《一起读 kubernetes 源码》原来 k8s 也有 GC

// pkg/kubelet/kubelet.go:231
// Bootstrap is a bootstrapping interface for kubelet, targets the initialization protocol
type Bootstrap interface {
	StartGarbageCollection()
	ListenAndServe(kubeCfg *kubeletconfiginternal.KubeletConfiguration, tlsOptions *server.TLSOptions, auth server.AuthInterface, tp trace.TracerProvider)
	...
}

// pkg/kubelet/kubelet.go:1395
// StartGarbageCollection starts garbage collection threads.
func (kl *Kubelet) StartGarbageCollection() {
	loggedContainerGCFailure := false
	go wait.Until(func() {
		ctx := context.Background()
		if err := kl.containerGC.GarbageCollect(ctx); err != nil {
			// ...
		} else {
			// ...
		}
	}, ContainerGCPeriod, wait.NeverStop)

	prevImageGCFailed := false
	go wait.Until(func() {
		ctx := context.Background()
		if err := kl.imageManager.GarbageCollect(ctx); err != nil {
			// ...
		} else {
			// ...
		}
	}, ImageGCPeriod, wait.NeverStop)
}

// pkg/kubelet/kuberuntime/kuberuntime_gc.go:407
func (cgc *containerGC) GarbageCollect(ctx context.Context, gcPolicy kubecontainer.GCPolicy, allSourcesReady bool, evictNonDeletedPods bool) error {
	ctx, otelSpan := cgc.tracer.Start(ctx, "Containers/GarbageCollect")
	defer otelSpan.End()
	errors := []error{}
	// Remove evictable containers
	if err := cgc.evictContainers(ctx, gcPolicy, allSourcesReady, evictNonDeletedPods); err != nil {
		errors = append(errors, err)
	}

	// Remove sandboxes with zero containers
	if err := cgc.evictSandboxes(ctx, evictNonDeletedPods); err != nil {
		errors = append(errors, err)
	}

	// Remove pod sandbox log directory
	if err := cgc.evictPodLogsDirectories(ctx, allSourcesReady); err != nil {
		errors = append(errors, err)
	}
	return utilerrors.NewAggregate(errors)
}

// pkg/kubelet/kuberuntime/kuberuntime_gc.go:226
// evict all containers that are evictable
func (cgc *containerGC) evictContainers(ctx context.Context, gcPolicy kubecontainer.GCPolicy, allSourcesReady bool, evictNonDeletedPods bool) error {
	// Separate containers by evict units.
	evictUnits, err := cgc.evictableContainers(ctx, gcPolicy.MinAge)
	if err != nil {
		return err
	}

	// Remove deleted pod containers if all sources are ready.
	if allSourcesReady {
		for key, unit := range evictUnits {
			if cgc.podStateProvider.ShouldPodContentBeRemoved(key.uid) || (evictNonDeletedPods && cgc.podStateProvider.ShouldPodRuntimeBeRemoved(key.uid)) {
				cgc.removeOldestN(ctx, unit, len(unit)) // Remove all.
				delete(evictUnits, key)
			}
		}
	}

	// Enforce max containers per evict unit.
	if gcPolicy.MaxPerPodContainer >= 0 {
		cgc.enforceMaxContainersPerEvictUnit(ctx, evictUnits, gcPolicy.MaxPerPodContainer)
	}

	// Enforce max total number of containers.
	if gcPolicy.MaxContainers >= 0 && evictUnits.NumContainers() > gcPolicy.MaxContainers {
		// Leave an equal number of containers per evict unit (min: 1).
		numContainersPerEvictUnit := gcPolicy.MaxContainers / evictUnits.NumEvictUnits()
		if numContainersPerEvictUnit < 1 {
			numContainersPerEvictUnit = 1
		}
		cgc.enforceMaxContainersPerEvictUnit(ctx, evictUnits, numContainersPerEvictUnit)

