dongjoon-hyun commented on a change in pull request #30892:
URL: https://github.com/apache/spark/pull/30892#discussion_r549225990
##########
File path:
resource-managers/kubernetes/core/src/main/scala/org/apache/spark/scheduler/cluster/k8s/ExecutorPodsSnapshot.scala
##########
@@ -65,14 +72,35 @@ object ExecutorPodsSnapshot extends Logging {
case "pending" =>
PodPending(pod)
case "running" =>
+ // If we're checking all containers look for any non-zero exits
if (shouldCheckAllContainers &&
"Never" == pod.getSpec.getRestartPolicy &&
pod.getStatus.getContainerStatuses.stream
.map[ContainerStateTerminated](cs => cs.getState.getTerminated)
.anyMatch(t => t != null && t.getExitCode != 0)) {
PodFailed(pod)
} else {
- PodRunning(pod)
+ // Otherwise look for the Spark container
+ val sparkContainerStatusOpt =
pod.getStatus.getContainerStatuses.asScala
+ .find(_.getName() == sparkContainerName)
+ sparkContainerStatusOpt match {
+ case Some(sparkContainerStatus) =>
+ sparkContainerStatus.getState.getTerminated match {
+ case t if t.getExitCode != 0 =>
+ PodFailed(pod)
+ case t if t.getExitCode == 0 =>
+ PodSucceeded(pod)
+ case _ =>
+ logWarning(s"Unable to find container
${sparkContainerName} in pod ${pod} " +
+ "defaulting to entire pod status (running).")
+ PodRunning(pod)
+ }
+ // If we can't find the Spark container status, fall back to the
pod status
+ case _ =>
+ logWarning(s"Unable to find container ${sparkContainerName} in
pod ${pod} " +
+ "defaulting to entire pod status (running).")
Review comment:
Indentation?
----------------------------------------------------------------
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
