想系统学习k8s源码，云原生的可以加：mkjnnm
replicaset controller分析分为3大块进行，分别是：
（1）replicaset controller初始化和启动分析；
（2）replicaset controller核心处理逻辑分析；
（3）replicaset controller expectations机制分析。
本篇进行replicaset controller核心处理逻辑分析。
replicaset controller 核心处理逻辑
经过前面分析的replicaset controller的初始化与启动，知道了replicaset controller监听 replicaset、pod对象的add、update 与 delete 事件，然后对 replicaset 对象做相应的调谐处理，这里来接着分析replicaset controller的调谐处理（核心处理）逻辑，从rsc.syncHandler作为入口进行分析。
syncHandler
rsc.syncHandler即rsc.syncReplicaSet方法，主要逻辑：
（1）获取replicaset对象以及关联的pod对象列表；
（2）调用rsc.expectations.SatisfiedExpectations，判断上一轮对replicaset期望副本的创删操作是否完成，也可以认为是判断上一次对replicaset对象的调谐操作中，调用的rsc.manageReplicas方法是否执行完成；
（3）如果上一轮对replicaset期望副本的创删操作已经完成，且 replicaset 对象的 DeletionTimestamp 字段为nil，则调用 rsc.manageReplicas 做r eplicaset 期望副本的核心调谐处理，即创删pod；
（4）调用calculateStatus计算replicaset的status，并更新。
// syncReplicaSet will sync the ReplicaSet with the given key if it has had its expectations fulfilled,
// meaning it did not expect to see any more of its pods created or deleted. This function is not meant to be
// invoked concurrently with the same key.
func (rsc *ReplicaSetController) syncReplicaSet(ctx context.Context, key string) error {
logger := klog.FromContext(ctx)
startTime := time.Now()
defer func() {
logger.Info("Finished syncing", "kind", rsc.Kind, "key", key, "duration", time.Since(startTime))
}()
namespace, name, err := cache.SplitMetaNamespaceKey(key)
if err != nil {
return err
}
rs, err := rsc.rsLister.ReplicaSets(namespace).Get(name)
if apierrors.IsNotFound(err) {
logger.V(4).Info("deleted", "kind", rsc.Kind, "key", key)
rsc.expectations.DeleteExpectations(logger, key)
return nil
}
if err != nil {
return err
}
rsNeedsSync := rsc.expectations.SatisfiedExpectations(logger, key)
selector, err := metav1.LabelSelectorAsSelector(rs.Spec.Selector)
if err != nil {
utilruntime.HandleError(fmt.Errorf("error converting pod selector to selector for rs %v/%v: %v", namespace, name, err))
return nil
}
// list all pods to include the pods that don't match the rs`s selector
// anymore but has the stale controller ref.
// TODO: Do the List and Filter in a single pass, or use an index.
allPods, err := rsc.podLister.Pods(rs.Namespace).List(labels.Everything())
if err != nil {
return err
}
// Ignore inactive pods.
filteredPods := controller.FilterActivePods(logger, allPods)
// NOTE: filteredPods are pointing to objects from cache - if you need to
// modify them, you need to copy it first.
filteredPods, err = rsc.claimPods(ctx, rs, selector, filteredPods)
if err != nil {
return err
}
var manageReplicasErr error
if rsNeedsSync && rs.DeletionTimestamp == nil {
manageReplicasErr = rsc.manageReplicas(ctx, filteredPods, rs)
}
rs = rs.DeepCopy()
newStatus := calculateStatus(rs, filteredPods, manageReplicasErr)
// Always updates status as pods come up or die.
updatedRS, err := updateReplicaSetStatus(logger, rsc.kubeClient.AppsV1().ReplicaSets(rs.Namespace), rs, newStatus)
if err != nil {
// Multiple things could lead to this update failing. Requeuing the replica set ensures
// Returning an error causes a requeue without forcing a hotloop
return err
}
// Resync the ReplicaSet after MinReadySeconds as a last line of defense to guard against clock-skew.
