Github user mgaido91 commented on a diff in the pull request:
https://github.com/apache/spark/pull/21758#discussion_r204312715
--- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
---
@@ -1411,6 +1420,76 @@ class DAGScheduler(
}
}
+ case failure: TaskFailedReason if task.isBarrier =>
+ // Also handle the task failed reasons here.
+ failure match {
+ case Resubmitted =>
+ handleResubmittedFailure(task, stage)
+
+ case _ => // Do nothing.
+ }
+
+ // Always fail the current stage and retry all the tasks when a
barrier task fail.
+ val failedStage = stageIdToStage(task.stageId)
+ logInfo(s"Marking $failedStage (${failedStage.name}) as failed due
to a barrier task " +
+ "failed.")
+ val message = s"Stage failed because barrier task $task finished
unsuccessfully. " +
+ s"${failure.toErrorString}"
--- End diff --
nit: unneeded `s`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
