gyfora commented on code in PR #777:
URL:
https://github.com/apache/flink-kubernetes-operator/pull/777#discussion_r1492764973
##########
flink-kubernetes-operator/src/main/java/org/apache/flink/kubernetes/operator/service/AbstractFlinkService.java:
##########
@@ -898,58 +899,50 @@ public JobDetailsInfo getJobDetailsInfo(JobID jobID,
Configuration conf) throws
}
}
- /** Wait until the FLink cluster has completely shut down. */
- @VisibleForTesting
- void waitForClusterShutdown(String namespace, String clusterId, long
shutdownTimeout) {
- LOG.info("Waiting for cluster shutdown...");
-
- boolean jobManagerRunning = true;
- boolean taskManagerRunning = true;
- boolean serviceRunning = true;
+ /** Returns a list of Kubernetes Deployment names for given cluster. */
+ protected abstract List<String> getDeploymentNames(String namespace,
String clusterId);
- for (int i = 0; i < shutdownTimeout; i++) {
- if (jobManagerRunning) {
- PodList jmPodList = getJmPodList(namespace, clusterId);
+ /** Wait until the FLink cluster has completely shut down. */
+ protected void waitForClusterShutdown(
+ String namespace, String clusterId, long shutdownTimeout) {
+ long timeoutAt = System.currentTimeMillis() + shutdownTimeout * 1000;
+ LOG.info("Waiting {} seconds for cluster shutdown...",
shutdownTimeout);
- if (jmPodList == null || jmPodList.getItems().isEmpty()) {
- jobManagerRunning = false;
- }
- }
- if (taskManagerRunning) {
- PodList tmPodList = getTmPodList(namespace, clusterId);
+ for (var deploymentName : getDeploymentNames(namespace, clusterId)) {
+ long deploymentTimeout = timeoutAt - System.currentTimeMillis();
- if (tmPodList.getItems().isEmpty()) {
- taskManagerRunning = false;
- }
+ if (!waitForDeploymentToBeRemoved(namespace, deploymentName,
deploymentTimeout)) {
+ LOG.error(
+ "Failed to shut down cluster {} (deployment {}) in {}
seconds, proceeding...",
+ clusterId,
+ deploymentName,
+ shutdownTimeout);
+ return;
}
+ }
+ }
- if (serviceRunning) {
- Service service =
- kubernetesClient
- .services()
- .inNamespace(namespace)
- .withName(
-
ExternalServiceDecorator.getExternalServiceName(clusterId))
- .get();
- if (service == null) {
- serviceRunning = false;
- }
- }
+ /** Wait until Deployment is removed, return false if timed out, otherwise
return true. */
+ @VisibleForTesting
+ boolean waitForDeploymentToBeRemoved(String namespace, String
deploymentName, long timeout) {
+ LOG.info(
+ "Waiting for Deployment {} to shut down with {} ms timeout...",
Review Comment:
Can we display this timeout log in seconds to be consistent?
--
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: issues-unsubscr...@flink.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
