beliefer commented on code in PR #50020:
URL: https://github.com/apache/spark/pull/50020#discussion_r1976539087
##########
core/src/main/scala/org/apache/spark/BarrierCoordinator.scala:
##########
@@ -122,23 +124,40 @@ private[spark] class BarrierCoordinator(
// Init a TimerTask for a barrier() call.
private def initTimerTask(state: ContextBarrierState): Unit = {
timerTask = new TimerTask {
- override def run(): Unit = state.synchronized {
- // Timeout current barrier() call, fail all the sync requests.
- requesters.foreach(_.sendFailure(new SparkException("The coordinator
didn't get all " +
- s"barrier sync requests for barrier epoch $barrierEpoch from
$barrierId within " +
- s"$timeoutInSecs second(s).")))
- cleanupBarrierStage(barrierId)
- }
+ override def run(): Unit =
+ try {
+ state.synchronized {
+ if (!Thread.currentThread().isInterrupted()) {
+ // Timeout current barrier() call, fail all the sync requests.
+ requesters.foreach(
+ _.sendFailure(new SparkException("The coordinator didn't get
all " +
+ s"barrier sync requests for barrier epoch +" +
+ s" $barrierEpoch from $barrierId within " +
+ s"$timeoutInSecs second(s).")))
+ cleanupBarrierStage(barrierId)
+ }
+ }
+ } catch {
+ case _: InterruptedException =>
+ // Handle interruption gracefully
+ Thread.currentThread().interrupt()
+ case e: Exception => new SparkException("Error during " +
+ s"running of barrier tasks for " +
+ s"$barrierId", e)
Review Comment:
What exception here?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