if manageReplicasErr == nil && updatedRS.Spec.MinReadySeconds > 0 &&
updatedRS.Status.ReadyReplicas == *(updatedRS.Spec.Replicas) &&
updatedRS.Status.AvailableReplicas != *(updatedRS.Spec.Replicas) {
rsc.queue.AddAfter(key, time.Duration(updatedRS.Spec.MinReadySeconds)*time.Second)
}
return manageReplicasErr
}
1. rsc.expectations.SatisfiedExpectations
该方法主要是判断上一轮对replicaset期望副本的创删操作是否完成，也可以认为是判断上一次对replicaset对象的调谐操作中，调用的rsc.manageReplicas方法是否执行完成。待上一次创建删除pod的操作完成后，才能进行下一次的rsc.manageReplicas方法调用。
若某replicaset对象的调谐中从未调用过rsc.manageReplicas方法，或上一轮调谐时创建/删除pod的数量已达成或调用rsc.manageReplicas后已达到超时期限（超时时间5分钟），则返回true，代表上一次创建删除pod的操作完成，可以进行下一次的rsc.manageReplicas方法调用，否则返回false。
expectations记录了replicaset对象在某一次调谐中期望创建/删除的pod数量，pod创建/删除完成后，该期望数会相应的减少，当期望创建/删除的pod数量小于等于0时，说明上一次调谐中期望创建/删除的pod数量已经达到，返回true。
// SatisfiedExpectations returns true if the required adds/dels for the given controller have been observed.
// Add/del counts are established by the controller at sync time, and updated as controllees are observed by the controller
// manager.
func (r *ControllerExpectations) SatisfiedExpectations(logger klog.Logger, controllerKey string) bool {
if exp, exists, err := r.GetExpectations(controllerKey); exists {
if exp.Fulfilled() {
logger.V(4).Info("Controller expectations fulfilled", "expectations", exp)
return true
} else if exp.isExpired() {
logger.V(4).Info("Controller expectations expired", "expectations", exp)
return true
} else {
logger.V(4).Info("Controller still waiting on expectations", "expectations", exp)
return false
}
} else if err != nil {
logger.V(2).Info("Error encountered while checking expectations, forcing sync", "err", err)
} else {
// When a new controller is created, it doesn't have expectations.
// When it doesn't see expected watch events for > TTL, the expectations expire.
// - In this case it wakes up, creates/deletes controllees, and sets expectations again.
// When it has satisfied expectations and no controllees need to be created/destroyed > TTL, the expectations expire.
// - In this case it continues without setting expectations till it needs to create/delete controllees.
logger.V(4).Info("Controller either never recorded expectations, or the ttl expired", "controller", controllerKey)
}
// Trigger a sync if we either encountered and error (which shouldn't happen since we're
// getting from local store) or this controller hasn't established expectations.
return true
}
2.rsc.manageReplicas
核心创建删除pod方法，主要是根据 replicaset 所期望的pod数量与现存pod数量做比较，然后根据比较结果来创建/删除pod，最终使得replicaset对象所期望的pod数量与现存pod数量相等，需要特别注意的是，每一次调用rsc.manageReplicas方法，创建/删除pod的个数上限为500。
在replicaset对象的调谐中，rsc.manageReplicas方法不一定每一次都会调用执行，只有当rsc.expectations.SatisfiedExpectations方法返回true，且replicaset对象的DeletionTimestamp属性为空时，才会进行rsc.manageReplicas方法的调用。
先简单的看一下代码，代码后面会做详细的逻辑分析。
// 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 {
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
}
logger := klog.FromContext(ctx)
if diff < 0 {
diff *= -1
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(logger, rsKey, diff)
logger.V(2).Info("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.
