【kubernetes/k8s源码分析】kubectl-controller-manager之pod gc源码分析

 

参数：

   --controllers strings：配置需要enable的列表

        這裏也包括podgc

         All controllers: attachdetach, bootstrapsigner, clusterrole-aggregation, cronjob, csrapproving,
                csrcleaner, csrsigning, daemonset, deployment, disruption, endpoint, garbagecollector,
                horizontalpodautoscaling, job, namespace, nodeipam, nodelifecycle, persistentvolume-binder,
                persistentvolume-expander, podgc, pv-protection, pvc-protection, replicaset, replicationcontroller,
                resourcequota, route, service, serviceaccount, serviceaccount-token, statefulset, tokencleaner, ttl,
                ttl-after-finished
                Disabled-by-default controllers: bootstrapsigner, tokencleaner (default [*])

PodGCController结构体

• kubeClient：与APIServer的client
• PodLister：list Pods
• podListerSynced：判断PodLister是否Synced
• deletePod：调用apiserver删除对应pod
• terminatedPodThreshold：启动参数--terminated-pod-gc-threshold，默认为12500，<0意味着关闭gc

type PodGCController struct {
	kubeClient clientset.Interface

	podLister       corelisters.PodLister
	podListerSynced cache.InformerSynced

	deletePod              func(namespace, name string) error
	terminatedPodThreshold int
}

 

0. 開始：

  初始化注册podgc：controllers["podgc"] = startPodGCController

// NewControllerInitializers is a public map of named controller groups (you can start more than one in an init func)
// paired to their InitFunc.  This allows for structured downstream composition and subdivision.
func NewControllerInitializers(loopMode ControllerLoopMode) map[string]InitFunc {
	controllers := map[string]InitFunc{}
	controllers["endpoint"] = startEndpointController
	controllers["replicationcontroller"] = startReplicationController
	controllers["podgc"] = startPodGCController
	

	return controllers
}

1 startPodGCController函数

   调用NewPodGC初始化，执行Run方法

func startPodGCController(ctx ControllerContext) (http.Handler, bool, error) {
	go podgc.NewPodGC(
		ctx.ClientBuilder.ClientOrDie("pod-garbage-collector"),
		ctx.InformerFactory.Core().V1().Pods(),
		int(ctx.ComponentConfig.PodGCController.TerminatedPodGCThreshold),
	).Run(ctx.Stop)
	return nil, true, nil
}

  1.1 NewPodGC函数

    路径：pkg/controller/podgc/gc_controller.go

    初始化PodGCController结构体，结构体如上

    kubeClient.CoreV1().Pods(namespace).Delete(name, metav1.NewDeleteOptions(0)，表示立即删除（Use zero to indicate immediate deletion）

func NewPodGC(kubeClient clientset.Interface, podInformer coreinformers.PodInformer, terminatedPodThreshold int) *PodGCController {
	if kubeClient != nil && kubeClient.CoreV1().RESTClient().GetRateLimiter() != nil {
		metrics.RegisterMetricAndTrackRateLimiterUsage("gc_controller", kubeClient.CoreV1().RESTClient().GetRateLimiter())
	}
	gcc := &PodGCController{
		kubeClient:             kubeClient,
		terminatedPodThreshold: terminatedPodThreshold,
		deletePod: func(namespace, name string) error {
			glog.Infof("PodGC is force deleting Pod: %v/%v", namespace, name)
			return kubeClient.CoreV1().Pods(namespace).Delete(name, metav1.NewDeleteOptions(0))
		},
	}

	gcc.podLister = podInformer.Lister()
	gcc.podListerSynced = podInformer.Informer().HasSynced

	return gcc
}

  1.2 Run函数

    启动goruntine协程，间隔20s执行完一次gcc.gc进行Pod回收

func (gcc *PodGCController) Run(stop <-chan struct{}) {
	defer utilruntime.HandleCrash()

	glog.Infof("Starting GC controller")
	defer glog.Infof("Shutting down GC controller")

	if !controller.WaitForCacheSync("GC", stop, gcc.podListerSynced) {
		return
	}

	go wait.Until(gcc.gc, gcCheckPeriod, stop)

