Github user edwinalu commented on a diff in the pull request: https://github.com/apache/spark/pull/21221#discussion_r198682884 --- Diff: core/src/main/scala/org/apache/spark/scheduler/EventLoggingListener.scala --- @@ -169,6 +181,28 @@ private[spark] class EventLoggingListener( // Events that trigger a flush override def onStageCompleted(event: SparkListenerStageCompleted): Unit = { + if (shouldLogExecutorMetricsUpdates) { + // clear out any previous attempts, that did not have a stage completed event + val prevAttemptId = event.stageInfo.attemptNumber() - 1 + for (attemptId <- 0 to prevAttemptId) { + liveStageExecutorMetrics.remove((event.stageInfo.stageId, attemptId)) + } + + // log the peak executor metrics for the stage, for each live executor, + // whether or not the executor is running tasks for the stage + val executorMap = liveStageExecutorMetrics.remove( + (event.stageInfo.stageId, event.stageInfo.attemptNumber())) + executorMap.foreach { + executorEntry => { + for ((executorId, peakExecutorMetrics) <- executorEntry) { --- End diff -- Yes, the naming is confusing. Changed to the 1st option.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org