Skip to content

Wait for snapshot finalization in testSnapshotAPMMetrics() #132767

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

Closed
JeremyDahlgren wants to merge 1 commit into from
Closed

Wait for snapshot finalization in testSnapshotAPMMetrics() #132767

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
3 changes: 0 additions & 3 deletions muted-tests.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -504,9 +504,6 @@ tests:
- class: org.elasticsearch.xpack.ml.integration.RevertModelSnapshotIT
method: testRevertModelSnapshot
issue: https://github.com/elastic/elasticsearch/issues/132733
- class: org.elasticsearch.repositories.SnapshotMetricsIT
method: testSnapshotAPMMetrics
issue: https://github.com/elastic/elasticsearch/issues/132731

# Examples:
#
Expand Down
19 changes: 12 additions & 7 deletions server/src/internalClusterTest/java/org/elasticsearch/repositories/SnapshotMetricsIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
import java.util.List;
import java.util.Map;
import java.util.concurrent.CyclicBarrier;
import java.util.concurrent.atomic.AtomicReference;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import java.util.stream.StreamSupport;
Expand Down Expand Up @@ -133,8 +134,17 @@ public void testSnapshotAPMMetrics() throws Exception {

// wait for snapshot to finish to test the other metrics
awaitNumberOfSnapshotsInProgress(0);
final TimeValue snapshotElapsedTime = TimeValue.timeValueNanos(System.nanoTime() - beforeCreateSnapshotNanos);
collectMetrics();
final AtomicReference<TimeValue> elapsedTimeValueRef = new AtomicReference<>();
// Sanity check snapshot completion metric observations recorded in snapshot finalization.
// Use assertBusy() so the finalization code has time to run after the SnapshotsInProgress cluster state update has completed.
assertBusy(() -> {
collectMetrics();
elapsedTimeValueRef.set(TimeValue.timeValueNanos(System.nanoTime() - beforeCreateSnapshotNanos));
assertThat(getTotalClusterLongCounterValue(SnapshotMetrics.SNAPSHOTS_COMPLETED), equalTo(1L));
assertDoubleHistogramMetrics(SnapshotMetrics.SNAPSHOT_DURATION, hasSize(1));
assertDoubleHistogramMetrics(SnapshotMetrics.SNAPSHOT_DURATION, everyItem(lessThan(elapsedTimeValueRef.get().secondsFrac())));
});
final TimeValue snapshotElapsedTime = elapsedTimeValueRef.get();

// sanity check blobs, bytes and throttling metrics
assertThat(getTotalClusterLongCounterValue(SnapshotMetrics.SNAPSHOT_BLOBS_UPLOADED), greaterThan(0L));
Expand All @@ -143,16 +153,11 @@ public void testSnapshotAPMMetrics() throws Exception {
assertThat(getTotalClusterLongCounterValue(SnapshotMetrics.SNAPSHOT_RESTORE_THROTTLE_DURATION), equalTo(0L));

assertThat(getTotalClusterLongCounterValue(SnapshotMetrics.SNAPSHOTS_STARTED), equalTo(1L));
assertThat(getTotalClusterLongCounterValue(SnapshotMetrics.SNAPSHOTS_COMPLETED), equalTo(1L));

// Sanity check shard duration observations
assertDoubleHistogramMetrics(SnapshotMetrics.SNAPSHOT_SHARDS_DURATION, hasSize(numShards));
assertDoubleHistogramMetrics(SnapshotMetrics.SNAPSHOT_SHARDS_DURATION, everyItem(lessThan(snapshotElapsedTime.secondsFrac())));

// Sanity check snapshot observations
assertDoubleHistogramMetrics(SnapshotMetrics.SNAPSHOT_DURATION, hasSize(1));
assertDoubleHistogramMetrics(SnapshotMetrics.SNAPSHOT_DURATION, everyItem(lessThan(snapshotElapsedTime.secondsFrac())));

// Work out the maximum amount of concurrency per node
final ThreadPool tp = internalCluster().getDataNodeInstance(ThreadPool.class);
final int snapshotThreadPoolSize = tp.info(ThreadPool.Names.SNAPSHOT).getMax();
Expand Down