		// If we still need to evict, evict oldest first.
		numContainers := evictUnits.NumContainers()
		if numContainers > gcPolicy.MaxContainers {
			flattened := make([]containerGCInfo, 0, numContainers)
			for key := range evictUnits {
				flattened = append(flattened, evictUnits[key]...)
			}
			sort.Sort(byCreated(flattened))

			cgc.removeOldestN(ctx, flattened, numContainers-gcPolicy.MaxContainers)
		}
	}
	return nil
}

func (im *realImageGCManager) GarbageCollect(ctx context.Context) error {
	ctx, otelSpan := im.tracer.Start(ctx, "Images/GarbageCollect")
	defer otelSpan.End()
	// Get disk usage on disk holding images.
	fsStats, err := im.statsProvider.ImageFsStats(ctx)
	if err != nil {
		return err
	}

	var capacity, available int64
	if fsStats.CapacityBytes != nil {
		capacity = int64(*fsStats.CapacityBytes)
	}
	if fsStats.AvailableBytes != nil {
		available = int64(*fsStats.AvailableBytes)
	}

	if available > capacity {
		klog.InfoS("Availability is larger than capacity", "available", available, "capacity", capacity)
		available = capacity
	}

	// ....

	// If over the max threshold, free enough to place us at the lower threshold.
	usagePercent := 100 - int(available*100/capacity)
	if usagePercent >= im.policy.HighThresholdPercent {
		amountToFree := capacity*int64(100-im.policy.LowThresholdPercent)/100 - available
		klog.InfoS("Disk usage on image filesystem is over the high threshold, trying to free bytes down to the low threshold", "usage", usagePercent, "highThreshold", im.policy.HighThresholdPercent, "amountToFree", amountToFree, "lowThreshold", im.policy.LowThresholdPercent)
		freed, err := im.freeSpace(ctx, amountToFree, time.Now())
		if err != nil {
			return err
		}

		// ....
	}

	return nil
}

func (im *realImageGCManager) freeSpace(ctx context.Context, bytesToFree int64, freeTime time.Time) (int64, error) {
	imagesInUse, err := im.detectImages(ctx, freeTime)
	// ...

	im.imageRecordsLock.Lock()
	defer im.imageRecordsLock.Unlock()

	// Get all images in eviction order.
	images := make([]evictionInfo, 0, len(im.imageRecords))
	for image, record := range im.imageRecords {
		if isImageUsed(image, imagesInUse) {
			klog.V(5).InfoS("Image ID is being used", "imageID", image)
			continue
		}
		// Check if image is pinned, prevent garbage collection
		if record.pinned {
			klog.V(5).InfoS("Image is pinned, skipping garbage collection", "imageID", image)
			continue

		}
		images = append(images, evictionInfo{
			id:          image,
			imageRecord: *record,
		})
	}
	sort.Sort(byLastUsedAndDetected(images))

	// Delete unused images until we've freed up enough space.
	var deletionErrors []error
	spaceFreed := int64(0)
	for _, image := range images {
		// ....

		// Remove image. Continue despite errors.
		klog.InfoS("Removing image to free bytes", "imageID", image.id, "size", image.size)
		err := im.runtime.RemoveImage(ctx, container.ImageSpec{Image: image.id})
		if err != nil {
			deletionErrors = append(deletionErrors, err)
			continue
		}
		// ....
	}

	// ....
	return spaceFreed, nil
}

go wait.Until(fn, ContainerGCPeriod, wait.NeverStop)

// vendor/k8s.io/apimachinery/pkg/util/wait/backoff.go:210
func BackoffUntil(f func(), backoff BackoffManager, sliding bool, stopCh <-chan struct{}) {
	var t clock.Timer
	for {
		select {
		case <-stopCh:
			return
		default:
		}

		if !sliding {
			t = backoff.Backoff()
		}

		func() {
			defer runtime.HandleCrash()
			f()
		}()

		if sliding {
			t = backoff.Backoff()
		}

		// NOTE: b/c there is no priority selection in golang
		// it is possible for this to race, meaning we could
		// trigger t.C and stopCh, and t.C select falls through.
		// In order to mitigate we re-check stopCh at the beginning
		// of every loop to prevent extra executions of f().
		select {
		case <-stopCh:
			if !t.Stop() {
				<-t.C()
			}
			return
		case <-t.C():
		}
	}
}