rocksdb/db_stress_tool/db_stress_driver.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

217 lines
6.5 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.
//
#ifdef GFLAGS
#include "db_stress_tool/db_stress_common.h"
#include "utilities/fault_injection_fs.h"
namespace ROCKSDB_NAMESPACE {
void ThreadBody(void* v) {
ThreadState* thread = reinterpret_cast<ThreadState*>(v);
SharedState* shared = thread->shared;
if (!FLAGS_skip_verifydb && shared->ShouldVerifyAtBeginning()) {
thread->shared->GetStressTest()->VerifyDb(thread);
}
{
MutexLock l(shared->GetMutex());
shared->IncInitialized();
if (shared->AllInitialized()) {
shared->GetCondVar()->SignalAll();
}
while (!shared->Started()) {
shared->GetCondVar()->Wait();
}
}
thread->shared->GetStressTest()->OperateDb(thread);
{
MutexLock l(shared->GetMutex());
shared->IncOperated();
if (shared->AllOperated()) {
shared->GetCondVar()->SignalAll();
}
while (!shared->VerifyStarted()) {
shared->GetCondVar()->Wait();
}
}
if (!FLAGS_skip_verifydb) {
thread->shared->GetStressTest()->VerifyDb(thread);
}
{
MutexLock l(shared->GetMutex());
shared->IncDone();
if (shared->AllDone()) {
shared->GetCondVar()->SignalAll();
}
}
}
bool RunStressTestImpl(SharedState* shared) {
SystemClock* clock = db_stress_env->GetSystemClock().get();
StressTest* stress = shared->GetStressTest();
if (shared->ShouldVerifyAtBeginning() && FLAGS_preserve_unverified_changes) {
Status s = InitUnverifiedSubdir(FLAGS_db);
if (s.ok() && !FLAGS_expected_values_dir.empty()) {
s = InitUnverifiedSubdir(FLAGS_expected_values_dir);
}
if (!s.ok()) {
fprintf(stderr, "Failed to setup unverified state dir: %s\n",
s.ToString().c_str());
exit(1);
}
}
stress->InitDb(shared);
stress->FinishInitDb(shared);
if (FLAGS_sync_fault_injection) {
fault_fs_guard->SetFilesystemDirectWritable(false);
}
if (FLAGS_write_fault_one_in) {
fault_fs_guard->EnableWriteErrorInjection();
}
uint32_t n = FLAGS_threads;
uint64_t now = clock->NowMicros();
fprintf(stdout, "%s Initializing worker threads\n",
clock->TimeToString(now / 1000000).c_str());
shared->SetThreads(n);
if (FLAGS_compaction_thread_pool_adjust_interval > 0) {
shared->IncBgThreads();
}
if (FLAGS_continuous_verification_interval > 0) {
shared->IncBgThreads();
}
std::vector<ThreadState*> threads(n);
for (uint32_t i = 0; i < n; i++) {
threads[i] = new ThreadState(i, shared);
db_stress_env->StartThread(ThreadBody, threads[i]);
}
ThreadState bg_thread(0, shared);
if (FLAGS_compaction_thread_pool_adjust_interval > 0) {
db_stress_env->StartThread(PoolSizeChangeThread, &bg_thread);
}
ThreadState continuous_verification_thread(0, shared);
if (FLAGS_continuous_verification_interval > 0) {
db_stress_env->StartThread(DbVerificationThread,
&continuous_verification_thread);
}
// Each thread goes through the following states:
// initializing -> wait for others to init -> read/populate/depopulate
// wait for others to operate -> verify -> done
{
MutexLock l(shared->GetMutex());
while (!shared->AllInitialized()) {
shared->GetCondVar()->Wait();
}
if (shared->ShouldVerifyAtBeginning()) {
if (shared->HasVerificationFailedYet()) {
fprintf(stderr, "Crash-recovery verification failed :(\n");
} else {
fprintf(stdout, "Crash-recovery verification passed :)\n");
Status s = DestroyUnverifiedSubdir(FLAGS_db);
if (s.ok() && !FLAGS_expected_values_dir.empty()) {
s = DestroyUnverifiedSubdir(FLAGS_expected_values_dir);
}
if (!s.ok()) {
fprintf(stderr, "Failed to cleanup unverified state dir: %s\n",
s.ToString().c_str());
exit(1);
}
}
}
// This is after the verification step to avoid making all those `Get()`s
// and `MultiGet()`s contend on the DB-wide trace mutex.
if (!FLAGS_expected_values_dir.empty()) {
stress->TrackExpectedState(shared);
}
now = clock->NowMicros();
fprintf(stdout, "%s Starting database operations\n",
clock->TimeToString(now / 1000000).c_str());
shared->SetStart();
shared->GetCondVar()->SignalAll();
while (!shared->AllOperated()) {
shared->GetCondVar()->Wait();
}
now = clock->NowMicros();
if (FLAGS_test_batches_snapshots) {
fprintf(stdout, "%s Limited verification already done during gets\n",
clock->TimeToString((uint64_t)now / 1000000).c_str());
} else if (FLAGS_skip_verifydb) {
fprintf(stdout, "%s Verification skipped\n",
clock->TimeToString((uint64_t)now / 1000000).c_str());
} else {
fprintf(stdout, "%s Starting verification\n",
clock->TimeToString((uint64_t)now / 1000000).c_str());
}
shared->SetStartVerify();
shared->GetCondVar()->SignalAll();
while (!shared->AllDone()) {
shared->GetCondVar()->Wait();
}
}
for (unsigned int i = 1; i < n; i++) {
threads[0]->stats.Merge(threads[i]->stats);
}
threads[0]->stats.Report("Stress Test");
for (unsigned int i = 0; i < n; i++) {
delete threads[i];
threads[i] = nullptr;
}
now = clock->NowMicros();
if (!FLAGS_skip_verifydb && !FLAGS_test_batches_snapshots &&
!shared->HasVerificationFailedYet()) {
fprintf(stdout, "%s Verification successful\n",
clock->TimeToString(now / 1000000).c_str());
}
stress->PrintStatistics();
if (FLAGS_compaction_thread_pool_adjust_interval > 0 ||
FLAGS_continuous_verification_interval > 0) {
MutexLock l(shared->GetMutex());
shared->SetShouldStopBgThread();
while (!shared->BgThreadsFinished()) {
shared->GetCondVar()->Wait();
}
}
if (shared->HasVerificationFailedYet()) {
fprintf(stderr, "Verification failed :(\n");
return false;
}
return true;
}
bool RunStressTest(SharedState* shared) {
ThreadStatusUtil::RegisterThread(db_stress_env, ThreadStatus::USER);
bool result = RunStressTestImpl(shared);
ThreadStatusUtil::UnregisterThread();
return result;
}
} // namespace ROCKSDB_NAMESPACE
#endif // GFLAGS