turboFei commented on code in PR #3175:
URL: https://github.com/apache/celeborn/pull/3175#discussion_r2052006124
##########
client-spark/spark-3/src/main/scala/org/apache/spark/shuffle/celeborn/ShuffleFetchFailureReportTaskCleanListener.scala:
##########
@@ -19,10 +19,25 @@ package org.apache.spark.shuffle.celeborn
import org.apache.spark.scheduler.{SparkListener, SparkListenerStageCompleted}
-class ShuffleFetchFailureReportTaskCleanListener extends SparkListener {
+import org.apache.celeborn.common.internal.Logging
+
+class ShuffleFetchFailureReportTaskCleanListener extends SparkListener with
Logging {
override def onStageCompleted(stageCompleted: SparkListenerStageCompleted):
Unit = {
- SparkUtils.removeStageReportedShuffleFetchFailureTaskIds(
- stageCompleted.stageInfo.stageId,
- stageCompleted.stageInfo.attemptNumber())
+ val stageId = stageCompleted.stageInfo.stageId
+ val stageAttemptId = stageCompleted.stageInfo.attemptNumber()
+ val shuffleFetchFailureTaskIds =
+ SparkUtils.removeStageReportedShuffleFetchFailureTaskIds(stageId,
stageAttemptId)
+ if (shuffleFetchFailureTaskIds != null) {
+ val taskSetManager = SparkUtils.getTaskSetManager(stageId,
stageAttemptId)
Review Comment:
thanks
--
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]
