Skip to content

Flink: Fix flaky TestMonitorSource.testStateRestore #16548

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
wombatu-kun wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Flink: Fix flaky TestMonitorSource.testStateRestore #16548

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
15 changes: 10 additions & 5 deletions ...0/flink/src/test/java/org/apache/iceberg/flink/maintenance/operator/OperatorTestBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import java.time.LocalDateTime;
import java.time.ZoneOffset;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import javax.annotation.Nullable;
import org.apache.flink.configuration.Configuration;
Expand Down Expand Up @@ -373,11 +374,15 @@ protected TableLoader tableLoader() {
protected static String closeJobClient(JobClient jobClient, File savepointDir) {
if (jobClient != null) {
if (savepointDir != null) {
// Stop with savepoint
jobClient.stopWithSavepoint(false, savepointDir.getPath(), SavepointFormatType.CANONICAL);
// Wait until the savepoint is created and the job has been stopped
Awaitility.await().until(() -> savepointDir.listFiles(File::isDirectory).length == 1);
return savepointDir.listFiles(File::isDirectory)[0].getAbsolutePath();
// Stop with a savepoint; get() blocks until it is fully written and returns its path, so
// that a job restoring from it does not race the savepoint completion
try {
return jobClient
.stopWithSavepoint(false, savepointDir.getPath(), SavepointFormatType.CANONICAL)
.get();
} catch (InterruptedException | ExecutionException e) {
throw new RuntimeException(e);
}
} else {
jobClient.cancel();
}
Expand Down
3 changes: 2 additions & 1 deletion .../flink/src/test/java/org/apache/iceberg/flink/maintenance/operator/TestMonitorSource.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,7 +229,8 @@ void testStateRestore(
streamGraph.setSavepointRestoreSettings(SavepointRestoreSettings.forPath(savepointPath));
CompletableFuture<JobID> jobIDCompletableFuture = clusterClient.submitJob(streamGraph);
try {
assertThat(resultWithSavepoint.poll(Duration.ofSeconds(5L))).isEqualTo(EMPTY_EVENT);
// Restoring from a savepoint on a busy cluster may take longer than the default 5s poll
assertThat(resultWithSavepoint.poll(Duration.ofSeconds(30L))).isEqualTo(EMPTY_EVENT);
} finally {
clusterClient.cancel(jobIDCompletableFuture.get());
}
Expand Down
15 changes: 10 additions & 5 deletions ...1/flink/src/test/java/org/apache/iceberg/flink/maintenance/operator/OperatorTestBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import java.time.LocalDateTime;
import java.time.ZoneOffset;
import java.util.List;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import javax.annotation.Nullable;
import org.apache.flink.configuration.Configuration;
Expand Down Expand Up @@ -373,11 +374,15 @@ protected TableLoader tableLoader() {
protected static String closeJobClient(JobClient jobClient, File savepointDir) {
if (jobClient != null) {
if (savepointDir != null) {
// Stop with savepoint
jobClient.stopWithSavepoint(false, savepointDir.getPath(), SavepointFormatType.CANONICAL);
// Wait until the savepoint is created and the job has been stopped
Awaitility.await().until(() -> savepointDir.listFiles(File::isDirectory).length == 1);
return savepointDir.listFiles(File::isDirectory)[0].getAbsolutePath();
// Stop with a savepoint; get() blocks until it is fully written and returns its path, so
// that a job restoring from it does not race the savepoint completion
try {
return jobClient
.stopWithSavepoint(false, savepointDir.getPath(), SavepointFormatType.CANONICAL)
.get();
} catch (InterruptedException | ExecutionException e) {
throw new RuntimeException(e);
}
} else {
jobClient.cancel();
}
Expand Down
3 changes: 2 additions & 1 deletion .../flink/src/test/java/org/apache/iceberg/flink/maintenance/operator/TestMonitorSource.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,7 +229,8 @@ void testStateRestore(
streamGraph.setSavepointRestoreSettings(SavepointRestoreSettings.forPath(savepointPath));
CompletableFuture<JobID> jobIDCompletableFuture = clusterClient.submitJob(streamGraph);
try {
assertThat(resultWithSavepoint.poll(Duration.ofSeconds(5L))).isEqualTo(EMPTY_EVENT);
// Restoring from a savepoint on a busy cluster may take longer than the default 5s poll
assertThat(resultWithSavepoint.poll(Duration.ofSeconds(30L))).isEqualTo(EMPTY_EVENT);
} finally {
clusterClient.cancel(jobIDCompletableFuture.get());
}
Expand Down