	<-stop
}

 

2. gc函数

•     List获得所有pod信息
•     gcTerminated函数
•     gcOrphaned函数回收Orphaned pods
•     gcUnschedulerTerminating函数回收UnscheduledTerminating pods

func (gcc *PodGCController) gc() {
	pods, err := gcc.podLister.List(labels.Everything())
	if err != nil {
		glog.Errorf("Error while listing all Pods: %v", err)
		return
	}
	if gcc.terminatedPodThreshold > 0 {
		gcc.gcTerminated(pods)
	}
	gcc.gcOrphaned(pods)
	gcc.gcUnscheduledTerminating(pods)
}

 

3. gcTerminated函数

    这个比较简单，对于终止的进行直接删除，中间有一些小逻辑进行处理

func (gcc *PodGCController) gcTerminated(pods []*v1.Pod) {
	terminatedPods := []*v1.Pod{}
	for _, pod := range pods {
		if isPodTerminated(pod) {
			terminatedPods = append(terminatedPods, pod)
		}
	}

	terminatedPodCount := len(terminatedPods)
	sort.Sort(byCreationTimestamp(terminatedPods))

	deleteCount := terminatedPodCount - gcc.terminatedPodThreshold

	if deleteCount > terminatedPodCount {
		deleteCount = terminatedPodCount
	}
	if deleteCount > 0 {
		glog.Infof("garbage collecting %v pods", deleteCount)
	}

	var wait sync.WaitGroup
	for i := 0; i < deleteCount; i++ {
		wait.Add(1)
		go func(namespace string, name string) {
			defer wait.Done()
			if err := gcc.deletePod(namespace, name); err != nil {
				// ignore not founds
				defer utilruntime.HandleError(err)
			}
		}(terminatedPods[i].Namespace, terminatedPods[i].Name)
	}
	wait.Wait()
}

4. gcOrphaned函数

      删除已经绑定到node的，但是又不再node列表中的pod，就是孤儿

// gcOrphaned deletes pods that are bound to nodes that don't exist.
func (gcc *PodGCController) gcOrphaned(pods []*v1.Pod) {
	glog.V(4).Infof("GC'ing orphaned")
	// We want to get list of Nodes from the etcd, to make sure that it's as fresh as possible.
	nodes, err := gcc.kubeClient.CoreV1().Nodes().List(metav1.ListOptions{})
	if err != nil {
		return
	}
	nodeNames := sets.NewString()
	for i := range nodes.Items {
		nodeNames.Insert(nodes.Items[i].Name)
	}

	for _, pod := range pods {
		if pod.Spec.NodeName == "" {
			continue
		}
		if nodeNames.Has(pod.Spec.NodeName) {
			continue
		}
		glog.V(2).Infof("Found orphaned Pod %v/%v assigned to the Node %v. Deleting.", pod.Namespace, pod.Name, pod.Spec.NodeName)
		if err := gcc.deletePod(pod.Namespace, pod.Name); err != nil {
			utilruntime.HandleError(err)
		} else {
			glog.V(0).Infof("Forced deletion of orphaned Pod %v/%v succeeded", pod.Namespace, pod.Name)
		}
	}
}

4. gcUnscheduledTerminating函数

  删除状态是删除状态的，或者没有被调度到node的pod

// gcUnscheduledTerminating deletes pods that are terminating and haven't been scheduled to a particular node.
func (gcc *PodGCController) gcUnscheduledTerminating(pods []*v1.Pod) {
	glog.V(4).Infof("GC'ing unscheduled pods which are terminating.")

	for _, pod := range pods {
		if pod.DeletionTimestamp == nil || len(pod.Spec.NodeName) > 0 {
			continue
		}

		glog.V(2).Infof("Found unscheduled terminating Pod %v/%v not assigned to any Node. Deleting.", pod.Namespace, pod.Name)
		if err := gcc.deletePod(pod.Namespace, pod.Name); err != nil {
			utilruntime.HandleError(err)
		} else {
			glog.V(0).Infof("Forced deletion of unscheduled terminating Pod %v/%v succeeded", pod.Namespace, pod.Name)
		}
	}
}