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.
if skippedPods := diff - successfulCreations; skippedPods > 0 {
logger.V(2).Info("Slow-start failure. Skipping creation of pods, decrementing expectations", "podsSkipped", skippedPods, "kind", rsc.Kind, "replicaSet", klog.KObj(rs))
for i := 0; i < skippedPods; i++ {
// Decrement the expected number of creates because the informer won't observe this pod
rsc.expectations.CreationObserved(logger, rsKey)
}
}
return err
} else if diff > 0 {
if diff > rsc.burstReplicas {
diff = rsc.burstReplicas
}
logger.V(2).Info("Too many replicas", "replicaSet", klog.KObj(rs), "need", *(rs.Spec.Replicas), "deleting", diff)
relatedPods, err := rsc.getIndirectlyRelatedPods(logger, rs)
utilruntime.HandleError(err)
// Choose which Pods to delete, preferring those in earlier phases of startup.
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(logger, rsKey, getPodKeys(podsToDelete))
errCh := make(chan error, diff)
var wg sync.WaitGroup
wg.Add(diff)
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(logger, rsKey, podKey)
if !apierrors.IsNotFound(err) {
logger.V(2).Info("Failed to delete pod, decremented expectations", "pod", podKey, "kind", rsc.Kind, "replicaSet", klog.KObj(rs))
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
}
diff = 现存pod数量 - 期望的pod数量
diff := len(filteredPods) - int(*(rs.Spec.Replicas))
（1）当现存pod数量比期望的少时，需要创建pod，进入创建pod的逻辑代码块。
（2）当现存pod数量比期望的多时，需要删除pod，进入删除pod的逻辑代码块。\
2.1 创建 pod 逻辑
主要逻辑：
（1）运算获取需要创建的pod数量，并设置数量上限500；
（2）调用rsc.expectations.ExpectCreations，将本轮调谐期望创建的pod数量设置进expectations；
（3）调用slowStartBatch函数来对pod进行创建逻辑处理；
（4）调用slowStartBatch函数完成后，计算获取创建失败的pod的数量，然后调用相应次数的rsc.expectations.CreationObserved方法，减去本轮调谐中期望创建的pod数量。
为什么要减呢？因为expectations记录了replicaset对象在某一次调谐中期望创建/删除的pod数量，pod创建/删除完成后，replicaset controller会watch到pod的创建/删除事件，从而调用rsc.expectations.CreationObserved方法来使期望创建/删除的pod数量减少。当有相应数量的pod创建/删除失败后，replicaset controller是不会watch到相应的pod创建/删除事件的，所以必须把本轮调谐期望创建/删除的pod数量做相应的减法，否则本轮调谐中的期望创建/删除pod数量永远不可能小于等于0，这样的话，rsc.expectations.SatisfiedExpectations方法就只会等待expectations超时期限到达才会返回true了。
2.1.1 slowStartBatch
来看到 slowStartBatch，可以看到创建pod的算法为：
（1）每次批量创建的 pod 数依次为 1、2、4、8…，呈指数级增长，起与要创建的pod数量相同的goroutine来负责创建pod。
（2）创建pod按1、2、4、8…的递增趋势分多批次进行，若某批次创建pod有失败的（如apiserver限流，丢弃请求等，注意：超时除外，因为initialization处理有可能超时），则后续批次不再进行，结束本次函数调用。
// 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 := min(remaining, initialBatchSize); batchSize > 0; batchSize = min(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
}
// 这里的 fn 就是创建pod的回调方法 ,最终调用
// newPod, err := r.KubeClient.CoreV1().Pods(namespace).Create(ctx, pod, metav1.CreateOptions{})
2.2 删除 pod
主要逻辑：
（1）运算获取需要删除的pod数量，并设置数量上限500；
（2）根据要缩容删除的pod数量，先调用getPodsToDelete函数找出需要删除的pod列表；
（3）调用rsc.expectations.ExpectCreations，将本轮调谐期望删除的pod数量设置进expectations；
（4）每个pod拉起一个goroutine，调用rsc.podControl.DeletePod来删除该pod；
（5）对于删除失败的pod，会调用rsc.expectations.DeletionObserved方法，减去本轮调谐中期望创建的pod数量。
至于为什么要减，原因跟上面创建逻辑代码块中分析的一样。
（6）等待所有gorouutine完成，return返回。
} else if diff > 0 {
if diff > rsc.burstReplicas {
diff = rsc.burstReplicas
}
logger.V(2).Info("Too many replicas", "replicaSet", klog.KObj(rs), "need", *(rs.Spec.Replicas), "deleting", diff)
relatedPods, err := rsc.getIndirectlyRelatedPods(logger, rs)
utilruntime.HandleError(err)
// Choose which Pods to delete, preferring those in earlier phases of startup.
