【kubernetes/k8s源码分析】 controller-manager之replicaset源码分析

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/zhonglinzhang/article/details/82997549

ReplicaSet简介

    Kubernetes 中建议使用 ReplicaSet来取代 ReplicationController。ReplicaSet 跟 ReplicationController 没有本质的不同， ReplicaSet 支持集合式的 selector（ReplicationController 仅支持等式）

    但建议使用 Deployment 来自动管理 ReplicaSet，这样就无需担心跟其他机制的不兼容问题（比如 ReplicaSet 不支持 rolling-update 但 Deployment 支持），并且Deployment还支持版本记录、回滚、暂停升级等高级特性。

0. 開始：

func NewControllerInitializers() map[string]InitFunc {
	controllers := map[string]InitFunc{}

	controllers["deployment"] = startDeploymentController
	controllers["replicaset"] = startReplicaSetController
	
	return controllers
}

0.1 startReplicaSetController函数

• 判断replicasets是否开启
• 创建并初始化ReplicaSetController对象。启动ReplicaSetController对象的Run方法，循环处理流程

func startReplicaSetController(ctx ControllerContext) (bool, error) {
	if !ctx.AvailableResources[schema.GroupVersionResource{Group: "extensions", Version: "v1beta1", Resource: "replicasets"}] {
		return false, nil
	}
	go replicaset.NewReplicaSetController(
		ctx.InformerFactory.Extensions().V1beta1().ReplicaSets(),
		ctx.InformerFactory.Core().V1().Pods(),
		ctx.ClientBuilder.ClientOrDie("replicaset-controller"),
		replicaset.BurstReplicas,
	).Run(int(ctx.Options.ConcurrentRSSyncs), ctx.Stop)
	return true, nil
}

0.2 ReplicaSetController的Run函数

     启动一堆work进行处理

// Run begins watching and syncing.
func (rsc *ReplicaSetController) Run(workers int, stopCh <-chan struct{}) {
	defer utilruntime.HandleCrash()
	defer rsc.queue.ShutDown()

	controllerName := strings.ToLower(rsc.Kind)
	glog.Infof("Starting %v controller", controllerName)
	defer glog.Infof("Shutting down %v controller", controllerName)

	if !controller.WaitForCacheSync(rsc.Kind, stopCh, rsc.podListerSynced, rsc.rsListerSynced) {
		return
	}

	for i := 0; i < workers; i++ {
		go wait.Until(rsc.worker, time.Second, stopCh)
	}

	<-stopCh
}

0.3 主要函数syncHandler这个函数注册的为syncReplicaSet，在  NewBaseController中体现

// worker runs a worker thread that just dequeues items, processes them, and marks them done.
// It enforces that the syncHandler is never invoked concurrently with the same key.
func (rsc *ReplicaSetController) worker() {
	for rsc.processNextWorkItem() {
	}
}

func (rsc *ReplicaSetController) processNextWorkItem() bool {
	key, quit := rsc.queue.Get()
	if quit {
		return false
	}
	defer rsc.queue.Done(key)

	err := rsc.syncHandler(key.(string))
	if err == nil {
		rsc.queue.Forget(key)
		return true
	}

	utilruntime.HandleError(fmt.Errorf("Sync %q failed with %v", key, err))
	rsc.queue.AddRateLimited(key)

	return true
}

1. NewReplicaSetController函数

    路径： pkg/controller/replicaset/replica_set.go

  1.1 创建eventBroadcaster并设置属性

eventBroadcaster := record.NewBroadcaster()
	eventBroadcaster.StartLogging(glog.Infof)
	eventBroadcaster.StartRecordingToSink(&v1core.EventSinkImpl{Interface: v1core.New(kubeClient.CoreV1().RESTClient()).Events("")})

  1.2 创建ReplicaSetController对象，包括k8s client，队列等

	rsc := &ReplicaSetController{
		GroupVersionKind: gvk,
		kubeClient:       kubeClient,
		podControl:       podControl,
		burstReplicas:    burstReplicas,
		expectations:     controller.NewUIDTrackingControllerExpectations(controller.NewControllerExpectations()),
		queue:            workqueue.NewNamedRateLimitingQueue(workqueue.DefaultControllerRateLimiter(), queueName),
	}

