vanzin commented on a change in pull request #26218: [SPARK-29562][sql] Speed
up and slim down metric aggregation in SQL listener.
URL: https://github.com/apache/spark/pull/26218#discussion_r338837946
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/ui/SQLAppStatusListener.scala
##########
@@ -140,7 +146,16 @@ class SQLAppStatusListener(
override def onExecutorMetricsUpdate(event:
SparkListenerExecutorMetricsUpdate): Unit = {
event.accumUpdates.foreach { case (taskId, stageId, attemptId,
accumUpdates) =>
- updateStageMetrics(stageId, attemptId, taskId, accumUpdates, false)
+ updateStageMetrics(stageId, attemptId, taskId,
SQLAppStatusListener.UNKNOWN_PARTITION,
+ accumUpdates, false)
+ }
+ }
+
+ override def onTaskStart(event: SparkListenerTaskStart): Unit = {
+ Option(stageMetrics.get(event.stageId)).foreach { stage =>
+ if (stage.attemptId == event.stageAttemptId) {
+ stage.registerTask(event.taskInfo.taskId, event.taskInfo.index)
Review comment:
See below.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