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(logger, rsKey, getPodKeys(podsToDelete))
errCh := make(chan error, diff)
var wg sync.WaitGroup
wg.Add(diff)
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(logger, rsKey, podKey)
if !apierrors.IsNotFound(err) {
logger.V(2).Info("Failed to delete pod, decremented expectations", "pod", podKey, "kind", rsc.Kind, "replicaSet", klog.KObj(rs))
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:
}
}
2.1.1 getPodsToDelete
getPodsToDelete：根据要缩容删除的pod数量，然后返回需要删除的pod列表。
func getPodsToDelete(filteredPods, relatedPods []*v1.Pod, diff int) []*v1.Pod {
// No need to sort pods if we are about to delete all of them.
// diff will always be <= len(filteredPods), so not need to handle > case.
if diff < len(filteredPods) {
podsWithRanks := getPodsRankedByRelatedPodsOnSameNode(filteredPods, relatedPods)
sort.Sort(podsWithRanks)
reportSortingDeletionAgeRatioMetric(filteredPods, diff)
}
return filteredPods[:diff]
}
// getPodsRankedByRelatedPodsOnSameNode returns an ActivePodsWithRanks value
// that wraps podsToRank and assigns each pod a rank equal to the number of
// active pods in relatedPods that are colocated on the same node with the pod.
// relatedPods generally should be a superset of podsToRank.
func getPodsRankedByRelatedPodsOnSameNode(podsToRank, relatedPods []*v1.Pod) controller.ActivePodsWithRanks {
podsOnNode := make(map[string]int)
for _, pod := range relatedPods {
if controller.IsPodActive(pod) {
podsOnNode[pod.Spec.NodeName]++
}
}
ranks := make([]int, len(podsToRank))
for i, pod := range podsToRank {
ranks[i] = podsOnNode[pod.Spec.NodeName]
}
return controller.ActivePodsWithRanks{Pods: podsToRank, Rank: ranks, Now: metav1.Now()}
}
筛选要删除的pod逻辑
按照下面的排序规则，从上到下进行排序，各个条件相互互斥，符合其中一个条件则排序完成：
（1）优先删除没有绑定node的pod；
（2）优先删除处于Pending状态的pod，然后是Unknown，最后才是Running；
（3）优先删除Not ready的pod，然后才是ready的pod；
（4）按同node上所属replicaset的pod数量排序，优先删除所属replicaset的pod数量多的node上的pod； （5）按pod ready的时间排序，优先删除ready时间最短的pod；
（6）优先删除pod中容器重启次数较多的pod；
（7）按pod创建时间排序，优先删除创建时间最短的pod。
// Less compares two pods with corresponding ranks and returns true if the first
// one should be preferred for deletion.
