rocksdb/table/block_based/uncompression_dict_reader.cc
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

127 lines
4.1 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).
//
#include "table/block_based/uncompression_dict_reader.h"
#include "logging/logging.h"
#include "monitoring/perf_context_imp.h"
#include "table/block_based/block_based_table_reader.h"
#include "util/compression.h"
namespace ROCKSDB_NAMESPACE {
Status UncompressionDictReader::Create(
const BlockBasedTable* table, const ReadOptions& ro,
FilePrefetchBuffer* prefetch_buffer, bool use_cache, bool prefetch,
bool pin, BlockCacheLookupContext* lookup_context,
std::unique_ptr<UncompressionDictReader>* uncompression_dict_reader) {
assert(table);
assert(table->get_rep());
assert(!pin || prefetch);
assert(uncompression_dict_reader);
CachableEntry<UncompressionDict> uncompression_dict;
if (prefetch || !use_cache) {
const Status s = ReadUncompressionDictionary(
table, prefetch_buffer, ro, use_cache, nullptr /* get_context */,
lookup_context, &uncompression_dict);
if (!s.ok()) {
return s;
}
if (use_cache && !pin) {
uncompression_dict.Reset();
}
}
uncompression_dict_reader->reset(
new UncompressionDictReader(table, std::move(uncompression_dict)));
return Status::OK();
}
Status UncompressionDictReader::ReadUncompressionDictionary(
const BlockBasedTable* table, FilePrefetchBuffer* prefetch_buffer,
const ReadOptions& read_options, bool use_cache, GetContext* get_context,
BlockCacheLookupContext* lookup_context,
CachableEntry<UncompressionDict>* uncompression_dict) {
// TODO: add perf counter for compression dictionary read time
assert(table);
assert(uncompression_dict);
assert(uncompression_dict->IsEmpty());
const BlockBasedTable::Rep* const rep = table->get_rep();
assert(rep);
assert(!rep->compression_dict_handle.IsNull());
const Status s = table->RetrieveBlock(
prefetch_buffer, read_options, rep->compression_dict_handle,
UncompressionDict::GetEmptyDict(), uncompression_dict, get_context,
lookup_context,
/* for_compaction */ false, use_cache,
/* async_read */ false);
if (!s.ok()) {
ROCKS_LOG_WARN(
rep->ioptions.logger,
"Encountered error while reading data from compression dictionary "
"block %s",
s.ToString().c_str());
}
return s;
}
Status UncompressionDictReader::GetOrReadUncompressionDictionary(
FilePrefetchBuffer* prefetch_buffer, const ReadOptions& ro, bool no_io,
bool verify_checksums, GetContext* get_context,
BlockCacheLookupContext* lookup_context,
CachableEntry<UncompressionDict>* uncompression_dict) const {
assert(uncompression_dict);
if (!uncompression_dict_.IsEmpty()) {
uncompression_dict->SetUnownedValue(uncompression_dict_.GetValue());
return Status::OK();
}
ReadOptions read_options;
if (no_io) {
read_options.read_tier = kBlockCacheTier;
}
read_options.verify_checksums = verify_checksums;
read_options.io_activity = ro.io_activity;
return ReadUncompressionDictionary(table_, prefetch_buffer, read_options,
cache_dictionary_blocks(), get_context,
lookup_context, uncompression_dict);
}
size_t UncompressionDictReader::ApproximateMemoryUsage() const {
assert(!uncompression_dict_.GetOwnValue() ||
uncompression_dict_.GetValue() != nullptr);
size_t usage = uncompression_dict_.GetOwnValue()
? uncompression_dict_.GetValue()->ApproximateMemoryUsage()
: 0;
#ifdef ROCKSDB_MALLOC_USABLE_SIZE
usage += malloc_usable_size(const_cast<UncompressionDictReader*>(this));
#else
usage += sizeof(*this);
#endif // ROCKSDB_MALLOC_USABLE_SIZE
return usage;
}
bool UncompressionDictReader::cache_dictionary_blocks() const {
assert(table_);
assert(table_->get_rep());
return table_->get_rep()->table_options.cache_index_and_filter_blocks;
}
} // namespace ROCKSDB_NAMESPACE