【提问】pkg/controller/deployment/deployment_controller.go 中，updateDeployment 和 updateReplicaSet 两个函数，为啥 updateReplicaSet 中有对比 ResourceVersion 的步骤而 updateDeployment 中没有？

[WisWang]

问题描述

最近在学习 informer 机制，但是还是不太了解 resync 的实际用途，现在遇到如下问题：

在 pkg/controller/deployment/deployment_controller.go 101行 中的 NewDeploymentController 会传入 DeploymentInformer 和 ReplicaSetInformer，为什么这两个 Informer 的 AddEventHandler 中 注册的 UpdateFunc “dc.updateDeployment dc.updateReplicaSet” updateReplicaSet 中有对比 ResourceVersion 的步骤而 updateDeployment 中没有？

相关代码

pkg/controller/deployment/deployment_controller.go:
func NewDeploymentController(dInformer appsinformers.DeploymentInformer, rsInformer appsinformers.ReplicaSetInformer, podInformer coreinformers.PodInformer, client clientset.Interface) (*DeploymentController, error) {
	eventBroadcaster := record.NewBroadcaster()
	eventBroadcaster.StartStructuredLogging(0)
	eventBroadcaster.StartRecordingToSink(&v1core.EventSinkImpl{Interface: client.CoreV1().Events("")})

	if client != nil && client.CoreV1().RESTClient().GetRateLimiter() != nil {
		if err := ratelimiter.RegisterMetricAndTrackRateLimiterUsage("deployment_controller", client.CoreV1().RESTClient().GetRateLimiter()); err != nil {
			return nil, err
		}
	}
	dc := &DeploymentController{
		client:        client,
		eventRecorder: eventBroadcaster.NewRecorder(scheme.Scheme, v1.EventSource{Component: "deployment-controller"}),
		queue:         workqueue.NewNamedRateLimitingQueue(workqueue.DefaultControllerRateLimiter(), "deployment"),
	}
	dc.rsControl = controller.RealRSControl{
		KubeClient: client,
		Recorder:   dc.eventRecorder,
	}

	dInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc:    dc.addDeployment,
		UpdateFunc: dc.updateDeployment,
		// This will enter the sync loop and no-op, because the deployment has been deleted from the store.
		DeleteFunc: dc.deleteDeployment,
	})
	rsInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc:    dc.addReplicaSet,
		UpdateFunc: dc.updateReplicaSet,
		DeleteFunc: dc.deleteReplicaSet,
	})
	podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		DeleteFunc: dc.deletePod,
	})

	dc.syncHandler = dc.syncDeployment
	dc.enqueueDeployment = dc.enqueue

	dc.dLister = dInformer.Lister()
	dc.rsLister = rsInformer.Lister()
	dc.podLister = podInformer.Lister()
	dc.dListerSynced = dInformer.Informer().HasSynced
	dc.rsListerSynced = rsInformer.Informer().HasSynced
	dc.podListerSynced = podInformer.Informer().HasSynced
	return dc, nil
}
func (dc *DeploymentController) updateDeployment(old, cur interface{}) {
	oldD := old.(*apps.Deployment)
	curD := cur.(*apps.Deployment)
	klog.V(4).Infof("Updating deployment %s", oldD.Name)
	dc.enqueueDeployment(curD)
}
func (dc *DeploymentController) updateReplicaSet(old, cur interface{}) {
	curRS := cur.(*apps.ReplicaSet)
	oldRS := old.(*apps.ReplicaSet)
	if curRS.ResourceVersion == oldRS.ResourceVersion {
		// Periodic resync will send update events for all known replica sets.
		// Two different versions of the same replica set will always have different RVs.
		return
	}

	curControllerRef := metav1.GetControllerOf(curRS)
	oldControllerRef := metav1.GetControllerOf(oldRS)
	controllerRefChanged := !reflect.DeepEqual(curControllerRef, oldControllerRef)
	if controllerRefChanged && oldControllerRef != nil {
		// The ControllerRef was changed. Sync the old controller, if any.
		if d := dc.resolveControllerRef(oldRS.Namespace, oldControllerRef); d != nil {
			dc.enqueueDeployment(d)
		}
	}

	// If it has a ControllerRef, that's all that matters.
	if curControllerRef != nil {
		d := dc.resolveControllerRef(curRS.Namespace, curControllerRef)
		if d == nil {
			return
		}
		klog.V(4).Infof("ReplicaSet %s updated.", curRS.Name)
		dc.enqueueDeployment(d)
		return
	}

	// Otherwise, it's an orphan. If anything changed, sync matching controllers
	// to see if anyone wants to adopt it now.
	labelChanged := !reflect.DeepEqual(curRS.Labels, oldRS.Labels)
	if labelChanged || controllerRefChanged {
		ds := dc.getDeploymentsForReplicaSet(curRS)
		if len(ds) == 0 {
			return
		}
		klog.V(4).Infof("Orphan ReplicaSet %s updated.", curRS.Name)
		for _, d := range ds {
			dc.enqueueDeployment(d)
		}
	}
}

[WisWang]

这个问题我也问了一下，kubernetes 的联合创始人 Brendan Burns [email protected]，下面是他的回复：

I'm not super familiar with that code since I wasn't involved in writting it, but my guess from looking at it is that it is an oversight. In both cases it is possible that there will be an "update" where the resource version doesn't change, due to a re-list of the resources. Such an "update" is in fact a no-op and should be ignored. So I think it would be reasonable to add the same check to the updateDeployment code.

还是没回答我的问题，resync 是为了 reconcile 业务逻辑和内存缓存（ 最近一次 relist 的结果 ）的。就是说有对比 resource version 的 controller 是不需要这一步 reconcile 的，而没有对比 resource version 的是需要这一步 reconcile 的，难道说 Deployment 需要 reconcile 业务逻辑和内存缓存，而 ReplicaSet 不需要？ 我的博客对这个有更详细的记录。