func (s ActivePodsWithRanks) Less(i, j int) bool {
// 1. Unassigned < assigned
// If only one of the pods is unassigned, the unassigned one is smaller
if s.Pods[i].Spec.NodeName != s.Pods[j].Spec.NodeName && (len(s.Pods[i].Spec.NodeName) == 0 || len(s.Pods[j].Spec.NodeName) == 0) {
return len(s.Pods[i].Spec.NodeName) == 0
}
// 2. PodPending < PodUnknown < PodRunning
if podPhaseToOrdinal[s.Pods[i].Status.Phase] != podPhaseToOrdinal[s.Pods[j].Status.Phase] {
return podPhaseToOrdinal[s.Pods[i].Status.Phase] < podPhaseToOrdinal[s.Pods[j].Status.Phase]
}
// 3. Not ready < ready
// If only one of the pods is not ready, the not ready one is smaller
if podutil.IsPodReady(s.Pods[i]) != podutil.IsPodReady(s.Pods[j]) {
return !podutil.IsPodReady(s.Pods[i])
}
// 4. lower pod-deletion-cost < higher pod-deletion cost
if utilfeature.DefaultFeatureGate.Enabled(features.PodDeletionCost) {
pi, _ := helper.GetDeletionCostFromPodAnnotations(s.Pods[i].Annotations)
pj, _ := helper.GetDeletionCostFromPodAnnotations(s.Pods[j].Annotations)
if pi != pj {
return pi < pj
}
}
// 5. Doubled up < not doubled up
// If one of the two pods is on the same node as one or more additional
// ready pods that belong to the same replicaset, whichever pod has more
// colocated ready pods is less
if s.Rank[i] != s.Rank[j] {
return s.Rank[i] > s.Rank[j]
}
// TODO: take availability into account when we push minReadySeconds information from deployment into pods,
// see https://github.com/kubernetes/kubernetes/issues/22065
// 6. Been ready for empty time < less time < more time
// If both pods are ready, the latest ready one is smaller
if podutil.IsPodReady(s.Pods[i]) && podutil.IsPodReady(s.Pods[j]) {
readyTime1 := podReadyTime(s.Pods[i])
readyTime2 := podReadyTime(s.Pods[j])
if !readyTime1.Equal(readyTime2) {
if !utilfeature.DefaultFeatureGate.Enabled(features.LogarithmicScaleDown) {
return afterOrZero(readyTime1, readyTime2)
} else {
if s.Now.IsZero() || readyTime1.IsZero() || readyTime2.IsZero() {
return afterOrZero(readyTime1, readyTime2)
}
rankDiff := logarithmicRankDiff(*readyTime1, *readyTime2, s.Now)
if rankDiff == 0 {
return s.Pods[i].UID < s.Pods[j].UID
}
return rankDiff < 0
}
}
}
// 7. Pods with containers with higher restart counts < lower restart counts
if maxContainerRestarts(s.Pods[i]) != maxContainerRestarts(s.Pods[j]) {
return maxContainerRestarts(s.Pods[i]) > maxContainerRestarts(s.Pods[j])
}
// 8. Empty creation time pods < newer pods < older pods
if !s.Pods[i].CreationTimestamp.Equal(&s.Pods[j].CreationTimestamp) {
if !utilfeature.DefaultFeatureGate.Enabled(features.LogarithmicScaleDown) {
return afterOrZero(&s.Pods[i].CreationTimestamp, &s.Pods[j].CreationTimestamp)
} else {
if s.Now.IsZero() || s.Pods[i].CreationTimestamp.IsZero() || s.Pods[j].CreationTimestamp.IsZero() {
return afterOrZero(&s.Pods[i].CreationTimestamp, &s.Pods[j].CreationTimestamp)
}
rankDiff := logarithmicRankDiff(s.Pods[i].CreationTimestamp, s.Pods[j].CreationTimestamp, s.Now)
if rankDiff == 0 {
