Skip to content

HDDS-15828. Fix flaky TestDirectoryDeletingServiceWithFSO snapshot cleanup. #10726

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
jojochuang wants to merge 2 commits into
base: master
Choose a base branch
from
Open

HDDS-15828. Fix flaky TestDirectoryDeletingServiceWithFSO snapshot cleanup. #10726

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4f35f7d
HDDS-15828. Fix flaky TestDirectoryDeletingServiceWithFSO snapshot cl…
jojochuang Jul 11, 2026
e24f4f0
Potential fix for pull request finding
jojochuang Jul 13, 2026
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
44 changes: 26 additions & 18 deletions ...src/test/java/org/apache/hadoop/ozone/om/service/TestDirectoryDeletingServiceWithFSO.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -571,7 +571,7 @@ public void testAOSKeyDeletingWithSnapshotCreateParallelExecution()
Table<String, SnapshotInfo> snapshotInfoTable = omMetadataManager.getSnapshotInfoTable();
Table<String, OmKeyInfo> deletedDirTable = omMetadataManager.getDeletedDirTable();
Table<String, String> renameTable = omMetadataManager.getSnapshotRenamedTable();
cluster.getOzoneManager().getKeyManager().getSnapshotDeletingService().shutdown();
cluster.getOzoneManager().getKeyManager().getSnapshotDeletingService().suspend();
DirectoryDeletingService dirDeletingService = cluster.getOzoneManager().getKeyManager().getDirDeletingService();
// Suspend KeyDeletingService
dirDeletingService.suspend();
Comment on lines +574 to 577
Comment on lines +574 to 577
Expand Down Expand Up @@ -659,23 +659,7 @@ public void testAOSKeyDeletingWithSnapshotCreateParallelExecution()
service.runPeriodicalTaskNow();
store.deleteSnapshot(testVolumeName, testBucketName, snap1);
cluster.getOzoneManager().awaitDoubleBufferFlush();
cluster.restartOzoneManager();
cluster.waitForClusterToBeReady();
cluster.getOzoneManager().awaitDoubleBufferFlush();
SnapshotDeletingService snapshotDeletingService =
cluster.getOzoneManager().getKeyManager().getSnapshotDeletingService();
GenericTestUtils.waitFor(() -> {
try {
snapshotDeletingService.runPeriodicalTaskNow();
cluster.getOzoneManager().awaitDoubleBufferFlush();
long currentSnapshotCount = cluster.getOzoneManager().getMetadataManager()
.countRowsInTable(cluster.getOzoneManager().getMetadataManager().getSnapshotInfoTable());
return currentSnapshotCount <= initialSnapshotCount;
} catch (Exception e) {
throw new RuntimeException(e);
}
}, 100, 10000);
assertTableRowCount(cluster.getOzoneManager().getMetadataManager().getSnapshotInfoTable(), initialSnapshotCount);
waitForSnapshotsPurged(snapshotInfoTable, initialSnapshotCount);
dirDeletingService.resume();
}

Expand Down Expand Up @@ -789,6 +773,8 @@ public void testDirDeletedTableCleanUpForSnapshot() throws Exception {

// Manual cleanup deletedDirTable for next tests
client.getObjectStore().deleteSnapshot(volumeName, bucketName, "snap1");
cluster.getOzoneManager().awaitDoubleBufferFlush();
waitForSnapshotsPurged(snapshotInfoTable, 0);
cleanupTables();
}

Expand Down Expand Up @@ -823,6 +809,28 @@ static void assertSubPathsCount(LongSupplier pathCount, long expectedCount)
1000, 120000);
}

/**
* Wait until SnapshotDeletingService has purged snapshots and snapshotInfoTable
* reaches the expected row count.
*/
private void waitForSnapshotsPurged(Table<String, SnapshotInfo> snapshotInfoTable,
int expectedCount) throws Exception {
SnapshotDeletingService snapshotDeletingService =
cluster.getOzoneManager().getKeyManager().getSnapshotDeletingService();
snapshotDeletingService.resume();
GenericTestUtils.waitFor(() -> {
try {
snapshotDeletingService.runPeriodicalTaskNow();
cluster.getOzoneManager().awaitDoubleBufferFlush();
return cluster.getOzoneManager().getMetadataManager()
.countRowsInTable(snapshotInfoTable) == expectedCount;
} catch (Exception e) {
throw new RuntimeException("Failed to run SnapshotDeletingService purge task", e);
}
}, 1000, 120000);
assertTableRowCount(snapshotInfoTable, expectedCount);
}
Comment on lines +820 to +832

private void assertTableRowCount(Table<String, ?> table, int count)
throws TimeoutException, InterruptedException {
GenericTestUtils.waitFor(() -> assertTableRowCount(count, table), 1000,
Expand Down
Loading