vlambda博客
学习文章列表

kubernetes/pkg/kubelet/kuberuntime/kuberuntime_container.go

m.killContainer --> m.internalLifecycle.PreStopContainer-->m.runtimeService.StopContainer

1. for _, container := range runningPod.Containers {
   go func(container *kubecontainer.Container) {
   defer utilruntime.HandleCrash()
   defer wg.Done()
   
   killContainerResult := kubecontainer.NewSyncResult(kubecontainer.KillContainer, container.Name)
   if err := m.killContainer(pod, container.ID, container.Name, "Need to kill Pod", gracePeriodOverride); err != nil {
   killContainerResult.Fail(kubecontainer.ErrKillContainer, err.Error())
   }
   containerResults <- killContainerResult
   }(container)
   }

2. if err := m.internalLifecycle.PreStopContainer(containerID.ID); err != nil { return err }

3. err := m.runtimeService.StopContainer(containerID.ID, gracePeriod)

// killContainersWithSyncResult kills all pod's containers with sync results.
func (m *kubeGenericRuntimeManager) killContainersWithSyncResult(pod *v1.Pod, runningPod kubecontainer.Pod, gracePeriodOverride *int64) (syncResults []*kubecontainer.SyncResult) {
	containerResults := make(chan *kubecontainer.SyncResult, len(runningPod.Containers))
	wg := sync.WaitGroup{}

	wg.Add(len(runningPod.Containers))
	for _, container := range runningPod.Containers {
		go func(container *kubecontainer.Container) {
			defer utilruntime.HandleCrash()
			defer wg.Done()

			killContainerResult := kubecontainer.NewSyncResult(kubecontainer.KillContainer, container.Name)
			if err := m.killContainer(pod, container.ID, container.Name, "Need to kill Pod", gracePeriodOverride); err != nil {
				killContainerResult.Fail(kubecontainer.ErrKillContainer, err.Error())
			}
			containerResults <- killContainerResult
		}(container)
	}
	wg.Wait()
	close(containerResults)

	for containerResult := range containerResults {
		syncResults = append(syncResults, containerResult)
	}
	return
}


func (m *kubeGenericRuntimeManager) killContainer(pod *v1.Pod, containerID kubecontainer.ContainerID, containerName string, reason string, gracePeriodOverride *int64) error {
	var containerSpec *v1.Container
	if pod != nil {
		if containerSpec = kubecontainer.GetContainerSpec(pod, containerName); containerSpec == nil {
			return fmt.Errorf("failed to get containerSpec %q(id=%q) in pod %q when killing container for reason %q",
				containerName, containerID.String(), format.Pod(pod), reason)
		}
	} else {
		// Restore necessary information if one of the specs is nil.
		restoredPod, restoredContainer, err := m.restoreSpecsFromContainerLabels(containerID)
		if err != nil {
			return err
		}
		pod, containerSpec = restoredPod, restoredContainer
	}

	// 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
	}

	glog.V(2).Infof("Killing container %q with %d second grace period", containerID.String(), gracePeriod)

	// 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
		glog.V(3).Infof("Killing container %q, but using %d second grace period override", containerID, gracePeriod)
	}

	err := m.runtimeService.StopContainer(containerID.ID, gracePeriod)
	if err != nil {
		glog.Errorf("Container %q termination failed with gracePeriod %d: %v", containerID.String(), gracePeriod, err)
	} else {
		glog.V(3).Infof("Container %q exited normally", containerID.String())
	}

	message := fmt.Sprintf("Killing container with id %s", containerID.String())
	if reason != "" {
		message = fmt.Sprint(message, ":", reason)
	}
	m.recordContainerEvent(pod, containerSpec, containerID.ID, v1.EventTypeNormal, events.KillingContainer, message)
	m.containerRefManager.ClearRef(containerID)

	return err
}

kubernetes/pkg/kubelet/kuberuntime/kuberuntime_manager.go

// killPodWithSyncResult kills a runningPod and returns SyncResult.
// Note: The pod passed in could be *nil* when kubelet restarted.
func (m *kubeGenericRuntimeManager) killPodWithSyncResult(pod *v1.Pod, runningPod kubecontainer.Pod, gracePeriodOverride *int64) (result kubecontainer.PodSyncResult) {
	killContainerResults := m.killContainersWithSyncResult(pod, runningPod, gracePeriodOverride)
	for _, containerResult := range killContainerResults {
		result.AddSyncResult(containerResult)
	}