return s.Pods[i].UID < s.Pods[j].UID
}
return rankDiff < 0
}
}
return false
}
2.2.2 创建和删除 pod 方法
func (r RealPodControl) createPods(ctx context.Context, namespace string, pod *v1.Pod, object runtime.Object) error {
if len(labels.Set(pod.Labels)) == 0 {
return fmt.Errorf("unable to create pods, no labels")
}
newPod, err := r.KubeClient.CoreV1().Pods(namespace).Create(ctx, pod, metav1.CreateOptions{})
if err != nil {
// only send an event if the namespace isn't terminating
if !apierrors.HasStatusCause(err, v1.NamespaceTerminatingCause) {
r.Recorder.Eventf(object, v1.EventTypeWarning, FailedCreatePodReason, "Error creating: %v", err)
}
return err
}
logger := klog.FromContext(ctx)
accessor, err := meta.Accessor(object)
if err != nil {
logger.Error(err, "parentObject does not have ObjectMeta")
return nil
}
logger.V(4).Info("Controller created pod", "controller", accessor.GetName(), "pod", klog.KObj(newPod))
r.Recorder.Eventf(object, v1.EventTypeNormal, SuccessfulCreatePodReason, "Created pod: %v", newPod.Name)
return nil
}
func (r RealPodControl) DeletePod(ctx context.Context, namespace string, podID string, object runtime.Object) error {
accessor, err := meta.Accessor(object)
if err != nil {
return fmt.Errorf("object does not have ObjectMeta, %v", err)
}
logger := klog.FromContext(ctx)
logger.V(2).Info("Deleting pod", "controller", accessor.GetName(), "pod", klog.KRef(namespace, podID))
if err := r.KubeClient.CoreV1().Pods(namespace).Delete(ctx, podID, metav1.DeleteOptions{}); err != nil {
if apierrors.IsNotFound(err) {
logger.V(4).Info("Pod has already been deleted.", "pod", klog.KRef(namespace, podID))
return err
}
r.Recorder.Eventf(object, v1.EventTypeWarning, FailedDeletePodReason, "Error deleting: %v", err)
return fmt.Errorf("unable to delete pods: %v", err)
}
r.Recorder.Eventf(object, v1.EventTypeNormal, SuccessfulDeletePodReason, "Deleted pod: %v", podID)
return nil
}
3. calculateStatus
calculateStatus函数计算并返回replicaset对象的status。
怎么计算status呢？
（1）根据现存pod数量、Ready状态的pod数量、availabel状态的pod数量等，给replicaset对象的status的Replicas、ReadyReplicas、AvailableReplicas等字段赋值；
（2）根据replicaset对象现有status中的condition配置以及前面调用rsc.manageReplicas方法后是否有错误，来决定给status新增condition或移除condition，conditionType为ReplicaFailure。
当调用rsc.manageReplicas方法出错，且replicaset对象的status中，没有conditionType为ReplicaFailure的condition，则新增conditionType为ReplicaFailure的condition，表示该replicaset创建/删除pod出错；
当调用rsc.manageReplicas方法没有任何错误，且replicaset对象的status中，有conditionType为ReplicaFailure的condition，则去除该condition，表示该replicaset创建/删除pod成功。
func calculateStatus(rs *apps.ReplicaSet, filteredPods []*v1.Pod, manageReplicasErr error) apps.ReplicaSetStatus {
newStatus := rs.Status
// Count the number of pods that have labels matching the labels of the pod
// template of the replica set, the matching pods may have more
// labels than are in the template. Because the label of podTemplateSpec is
// a superset of the selector of the replica set, so the possible
// matching pods must be part of the filteredPods.
