rocksdb/db_stress_tool/db_stress_driver.cc
Hui Xiao 75a1230ce8 Fix improper ExpectedValute::Exists() usages and disable compaction during VerifyDB() in crash test (#12933)
Summary:
**Context:**
Adding assertion `!PendingPut()&&!PendingDelete()` in `ExpectedValute::Exists()` surfaced a couple improper usages of `ExpectedValute::Exists()` in the crash test
- Commit phase of `ExpectedValue::Delete()`/`SyncDelete()`:
When we issue delete to expected value during commit phase or `SyncDelete()` (used in crash recovery verification) as below, we don't really care about the result.
d458331ee9/db_stress_tool/expected_state.cc (L73)
d458331ee9/db_stress_tool/expected_value.cc (L52)
That means, we don't really need to check for `Exists()` d458331ee9/db_stress_tool/expected_value.cc (L24-L26).
This actually gives an alternative solution to b65e29a4a9 to solve false-positive assertion violation.
- TestMultiGetXX() path: `Exists()` is called without holding the lock as required

f63428bcc7/db_stress_tool/no_batched_ops_stress.cc (L2688)
```
void MaybeAddKeyToTxnForRYW(
      ThreadState* thread, int column_family, int64_t key, Transaction* txn,
      std::unordered_map<std::string, ExpectedValue>& ryw_expected_values) {
    assert(thread);
    assert(txn);

    SharedState* const shared = thread->shared;
    assert(shared);

    if (!shared->AllowsOverwrite(key) && shared->Exists(column_family, key)) {
      // Just do read your write checks for keys that allow overwrites.
      return;
    }

    // With a 1 in 10 probability, insert the just added key in the batch
    // into the transaction. This will create an overlap with the MultiGet
    // keys and exercise some corner cases in the code
    if (thread->rand.OneIn(10)) {
```

f63428bcc7/db_stress_tool/expected_state.h (L74-L76)

The assertion also failed if db stress compaction filter was invoked before crash recovery verification (`VerifyDB()`->`VerifyOrSyncValue()`) finishes.
f63428bcc7/db_stress_tool/db_stress_compaction_filter.h (L53)
It failed because it can encounter a key with pending state when checking for `Exists()` since that key's expected state has not been sync-ed with db state in `VerifyOrSyncValue()`.
f63428bcc7/db_stress_tool/no_batched_ops_stress.cc (L2579-L2591)

**Summary:**
This PR fixes above issues by
- not checking `Exists()` in commit phase/`SyncDelete()`
- using the concurrent version of key existence check like in other read
- conditionally temporarily disabling compaction till after crash recovery verification succeeds()

And add back the assertion `!PendingPut()&&!PendingDelete()`

Pull Request resolved: https://github.com/facebook/rocksdb/pull/12933

Test Plan: Rehearsal CI

Reviewed By: cbi42

Differential Revision: D61214889

Pulled By: hx235

fbshipit-source-id: ef25ba896e64330ddf330182314981516880c3e4
2024-08-15 12:32:59 -07:00

257 lines
8.2 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).
//
// 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.
//
#include "db_stress_tool/db_stress_shared_state.h"
#ifdef GFLAGS
#include "db_stress_tool/db_stress_common.h"
#include "utilities/fault_injection_fs.h"
namespace ROCKSDB_NAMESPACE {
void ThreadBody(void* v) {
ThreadStatusUtil::RegisterThread(db_stress_env, ThreadStatus::USER);
ThreadState* thread = static_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();
}
}
if (!FLAGS_verification_only) {
{
MutexLock l(shared->GetMutex());
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();
}
}
}
ThreadStatusUtil::UnregisterThread();
}
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);
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();
}
if (FLAGS_compressed_secondary_cache_size > 0 ||
FLAGS_compressed_secondary_cache_ratio > 0.0) {
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);
}
ThreadState compressed_cache_set_capacity_thread(0, shared);
if (FLAGS_compressed_secondary_cache_size > 0 ||
FLAGS_compressed_secondary_cache_ratio > 0.0) {
db_stress_env->StartThread(CompressedCacheSetCapacityThread,
&compressed_cache_set_capacity_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);
}
}
}
if (!FLAGS_verification_only) {
// 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);
}
if (FLAGS_sync_fault_injection || FLAGS_write_fault_one_in > 0) {
fault_fs_guard->SetFilesystemDirectWritable(false);
fault_fs_guard->SetInjectUnsyncedDataLoss(FLAGS_sync_fault_injection);
if (FLAGS_exclude_wal_from_write_fault_injection) {
fault_fs_guard->SetFileTypesExcludedFromWriteFaultInjection(
{FileType::kWalFile});
}
}
if (ShouldDisableAutoCompactionsBeforeVerifyDb()) {
Status s = stress->EnableAutoCompaction();
assert(s.ok());
}
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();
}
}
}
// If we are running verification_only
// stats will be empty and trying to report them will
// emit no ops or writes error. To avoid this, merging and reporting stats
// are not executed when running with verification_only
// TODO: We need to create verification stats (e.g. how many keys
// are verified by which method) and report them here instead of operation
// stats.
if (!FLAGS_verification_only) {
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());
}
if (!FLAGS_verification_only) {
stress->PrintStatistics();
}
if (FLAGS_compaction_thread_pool_adjust_interval > 0 ||
FLAGS_continuous_verification_interval > 0 ||
FLAGS_compressed_secondary_cache_size > 0 ||
FLAGS_compressed_secondary_cache_ratio > 0.0) {
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