Skip to content

Emit metrics on all task completions. #18766

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
gianm merged 10 commits into from
Jan 8, 2026
Merged

Emit metrics on all task completions. #18766

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
bc3dd70
Emit task metrics on all task completions.
gianm Nov 21, 2025
f180149
Fix test.
gianm Nov 29, 2025
e4e803a
Merge branch 'master' into ol-missing-metrics
gianm Dec 9, 2025
6d8b571
Merge branch 'master' into ol-missing-metrics
gianm Dec 30, 2025
f53a497
Merge branch 'master' into ol-missing-metrics
gianm Jan 7, 2026
eaa10a1
Fix race in TaskQueueTest: it needlessly shut down task3, which could…
gianm Jan 7, 2026
160f1fe
Use activeTasks for status in TaskQueue, since it is more authoritati…
gianm Jan 7, 2026
b06843b
Properly include failure message.
gianm Jan 7, 2026
9f30dcb
Fix testGetTaskStatus.
gianm Jan 7, 2026
d04008c
Wait for task logs to show up.
gianm Jan 8, 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
34 changes: 14 additions & 20 deletions indexing-service/src/main/java/org/apache/druid/indexing/overlord/TaskQueue.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -449,7 +449,6 @@ private void startPendingTaskOnRunner(TaskEntry entry, ListenableFuture<TaskStat
}
final TaskStatus taskStatus = TaskStatus.failure(task.getId(), errorMessage);
notifyStatus(entry, taskStatus, taskStatus.getErrorMsg());
emitTaskCompletionLogsAndMetrics(task, taskStatus);
return;
}
if (taskIsReady) {
Expand Down Expand Up @@ -749,8 +748,8 @@ private void notifyStatus(final TaskEntry entry, final TaskStatus taskStatus, St
}

shutdownTaskOnRunner(task.getId(), reasonFormat, args);

removeTaskLock(task);
emitTaskCompletionLogsAndMetrics(task, taskStatus);
requestManagement();

log.info("Completed notifyStatus for task[%s] with status[%s]", task.getId(), taskStatus);
Expand Down Expand Up @@ -811,9 +810,6 @@ private void handleStatus(final TaskStatus status)
task.getId(),
entry -> notifyStatus(entry, status, "notified status change from task")
);

// Emit event and log, if the task is done
emitTaskCompletionLogsAndMetrics(task, status);
}
catch (Exception e) {
log.makeAlert(e, "Failed to handle task status")
Expand Down Expand Up @@ -1073,24 +1069,22 @@ public Map<String, Task> getActiveTasksForDatasource(String datasource)

private void emitTaskCompletionLogsAndMetrics(final Task task, final TaskStatus status)
{
if (status.isComplete()) {
final ServiceMetricEvent.Builder metricBuilder = ServiceMetricEvent.builder();
IndexTaskUtils.setTaskDimensions(metricBuilder, task);
IndexTaskUtils.setTaskStatusDimensions(metricBuilder, status);

emitter.emit(metricBuilder.setMetric("task/run/time", status.getDuration()));
final ServiceMetricEvent.Builder metricBuilder = ServiceMetricEvent.builder();
IndexTaskUtils.setTaskDimensions(metricBuilder, task);
IndexTaskUtils.setTaskStatusDimensions(metricBuilder, status);

if (status.isSuccess()) {
Counters.incrementAndGetLong(totalSuccessfulTaskCount, getMetricKey(task));
} else {
Counters.incrementAndGetLong(totalFailedTaskCount, getMetricKey(task));
}
emitter.emit(metricBuilder.setMetric("task/run/time", status.getDuration()));

log.info(
"Completed task[%s] with status[%s] in [%d]ms.",
task.getId(), status, status.getDuration()
);
if (status.isSuccess()) {
Counters.incrementAndGetLong(totalSuccessfulTaskCount, getMetricKey(task));
} else {
Counters.incrementAndGetLong(totalFailedTaskCount, getMetricKey(task));
}

log.info(
"Completed task[%s] with status[%s] in [%d]ms.",
task.getId(), status, status.getDuration()
);
}

private void validateTaskPayload(Task task)
Expand Down
Loading