sarutak commented on code in PR #59112:
URL: https://github.com/apache/spark/pull/59112#discussion_r4136900099
##########
resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPVCResizePlugin.scala:
##########
@@ -121,23 +121,28 @@ class ExecutorPVCResizeDriverPlugin extends DriverPlugin
with Logging {
}
private[k8s] def checkAndResizePVCs(): Unit = {
- logInfo(s"Latest PVC usage reports: $latestReports")
val appId = sparkContext.applicationId
sparkContext.schedulerBackend match {
case b: KubernetesClusterSchedulerBackend =>
val client = b.kubernetesClient
+ // Skip terminated pods kept by deleteOnTermination=false since their
reports are stale.
val pods = client.pods()
.inNamespace(namespace)
.withLabel(SPARK_APP_ID_LABEL, appId)
.withLabel(SPARK_ROLE_LABEL, SPARK_POD_EXECUTOR_ROLE)
+ .withoutLabel(SPARK_EXECUTOR_INACTIVE_LABEL, "true")
.list()
.getItems.asScala
val podByExecId = pods.flatMap { p =>
Option(p.getMetadata.getLabels.get(SPARK_EXECUTOR_ID_LABEL)).map(_
-> p)
}.toMap
+ // Drop reports of executors without a pod so that latestReports does
not grow unbounded.
+ latestReports.keySet().retainAll(podByExecId.keySet.asJava)
Review Comment:
Got it. Thank you @dongjoon-hyun.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
