From aac60b6cbbe330bd6c9ef37bc52ec607fe8f6298 Mon Sep 17 00:00:00 2001
From: wackxu <xushiwei5@huawei.com>
Date: Thu, 30 Nov 2017 16:46:17 +0800
Subject: [PATCH] delete a node from its cache if it gets node not found error

---
 plugin/pkg/scheduler/factory/factory.go | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/plugin/pkg/scheduler/factory/factory.go b/plugin/pkg/scheduler/factory/factory.go
index 764f449ccc4..a52b8d69fc0 100644
--- a/plugin/pkg/scheduler/factory/factory.go
+++ b/plugin/pkg/scheduler/factory/factory.go
@@ -1109,6 +1109,21 @@ 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)
 			}