Merge pull request #22067 from derekwaynecarr/ns_controller_errors

e2e flake fix: Namespace controller error handling improvements

pkg/controller/namespace/namespace_controller.go

@@ -112,11 +112,16 @@ func (nm *NamespaceController) worker() {
 			if err := nm.syncNamespaceFromKey(key.(string)); err != nil {
 				if estimate, ok := err.(*contentRemainingError); ok {
 					go func() {
+						defer utilruntime.HandleCrash()
 						t := estimate.Estimate/2 + 1
 						glog.V(4).Infof("Content remaining in namespace %s, waiting %d seconds", key, t)
 						time.Sleep(time.Duration(t) * time.Second)
 						nm.queue.Add(key)
 					}()
+				} else {
+					// rather than wait for a full resync, re-add the namespace to the queue to be processed
+					nm.queue.Add(key)
+					utilruntime.HandleError(err)
 				}
 			}
 		}()

pkg/controller/namespace/namespace_controller_utils.go

@@ -244,6 +244,12 @@ func syncNamespace(kubeClient clientset.Interface, versions *unversioned.APIVers
 	// we have removed content, so mark it finalized by us
 	result, err := retryOnConflictError(kubeClient, namespace, finalizeNamespaceFunc)
 	if err != nil {
+		// in normal practice, this should not be possible, but if a deployment is running
+		// two controllers to do namespace deletion that share a common finalizer token it's
+		// possible that a not found could occur since the other controller would have finished the delete.
+		if errors.IsNotFound(err) {
+			return nil
+		}
 		return err
 	}