原 荐 深度解析Kubernetes Pod

apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  name: zk-pdb
spec:
  minAvailable: 2
  selector:
    matchLabels:
      app: zookeeper

$ kubectl get poddisruptionbudgets
NAME      MIN-AVAILABLE   ALLOWED-DISRUPTIONS   AGE
zk-pdb    2               1                     7s

$ kubectl get poddisruptionbudgets zk-pdb -o yaml
apiVersion: policy/v1beta1
kind: PodDisruptionBudget
metadata:
  creationTimestamp: 2017-08-28T02:38:26Z
  generation: 1
  name: zk-pdb
...
status:
  currentHealthy: 3
  desiredHealthy: 3
  disruptedPods: null
  disruptionsAllowed: 1
  expectedPods: 3
  observedGeneration: 1

pkg/controller/disruption/disruption.go:498

func (dc *DisruptionController) trySync(pdb *policy.PodDisruptionBudget) error {
	pods, err := dc.getPodsForPdb(pdb)
	if err != nil {
		dc.recorder.Eventf(pdb, v1.EventTypeWarning, "NoPods", "Failed to get pods: %v", err)
		return err
	}
	if len(pods) == 0 {
		dc.recorder.Eventf(pdb, v1.EventTypeNormal, "NoPods", "No matching pods found")
	}

	expectedCount, desiredHealthy, err := dc.getExpectedPodCount(pdb, pods)
	if err != nil {
		dc.recorder.Eventf(pdb, v1.EventTypeWarning, "CalculateExpectedPodCountFailed", "Failed to calculate the number of expected pods: %v", err)
		return err
	}

	currentTime := time.Now()
	disruptedPods, recheckTime := dc.buildDisruptedPodMap(pods, pdb, currentTime)
	currentHealthy := countHealthyPods(pods, disruptedPods, currentTime)
	err = dc.updatePdbStatus(pdb, currentHealthy, desiredHealthy, expectedCount, disruptedPods)

	if err == nil && recheckTime != nil {
		// There is always at most one PDB waiting with a particular name in the queue,
		// and each PDB in the queue is associated with the lowest timestamp
		// that was supplied when a PDB with that name was added.
		dc.enqueuePdbForRecheck(pdb, recheckTime.Sub(currentTime))
	}
	return err
}

pkg/apis/policy/types.go:48

type PodDisruptionBudgetStatus struct {
	// Most recent generation observed when updating this PDB status. PodDisruptionsAllowed and other
	// status informatio is valid only if observedGeneration equals to PDB's object generation.
	// +optional
	ObservedGeneration int64 `json:"observedGeneration,omitempty" protobuf:"varint,1,opt,name=observedGeneration"`

	// DisruptedPods contains information about pods whose eviction was
	// processed by the API server eviction subresource handler but has not
	// yet been observed by the PodDisruptionBudget controller.
	// A pod will be in this map from the time when the API server processed the
	// eviction request to the time when the pod is seen by PDB controller
	// as having been marked for deletion (or after a timeout). The key in the map is the name of the pod
	// and the value is the time when the API server processed the eviction request. If
	// the deletion didn't occur and a pod is still there it will be removed from
	// the list automatically by PodDisruptionBudget controller after some time.
	// If everything goes smooth this map should be empty for the most of the time.
	// Large number of entries in the map may indicate problems with pod deletions.
	DisruptedPods map[string]metav1.Time `json:"disruptedPods" protobuf:"bytes,2,rep,name=disruptedPods"`

	// Number of pod disruptions that are currently allowed.
	PodDisruptionsAllowed int32 `json:"disruptionsAllowed" protobuf:"varint,3,opt,name=disruptionsAllowed"`

	// current number of healthy pods
	CurrentHealthy int32 `json:"currentHealthy" protobuf:"varint,4,opt,name=currentHealthy"`

	// minimum desired number of healthy pods
	DesiredHealthy int32 `json:"desiredHealthy" protobuf:"varint,5,opt,name=desiredHealthy"`

