Kubernetes 中 Pod 的优雅退出机制

func (m *kubeGenericRuntimeManager) killContainer(pod *v1.Pod, containerID kubecontainer.ContainerID, containerName string, message string, reason containerKillReason, gracePeriodOverride *int64) error {
   ...
 // From this point, pod and container must be non-nil.
 gracePeriod := int64(minimumGracePeriodInSeconds)
 switch {
 case pod.DeletionGracePeriodSeconds != nil:
  gracePeriod = *pod.DeletionGracePeriodSeconds
 case pod.Spec.TerminationGracePeriodSeconds != nil:
  gracePeriod = *pod.Spec.TerminationGracePeriodSeconds

  switch reason {
  case reasonStartupProbe:
   if containerSpec.StartupProbe != nil && containerSpec.StartupProbe.TerminationGracePeriodSeconds != nil {
    gracePeriod = *containerSpec.StartupProbe.TerminationGracePeriodSeconds
   }
  case reasonLivenessProbe:
   if containerSpec.LivenessProbe != nil && containerSpec.LivenessProbe.TerminationGracePeriodSeconds != nil {
    gracePeriod = *containerSpec.LivenessProbe.TerminationGracePeriodSeconds
   }
  }
 }

 // Run internal pre-stop lifecycle hook
 if err := m.internalLifecycle.PreStopContainer(containerID.ID); err != nil {
  return err
 }

 // Run the pre-stop lifecycle hooks if applicable and if there is enough time to run it
 if containerSpec.Lifecycle != nil && containerSpec.Lifecycle.PreStop != nil && gracePeriod > 0 {
  gracePeriod = gracePeriod - m.executePreStopHook(pod, containerID, containerSpec, gracePeriod)
 }
 // always give containers a minimal shutdown window to avoid unnecessary SIGKILLs
 if gracePeriod < minimumGracePeriodInSeconds {
  gracePeriod = minimumGracePeriodInSeconds
 }
 if gracePeriodOverride != nil {
  gracePeriod = *gracePeriodOverride
 }

 err := m.runtimeService.StopContainer(containerID.ID, gracePeriod)
   ...
 return nil
}

func calculateEffectiveGracePeriod(status *podSyncStatus, pod *v1.Pod, options *KillPodOptions) (int64, bool) {
 gracePeriod := status.gracePeriod
 // this value is bedrock truth - the apiserver owns telling us this value calculated by apiserver
 if override := pod.DeletionGracePeriodSeconds; override != nil {
  if gracePeriod == 0 || *override < gracePeriod {
   gracePeriod = *override
  }
 }
 // we allow other parts of the kubelet (namely eviction) to request this pod be terminated faster
 if options != nil {
  if override := options.PodTerminationGracePeriodSecondsOverride; override != nil {
   if gracePeriod == 0 || *override < gracePeriod {
    gracePeriod = *override
   }
  }
 }
 // make a best effort to default this value to the pod's desired intent, in the event
 // the kubelet provided no requested value (graceful termination?)
 if gracePeriod == 0 && pod.Spec.TerminationGracePeriodSeconds != nil {
  gracePeriod = *pod.Spec.TerminationGracePeriodSeconds
 }
 // no matter what, we always supply a grace period of 1
 if gracePeriod < 1 {
  gracePeriod = 1
 }
 return gracePeriod, status.gracePeriod != 0 && status.gracePeriod != gracePeriod
}

func (podStrategy) CheckGracefulDelete(ctx context.Context, obj runtime.Object, options *metav1.DeleteOptions) bool {
 if options == nil {
  return false
 }
 pod := obj.(*api.Pod)
 period := int64(0)
 // user has specified a value
 if options.GracePeriodSeconds != nil {
  period = *options.GracePeriodSeconds
 } else {
  // use the default value if set, or deletes the pod immediately (0)
  if pod.Spec.TerminationGracePeriodSeconds != nil {
   period = *pod.Spec.TerminationGracePeriodSeconds
  }
 }
 // if the pod is not scheduled, delete immediately
 if len(pod.Spec.NodeName) == 0 {
  period = 0
 }
 // if the pod is already terminated, delete immediately
 if pod.Status.Phase == api.PodFailed || pod.Status.Phase == api.PodSucceeded {
  period = 0
 }

 if period < 0 {
  period = 1
 }

 // ensure the options and the pod are in sync
 options.GracePeriodSeconds = &period
 return true
}

func (m *managerImpl) synchronize(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc) []*v1.Pod {
   ...
 // we kill at most a single pod during each eviction interval
 for i := range activePods {
  pod := activePods[i]
  gracePeriodOverride := int64(0)
  if !isHardEvictionThreshold(thresholdToReclaim) {
   gracePeriodOverride = m.config.MaxPodGracePeriodSeconds
  }
  message, annotations := evictionMessage(resourceToReclaim, pod, statsFunc)
  if m.evictPod(pod, gracePeriodOverride, message, annotations) {
   metrics.Evictions.WithLabelValues(string(thresholdToReclaim.Signal)).Inc()
   return []*v1.Pod{pod}
  }
 }
 ...
}

 // Map of signal names to quantities that defines hard eviction thresholds. For example: {"memory.available": "300Mi"}.
 EvictionHard map[string]string
 // Map of signal names to quantities that defines soft eviction thresholds.  For example: {"memory.available": "300Mi"}.
 EvictionSoft map[string]string
 // Map of signal names to quantities that defines grace periods for each soft eviction signal. For example: {"memory.available": "30s"}.
 EvictionSoftGracePeriod map[string]string
 // Duration for which the kubelet has to wait before transitioning out of an eviction pressure condition.
 EvictionPressureTransitionPeriod metav1.Duration
 // Maximum allowed grace period (in seconds) to use when terminating pods in response to a soft eviction threshold being met.
 EvictionMaxPodGracePeriod int32

func killPodNow(podWorkers PodWorkers, recorder record.EventRecorder) eviction.KillPodFunc {
 return func(pod *v1.Pod, isEvicted bool, gracePeriodOverride *int64, statusFn func(*v1.PodStatus)) error {
  // determine the grace period to use when killing the pod
  gracePeriod := int64(0)
  if gracePeriodOverride != nil {
   gracePeriod = *gracePeriodOverride
  } else if pod.Spec.TerminationGracePeriodSeconds != nil {
   gracePeriod = *pod.Spec.TerminationGracePeriodSeconds
  }

  // we timeout and return an error if we don't get a callback within a reasonable time.
  // the default timeout is relative to the grace period (we settle on 10s to wait for kubelet->runtime traffic to complete in sigkill)
  timeout := int64(gracePeriod + (gracePeriod / 2))
  minTimeout := int64(10)
  if timeout < minTimeout {
   timeout = minTimeout
  }
  timeoutDuration := time.Duration(timeout) * time.Second

  // open a channel we block against until we get a result
  ch := make(chan struct{}, 1)
  podWorkers.UpdatePod(UpdatePodOptions{
   Pod:        pod,
   UpdateType: kubetypes.SyncPodKill,
   KillPodOptions: &KillPodOptions{
    CompletedCh:                              ch,
    Evict:                                    isEvicted,
    PodStatusFunc:                            statusFn,
    PodTerminationGracePeriodSecondsOverride: gracePeriodOverride,
   },
  })

  // wait for either a response, or a timeout
  select {
  case <-ch:
   return nil
  case <-time.After(timeoutDuration):
   recorder.Eventf(pod, v1.EventTypeWarning, events.ExceededGracePeriod, "Container runtime did not kill the pod within specified grace period.")
   return fmt.Errorf("timeout waiting to kill pod")
  }
 }
}