Github user kayousterhout commented on a diff in the pull request: https://github.com/apache/spark/pull/14079#discussion_r74333404 --- Diff: core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala --- @@ -770,9 +794,19 @@ private[spark] class TaskSetManager( logError("Unknown TaskEndReason: " + e) None } - // always add to failed executors - failedExecutors.getOrElseUpdate(index, new HashMap[String, Long]()). - put(info.executorId, clock.getTimeMillis()) + + // we might rack up a bunch of fetch-failures in rapid succession, due to a bad node. But + // that bad node will get handled separately by spark's stage-failure handling mechanism. It + // shouldn't penalize *this* executor at all, so don't count it as a task-failure as far as + // the blacklist is concerned. + val countTowardsTaskFailures = reason match { + case fail: TaskFailedReason => fail.countTowardsTaskFailures --- End diff -- Cool thanks for fixing this!!
--- 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