Github user liyinan926 commented on a diff in the pull request:
https://github.com/apache/spark/pull/21241#discussion_r186780738
--- Diff:
resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/KubernetesClusterSchedulerBackend.scala
---
@@ -320,50 +322,83 @@ private[spark] class
KubernetesClusterSchedulerBackend(
override def eventReceived(action: Action, pod: Pod): Unit = {
val podName = pod.getMetadata.getName
val podIP = pod.getStatus.getPodIP
-
+ val podPhase = pod.getStatus.getPhase
action match {
- case Action.MODIFIED if (pod.getStatus.getPhase == "Running"
+ case Action.MODIFIED if (podPhase == "Running"
&& pod.getMetadata.getDeletionTimestamp == null) =>
val clusterNodeName = pod.getSpec.getNodeName
logInfo(s"Executor pod $podName ready, launched at
$clusterNodeName as IP $podIP.")
executorPodsByIPs.put(podIP, pod)
- case Action.DELETED | Action.ERROR =>
+ case Action.MODIFIED if (podPhase == "Init:Error" || podPhase ==
"Init:CrashLoopBackoff")
+ && pod.getMetadata.getDeletionTimestamp == null =>
val executorId = getExecutorId(pod)
- logDebug(s"Executor pod $podName at IP $podIP was at $action.")
- if (podIP != null) {
- executorPodsByIPs.remove(podIP)
+ failedInitExecutors.add(executorId)
+ if (failedInitExecutors.size >= executorMaxInitErrors) {
+ val errorMessage = s"Aborting Spark application because
$executorMaxInitErrors" +
+ s" executors failed to start. The maximum number of allowed
startup failures is" +
+ s" $executorMaxInitErrors. Please contact your cluster
administrator or increase" +
+ s" your setting of
${KUBERNETES_EXECUTOR_MAX_INIT_ERRORS.key}."
+ logError(errorMessage)
+
KubernetesClusterSchedulerBackend.this.scheduler.sc.stopInNewThread()
--- End diff --
Why you need to call this?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
