You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@flink.apache.org by xt...@apache.org on 2023/02/22 09:55:44 UTC
[flink] branch release-1.17 updated: [FLINK-31169][k8s] Fix that pod termination may be mis-treated as fatal error.
This is an automated email from the ASF dual-hosted git repository.
xtsong pushed a commit to branch release-1.17
in repository https://gitbox.apache.org/repos/asf/flink.git
The following commit(s) were added to refs/heads/release-1.17 by this push:
new bfadd9c6922 [FLINK-31169][k8s] Fix that pod termination may be mis-treated as fatal error.
bfadd9c6922 is described below
commit bfadd9c69223765d485ed2371fa108b25756c1fc
Author: Xintong Song <to...@gmail.com>
AuthorDate: Wed Feb 22 10:13:26 2023 +0800
[FLINK-31169][k8s] Fix that pod termination may be mis-treated as fatal error.
This closes #21986
---
.../flink/kubernetes/KubernetesResourceManagerDriver.java | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/flink-kubernetes/src/main/java/org/apache/flink/kubernetes/KubernetesResourceManagerDriver.java b/flink-kubernetes/src/main/java/org/apache/flink/kubernetes/KubernetesResourceManagerDriver.java
index 259cf1b63f6..508e791e79e 100644
--- a/flink-kubernetes/src/main/java/org/apache/flink/kubernetes/KubernetesResourceManagerDriver.java
+++ b/flink-kubernetes/src/main/java/org/apache/flink/kubernetes/KubernetesResourceManagerDriver.java
@@ -228,6 +228,8 @@ public class KubernetesResourceManagerDriver
podName);
stopPod(taskManagerPod.getName());
}
+ } else if (t instanceof RetryableException) {
+ // ignore
} else {
log.error("Error completing resource request.", t);
ExceptionUtils.rethrow(t);
@@ -376,7 +378,8 @@ public class KubernetesResourceManagerDriver
requestResourceFutures.remove(podName);
if (requestResourceFuture != null) {
log.warn("Pod {} is terminated before being scheduled.", podName);
- requestResourceFuture.completeExceptionally(new FlinkException("Pod is terminated."));
+ requestResourceFuture.completeExceptionally(
+ new RetryableException("Pod is terminated."));
}
getResourceEventHandler()
@@ -452,4 +455,12 @@ public class KubernetesResourceManagerDriver
}
}
}
+
+ private static class RetryableException extends FlinkException {
+ private static final long serialVersionUID = 1L;
+
+ RetryableException(String message) {
+ super(message);
+ }
+ }
}