	// total number of pods counted by this disruption budget
	ExpectedPods int32 `json:"expectedPods" protobuf:"varint,6,opt,name=expectedPods"`
}

pkg/registry/core/pod/storage/eviction.go:81

// Create attempts to create a new eviction.  That is, it tries to evict a pod.
func (r *EvictionREST) Create(ctx genericapirequest.Context, obj runtime.Object, createValidation rest.ValidateObjectFunc, includeUninitialized bool) (runtime.Object, error) {
	eviction := obj.(*policy.Eviction)

	obj, err := r.store.Get(ctx, eviction.Name, &metav1.GetOptions{})
	if err != nil {
		return nil, err
	}
	pod := obj.(*api.Pod)
	var rtStatus *metav1.Status
	var pdbName string
	err = retry.RetryOnConflict(EvictionsRetry, func() error {
		pdbs, err := r.getPodDisruptionBudgets(ctx, pod)
		if err != nil {
			return err
		}

		if len(pdbs) > 1 {
			rtStatus = &metav1.Status{
				Status:  metav1.StatusFailure,
				Message: "This pod has more than one PodDisruptionBudget, which the eviction subresource does not support.",
				Code:    500,
			}
			return nil
		} else if len(pdbs) == 1 {
			pdb := pdbs[0]
			pdbName = pdb.Name
			// Try to verify-and-decrement

			// If it was false already, or if it becomes false during the course of our retries,
			// raise an error marked as a 429.
			if err := r.checkAndDecrement(pod.Namespace, pod.Name, pdb); err != nil {
				return err
			}
		}
		return nil
	})
	if err == wait.ErrWaitTimeout {
		err = errors.NewTimeoutError(fmt.Sprintf("couldn't update PodDisruptionBudget %q due to conflicts", pdbName), 10)
	}
	if err != nil {
		return nil, err
	}

	if rtStatus != nil {
		return rtStatus, nil
	}

	// At this point there was either no PDB or we succeded in decrementing

	// Try the delete
	_, _, err = r.store.Delete(ctx, eviction.Name, eviction.DeleteOptions)
	if err != nil {
		return nil, err
	}

	// Success!
	return &metav1.Status{Status: metav1.StatusSuccess}, nil
}

{
  "apiVersion": "policy/v1beta1",
  "kind": "Eviction",
  "metadata": {
    "name": "quux",
    "namespace": "default"
  }
}

$ curl -v -H 'Content-type: application/json' http://127.0.0.1:8080/api/v1/namespaces/default/pods/quux/eviction -d @eviction.json

// checkAndDecrement checks if the provided PodDisruptionBudget allows any disruption.
func (r *EvictionREST) checkAndDecrement(namespace string, podName string, pdb policy.PodDisruptionBudget) error {
	if pdb.Status.ObservedGeneration < pdb.Generation {
		// TODO(mml): Add a Retry-After header.  Once there are time-based
		// budgets, we can sometimes compute a sensible suggested value.  But
		// even without that, we can give a suggestion (10 minutes?) that
		// prevents well-behaved clients from hammering us.
		err := errors.NewTooManyRequests("Cannot evict pod as it would violate the pod's disruption budget.", 0)
		err.ErrStatus.Details.Causes = append(err.ErrStatus.Details.Causes, metav1.StatusCause{Type: "DisruptionBudget", Message: fmt.Sprintf("The disruption budget %s is still being processed by the server.", pdb.Name)})
		return err
	}
	if pdb.Status.PodDisruptionsAllowed < 0 {
		return errors.NewForbidden(policy.Resource("poddisruptionbudget"), pdb.Name, fmt.Errorf("pdb disruptions allowed is negative"))
	}
	if len(pdb.Status.DisruptedPods) > MaxDisruptedPodSize {
		return errors.NewForbidden(policy.Resource("poddisruptionbudget"), pdb.Name, fmt.Errorf("DisruptedPods map too big - too many evictions not confirmed by PDB controller"))
	}
	if pdb.Status.PodDisruptionsAllowed == 0 {
		err := errors.NewTooManyRequests("Cannot evict pod as it would violate the pod's disruption budget.", 0)
		err.ErrStatus.Details.Causes = append(err.ErrStatus.Details.Causes, metav1.StatusCause{Type: "DisruptionBudget", Message: fmt.Sprintf("The disruption budget %s needs %d healthy pods and has %d currently", pdb.Name, pdb.Status.DesiredHealthy, pdb.Status.CurrentHealthy)})
		return err
	}

	pdb.Status.PodDisruptionsAllowed--
	if pdb.Status.DisruptedPods == nil {
		pdb.Status.DisruptedPods = make(map[string]metav1.Time)
	}
	// Eviction handler needs to inform the PDB controller that it is about to delete a pod
	// so it should not consider it as available in calculations when updating PodDisruptions allowed.
	// If the pod is not deleted within a reasonable time limit PDB controller will assume that it won't
	// be deleted at all and remove it from DisruptedPod map.
	pdb.Status.DisruptedPods[podName] = metav1.Time{Time: time.Now()}
	if _, err := r.podDisruptionBudgetClient.PodDisruptionBudgets(namespace).UpdateStatus(&pdb); err != nil {
		return err
	}

	return nil
}