Skip to content

Fix SnapshotShardStatus Reporting for Failed Shard (#48556) #48689

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

Merged
merged 1 commit into from
Oct 30, 2019
Merged

Fix SnapshotShardStatus Reporting for Failed Shard (#48556) #48689

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
13 changes: 3 additions & 10 deletions server/src/main/java/org/elasticsearch/repositories/blobstore/BlobStoreRepository.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,6 @@
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.store.RateLimiter;
import org.apache.lucene.util.SetOnce;
import org.elasticsearch.ExceptionsHelper;
import org.elasticsearch.Version;
import org.elasticsearch.action.ActionListener;
import org.elasticsearch.action.ActionRunnable;
Expand Down Expand Up @@ -995,12 +994,6 @@ public void snapshotShard(Store store, MapperService mapperService, SnapshotId s
IndexCommit snapshotIndexCommit, IndexShardSnapshotStatus snapshotStatus, ActionListener<Void> listener) {
final ShardId shardId = store.shardId();
final long startTime = threadPool.absoluteTimeInMillis();
final StepListener<Void> snapshotDoneListener = new StepListener<>();
snapshotDoneListener.whenComplete(listener::onResponse, e -> {
snapshotStatus.moveToFailed(threadPool.absoluteTimeInMillis(), ExceptionsHelper.detailedMessage(e));
listener.onFailure(e instanceof IndexShardSnapshotFailedException ? (IndexShardSnapshotFailedException) e
: new IndexShardSnapshotFailedException(store.shardId(), e));
});
try {
logger.debug("[{}] [{}] snapshot to [{}] ...", shardId, snapshotId, metadata.name());

Expand Down Expand Up @@ -1137,8 +1130,8 @@ public void snapshotShard(Store store, MapperService mapperService, SnapshotId s
snapshotId, shardId), e);
}
snapshotStatus.moveToDone(threadPool.absoluteTimeInMillis());
snapshotDoneListener.onResponse(null);
}, snapshotDoneListener::onFailure);
listener.onResponse(null);
}, listener::onFailure);
if (indexIncrementalFileCount == 0) {
allFilesUploadedListener.onResponse(Collections.emptyList());
return;
Expand Down Expand Up @@ -1181,7 +1174,7 @@ public void onFailure(Exception e) {
});
}
} catch (Exception e) {
snapshotDoneListener.onFailure(e);
listener.onFailure(e);
}
}

Expand Down
4 changes: 3 additions & 1 deletion server/src/main/java/org/elasticsearch/snapshots/SnapshotShardsService.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,8 +292,10 @@ public void onResponse(final Void aVoid) {

@Override
public void onFailure(Exception e) {
final String failure = ExceptionsHelper.detailedMessage(e);
snapshotStatus.moveToFailed(threadPool.absoluteTimeInMillis(), failure);
logger.warn(() -> new ParameterizedMessage("[{}][{}] failed to snapshot shard", shardId, snapshot), e);
notifyFailedSnapshotShard(snapshot, shardId, ExceptionsHelper.detailedMessage(e));
notifyFailedSnapshotShard(snapshot, shardId, failure);
}
});
}
Expand Down
6 changes: 6 additions & 0 deletions server/src/test/java/org/elasticsearch/snapshots/DedicatedClusterSnapshotRestoreIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1224,6 +1224,12 @@ public void testDataNodeRestartWithBusyMasterDuringSnapshot() throws Exception {
disruption.startDisrupting();
logger.info("--> restarting data node, which should cause primary shards to be failed");
internalCluster().restartNode(dataNode, InternalTestCluster.EMPTY_CALLBACK);

logger.info("--> wait for shard snapshots to show as failed");
assertBusy(() -> assertThat(
client().admin().cluster().prepareSnapshotStatus("test-repo").setSnapshots("test-snap").get().getSnapshots()
.get(0).getShardsStats().getFailedShards(), greaterThanOrEqualTo(1)), 60L, TimeUnit.SECONDS);

unblockNode("test-repo", dataNode);
disruption.stopDisrupting();
// check that snapshot completes
Expand Down