-
Notifications
You must be signed in to change notification settings - Fork 164
/
db_stress_driver.cc
268 lines (239 loc) · 8.71 KB
/
db_stress_driver.cc
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
// 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) {
ThreadStatusUtil::RegisterThread(db_stress_env, ThreadStatus::USER);
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();
}
}
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);
if (FLAGS_write_fault_one_in) {
if (!FLAGS_sync_fault_injection) {
// unsynced WAL loss is not supported without sync_fault_injection
fault_fs_guard->SetDirectWritableTypes({kWalFile});
}
IOStatus error_msg;
if (FLAGS_inject_error_severity <= 1 || FLAGS_inject_error_severity > 2) {
error_msg = IOStatus::IOError("Retryable injected write error");
error_msg.SetRetryable(true);
} else if (FLAGS_inject_error_severity == 2) {
error_msg = IOStatus::IOError("Fatal injected write error");
error_msg.SetDataLoss(true);
}
// TODO: inject write error for other file types including
// MANIFEST, CURRENT, and WAL files.
fault_fs_guard->SetRandomWriteError(
shared->GetSeed(), FLAGS_write_fault_one_in, error_msg,
/*inject_for_all_file_types=*/false, {FileType::kTableFile});
fault_fs_guard->SetFilesystemDirectWritable(false);
fault_fs_guard->EnableWriteErrorInjection();
}
if (FLAGS_sync_fault_injection) {
fault_fs_guard->SetFilesystemDirectWritable(false);
}
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);
}
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();
}
}
}
// 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