K8s工作负载-ReplicaSet

基于1.25

什么是ReplicaSet

ReplicaSet的为指定Pod维护一个副本数量的集合，缩写RS

  • 一般新版本，用户不直接操作RS
  • 通过Deployment的生命周期，来管理RS

ReplicaSetSpec

// ReplicaSetSpec is the specification of a ReplicaSet.
// As the internal representation of a ReplicaSet, it must have
// a Template set.
type ReplicaSetSpec struct {
	// Replicas is the number of desired replicas.
  // 期望副本数量
	Replicas int32

	// Minimum number of seconds for which a newly created pod should be ready
	// without any of its container crashing, for it to be considered available.
	// Defaults to 0 (pod will be considered available as soon as it is ready)
	// +optional
  // 最小准备就绪时间，默认0s
	MinReadySeconds int32

	// Selector is a label query over pods that should match the replica count.
	// Must match in order to be controlled.
	// If empty, defaulted to labels on pod template.
	// More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/#label-selectors
	// +optional
  // 标签选择器，跟PodTempldate匹配
	Selector *metav1.LabelSelector

	// Template is the object that describes the pod that will be created if
	// insufficient replicas are detected.
	// +optional
  // 描述Deployment管理的Pod
	Template api.PodTemplateSpec
}

同步副本操作

RS控制器负责调谐RS状态

  • manageReplicas func是核心实现，完成同步副本调用

// manageReplicas checks and updates replicas for the given ReplicaSet.
// Does NOT modify <filteredPods>.
// It will requeue the replica set in case of an error while creating/deleting pods.
func (rsc *ReplicaSetController) manageReplicas(ctx context.Context, filteredPods []*v1.Pod, rs *apps.ReplicaSet) error {
  // 计算差值
	diff := len(filteredPods) - int(*(rs.Spec.Replicas))
	rsKey, err := controller.KeyFunc(rs)
	if err != nil {
		utilruntime.HandleError(fmt.Errorf("couldn't get key for %v %#v: %v", rsc.Kind, rs, err))
		return nil
	}
  // 差值小于0，需要创建Pod
	if diff < 0 {
		diff *= -1
    // 单次创建不能大于500
		if diff > rsc.burstReplicas {
			diff = rsc.burstReplicas
		}
		// TODO: Track UIDs of creates just like deletes. The problem currently
		// is we'd need to wait on the result of a create to record the pod's
		// UID, which would require locking *across* the create, which will turn
		// into a performance bottleneck. We should generate a UID for the pod
		// beforehand and store it via ExpectCreations.
		rsc.expectations.ExpectCreations(rsKey, diff)
		klog.V(2).InfoS("Too few replicas", "replicaSet", klog.KObj(rs), "need", *(rs.Spec.Replicas), "creating", diff)
		// Batch the pod creates. Batch sizes start at SlowStartInitialBatchSize
		// and double with each successful iteration in a kind of "slow start".
		// This handles attempts to start large numbers of pods that would
		// likely all fail with the same error. For example a project with a
		// low quota that attempts to create a large number of pods will be
		// prevented from spamming the API service with the pod create requests
		// after one of its pods fails.  Conveniently, this also prevents the
		// event spam that those failures would generate.
    // 并发的创建Pod，返回成功实例化的Pod
		successfulCreations, err := slowStartBatch(diff, controller.SlowStartInitialBatchSize, func() error {
			err := rsc.podControl.CreatePods(ctx, rs.Namespace, &rs.Spec.Template, rs, metav1.NewControllerRef(rs, rsc.GroupVersionKind))
			if err != nil {
				if apierrors.HasStatusCause(err, v1.NamespaceTerminatingCause) {
					// if the namespace is being terminated, we don't have to do
					// anything because any creation will fail
					return nil
				}
			}
			return err
		})