	// stop sandbox, the sandbox will be removed in GarbageCollect
	killSandboxResult := kubecontainer.NewSyncResult(kubecontainer.KillPodSandbox, runningPod.ID)
	result.AddSyncResult(killSandboxResult)
	// Stop all sandboxes belongs to same pod
	for _, podSandbox := range runningPod.Sandboxes {
		if err := m.runtimeService.StopPodSandbox(podSandbox.ID.ID); err != nil {
			killSandboxResult.Fail(kubecontainer.ErrKillPodSandbox, err.Error())
			glog.Errorf("Failed to stop sandbox %q", podSandbox.ID)
		}
	}

	return
}

kubernetes/pkg/kubelet/dockershim/docker_container.go

// StopContainer stops a running container with a grace period (i.e., timeout).
func (ds *dockerService) StopContainer(containerID string, timeout int64) error {
	return ds.client.StopContainer(containerID, time.Duration(timeout)*time.Second)
}

kubernetes/pkg/kubelet/dockershim/libdocker/kube_docker_client.go

// Stopping an already stopped container will not cause an error in dockerapi.
func (d *kubeDockerClient) StopContainer(id string, timeout time.Duration) error {
	ctx, cancel := d.getCustomTimeoutContext(timeout)
	defer cancel()
	err := d.client.ContainerStop(ctx, id, &timeout)
	if ctxErr := contextError(ctx); ctxErr != nil {
		return ctxErr
	}
	return err
}

github.com/docker/docker/client/container_stop.go

// ContainerStop stops a container without terminating the process.
// The process is blocked until the container stops or the timeout expires.
func (cli *Client) ContainerStop(ctx context.Context, containerID string, timeout *time.Duration) error {
	query := url.Values{}
	if timeout != nil {
		query.Set("t", timetypes.DurationToSecondsString(*timeout))
	}
	resp, err := cli.post(ctx, "/containers/"+containerID+"/stop", query, nil, nil)
	ensureReaderClosed(resp)
	return err
}

github.com/docker/docke

func runStop(dockerCli command.Cli, opts *stopOptions) error {
	ctx := context.Background()

	var timeout *time.Duration
	if opts.timeChanged {
		timeoutValue := time.Duration(opts.time) * time.Second
		timeout = &timeoutValue
	}

	var errs []string

	errChan := parallelOperation(ctx, opts.containers, func(ctx context.Context, id string) error {
		return dockerCli.Client().ContainerStop(ctx, id, timeout)
	})
	for _, container := range opts.containers {
		if err := <-errChan; err != nil {
			errs = append(errs, err.Error())
			continue
		}
		fmt.Fprintln(dockerCli.Out(), container)
	}
	if len(errs) > 0 {
		return errors.New(strings.Join(errs, "\n"))
	}
	return nil
}

github.com/docker/docke

// containerStop sends a stop signal, waits, sends a kill signal.
func (daemon *Daemon) containerStop(container *containerpkg.Container, seconds int) error {
	if !container.IsRunning() {
		return nil
	}

	stopSignal := container.StopSignal()
	// 1. Send a stop signal
	if err := daemon.killPossiblyDeadProcess(container, stopSignal); err != nil {
		// While normally we might "return err" here we're not going to
		// because if we can't stop the container by this point then
		// it's probably because it's already stopped. Meaning, between
		// the time of the IsRunning() call above and now it stopped.
		// Also, since the err return will be environment specific we can't
		// look for any particular (common) error that would indicate
		// that the process is already dead vs something else going wrong.
		// So, instead we'll give it up to 2 more seconds to complete and if
		// by that time the container is still running, then the error
		// we got is probably valid and so we force kill it.
		ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
		defer cancel()

		if status := <-container.Wait(ctx, containerpkg.WaitConditionNotRunning); status.Err() != nil {
			logrus.Infof("Container failed to stop after sending signal %d to the process, force killing", stopSignal)
			if err := daemon.killPossiblyDeadProcess(container, 9); err != nil {
				return err
			}
		}
	}

	// 2. Wait for the process to exit on its own
	ctx := context.Background()
	if seconds >= 0 {
		var cancel context.CancelFunc
		ctx, cancel = context.WithTimeout(ctx, time.Duration(seconds)*time.Second)
		defer cancel()
	}

	if status := <-container.Wait(ctx, containerpkg.WaitConditionNotRunning); status.Err() != nil {
		logrus.Infof("Container %v failed to exit within %d seconds of signal %d - using the force", container.ID, seconds, stopSignal)
		// 3. If it doesn't, then send SIGKILL
		if err := daemon.Kill(container); err != nil {
			// Wait without a timeout, ignore result.
			<-container.Wait(context.Background(), containerpkg.WaitConditionNotRunning)
			logrus.Warn(err) // Don't return error because we only care that container is stopped, not what function stopped it
		}
	}

	daemon.LogContainerEvent(container, "stop")
	return nil
}

github.com/docker/docke

// containerStop sends a stop signal, waits, sends a kill signal.
func (daemon *Daemon) containerStop(container *containerpkg.Container, seconds int) error {
	if !container.IsRunning() {
		return nil
	}

