Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/22001#discussion_r209460279 --- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala --- @@ -929,11 +963,38 @@ class DAGScheduler( // HadoopRDD whose underlying HDFS files have been deleted. finalStage = createResultStage(finalRDD, func, partitions, jobId, callSite) } catch { + case e: Exception if e.getMessage.contains( + DAGScheduler.ERROR_MESSAGE_BARRIER_REQUIRE_MORE_SLOTS_THAN_CURRENT_TOTAL_NUMBER) => + logWarning(s"The job $jobId requires to run a barrier stage that requires more slots " + + "than the total number of slots in the cluster currently.") + jobIdToNumTasksCheckFailures.compute(jobId, new BiFunction[Int, Int, Int] { --- End diff -- minor: Should have an inline comment that mentions the implicit conversation from `null` to `0: Int` to handle new keys.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org