HeartSaVioR commented on a change in pull request #25943:
[WIP][SPARK-29261][SQL][CORE] Support recover live entities from KVStore for
(SQL)AppStatusListener
URL: https://github.com/apache/spark/pull/25943#discussion_r331386987
##########
File path: core/src/main/scala/org/apache/spark/status/AppStatusListener.scala
##########
@@ -103,6 +104,81 @@ private[spark] class AppStatusListener(
}
}
+ // visible for tests
+ private[spark] def recoverLiveEntities(): Unit = {
+ if (!live) {
+ kvstore.view(classOf[JobDataWrapper])
+ .asScala.filter(_.info.status == JobExecutionStatus.RUNNING)
+ .map(_.toLiveJob).foreach(job => liveJobs.put(job.jobId, job))
+
+ kvstore.view(classOf[StageDataWrapper]).asScala
+ .filter { stageData =>
+ stageData.info.status == v1.StageStatus.PENDING ||
+ stageData.info.status == v1.StageStatus.ACTIVE
+ }
+ .map { stageData =>
+ val stageId = stageData.info.stageId
+ val jobs = liveJobs.values.filter(_.stageIds.contains(stageId)).toSeq
+ stageData.toLiveStage(jobs)
+ }.foreach { stage =>
+ val stageId = stage.info.stageId
+ val stageAttempt = stage.info.attemptNumber()
+ liveStages.put((stageId, stageAttempt), stage)
+
+ kvstore.view(classOf[ExecutorStageSummaryWrapper])
+ .index("stage")
+ .first(Array(stageId, stageAttempt))
+ .last(Array(stageId, stageAttempt))
+ .asScala
+ .map(_.toLiveExecutorStageSummary)
+ .foreach { esummary =>
+ stage.executorSummaries.put(esummary.executorId, esummary)
+ if (esummary.isBlacklisted) {
+ stage.blackListedExecutors += esummary.executorId
+ liveExecutors(esummary.executorId).isBlacklisted = true
+ liveExecutors(esummary.executorId).blacklistedInStages += stageId
+ }
+ }
+
+
+ kvstore.view(classOf[TaskDataWrapper])
+ .parent(Array(stageId, stageAttempt))
+ .index(TaskIndexNames.STATUS)
+ .first(TaskState.RUNNING.toString)
+ .last(TaskState.RUNNING.toString)
+ .closeableIterator().asScala
Review comment:
Just a sake of understanding, any reason to use closeableIterator here and
don't use it for others?
----------------------------------------------------------------
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]
