Merge pull request #56622 from wackxu/nodemiss

Automatic merge from submit-queue. If you want to cherry-pick this change to another branch, please follow the instructions <a href="https://github.com/kubernetes/community/blob/master/contributors/devel/cherry-picks.md">here</a>. delete a node from its cache if it gets node not found error **What this PR does / why we need it**: delete a node from its cache if it gets node not found error **Which issue(s) this PR fixes** *(optional, in `fixes #<issue number>(, fixes #<issue_number>, ...)` format, will close the issue(s) when PR gets merged)*: Fixes # https://github.com/kubernetes/kubernetes/issues/56261 **Special notes for your reviewer**: **Release note**: ```release-note NONE ```

Merge pull request #56622 from wackxu/nodemiss
7335c41e · Kubernetes Submit Queue · GitHub · b97e1760 · aac60b6c · 7335c41e
Unverified Commit 7335c41e authored Dec 12, 2017 by Kubernetes Submit Queue Committed by GitHub Dec 12, 2017
Hide whitespace changes
Inline Side-by-side

Showing with 15 additions and 0 deletions

factory.go plugin/pkg/scheduler/factory/factory.go +15 -0

No files found.
--- a/plugin/pkg/scheduler/factory/factory.go
+++ b/plugin/pkg/scheduler/factory/factory.go
@@ -1139,6 +1139,21 @@ func (factory *configFactory) MakeDefaultErrorFunc(backoff *util.PodBackoff, pod
 		} else {
 			if _, ok := err.(*core.FitError); ok {
 				glog.V(4).Infof("Unable to schedule %v %v: no fit: %v; waiting", pod.Namespace, pod.Name, err)
+			} else if errors.IsNotFound(err) {
+				if errStatus, ok := err.(errors.APIStatus); ok && errStatus.Status().Details.Kind == "node" {
+					nodeName := errStatus.Status().Details.Name
+					// when node is not found, We do not remove the node right away. Trying again to get
+					// the node and if the node is still not found, then remove it from the scheduler cache.
+					_, err := factory.client.CoreV1().Nodes().Get(nodeName, metav1.GetOptions{})
+					if err != nil && errors.IsNotFound(err) {
+						node := v1.Node{ObjectMeta: metav1.ObjectMeta{Name: nodeName}}
+						factory.schedulerCache.RemoveNode(&node)
+						// invalidate cached predicate for the node
+						if factory.enableEquivalenceClassCache {
+							factory.equivalencePodCache.InvalidateAllCachedPredicateItemOfNode(nodeName)
+						}
+					}
+				}
 			} else {
 				glog.Errorf("Error scheduling %v %v: %v; retrying", pod.Namespace, pod.Name, err)
 			}