Skip to content

KAFKA-20685: Delete checkpoint file when EOS task completes restoration (4.2) #22548

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
zoro30102000 wants to merge 1 commit into
base: 4.2
Choose a base branch
from
+42 −0
Open

KAFKA-20685: Delete checkpoint file when EOS task completes restoration (4.2) #22548

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
8 changes: 8 additions & 0 deletions streams/src/main/java/org/apache/kafka/streams/processor/internals/StreamTask.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -306,6 +306,14 @@ public void completeRestoration(final java.util.function.Consumer<Set<TopicParti
processorContext.initialize();
if (!eosEnabled) {
maybeCheckpoint(true);
} else {
// Deleting checkpoint file written during restoration before transition to RUNNING state (KAFKA-20685)
try {
stateMgr.deleteCheckPointFileIfEOSEnabled();
log.debug("Deleted check point file upon completing restoration with EOS enabled");
} catch (final IOException ioe) {
log.error("Encountered error while deleting the checkpoint file upon completing restoration", ioe);
}
}

transitionTo(State.RUNNING);
Expand Down
34 changes: 34 additions & 0 deletions streams/src/test/java/org/apache/kafka/streams/processor/internals/StreamTaskTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3057,6 +3057,40 @@ public void shouldNotCheckpointAfterRestorationWhenExactlyOnceEnabled() {
verify(recordCollector, never()).offsets();
}

@Test
public void shouldDeleteCheckpointFileAfterRestorationWhenExactlyOnceEnabled() throws IOException {
final ProcessorStateManager processorStateManager = mockStateManager();
recordCollector = mock(RecordCollectorImpl.class);

task = createStatefulTask(createConfig(EXACTLY_ONCE_V2, "100"), true, processorStateManager);
task.initializeIfNeeded();
task.completeRestoration(noOpResetter -> { });
verify(processorStateManager).deleteCheckPointFileIfEOSEnabled();
}

@Test
public void shouldNotDeleteCheckpointFileAfterRestorationWhenAtLeastOnceEnabled() throws IOException {
final ProcessorStateManager processorStateManager = mockStateManager();
recordCollector = mock(RecordCollectorImpl.class);

task = createStatefulTask(createConfig(AT_LEAST_ONCE, "100"), true, processorStateManager);
task.initializeIfNeeded();
task.completeRestoration(noOpResetter -> { });
verify(processorStateManager, never()).deleteCheckPointFileIfEOSEnabled();
}

@Test
public void shouldStillCompleteRestorationWhenCheckpointFileDeletionFails() throws IOException {
final ProcessorStateManager processorStateManager = mockStateManager();
recordCollector = mock(RecordCollectorImpl.class);
doThrow(new IOException("KABOOM!")).when(processorStateManager).deleteCheckPointFileIfEOSEnabled();

task = createStatefulTask(createConfig(EXACTLY_ONCE_V2, "100"), true, processorStateManager);
task.initializeIfNeeded();
task.completeRestoration(noOpResetter -> { });
assertEquals(RUNNING, task.state());
}

@Test
public void punctuateShouldNotHandleFailProcessingExceptionAndThrowStreamsException() {
when(stateManager.taskId()).thenReturn(taskId);
Expand Down