Kubernetes PodGC Controller源码分析

cmd/kube-controller-manager/app/controllermanager.go:180

func Run(s *options.CMServer) error {
   ...
	err := StartControllers(newControllerInitializers(), s, rootClientBuilder, clientBuilder, stop)
	...
}

func newControllerInitializers() map[string]InitFunc {
	controllers := map[string]InitFunc{}
	controllers["endpoint"] = startEndpointController
	...
	controllers["podgc"] = startPodGCController
	...

	return controllers
}

cmd/kube-controller-manager/app/core.go:66

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

pkg/controller/podgc/gc_controller.go:44

type PodGCController struct {
	kubeClient clientset.Interface

	podLister       corelisters.PodLister
	podListerSynced cache.InformerSynced

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

pkg/controller/podgc/gc_controller.go:54

func NewPodGC(kubeClient clientset.Interface, podInformer coreinformers.PodInformer, terminatedPodThreshold int) *PodGCController {
	if kubeClient != nil && kubeClient.Core().RESTClient().GetRateLimiter() != nil {
		metrics.RegisterMetricAndTrackRateLimiterUsage("gc_controller", kubeClient.Core().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.Core().Pods(namespace).Delete(name, metav1.NewDeleteOptions(0))
		},
	}

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

	return gcc
}

pkg/controller/podgc/gc_controller.go:73

func (gcc *PodGCController) Run(stop <-chan struct{}) {
	if !cache.WaitForCacheSync(stop, gcc.podListerSynced) {
		utilruntime.HandleError(fmt.Errorf("timed out waiting for caches to sync"))
		return
	}

	go wait.Until(gcc.gc, gcCheckPeriod, stop)
	<-stop
}

pkg/controller/podgc/gc_controller.go:83

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)
}

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()
}

// 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.Core().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 assigned to the Node %v. Deleting.", 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 %s succeeded", pod.Name)
		}
	}
}

pkg/controller/podgc/gc_controller.go:167

// 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 not assigned to any Node. Deleting.", 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 %s succeeded", pod.Name)
		}
	}
}