	stopSignal := container.StopSignal()
	// 1. Send a stop signal
	if err := daemon.killPossiblyDeadProcess(container, stopSignal); err != nil {
		// While normally we might "return err" here we're not going to
		// because if we can't stop the container by this point then
		// it's probably because it's already stopped. Meaning, between
		// the time of the IsRunning() call above and now it stopped.
		// Also, since the err return will be environment specific we can't
		// look for any particular (common) error that would indicate
		// that the process is already dead vs something else going wrong.
		// So, instead we'll give it up to 2 more seconds to complete and if
		// by that time the container is still running, then the error
		// we got is probably valid and so we force kill it.
		ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
		defer cancel()

		if status := <-container.Wait(ctx, containerpkg.WaitConditionNotRunning); status.Err() != nil {
			logrus.Infof("Container failed to stop after sending signal %d to the process, force killing", stopSignal)
			if err := daemon.killPossiblyDeadProcess(container, 9); err != nil {
				return err
			}
		}
	}

	// 2. Wait for the process to exit on its own
	ctx := context.Background()
	if seconds >= 0 {
		var cancel context.CancelFunc
		ctx, cancel = context.WithTimeout(ctx, time.Duration(seconds)*time.Second)
		defer cancel()
	}

	if status := <-container.Wait(ctx, containerpkg.WaitConditionNotRunning); status.Err() != nil {
		logrus.Infof("Container %v failed to exit within %d seconds of signal %d - using the force", container.ID, seconds, stopSignal)
		// 3. If it doesn't, then send SIGKILL
		if err := daemon.Kill(container); err != nil {
			// Wait without a timeout, ignore result.
			<-container.Wait(context.Background(), containerpkg.WaitConditionNotRunning)
			logrus.Warn(err) // Don't return error because we only care that container is stopped, not what function stopped it
		}
	}

	daemon.LogContainerEvent(container, "stop")
	return nil
}

docker-ce/kill.go at 523cf7e71252013fbb6a590be67a54b4a88c1dae · docker/docker-ce

// killPossibleDeadProcess is a wrapper around killSig() suppressing "no such process" error.
func (daemon *Daemon) killPossiblyDeadProcess(container *containerpkg.Container, sig int) error {
	err := daemon.killWithSignal(container, sig)
	if errdefs.IsNotFound(err) {
		e := errNoSuchProcess{container.GetPID(), sig}
		logrus.Debug(e)
		return e
	}
	return err
}

github.com/docker/docke

logrus.Debugf("Sending kill signal %d to container %s", sig, container.ID)

func (daemon *Daemon) killWithSignal(container *containerpkg.Container, sig int) error {
	logrus.Debugf("Sending kill signal %d to container %s", sig, container.ID)
	container.Lock()
	defer container.Unlock()

	if !container.Running {
		return errNotRunning(container.ID)
	}

	var unpause bool
	if container.Config.StopSignal != "" && syscall.Signal(sig) != syscall.SIGKILL {
		containerStopSignal, err := signal.ParseSignal(container.Config.StopSignal)
		if err != nil {
			return err
		}
		if containerStopSignal == syscall.Signal(sig) {
			container.ExitOnNext()
			unpause = container.Paused
		}
	} else {
		container.ExitOnNext()
		unpause = container.Paused
	}

	if !daemon.IsShuttingDown() {
		container.HasBeenManuallyStopped = true
		container.CheckpointTo(daemon.containersReplica)
	}

	// if the container is currently restarting we do not need to send the signal
	// to the process. Telling the monitor that it should exit on its next event
	// loop is enough
	if container.Restarting {
		return nil
	}

	if err := daemon.kill(container, sig); err != nil {
		if errdefs.IsNotFound(err) {
			unpause = false
			logrus.WithError(err).WithField("container", container.ID).WithField("action", "kill").Debug("container kill failed because of 'container not found' or 'no such process'")
			go func() {
				// We need to clean up this container but it is possible there is a case where we hit here before the exit event is processed
				// but after it was fired off.
				// So let's wait the container's stop timeout amount of time to see if the event is eventually processed.
				// Doing this has the side effect that if no event was ever going to come we are waiting a a longer period of time uneccessarily.
				// But this prevents race conditions in processing the container.
				ctx, cancel := context.WithTimeout(context.TODO(), time.Duration(container.StopTimeout())*time.Second)
				defer cancel()
				s := <-container.Wait(ctx, containerpkg.WaitConditionNotRunning)
				if s.Err() != nil {
					daemon.handleContainerExit(container, nil)
				}
			}()
		} else {
			return errors.Wrapf(err, "Cannot kill container %s", container.ID)
		}
	}

	if unpause {
		// above kill signal will be sent once resume is finished
		if err := daemon.containerd.Resume(context.Background(), container.ID); err != nil {
			logrus.Warnf("Cannot unpause container %s: %s", container.ID, err)
		}
	}

	attributes := map[string]string{
		"signal": fmt.Sprintf("%d", sig),
	}
	daemon.LogContainerEventWithAttributes(container, "kill", attributes)
	return nil
}

删除测试