fullyLabeledReplicasCount := 0
readyReplicasCount := 0
availableReplicasCount := 0
templateLabel := labels.Set(rs.Spec.Template.Labels).AsSelectorPreValidated()
for _, pod := range filteredPods {
if templateLabel.Matches(labels.Set(pod.Labels)) {
fullyLabeledReplicasCount++
}
if podutil.IsPodReady(pod) {
readyReplicasCount++
if podutil.IsPodAvailable(pod, rs.Spec.MinReadySeconds, metav1.Now()) {
availableReplicasCount++
}
}
}
failureCond := GetCondition(rs.Status, apps.ReplicaSetReplicaFailure)
if manageReplicasErr != nil && failureCond == nil {
var reason string
if diff := len(filteredPods) - int(*(rs.Spec.Replicas)); diff < 0 {
reason = "FailedCreate"
} else if diff > 0 {
reason = "FailedDelete"
}
cond := NewReplicaSetCondition(apps.ReplicaSetReplicaFailure, v1.ConditionTrue, reason, manageReplicasErr.Error())
SetCondition(&newStatus, cond)
} else if manageReplicasErr == nil && failureCond != nil {
RemoveCondition(&newStatus, apps.ReplicaSetReplicaFailure)
}
newStatus.Replicas = int32(len(filteredPods))
newStatus.FullyLabeledReplicas = int32(fullyLabeledReplicasCount)
newStatus.ReadyReplicas = int32(readyReplicasCount)
newStatus.AvailableReplicas = int32(availableReplicasCount)
return newStatus
}
4. udpateReplicaSetStatus
主要逻辑：
（1）判断新计算出来的status中的各个属性如Replicas、ReadyReplicas、AvailableReplicas以及Conditions是否与现存replicaset对象的status中的一致，一致则不用做更新操作，直接return；
（2）调用c.UpdateStatus更新replicaset的status。
// updateReplicaSetStatus attempts to update the Status.Replicas of the given ReplicaSet, with a single GET/PUT retry.
func updateReplicaSetStatus(logger klog.Logger, c appsclient.ReplicaSetInterface, rs *apps.ReplicaSet, newStatus apps.ReplicaSetStatus) (*apps.ReplicaSet, error) {
// This is the steady state. It happens when the ReplicaSet doesn't have any expectations, since
// we do a periodic relist every 30s. If the generations differ but the replicas are
// the same, a caller might've resized to the same replica count.
if rs.Status.Replicas == newStatus.Replicas &&
rs.Status.FullyLabeledReplicas == newStatus.FullyLabeledReplicas &&
rs.Status.ReadyReplicas == newStatus.ReadyReplicas &&
rs.Status.AvailableReplicas == newStatus.AvailableReplicas &&
rs.Generation == rs.Status.ObservedGeneration &&
reflect.DeepEqual(rs.Status.Conditions, newStatus.Conditions) {
return rs, nil
}
// Save the generation number we acted on, otherwise we might wrongfully indicate
// that we've seen a spec update when we retry.
// TODO: This can clobber an update if we allow multiple agents to write to the
// same status.
newStatus.ObservedGeneration = rs.Generation
var getErr, updateErr error
var updatedRS *apps.ReplicaSet
for i, rs := 0, rs; ; i++ {
logger.V(4).Info(fmt.Sprintf("Updating status for %v: %s/%s, ", rs.Kind, rs.Namespace, rs.Name) +
fmt.Sprintf("replicas %d->%d (need %d), ", rs.Status.Replicas, newStatus.Replicas, *(rs.Spec.Replicas)) +
fmt.Sprintf("fullyLabeledReplicas %d->%d, ", rs.Status.FullyLabeledReplicas, newStatus.FullyLabeledReplicas) +
fmt.Sprintf("readyReplicas %d->%d, ", rs.Status.ReadyReplicas, newStatus.ReadyReplicas) +
fmt.Sprintf("availableReplicas %d->%d, ", rs.Status.AvailableReplicas, newStatus.AvailableReplicas) +
fmt.Sprintf("sequence No: %v->%v", rs.Status.ObservedGeneration, newStatus.ObservedGeneration))
rs.Status = newStatus
updatedRS, updateErr = c.UpdateStatus(context.TODO(), rs, metav1.UpdateOptions{})
if updateErr == nil {
return updatedRS, nil
}
// Stop retrying if we exceed statusUpdateRetries - the replicaSet will be requeued with a rate limit.
if i >= statusUpdateRetries {
break
}
// Update the ReplicaSet with the latest resource version for the next poll
if rs, getErr = c.Get(context.TODO(), rs.Name, metav1.GetOptions{}); getErr != nil {
// If the GET fails we can't trust status.Replicas anymore. This error
// is bound to be more interesting than the update failure.
return nil, getErr
}
}
return nil, updateErr
}
扫一扫
733
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
