Merge pull request #39468 from NickrenREN/node-status-update

Automatic merge from submit-queue (batch tested with PRs 39661, 39740, 39801, 39468, 39743)

fix nodeStatusUpdateRetry count exceeding condition judgement

When tryUpdateNodeStatus() return err,err!=nil,  but nc.kubeClient.Core().Nodes().Get() return no err, err==nil,
And we run nodeStatusUpdateRetry times, when for loop ends, err == nil, we can not print error info and run continue, so maybe the condition judgement is not right
Maybe caused #38671

pkg/controller/node/nodecontroller.go

@@ -449,24 +449,24 @@ func (nc *NodeController) monitorNodeStatus() error {
 			continue
 		}
 		node := nodeCopy.(*v1.Node)
-		for rep := 0; rep < nodeStatusUpdateRetry; rep++ {
+		if err := wait.PollImmediate(retrySleepTime, retrySleepTime*nodeStatusUpdateRetry, func() (bool, error) {
 			gracePeriod, observedReadyCondition, currentReadyCondition, err = nc.tryUpdateNodeStatus(node)
 			if err == nil {
-				break
+				return true, nil
 			}
 			name := node.Name
 			node, err = nc.kubeClient.Core().Nodes().Get(name, metav1.GetOptions{})
 			if err != nil {
 				glog.Errorf("Failed while getting a Node to retry updating NodeStatus. Probably Node %s was deleted.", name)
-				break
+				return false, err
 			}
-			time.Sleep(retrySleepTime)
-		}
-		if err != nil {
-			glog.Errorf("Update status  of Node %v from NodeController exceeds retry count."+
-				"Skipping - no pods will be evicted.", node.Name)
+			return false, nil
+		}); err != nil {
+			glog.Errorf("Update status  of Node %v from NodeController error : %v. "+
+				"Skipping - no pods will be evicted.", node.Name, err)
 			continue
 		}
+
 		// We do not treat a master node as a part of the cluster for network disruption checking.
 		if !system.IsMasterNode(node.Name) {
 			zoneToNodeConditions[utilnode.GetZoneKey(node)] = append(zoneToNodeConditions[utilnode.GetZoneKey(node)], currentReadyCondition)