  1.3 rsInformer和podInformer对应的事件回调函数，被注册syncReplicaSet

	rsInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc:    rsc.enqueueReplicaSet,
		UpdateFunc: rsc.updateRS,
		// This will enter the sync loop and no-op, because the replica set has been deleted from the store.
		// Note that deleting a replica set immediately after scaling it to 0 will not work. The recommended
		// way of achieving this is by performing a `stop` operation on the replica set.
		DeleteFunc: rsc.enqueueReplicaSet,
	})
	rsc.rsLister = rsInformer.Lister()
	rsc.rsListerSynced = rsInformer.Informer().HasSynced

	podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc: rsc.addPod,
		// This invokes the ReplicaSet for every pod change, eg: host assignment. Though this might seem like
		// overkill the most frequent pod update is status, and the associated ReplicaSet will only list from
		// local storage, so it should be ok.
		UpdateFunc: rsc.updatePod,
		DeleteFunc: rsc.deletePod,
	})
	rsc.podLister = podInformer.Lister()
	rsc.podListerSynced = podInformer.Informer().HasSynced

	rsc.syncHandler = rsc.syncReplicaSet

2. syncReplicaSet函数

  2.1 获得namespace和name，并去的replicaset对象

	namespace, name, err := cache.SplitMetaNamespaceKey(key)
	if err != nil {
		return err
	}
	rs, err := rsc.rsLister.ReplicaSets(namespace).Get(name)
	if errors.IsNotFound(err) {
		glog.V(4).Infof("%v %v has been deleted", rsc.Kind, key)
		rsc.expectations.DeleteExpectations(key)
		return nil
	}
	if err != nil {
		return err
	}

2.2 获取namespace所有pod，并过滤调inactive的pod（active pod的Status.Phase不是Success  Failed 已经标记删除的）

	// list all pods to include the pods that don't match the rs`s selector
	// anymore but has the stale controller ref.
	// TODO: Do the List and Filter in a single pass, or use an index.
	allPods, err := rsc.podLister.Pods(rs.Namespace).List(labels.Everything())
	if err != nil {
		return err
	}
	// Ignore inactive pods.
	var filteredPods []*v1.Pod
	for _, pod := range allPods {
		if controller.IsPodActive(pod) {
			filteredPods = append(filteredPods, pod)
		}
	}

2.3 claimPods函数

   如果新创建无pod

func (rsc *ReplicaSetController) claimPods(rs *extensions.ReplicaSet, selector labels.Selector, filteredPods []*v1.Pod) ([]*v1.Pod, error) {
	// If any adoptions are attempted, we should first recheck for deletion with
	// an uncached quorum read sometime after listing Pods (see #42639).
	canAdoptFunc := controller.RecheckDeletionTimestamp(func() (metav1.Object, error) {
		fresh, err := rsc.kubeClient.ExtensionsV1beta1().ReplicaSets(rs.Namespace).Get(rs.Name, metav1.GetOptions{})
		if err != nil {
			return nil, err
		}
		if fresh.UID != rs.UID {
			return nil, fmt.Errorf("original %v %v/%v is gone: got uid %v, wanted %v", rsc.Kind, rs.Namespace, rs.Name, fresh.UID, rs.UID)
		}
		return fresh, nil
	})
	cm := controller.NewPodControllerRefManager(rsc.podControl, rs, selector, rsc.GroupVersionKind, canAdoptFunc)
	return cm.ClaimPods(filteredPods)
}

2.4 manageReplicas函数

    主要函数为manageReplicas

	var manageReplicasErr error
	if rsNeedsSync && rs.DeletionTimestamp == nil {
		manageReplicasErr = rsc.manageReplicas(filteredPods, rs)
	}

3. manageReplicas函数

   调节Pod的数量，多退少补。计算差值

 diff := len(filteredPods) - int(*(rs.Spec.Replicas))

3.1 diff少于replicas则少补，不能超过burstReplicas（好像是500）

	if diff < 0 {
		diff *= -1
		if diff > rsc.burstReplicas {
			diff = rsc.burstReplicas
		}

		rsc.expectations.ExpectCreations(rsKey, diff)
		
		successfulCreations, err := slowStartBatch(diff, controller.SlowStartInitialBatchSize, func() error {
			boolPtr := func(b bool) *bool { return &b }
			controllerRef := &metav1.OwnerReference{
				APIVersion:         rsc.GroupVersion().String(),
				Kind:               rsc.Kind,
				Name:               rs.Name,
				UID:                rs.UID,
				BlockOwnerDeletion: boolPtr(true),
				Controller:         boolPtr(true),
			}
			err := rsc.podControl.CreatePodsWithControllerRef(rs.Namespace, &rs.Spec.Template, rs, controllerRef)
			if err != nil && errors.IsTimeout(err) {
				
				return nil
			}
			return err
		})

		
		if skippedPods := diff - successfulCreations; skippedPods > 0 {
			
			for i := 0; i < skippedPods; i++ {
				// Decrement the expected number of creates because the informer won't observe this pod
				rsc.expectations.CreationObserved(rsKey)
			}
		}
		return err
	}