Github user squito commented on a diff in the pull request: https://github.com/apache/spark/pull/17088#discussion_r106668930 --- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala --- @@ -1365,18 +1369,25 @@ class DAGScheduler( */ private[scheduler] def handleExecutorLost( execId: String, - filesLost: Boolean, + fileLost: Boolean) { + removeExecutorAndUnregisterOutputOnExecutor(execId, + fileLost || !env.blockManager.externalShuffleServiceEnabled, None) + } + + + private[scheduler] def removeExecutorAndUnregisterOutputOnExecutor( + execId: String, + fileLost: Boolean, maybeEpoch: Option[Long] = None) { val currentEpoch = maybeEpoch.getOrElse(mapOutputTracker.getEpoch) if (!failedEpoch.contains(execId) || failedEpoch(execId) < currentEpoch) { failedEpoch(execId) = currentEpoch logInfo("Executor lost: %s (epoch %d)".format(execId, currentEpoch)) blockManagerMaster.removeExecutor(execId) - - if (filesLost || !env.blockManager.externalShuffleServiceEnabled) { - logInfo("Shuffle files lost for executor: %s (epoch %d)".format(execId, currentEpoch)) + if (fileLost) { // TODO: This will be really slow if we keep accumulating shuffle map stages for ((shuffleId, stage) <- shuffleIdToMapStage) { + logInfo("Shuffle files lost for executor: %s (epoch %d)".format(execId, currentEpoch)) --- End diff -- log should be outside the for loop, like it was before
--- 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