Skip to content

branch-4.2: [fix](fe) Avoid Meta Service queries during streaming job replay #69498 #69537

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
github-actions wants to merge 1 commit into
base: branch-4.2
Choose a base branch
from
Open

branch-4.2: [fix](fe) Avoid Meta Service queries during streaming job replay #69498 #69537

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions ...re/src/main/java/org/apache/doris/job/extensions/insert/streaming/StreamingInsertJob.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1125,7 +1125,7 @@ public void replayOnUpdated(StreamingInsertJob replayJob) {
modifyPropertiesInternal(replayJob.getProperties());
if (replayPersistInfo != null) {
setOffsetProviderPersist(replayPersistInfo);
if (tvfType != null && !Config.isCloudMode()) {
if (tvfType != null) {
offsetProvider.restoreFromPersistInfo(offsetProviderPersist);
}
} else {
Expand All @@ -1137,9 +1137,8 @@ public void replayOnUpdated(StreamingInsertJob replayJob) {
offsetProviderPersist, offsetProvider.getPersistInfo());
}
}
// When the pause state is restarted, it also needs to be updated
if (Config.isCloudMode()) {
replayOnCloudMode();
this.jobStatistic = replayJob.getJobStatistic();
}
} catch (Exception e) {
// should not happen
Expand Down
44 changes: 44 additions & 0 deletions ...apache/doris/job/extensions/insert/streaming/StreamingInsertJobOffsetPersistenceTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,6 +387,50 @@ public void testCloudReplayRefreshesPersistedOffset() {
Assert.assertFalse(recovered.hasMoreDataToConsume());
}

@Test
public void testCloudReplayDoesNotFetchProgressAndPendingFailurePreventsDispatch() throws Exception {
TestStreamingInsertJob job = Mockito.spy(newJob(new S3SourceOffsetProvider(), 1021L));
Deencapsulation.setField(job, "tvfType", S3TableValuedFunction.NAME);
Deencapsulation.setField(job, "runningStreamTask", null);
job.offsetProvider.restoreFromPersistInfo("{\"endFile\":\"data/a.csv\"}");
StreamingInsertJob replayJob = new StreamingInsertJob();
Deencapsulation.setField(replayJob, "jobId", 9001L);
Deencapsulation.setField(replayJob, "properties", new HashMap<String, String>());
Deencapsulation.setField(replayJob, "tvfType", S3TableValuedFunction.NAME);
replayJob.setJobStatus(JobStatus.PAUSED);
replayJob.getProperties().put(StreamingJobProperties.OFFSET_PROPERTY, "{\"fileName\":\"data/b.csv\"}");
replayJob.setOffsetProviderPersist("{\"endFile\":\"data/b.csv\"}");
replayJob.getJobStatistic().setScannedRows(10);
replayJob.getJobStatistic().setLoadBytes(218);
replayJob.getJobStatistic().setFileNumber(1);
replayJob.getJobStatistic().setFileSize(138);
replayJob.getJobStatistic().setFilteredRows(2);
StreamingInsertJob replayRecord = GsonUtils.GSON.fromJson(
GsonUtils.GSON.toJson(replayJob, StreamingInsertJob.class), StreamingInsertJob.class);
Mockito.doThrow(new JobException("MS unavailable")).when(job).replayOnCloudMode();

try (MockedStatic<Config> config = Mockito.mockStatic(Config.class)) {
config.when(Config::isCloudMode).thenReturn(true);

job.replayOnUpdated(replayRecord);

Mockito.verify(job, Mockito.never()).replayOnCloudMode();
Assertions.assertEquals(JobStatus.PAUSED, job.getJobStatus());
Assertions.assertEquals("{\"endFile\":\"data/b.csv\"}", job.getOffsetProviderPersist());
Assertions.assertEquals("{\"fileName\":\"data/b.csv\"}", job.offsetProvider.getShowCurrentOffset());
Assertions.assertEquals(replayJob.getJobStatistic().toJson(), job.getJobStatistic().toJson());

job.setJobStatus(JobStatus.PENDING);
new StreamingJobSchedulerTask(job).run();

Mockito.verify(job).replayOnCloudMode();
Assertions.assertEquals(JobStatus.PAUSED, job.getJobStatus());
Assertions.assertTrue(job.getFailureReason().getMsg().contains("MS unavailable"));
Mockito.verify(job, Mockito.never()).replayOffsetProviderIfNeed();
Mockito.verify(job, Mockito.never()).createStreamingTask();
}
}

@Test
public void testReplayUpdatedRestoresFinalStateAndRemovesCallback() {
TestStreamingInsertJob job = newJob(new JdbcSourceOffsetProvider(), 1013L);
Expand Down
Loading