		// Any skipped pods that we never attempted to start shouldn't be expected.
		// The skipped pods will be retried later. The next controller resync will
		// retry the slow start process.
    // 如果差值大于0，需要删除多余副本
		if skippedPods := diff - successfulCreations; skippedPods > 0 {
			klog.V(2).Infof("Slow-start failure. Skipping creation of %d pods, decrementing expectations for %v %v/%v", skippedPods, rsc.Kind, rs.Namespace, rs.Name)
			for i := 0; i < skippedPods; i++ {
				// Decrement the expected number of creates because the informer won't observe this pod
				rsc.expectations.CreationObserved(rsKey)
			}
		}
		return err
	} else if diff > 0 {
		if diff > rsc.burstReplicas {
			diff = rsc.burstReplicas
		}
		klog.V(2).InfoS("Too many replicas", "replicaSet", klog.KObj(rs), "need", *(rs.Spec.Replicas), "deleting", diff)

		relatedPods, err := rsc.getIndirectlyRelatedPods(rs)
		utilruntime.HandleError(err)

		// Choose which Pods to delete, preferring those in earlier phases of startup.
    // 获取可以被清理掉Pod
		podsToDelete := getPodsToDelete(filteredPods, relatedPods, diff)

		// Snapshot the UIDs (ns/name) of the pods we're expecting to see
		// deleted, so we know to record their expectations exactly once either
		// when we see it as an update of the deletion timestamp, or as a delete.
		// Note that if the labels on a pod/rs change in a way that the pod gets
		// orphaned, the rs will only wake up after the expectations have
		// expired even if other pods are deleted.
		rsc.expectations.ExpectDeletions(rsKey, getPodKeys(podsToDelete))

		errCh := make(chan error, diff)
		var wg sync.WaitGroup
		wg.Add(diff)
    // 并发删除Pod，如果删除成功，把Expectation的del字段减1
		for _, pod := range podsToDelete {
			go func(targetPod *v1.Pod) {
				defer wg.Done()
				if err := rsc.podControl.DeletePod(ctx, rs.Namespace, targetPod.Name, rs); err != nil {
					// Decrement the expected number of deletes because the informer won't observe this deletion
					podKey := controller.PodKey(targetPod)
					rsc.expectations.DeletionObserved(rsKey, podKey)
					if !apierrors.IsNotFound(err) {
						klog.V(2).Infof("Failed to delete %v, decremented expectations for %v %s/%s", podKey, rsc.Kind, rs.Namespace, rs.Name)
						errCh <- err
					}
				}
			}(pod)
		}
		wg.Wait()

		select {
		case err := <-errCh:
			// all errors have been reported before and they're likely to be the same, so we'll only return the first one we hit.
			if err != nil {
				return err
			}
		default:
		}
	}

	return nil
}

慢启动批量创建Pod

slowStartBatch func：实现并发创建Pod

// slowStartBatch tries to call the provided function a total of 'count' times,
// starting slow to check for errors, then speeding up if calls succeed.
//
// It groups the calls into batches, starting with a group of initialBatchSize.
// Within each batch, it may call the function multiple times concurrently.
//
// If a whole batch succeeds, the next batch may get exponentially larger.
// If there are any failures in a batch, all remaining batches are skipped
// after waiting for the current batch to complete.
//
// It returns the number of successful calls to the function.
func slowStartBatch(count int, initialBatchSize int, fn func() error) (int, error) {
	remaining := count
	successes := 0
	for batchSize := integer.IntMin(remaining, initialBatchSize); batchSize > 0; batchSize = integer.IntMin(2*batchSize, remaining) {
		errCh := make(chan error, batchSize)
		var wg sync.WaitGroup
		wg.Add(batchSize)
		for i := 0; i < batchSize; i++ {
			go func() {
				defer wg.Done()
				if err := fn(); err != nil {
					errCh <- err
				}
			}()
		}
		wg.Wait()
		curSuccesses := batchSize - len(errCh)
		successes += curSuccesses
		if len(errCh) > 0 {
			return successes, <-errCh
		}
		remaining -= batchSize
	}
	return successes, nil
}

创建Pod的流程