k8s daemonset controller源码分析

daemonset controller分析

daemonset controller简介

daemonset controller是kube-controller-manager组件中众多控制器中的一个，是 daemonset 资源对象的控制器，其通过对daemonset、pod、node、ControllerRevision四种资源的监听，当这四种资源发生变化时会触发 daemonset controller 对相应的daemonset资源进行调谐操作，从而完成daemonset在合适node上pod的创建、在不合适node上pod的删除、daemonset的滚动更新、daemonset状态status更新、旧版本daemonset清理等操作。

daemonset controller架构图

daemonset controller的大致组成和处理流程如下图，daemonset controller对daemonset、pod、node、ControllerRevision对象注册了event handler，当有事件时，会watch到然后将对应的daemonset对象放入到queue中，然后syncDaemonset方法为daemonset controller调谐daemonset对象的核心处理逻辑所在，从queue中取出daemonset对象，做调谐处理。

daemonset更新策略

（1）OnDelete：使用 OnDelete 更新策略时，在更新 DaemonSet pod模板后，只有当你手动删除老的 DaemonSet pods 之后，新的 DaemonSet Pod 才会被自动创建。
（2）RollingUpdate：默认的更新策略。使用 RollingUpdate 更新策略时，在更新 DaemonSet pod模板后， 老的 DaemonSet pods 将被删除，并且将根据滚动更新配置自动创建新的 DaemonSet pods。 滚动更新期间，最多只能有 DaemonSet 的一个 Pod 运行于每个节点上。

daemonset controller分析将分为两大块进行，分别是：
（1）daemonset controller初始化与启动分析；
（2）daemonset controller处理逻辑分析。

1.daemonset controller初始化与启动分析

基于tag v1.17.4

https://github.com/kubernetes/kubernetes/releases/tag/v1.17.4

直接看到startDaemonSetController函数，作为daemonset controller初始化与启动分析的入口。

startDaemonSetController

startDaemonSetController主要逻辑：
（1）调用daemon.NewDaemonSetsController新建并初始化DaemonSetsController；
（2）拉起一个goroutine，跑DaemonSetsController的Run方法。

// cmd/kube-controller-manager/app/apps.go
func startDaemonSetController(ctx ControllerContext) (http.Handler, bool, error) {
	if !ctx.AvailableResources[schema.GroupVersionResource{Group: "apps", Version: "v1", Resource: "daemonsets"}] {
		return nil, false, nil
	}
	dsc, err := daemon.NewDaemonSetsController(
		ctx.InformerFactory.Apps().V1().DaemonSets(),
		ctx.InformerFactory.Apps().V1().ControllerRevisions(),
		ctx.InformerFactory.Core().V1().Pods(),
		ctx.InformerFactory.Core().V1().Nodes(),
		ctx.ClientBuilder.ClientOrDie("daemon-set-controller"),
		flowcontrol.NewBackOff(1*time.Second, 15*time.Minute),
	)
	if err != nil {
		return nil, true, fmt.Errorf("error creating DaemonSets controller: %v", err)
	}
	go dsc.Run(int(ctx.ComponentConfig.DaemonSetController.ConcurrentDaemonSetSyncs), ctx.Stop)
	return nil, true, nil
}

1.1 daemon.NewDaemonSetsController

从daemon.NewDaemonSetsController函数代码中可以看到，daemonset controller注册了daemonset、node、pod与ControllerRevisions对象的EventHandler，也即对这几个对象的event进行监听，把event放入事件队列并做处理。并且将dsc.syncDaemonSet方法赋值给dsc.syncHandler，也即注册为核心处理方法，在dsc.Run方法中会调用该核心处理方法来调谐daemonset对象（核心处理方法后面会进行详细分析）。

// pkg/controller/daemon/daemon_controller.go
func NewDaemonSetsController(
	daemonSetInformer appsinformers.DaemonSetInformer,
	historyInformer appsinformers.ControllerRevisionInformer,
	podInformer coreinformers.PodInformer,
	nodeInformer coreinformers.NodeInformer,
	kubeClient clientset.Interface,
	failedPodsBackoff *flowcontrol.Backoff,
) (*DaemonSetsController, error) {
	eventBroadcaster := record.NewBroadcaster()
	eventBroadcaster.StartLogging(klog.Infof)
	eventBroadcaster.StartRecordingToSink(&v1core.EventSinkImpl{Interface: kubeClient.CoreV1().Events("")})

	if kubeClient != nil && kubeClient.CoreV1().RESTClient().GetRateLimiter() != nil {
		if err := ratelimiter.RegisterMetricAndTrackRateLimiterUsage("daemon_controller", kubeClient.CoreV1().RESTClient().GetRateLimiter()); err != nil {
			return nil, err
		}
	}
	dsc := &DaemonSetsController{
		kubeClient:    kubeClient,
		eventRecorder: eventBroadcaster.NewRecorder(scheme.Scheme, v1.EventSource{Component: "daemonset-controller"}),
		podControl: controller.RealPodControl{
			KubeClient: kubeClient,
			Recorder:   eventBroadcaster.NewRecorder(scheme.Scheme, v1.EventSource{Component: "daemonset-controller"}),
		},
		crControl: controller.RealControllerRevisionControl{
			KubeClient: kubeClient,
		},
		burstReplicas: BurstReplicas,
		expectations:  controller.NewControllerExpectations(),
		queue:         workqueue.NewNamedRateLimitingQueue(workqueue.DefaultControllerRateLimiter(), "daemonset"),
	}

	daemonSetInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc: func(obj interface{}) {
			ds := obj.(*apps.DaemonSet)
			klog.V(4).Infof("Adding daemon set %s", ds.Name)
			dsc.enqueueDaemonSet(ds)
		},
		UpdateFunc: func(old, cur interface{}) {
			oldDS := old.(*apps.DaemonSet)
			curDS := cur.(*apps.DaemonSet)
			klog.V(4).Infof("Updating daemon set %s", oldDS.Name)
			dsc.enqueueDaemonSet(curDS)
		},
		DeleteFunc: dsc.deleteDaemonset,
	})
	dsc.dsLister = daemonSetInformer.Lister()
	dsc.dsStoreSynced = daemonSetInformer.Informer().HasSynced

	historyInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc:    dsc.addHistory,
		UpdateFunc: dsc.updateHistory,
		DeleteFunc: dsc.deleteHistory,
	})
	dsc.historyLister = historyInformer.Lister()
	dsc.historyStoreSynced = historyInformer.Informer().HasSynced

	// Watch for creation/deletion of pods. The reason we watch is that we don't want a daemon set to create/delete
	// more pods until all the effects (expectations) of a daemon set's create/delete have been observed.
	podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc:    dsc.addPod,
		UpdateFunc: dsc.updatePod,
		DeleteFunc: dsc.deletePod,
	})
	dsc.podLister = podInformer.Lister()

	// This custom indexer will index pods based on their NodeName which will decrease the amount of pods we need to get in simulate() call.
	podInformer.Informer().GetIndexer().AddIndexers(cache.Indexers{
		"nodeName": indexByPodNodeName,
	})
	dsc.podNodeIndex = podInformer.Informer().GetIndexer()
	dsc.podStoreSynced = podInformer.Informer().HasSynced

	nodeInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
		AddFunc:    dsc.addNode,
		UpdateFunc: dsc.updateNode,
	},
	)
	dsc.nodeStoreSynced = nodeInformer.Informer().HasSynced
	dsc.nodeLister = nodeIn