236) ops/sec`

**Compaction/Flush**run till convergence
```
./db_bench -db=/dev/shm/testdb2/ -seed=1678564177044286 -benchmarks="fillseq[-X60]" -key_size=32 -value_size=512 -num=50000 -write_buffer_size=655  -disable_auto_compactions=false -target_file_size_base=655 -compression_type=none

rocksdb.sst.read.micros  COUNT : 33820
rocksdb.sst.read.flush.micros COUNT : 1800
rocksdb.sst.read.compaction.micros COUNT : 32020
```
Pre-change
`fillseq [AVG 46 runs] : 1391 (± 214) ops/sec;    0.7 (± 0.1) MB/sec`

Post-change (no regression, ~-0.4%)
`fillseq [AVG 46 runs] : 1385 (± 216) ops/sec;    0.7 (± 0.1) MB/sec`

Reviewed By: ajkr

Differential Revision: D44007011

Pulled By: hx235

fbshipit-source-id: a54c89e4846dfc9a135389edf3f3eedfea257132
2023-04-21 09:07:18 -07:00

173 lines
7.2 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).
#pragma once
#include <map>
#include <memory>
#include <string>
#include <vector>
#include "db/builder.h"
#include "db/table_properties_collector.h"
#include "rocksdb/comparator.h"
#include "rocksdb/memory_allocator.h"
#include "rocksdb/options.h"
#include "rocksdb/slice.h"
#include "table/block_based/block_builder.h"
#include "table/block_based/block_type.h"
#include "table/format.h"
#include "util/kv_map.h"
namespace ROCKSDB_NAMESPACE {
class BlockBuilder;
class BlockHandle;
class Env;
class Footer;
class Logger;
class RandomAccessFile;
struct TableProperties;
// Meta block names for metaindex
extern const std::string kPropertiesBlockName;
extern const std::string kPropertiesBlockOldName;
extern const std::string kCompressionDictBlockName;
extern const std::string kRangeDelBlockName;
class MetaIndexBuilder {
public:
MetaIndexBuilder(const MetaIndexBuilder&) = delete;
MetaIndexBuilder& operator=(const MetaIndexBuilder&) = delete;
MetaIndexBuilder();
void Add(const std::string& key, const BlockHandle& handle);
// Write all the added key/value pairs to the block and return the contents
// of the block.
Slice Finish();
private:
// store the sorted key/handle of the metablocks.
stl_wrappers::KVMap meta_block_handles_;
std::unique_ptr<BlockBuilder> meta_index_block_;
};
class PropertyBlockBuilder {
public:
PropertyBlockBuilder(const PropertyBlockBuilder&) = delete;
PropertyBlockBuilder& operator=(const PropertyBlockBuilder&) = delete;
PropertyBlockBuilder();
void AddTableProperty(const TableProperties& props);
void Add(const std::string& key, uint64_t value);
void Add(const std::string& key, const std::string& value);
void Add(const UserCollectedProperties& user_collected_properties);
// Write all the added entries to the block and return the block contents
Slice Finish();
private:
std::unique_ptr<BlockBuilder> properties_block_;
stl_wrappers::KVMap props_;
};
// Were we encounter any error occurs during user-defined statistics collection,
// we'll write the warning message to info log.
void LogPropertiesCollectionError(Logger* info_log, const std::string& method,
const std::string& name);
// Utility functions help table builder to trigger batch events for user
// defined property collectors.
// Return value indicates if there is any error occurred; if error occurred,
// the warning message will be logged.
// NotifyCollectTableCollectorsOnAdd() triggers the `Add` event for all
// property collectors.
bool NotifyCollectTableCollectorsOnAdd(
const Slice& key, const Slice& value, uint64_t file_size,
const std::vector<std::unique_ptr<IntTblPropCollector>>& collectors,
Logger* info_log);
void NotifyCollectTableCollectorsOnBlockAdd(
const std::vector<std::unique_ptr<IntTblPropCollector>>& collectors,
uint64_t block_uncomp_bytes, uint64_t block_compressed_bytes_fast,
uint64_t block_compressed_bytes_slow);
// NotifyCollectTableCollectorsOnFinish() triggers the `Finish` event for all
// property collectors. The collected properties will be added to `builder`.
bool NotifyCollectTableCollectorsOnFinish(
const std::vector<std::unique_ptr<IntTblPropCollector>>& collectors,
Logger* info_log, PropertyBlockBuilder* builder);
// Read table properties from a file using known BlockHandle.
// @returns a status to indicate if the operation succeeded. On success,
// *table_properties will point to a heap-allocated TableProperties
// object, otherwise value of `table_properties` will not be modified.
Status ReadTablePropertiesHelper(
const ReadOptions& ro, const BlockHandle& handle,
RandomAccessFileReader* file, FilePrefetchBuffer* prefetch_buffer,
const Footer& footer, const ImmutableOptions& ioptions,
std::unique_ptr<TableProperties>* table_properties,
MemoryAllocator* memory_allocator = nullptr);
// Read table properties from the properties block of a plain table.
// @returns a status to indicate if the operation succeeded. On success,
// *table_properties will point to a heap-allocated TableProperties
// object, otherwise value of `table_properties` will not be modified.
Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
uint64_t table_magic_number,
const ImmutableOptions& ioptions,
const ReadOptions& read_options,
std::unique_ptr<TableProperties>* properties,
MemoryAllocator* memory_allocator = nullptr,
FilePrefetchBuffer* prefetch_buffer = nullptr);
// Find the meta block from the meta index block. Returns OK and
// block_handle->IsNull() if not found.
Status FindOptionalMetaBlock(InternalIterator* meta_index_iter,
const std::string& meta_block_name,
BlockHandle* block_handle);
// Find the meta block from the meta index block. Returns Corruption if not
// found.
Status FindMetaBlock(InternalIterator* meta_index_iter,
const std::string& meta_block_name,
BlockHandle* block_handle);
// Find the meta block
Status FindMetaBlockInFile(RandomAccessFileReader* file, uint64_t file_size,
uint64_t table_magic_number,
const ImmutableOptions& ioptions,
const ReadOptions& read_options,
const std::string& meta_block_name,
BlockHandle* block_handle,
MemoryAllocator* memory_allocator = nullptr,
FilePrefetchBuffer* prefetch_buffer = nullptr,
Footer* footer_out = nullptr);
// Read meta block contents
Status ReadMetaIndexBlockInFile(RandomAccessFileReader* file,
uint64_t file_size, uint64_t table_magic_number,
const ImmutableOptions& ioptions,
const ReadOptions& read_options,
BlockContents* block_contents,
MemoryAllocator* memory_allocator = nullptr,
FilePrefetchBuffer* prefetch_buffer = nullptr,
Footer* footer_out = nullptr);
// Read the specified meta block with name meta_block_name
// from `file` and initialize `contents` with contents of this block.
// Return Status::OK in case of success.
Status ReadMetaBlock(RandomAccessFileReader* file,
FilePrefetchBuffer* prefetch_buffer, uint64_t file_size,
uint64_t table_magic_number,
const ImmutableOptions& ioptions,
const ReadOptions& read_options,
const std::string& meta_block_name, BlockType block_type,
BlockContents* contents,
MemoryAllocator* memory_allocator = nullptr);
} // namespace ROCKSDB_NAMESPACE