Ngone51 commented on a change in pull request #34092:
URL: https://github.com/apache/spark/pull/34092#discussion_r715434302
##########
File path: core/src/main/scala/org/apache/spark/status/AppStatusListener.scala
##########
@@ -1253,12 +1254,47 @@ private[spark] class AppStatusListener(
toDelete.foreach { j => kvstore.delete(j.getClass(), j.info.jobId) }
}
- private def cleanupStages(count: Long): Unit = {
- val countToDelete = calculateNumberToRemove(count,
conf.get(MAX_RETAINED_STAGES))
- if (countToDelete <= 0L) {
- return
+ private case class StageCompletionTime(
+ stageId: Int,
+ attemptId: Int,
+ completionTime: Long)
+
+ private def cleanupStagesWithInMemoryStore(countToDelete: Long):
Seq[Array[Int]] = {
+ val stageArray = new ArrayBuffer[StageCompletionTime]()
+ val stageDataCount = new mutable.HashMap[Int, Int]()
+ kvstore.view(classOf[StageDataWrapper]).forEach { s =>
+ // Here we keep track of the total number of StageDataWrapper entries
for each stage id.
+ // This will be used in cleaning up the RDDOperationGraphWrapper data.
+ if (stageDataCount.contains(s.info.stageId)) {
+ stageDataCount(s.info.stageId) += 1
+ } else {
+ stageDataCount(s.info.stageId) = 1
+ }
Review comment:
this's only needed for completed stages?
--
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.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
