Github user squito commented on a diff in the pull request: https://github.com/apache/spark/pull/8180#discussion_r37678288 --- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala --- @@ -746,6 +848,63 @@ class DAGScheduler( submitWaitingStages() } + private[scheduler] def handleMapStageSubmitted(jobId: Int, + dependency: ShuffleDependency[_, _, _], + callSite: CallSite, + listener: JobListener, + properties: Properties) { + // Submitting this map stage might still require the creation of some parent stages, so make + // sure that happens. + var finalStage: ShuffleMapStage = null + try { + // New stage creation may throw an exception if, for example, jobs are run on a + // HadoopRDD whose underlying HDFS files have been deleted. + finalStage = getShuffleMapStage(dependency, jobId) + } catch { + case e: Exception => + logWarning("Creating new stage failed due to exception - job: " + jobId, e) + listener.jobFailed(e) + return + } + if (finalStage != null) { --- End diff -- can you add a comment on how `finalStage` can be `null`? would be nice to also have this in `handleJobSubmitted` as well, actually
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org